VOLUME 13, ISSUE 5, MAY 2024

Abstract: It is important to study (a) 5 external senses and (b) 8 interoceptive (internal) senses using MUSE-2 to understand the roles of brain (survival) and mind (human decision maker) in human health. Survival and decision-making affect health, longevity, and quality of life. Senses for human survival are 5 external and 8 interoceptive (internal) senses, and psychological reactions. This document provides details on how to use MUSE-2 for biomedical disease prediction. Four MUSE EEG signals were measured using a Smartphone App called mind monitor (MM) in 10 different environments to predict health/disease conditions. This paper also discusses very creative and unique outreach K-16 education modules. Functionalized Bricks with Embedded Intelligence (FBEI) were developed under funding provided by NSF Center for Wireless Integrated Micro System (WIMS) [31]The FBEIs, published in 2020, are still unique in the world.

Abstract: Wide Area Network (WAN) is one of the most important parts of communication technology in the world, and the Internet is an idle example for WAN. But, without bandwidth nobody is able to communicate via the internet. Moreover, day to day increases the number of user traffic on the internet. In this case medical science also consumes a huge number of bandwidths by the A.I operation technique. Therefore, bandwidth distribution is one of the vital issues for the technology of communication. This paper shows how MikroTik will be able to fulfill the needs of bandwidth management in future.

Keywords: Internet, Traffic, Bandwidth, MikroTik.

Abstract: In this paper, the direct digital frequency synthesizer (DDS) specifications were improved by increasing the number of accumulator bits, increasing the memory capacity of the generated signal samples, using a DAC by increasing the number of its bits, as well as generating different types of analogue signals in a digital way. In this paper also, we discuss a practical mechanism of a digital function signals generator (DFSG) based on a direct digital frequency synthesizer (DDFS) using Cyclone II EP2C20F484C7 FPGA from ALTERA placed on education and development board DE-1 with the following parameters: -Output waveforms: Sin, Gaussian, Sinc, Square , Saw tooth ,Triangular, and Wight Noise Signals. -Frequency range:  (3Hz…..10000 KHz  ). -Frequency Resolution  (3Hz). -Signal amplitude  (5V). -With Reset the generator. -Frequency of the generated signal for all types (1MHz).

Keywords:  DFGS, DDFS , FPGA, DPNG , SIN, SINC ,SQUARE, SAWTOOTH, GAUSSIAN, TRIANGULAR  .

Abstract: In this study, a system that captures the spirit of sound detective work is presented. Similar to a musician, it analyzes the sound by first removing certain elements, recognizing individual instruments, confirming the notes or sounds they produce. The finished product is like to a information of how many instruments are involved in a particular audio file. It can be a fresh score or text, with the detection of pitch feature. It is available for listening, and people can enjoy the music immensely. This project accomplishes a number of things really effectively for listening to polyphonic music performed by multiple instruments at once. The implementation of automated project that allows the users to identify the instruments involved in the audio files and detect the pitches out of the detected instruments. We first dealed with the analyzing of monophonic instruments sound which involves only one instrument and got the accuracy of 70 % for 40 Epoch. While dealing with polyphonic instrument sound there were many complexity faced during the dataset collection and testing phase. From previous survey there is work only done on monophonic instruments .Since there were no work done on polyphonic instruments sound, there was no dataset available. The merging of the monophonic instrument sound taken from different websites were done, almost 30,000 audios were collected .The one audio file contains varying number of instruments merged .Some contains four ,some five instruments. For training it is 2630 and testing 81 audio files. While the user can provide any of audio files from total of 2462 audio files. The accuracy decreased since we are dealing with very complex, overlapping datasets. Re-labelling would provide good results. We got 30% accuracy with 40 Epoch. The detection of Instruments was determined. The Other features includes pitch detection and synchronization. The real-time pitch detection using the Web Audio API and microphone input, along with the ability to analyze pre-recorded audio files is implemented. The synchronization process allows the user to upload an audio file, analyze it, generate synchronized MIDI data, and present the synchronized output back to the user for further interaction or analysis. The goal is to enhance user satisfaction by providing music that aligns with their instrument detection, pitch detection and synchronization.

Keywords: Instrument Detection, Pitch Detection, Synchronization, MIDI Synthesizer, Polyphonic, Monophonic.

Abstract: Customer sentiment analysis is a process of extensive exploration of data stored on the web in the form of online reviews to identify and categorize the views expressed in a part of the text as customer sentiments. Customer Sentiment analysis acquires importance in many areas of business, politics, and thought. Study of Sentiment analysis contains a comprehensive overview of the most important studies in this field from the past to the recent studies. The main aim of this paper is to provide a empirical analysis using sentiment analysis techniques and classification of customer reviews using machine learning (ML) techniques. Sentiment analysis has emerged as a pivotal tool in deciphering and understanding human emotions from textual data. This paper provides a succinct overview of customer sentiment analysis, its methodologies, applications, and significance in contemporary digital environments. At its core, sentiment analysis employs computational techniques to discern the sentiment or emotional tone expressed within text data. Techniques range from rule-based systems to ML algorithms, enabling automated classification of text into positive, negative, or neutral sentiments. Applications span various domains, including social media monitoring, customer feedback analysis, market research, and brand reputation management

Keywords: Opinion mining, Customer reviews, decision-making, ML algorithms, Sentiment analysis, Classification.

Abstract: - Searching is an important operation in data structure helps to find specific data within a collection of data.Searching algorithms helps us in the retrieval of information which is stored within some data structures such as arrays, linked list and trees. Searching is a process of finding an element in the given list.Number of searching algorithms are available, here we have to find which algorithm is best suited according to the situation.This paper gives detailed study of how searching algorithm works and give their performance analysis with respect to time complexity.

Keywords: Linear search, Binary search, Data Structure

Abstract: Cardiovascular disease (CVD) is a global health burden, with heart attacks being a major contributor to mortality. Early detection of risk factors is crucial for preventive measures. This paper investigates the application of Convolutional Neural Networks (CNNs) for analysing retinal images to predict heart attack risk. The rationale lies in the ability of retinal vasculature to reflect systemic vascular health. CNNs, a powerful deep learning technique, are adept at learning intricate patterns from image data. By analysing retinal images, the proposed model can identify subtle features associated with an increased risk of heart attack. This approach offers a non-invasive and potentially cost-effective screening method for CVD. The effectiveness of the proposed method is evaluated using a benchmark retinal image dataset. Metrics such as accuracy, sensitivity, and specificity are employed to assess the model's performance.

Keywords: Convolution neural network , Retinal Image Analysis , Deep Learning ,Non-invasive Screening,

Abstract: Wi-Fi Sensor Networks (JVSNs) are delivered and independent Sensors that are related and processed together to measure quantities such as hotness. Humidness, pressure. Explosion levels Or vibrations. Group of substitute players,’Vs measure vehicular change (velocity. And monitor environments in the way that lightning condition. Soil composition and morion. At this time. JVSNs are took advantage of in applications as tool requests, Some Of bicycle uses are: bus tracking and delecriom weary pressure listening. Vehicle speed discovery. Instrument direction sign. Traffic signal. Overturning aid sensors Such uses maybe divided in bigger classifications in the way that safety. Safety. Atmosphere logistics. TO implement in an use and have an effective system. ‘ve need ‘o examine about WSN rechnologv. And allure parts. This paper is aimed ar providing trustworthy operating system architecture of WSW Ihar maybe implementedfor efficiency and occupied.Keywords- Wireless sensor network, Construction, capacity unit, WSN design challenges.

Abstract: In today's cybersecurity realm, combatting advanced threats requires innovative solutions for early detection and swift response. This system introduces a pioneering chatbot system tailored for cybersecurity, employing AI, ML, and NLP. It continuously monitors diverse data streams like network traffic and social media, using ML to pinpoint potential threats accurately, even zero-day vulnerabilities. Acting as a user-friendly interface, it allows real-time updates, incident report requests, and alerts, improving usability and decision-making. Integration capabilities enable seamless coordination across security platforms, maximizing current investments. Advanced automation features streamline incident response, with the chatbot autonomously initiating actions such as isolating compromised systems. This approach empowers organizations to protect vital assets in a dynamic digital landscape, leveraging AI, ML, and NLP to proactively tackle cyber threats.

Keywords: Cybersecurity, Chatbot system, AI, ML, NLP.

Abstract: Optical character recognition (OCR) technology place a vital role in converting handwritten text into digitalformat.This technology explores the development and implementation of OCR system to extract text from various source such as handwritten images and printed images.OCR is one of the challenging topics in the character recognition field.The process begin with the giving an input as image. First the image goes under the pre-processing technique to remove the noise, image obtained is processed to identify the required lines. The identified lines ae extracted using segmentation process. The model is used using Convolutional Neural Network technique.

Keywords: Convolutional neural network, handwritten character recognition.

Abstract: A comprehensive survey of lightweight cryptography (LWC) solutions tailored to address the security challenges inherent in Internet of Things (IoT) environments. Evaluating various cryptographic primitives, including block ciphers, stream ciphers, hash functions, and elliptic curve cryptography, the study highlights the efficacy of AES and ECC in resource-constrained IoT devices. Emphasizing the necessity of lightweight cryptographic solutions amidst real-world constraints, the paper underscores ongoing research efforts and identifies future directions to fortify the security posture of IoT ecosystems. Through meticulous analysis and synthesis of findings, this survey advocates for the critical role of LWC in ensuring the resilience of IoT technologies.

Keywords: Lightweight Cryptography; Internet of Things (IoT); Security Challenges; Cryptographic Primitives; Resource-Constrained Devices.

Abstract: Landslides or landslip occurs at the down slopes. Landslides are most common in the Asian countries. The movements of rock mass or soil under the gravity are causes due to both Natural and human activities. Increase in the hydrostatic pressure, by saturation of rain water, melting of snow, increase in groundwater level, increase of pore water pressure, volcanic eruptions and earthquakes are natural causes of the landslip. Human activities include the deforestation, cultivation, machinery vibrations, blasting mining etc. Landslide causes extensive loss to the human lives and properties this makes important to monitor and make early warning systems. An attempt is made to create low cost and effective warning system IOT based landslide detection system. Using Arduino, Wi-Fi module, Moisture Sensors, Temperature Sensors, Humidity Sensors, Tilt Sensors, Rain Gauge and Vibration sensors. When data is collected it is uploaded by Arduino to the cloud ThingSpeak which help to monitor the real time data and send alert to the end user via SMS on the mobile phone about the Landslide when it happens.

Keywords: Landslide, Arduino, Wireless sensor network, soil, Sensor Development.

Abstract: Storage and retrieval of long data in a relatively smaller space is a challenging task for communication engineer. Now a day’s CD’s, DVD’s, pen derives and hard disk are usually used for this purpose which are not capable holding large amount of data and also retrieval of data takes relatively last time . This study is a small effort to review the storage of data in 3D optical medium which will hold the large amount of data and will make retrieval easier.

Keywords: Optical Storage, optical memory, 3D optics, holographics.

Keywords: KarmikConnect, daily wages worker, streamlined interface, contractor, user friendly.

Abstract: This project explores the integration of artificial intelligence (AI) techniques to augment driver detection systems in automotive environments, aiming to enhance overall road safety. The proposed system leverages advanced computer vision algorithms and machine learning models to accurately identify and monitor drivers in real-time. Key aspects include facial recognition, gaze tracking, and behavioural analysis to assess driver attentiveness and emotional states. The AI-assisted driver detection system contributes to proactive safety measures by providing timely alerts for potential driver distraction, fatigue, or impairment, detects weather the driver is drowsy, and also if the driver is continuously distracted even after limited number of alerts, our system will notify drivers superior or relative about repeated mistakes as a part of security. The project involves the development and evaluation of a prototype using diverse datasets and simulation scenarios to validate the system's effectiveness in various driving conditions. The outcomes offer valuable insights into the potential of AI in mitigating road accidents and improving overall transportation safety.

Keywords: Artificial Intelligence, Machine Learning, driver distraction detection, Computer Vision, facial recognition, gaze tracking, behavioural analysis.

Abstract: Wireless Sensor Networks (WSNs) are distributed and independent Sensors that are connected and worked together to measure quantities such as temperature. humidity, pressure. noise levels Or vibrations. JVS,'Vs measure vehicular movement (velocity. and monitor conditions such as lightning condition. soil makeup and morion. Nowadays. JVSNs are utilized in applications as vehicle applications, Some Of vehicle applications are: vehicle tracking and delecriom tire pressure monitoring. vehicle speed detection. vehicle direction indicator. traffic control. reversing aid sensors Such applications can be divided in major categories such as safety. security. environment logistics. TO implement in an application and have an efficient system. 've need 'o consider about WSN rechnologv. and its components. This paper is aimed ar providing reliable software architecture of WSW Ihar could be implementedfor performance and working.

Keywords: Wireless sensor network, Architecture, power unit, WSN design challenges.

Keywords: Automated, CV2, Face Detection, Recognition, Machine Learning, Mental Health

Keywords: Natural Language Processing(NLP),Long Short Term Memory(LSTM)

Keywords: Transportation Safety, Behaviour Detection, Real-time Intervention, Driver Monitoring.

Abstract: Technological advancements empower multimedia data exchange within IoT, posing security risks. Steganography, bolstered by deep learning, complements encryption, enhancing concealment and detection. Categorization, methodologies, and evaluation metrics drive innovation in image and video steganography. ISN and video techniques increase capacity while ensuring quality. Robust defences against steganalysis are imperative for safeguarding sensitive data...

Keywords: Steganography, Cryptography, Multimedia data security, Deep learning, Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs)

Abstract: Quantum computing is an interdisciplinary field that seeks to understand the processing of information using quantum mechanics principles. Quantum computing is the exploitation of properties of quantum states such as superposition and entanglement to perform computation. Quantum computers harness the laws of quantum mechanics to perform certain calculations exponentially faster than today's supercomputers. DOE's Office of Science supports two quantum computing testbeds to advance the state of the art in quantum computing hardware. Abstract. Quantum Dots are fluorescence type semiconductor nano sized particles. They are made up of either heavy metal or inorganic material with size range from 2 to 10 nm. The word quantum dots itself indicates its quantum confinement and optical properties. Quantum computers have the potential to revolutionize computation by making certain types of classically intractable problems solvable. While no quantum computer is yet sophisticated enough to carry out calculations that a classical computer can't, great progress is under way.

Abstract: Cryogenic technology has revolutionized rocket propulsion systems, enabling higher performance and efficiency in space exploration missions. This paper presents a comprehensive review of the latest advancements in cryogenic technology for rockets, focusing on key developments in cryogenic engines, propellants, and materials. The historical evolution of cryogenic technology in rocketry is discussed, highlighting significant milestones and contributions from various countries, including India's notable achievements. The paper also examines the current state-of-the-art cryogenic engines used in rockets, analyzing their design principles. Additionally, recent research trends and future prospects in cryogenic technology for rocket are explored, emphasizing the potential for enhancing payload capacities, reducing launch costs, and enabling advanced space missions. Through a thorough analysis of literature and technical insights, this paper provides a valuable resource for researchers, engineers, and enthusiasts interested in the forefront of cryogenic technology in rocketry.  

Keywords: Cryogenic technology, Rocket propulsion, Cryogenic engines, Propellants

Keywords: Micro-service architecture, Cloud Computing, Spring Boot Framework, Monolithic Architecture, SOA (Service oriented architecture), Healthcare system.

Abstract: This project presents an innovative approach to a comprehensive Vehicle Security System leveraging advanced technologies for enhanced protection. The system integrates Keypad Password, Face Recognition, and Fingerprint sensor mechanisms, ensuring multi-layered access control. Raspberry Pi serves as the central processing unit, adapt these security features seamlessly. Additionally, a Servo Motor Unlocking System is implemented, utilizing fingerprint verification to activate the motor, enhancing security further. To prevent theft attempts, an Anti-Lift feature employs a Ultrasonic Sensor, triggering alarms and immobilizing the vehicle if unauthorized movement is detected. This union of biometric authentication, innovative motor unlocking, and anti-lift measures establishes a robust and intelligent security for vehicles, addressing modern challenges in vehicular safety and theft prevention.

Keywords: Raspberry Pi,Keypad Password, Face Recognition, Fingerprint sensor,Ultrasonic Sensor,Servo Motor.

Abstract: Addressing the escalating global mental health crisis, this project proposes "Mindcare" an AI-powered chatbot therapy system tailored to individual emotional states. Leveraging natural language processing and machine learning, Mind care offers personalized mental and physical activity recommendations, consultation support, and progress tracking functionalities. Methodologically, the project employs the knowledge Discovery Tools and exploratory case studies to evaluate chatbot interventions effectiveness. Data mining techniques uncover hidden patterns in mental health datasets, potentially reshaping treatment paradigms. Expected outcomes include enhanced accessibility to mental health services, early intervention, personalized progress tracking, improved quality of life, and reduced stigma. Mindcare's architecture integrates data processing, machine learning, and empathic user engagement, revolutionizing mental health assistance. Mind care aims to empower individuals to thrive emotionally and mentally, catalysing a positive shift in mental health care paradigms through personalized interventions and proactive support.

Keywords: Chatbot therapy, Natural language processing, Machine learning, Knowledge Discovery, Data mining Techniques, Intervention.

Abstract: A city can become a smart city through the use of numerous IOT-based components, such as traffic light control, street lighting, smart water supply management, and many more systems. A smart city has all the amenities that are required, including simple access to energy, water, transportation, and security, as well as a community that fosters safety and health. With the advancement of technology, the world is changing quickly these days. There are numerous safety concerns world wide as a result. The primary goal of this paper is to ensure that everyone who lives in a city has a life that they deserve. The definition of smart cities is typically based on three factors: geographic, environmental, and economic. Keywords: amenities, fosters, deserve, geographic

Abstract: As cloud computing solidifies its place in modern technology, effective monitoring becomes paramount for optimizing performance and resource utilization. This paper conducts a comprehensive survey of cloud monitoring architectures, with a focus on Adaptive Monitoring Architecture (HSACMA), which has the capacity to balance monitoring capabilities and resource consumption across cloud layers. The exploration extends to Federated Architecture for Resource Management and Monitoring in Clouds (FEDARGOS-V1), offering a specialized approach to reconcile monitoring requirements in federated cloud infrastructures. Additionally, the survey takes into consideration the Cloud Monitor architecture, an innovative solution for independent cloud evaluations, showcasing its potential through preliminary results. The investigation culminates with a glance at the ElasticSearch, Logstash, and Kibana (ELK) stack, highlighting its versatility in log analysis for cloud environments. This survey illuminates the diverse landscape of cloud monitoring, resource management, and evaluation mechanisms, encapsulating both established paradigms and emerging trends.

Keywords: Cloud services, Monitoring, Log analysis, ELK stack

Abstract: A solar mobile charger is a device that harnesses the power of solar energy to charge portable electronic devices such as smartphones, tablets, and laptops. It is an eco-friendly and sustainable solution to the problem of charging devices on the go, especially in outdoor and off-grid environments where access to power outlets is limited or unavailable.The construction of a solar mobile charger typically consists of four key components: a solar panel, a battery, a charge controller, and a USB port for connecting to the device. The solar panel is the heart of the system, converting sunlight into electricity through the photovoltaic effect. The generated electricity is then stored in the battery, which acts as a buffer and ensures a steady supply of power to the device. The charge controller is a crucial component that regulates the flow of power between the solar panel, battery, and device. It prevents overcharging of the battery, which can cause damage or reduce its lifespan, and protects the device from voltage spikes or surges. The USB port provides a universal interface for connecting to various devices, making the solar mobile charger compatible with a wide range of devices and brands.

Keywords: Solar panel, Battery, charge controller.

Abstract: The Automatic Packet Reporting System (APRS) represents a dynamic and versatile digital communication platform within the realm of amateur radio. Developed to facilitate real-time data exchange and tracking capabilities, APRS integrates GPS technology with packet radio transmission, enabling users to broadcast position reports, weather information, and messages over radio frequencies. This abstract explores the underlying principles, applications, and future prospects of APRS, highlighting its significance in emergency communication, outdoor recreation, and scientific research. Through an analysis of its advantages, limitations, and emerging trends, this study aims to provide insights into the evolving landscape of APRS technology and its diverse applications across various domains.   By examining the advancements in hardware implementations, protocol stack configurations, and integration with emerging technologies, this abstract offers a comprehensive overview of APRS's evolution and potential. Furthermore, it underscores the importance of community engagement, standardization efforts, and education initiatives in fostering the continued growth and adoption of APRS technology. Through collaborative endeavours and innovation, APRS stands poised to continue shaping the landscape of amateur radio and digital communication in the years to come.

Keywords: Frequency Shift Keying (FSK), Audio Frequency Shift Keying (AFSK), cyclic redundancy checks (CRC)

Abstract: Our project endeavors to create an all-encompassing platform that not only diagnoses plant diseases but also provides solutions for limited market access and social problems faced by farmers. By integrating advanced algorithms and leveraging data analytics, we seek to offer personalized recommendations and tailored support to farmers, thereby enhancing their productivity and profitability. Additionally, our platform promotes knowledge exchange and collaboration among stakeholders, fostering a culture of innovation and continuous improvement in agricultural practices. Through strategic partnerships and community-driven initiatives, we aim to address systemic inequalities, promote sustainable agricultural development, and create a more equitable and resilient farming ecosystem.

Keywords: ResNet, Image classification, Convolutional neural network (CNN), Data augmentation, One Cycle learning rate scheduling, Cross-entropy loss, Batch normalization, Maxpooling.

Abstract: Bicycles are the predominant mode of transportation for people in the 20th century. Since the invention of gasoline and diesel engines a few decades ago, fewer people are experiencing physical stress from their vehicles. Nevertheless, the world's petroleum reserves are about to run out in a few decades. As a result, the cost of gasoline and diesel is rising, which is the problem we are currently dealing with. People must explore more choices, such as hydrogen. Engine: An electronic car with solar panels is one of the finest possibilities; it will undoubtedly be expensive, but it mostly uses free natural resources. The newest technology, wireless charging, allows you to charge your car while you drive, saving you a ton of time. It is employed in a wide range of applications, including e-bikes, four-wheelers, two-wheelers, ambulances, and more. Among the many alternatives available, a wireless electronic vehicle charging system is one of the most expensive. We are implementing an Arduino-based e-vehicle charging system as a project in this work. While driving, this gadget can be used to remotely charge electronic vehicles. The automobile battery is charged by coils and a solar panel that is fixed into the road whenever the vehicle passes a national highway or road. This technique has a wide range of uses outside of the luxury market. However, the same idea is also applied in applications where saving time and non-renewable energy is crucial. This allows an electric car to be charged wirelessly while in motion or while parked. Additionally, utilizing the provided microcontroller, displays, and coils reduces charging time significantly. Roads and highways are suitable for using this device. The ATmega controller microcontroller is at the center of this system. This charging mechanism finds extensive use in the luxury car industry, where robustness and longevity are crucial attributes. Circuitry for a regulator that regulates voltage as needed. Additionally, the vehicle will not wait to charge and will always be in a state of continuous charging to reach its maximum capacity.

Keywords: ATmega328, Arduino, wireless charging, controller

Keywords: Webapp, Places, Travel, Tourist guide.

Abstract: The correct identification and prediction of fish species within aquatic environment are important for effective fisheries management, biodiversity conservation, and ecosystem health assessment. Traditional methods of identifying the species of the fish species used to rely on the manual observation or invasive sampling techniques, which can be time consuming, labour intensive, and may not always provide real time data. In this research paper, we present with development of a machine learning based fish species prediction model with the use of the sample data we collected on the various fish species. Our research paper demonstrate the effectiveness of the machine learning based fish species prediction model using some machine learning based algorithm. The paper states the usefulness and effectiveness of the fish species prediction model developed through the use of machine learning algorithms over the traditional approaches used to identify the fish species. Our aim towards developing this model and following this approach was to help contribute to the people that use traditional approach in today in this modern world of technology. Our research is mainly towards the use of new technology to develop the fish species prediction model using CNN and transfer learning to increase the effectiveness of the model by using the layers of the already built predictive model and adding layers to this predictive model and making it more coustomized towards our approach of identifying the fish species.

Keywords: CNN(Convolutional Neural Network), transfer learning, machine learning.

Abstract: This paper presents a mobile application tailored to empower women against harassment and violence. The app integrates location tracking for real-time sharing with trusted contacts and an SOS alert for immediate assistance. It streamlines incident reporting to nearby police stations and facilitates uploading images as evidence. User-friendly interfaces ensure accessibility across diverse demographics. Through iterative refinement, the app continuously enhances effectiveness and user satisfaction. By providing dynamic features, it enables women to assert their safety rights and fosters communities intolerant of harassment and violence.

Keywords: Women's safety, Mobile application, Harassment prevention, Violence intervention, Location tracking, SOS alert, Police reporting, Evidence uploading, User-friendly design.

Abstract: The integration of Internet of Things (IoT) technology and Android-predicated mobile applications has enabled the development of innovative solutions for sundry authentic-world scenarios. This abstract introduces a novel application of this technology stack in the form of a “Human Following Robo-Case”. This research explores the technical aspects of the Human-Following Suitcase, including sensor protocols, integration, communication impediment avoidance, and utilizer interface design. The findings highlight the feasibility and potential benefits of this innovative solution, amending peregrinate comfort and enhancing utilizer experiences. The ESP32-CAM plays a crucial role in the development of an IoT-enabled smart suitcase designed to autonomously follow a human user. Its integration enables the system to leverage computer vision and connectivity features to achieve real-time object detection and tracking. As the IoT ecosystem and Android platform perpetuate to evolve, the Human-Following Robo-Case represents an exhilarating application of these technologies in the field of perspicacious peregrinate adjuncts. This research aims to engender a perspicacious suitcase that leverages IoT sensors and Android-predicated control mechanisms to autonomously follow its utilizer, providing a seamless and convenient peregrinate experience. The suitcase incorporates a range of sensors, including GPS, ultrasonic, and inertial quantification unit (IMU) sensors, to accurately detect and track the utilizer's position and forms of kineticism.

Keywords: Internet of things, android application, Arduino UNO, robo-case, travel partner, esp32-cam, real-time monitoring.

Abstract: In the rapidly evolving digital landscape, cybersecurity has emerged as a critical imperative, safeguarding individuals, organizations, and nations from the ever-increasing sophistication of cyber threats. the fast headway of computerized advances has introduced in an time of exceptional cyber dangers requiring vigorous cybersecurity measures to protect people organizations and countries in the midst of this advancing scene counterfeit insights ai has developed as a imposing partner reshaping the flow of risk discovery occurrence reaction and prescient analytics this comprehensive survey digs into the transformative affect of ai on cybersecurity explaining its inventive applications challenges and moral consequences through an broad writing investigation increased by industry bits of knowledge and case considers we investigate the synergistic transaction between ai and cybersecurity crossing progressed machine learning calculations for danger distinguishing proof to robotized occurrence reaction frameworks moreover we scrutinize the moral suggestions emerging from ai-powered cyber assaults and the contemplations encompassing the dependable arrangement of ai inside cybersecurity systems by synthesizing current investigate discoveries and rising patterns this paper offers an quick viewpoint on the advancing part of ai in cybersecurity lighting up both its guarantees and potential pitfalls.

Keywords: Cyber Threats; Prescient analytics ; synergistic transaction; Ai-powered cyber assaults; potential pitfalls.

Abstract: Web3 or Web 3.0 is a term coined by the internet community to describe a new era of digital interaction. The upcoming version of the internet, Web3, is founded on token economics, decentralization, and blockchain technology. While Web2 revolved around user-generated content, we are now entering a phase where users will have more control over their data, identity, and transactions on the web. The concept of a decentralized digital system is central to Web3, and this is facilitated by blockchains. It ensures fairness and democracy in the web since no single party can dominate everything. Gavin Wood, who co-founded Ethereum, is credited with introducing the phrase “Web3”.

Keywords: WEB 3.0, Crypto, Blockchains

Abstract: Forge a cloud-driven, all-encompassing platform that unites laborers, farmers, and stakeholders, driving the labor market towards optimal efficiency and establishing a new standard of transparency in interactions. The project aims to develop a cloud-based digital platform fostering seamless connectivity among laborers, farmers, and relevant stakeholders. By leveraging this innovative platform, the project endeavors to elevate the efficiency and transparency of the labor market. Through advanced digital solutions, the platform will bridge the gap between labor supply and demand, enabling effective resource allocation. This dynamic ecosystem will empower farmers to access a reliable pool of labor while offering job opportunities to laborers. Real-time data analytics will facilitate informed decision-making, leading to optimized labor utilization. The platform's user-friendly interface ensures easy interaction for all participants, fostering collaboration and mutual benefits. Ultimately, the project aspires to revolutionize traditional labor practices, cultivating a modernized, inclusive, and technologically driven agricultural sector

Keywords: farmers, digital platform, connectivity, cloud-driven, collaboration, efficiency, labor supply, labor demand, resource allocation, all-encompassing platform.

Abstract: We're developing a solar-powered water filter as part of this project. The basic principle of reverse osmosis serves as the foundation for this project. Solar radiation is captured by solar panels. This energy is then stored in a battery. The purification unit and battery are connected by means of an electromagnetic relay. The purification unit is composed of a high-pressure motor, water tank, and reverse osmosis system. The pressure produced by the high pressure makes reverse osmosis possible. The control board keeps an eye on the water level in the tank and prevents overflow. Using this method, the cleaned water is delivered to the water tank.

Keywords: water purification, solar energy, Battery, RO system etc.

Abstract: The rapid expansion of the Internet of Things (IoT) introduces complex security challenges, particularly in the areas of device authentication, data integrity, and decentralized management. Traditional security mechanisms often fall short in addressing these issues due to the unique constraints and scalability requirements of IoT networks. In response, this paper proposes a secure, blockchain-based framework for IoT device registration and authentication, implemented in MATLAB. Utilizing the principles of Elliptic Curve Cryptography (ECC) for cryptographic key generation, our framework ensures a high level of security that is both efficient and scalable, suitable for the diverse ecosystem of IoT devices. Through the integration of blockchain technology, we offer a decentralized approach to IoT security, enhancing data integrity and device authenticity across the network. The proposed MATLAB simulation provides a practical and accessible platform for exploring the application of blockchain in securing IoT devices, demonstrating the framework's effectiveness in real-world scenarios. This work not only addresses the immediate security concerns of IoT networks but also lays the groundwork for future research and development in the convergence of blockchain technology and IoT security solutions.

Keywords: Internet of Things (IoT), IoT Security, Blockchain Technology, Device Authentication, ECC, MALAB Simulation.

Abstract: ´The system's development involves the collection and preprocessing of data, the selection and training of an ML algorithm, and the implementation of object detection for hand or palm recognition. The model predicts movement based on changes in palm position, allowing for seamless mouse pointer control. The system also includes an integration with the operating system to translate these movements into actual mouse pointer actions. This innovative approach presents an intuitive and hands-free method for computer interaction, potentially benefiting users with physical impairments or those seeking more natural and immersive computing experiences. The system utilizes ML algorithms to track and interpret the movements of a user's hand or palm, enabling precise control of a computer mouse pointer. The virtual palm pointer mouse addresses accessibility challenges by offering an intuitive and hands-free interface, abbreviating the reliance on traditional input contrivances. The system has the potential to benefit users with motor disabilities, ergonomic predilections, or those seeking a more natural and fluid interaction with digital interfaces. 

Keywords: smart browsing, hand gesture recognition, computer vision, image recognition, virtual mouse.

Abstract: Handwritten characters are still far from being replaced with the digital form. The occurrence of handwritten text is abundant. With a wide scope, the problem of handwritten letter recognition using computer vision and machine learning techniques has been a well pondered upon topic. The field has undergone phenomenal development, since the emergence of machine learning techniques. This paper introduces an Offline Kannada Handwritten Text Recognition system using Convolutional Neural Networks (CNNs). The primary objective is to extract text from scanned images, accurately identify Kannada characters, and make them accessible for various applications. This work on a major scale devises to bridge the gap between the state-of-the-art technologies, of deep learning, to automate the solution to handwritten character recognition, using convolutional neural networks. Convolutional neural networks have been known to have performed extremely well, on the vintage classification problem in the field of computer vision. Using the advantages of the architecture and leveraging on the preprocessing free deep learning techniques, we present a robust, dynamic and swift method to solve the problem of handwritten character recognition, for Kannada language. CNNs, known for their effectiveness in computer vision, are employed to automate the recognition of handwritten Kannada characters. To address the scarcity of Kannada training data, handwritten samples are collected from various sources, and two recognition methods are proposed, both relying solely on CNNs. The paper briefly mentions the exploration of different datasets, without providing specific accuracy figures.

Keywords: Convolutional Neural Network (CNN), Tesseract, OCR, Handwritten Text Recognition (HTR)

Abstract: The goal of this Paper is to create a sophisticated wildlife monitoring and alert system that counts and identifies animals and trees using deep learning techniques. The technology will examine photos and videos taken by security cameras placed in nature areas using cutting-edge deep learning algorithms. In order to reliably identify different species, convolutional neural networks (CNNs) trained on a variety of datasets are utilized in the first component, which focuses on animal identification and counting. By adding to the system's capacity to identify and count trees, the second part supports ecological research and conservation initiatives. The idea incorporates a Telegram bot to improve real-time communication by instantly notifying and updating pertinent stakeholders, like environmentalists, forest authorities, and animal researchers.

Abstract: This study presents the design and implementation of an electric bicycle powered by a Brushless DC (BLDC) motor operating at 36 volts. The aim is to create a sustainable and efficient mode of transportation by integrating modern electric propulsion technology into conventional bicycles. The project focuses on optimizing the performance, efficiency, and usability of the electric bicycle while ensuring safety and reliability. Key components include the BLDC motor, battery pack, motor controller, and user interface. The system is designed to provide smooth acceleration, adequate range, and easy control for riders of varying skill levels. The project also considers factors such as cost-effectiveness, environmental impact, and regulatory compliance. Experimental validation and field testing are conducted to assess the performance and practicality of the electric bicycle in real-world conditions. The results demonstrate the feasibility and potential benefits of electric bicycles as a sustainable transportation solution.

Abstract: In recent years, the popularity of e-commerce has soared. However, many e-commerce sites are not easily accessible for visually impaired individuals due to their complex layouts and numerous elements, which makes navigation difficult using screen readers. Our project aims to develop an inclusive e-commerce website specifically designed for visually impaired individuals. To address the accessibility issues they face online, we have integrated a voice assistant that enables users to navigate the website using voice commands. Additionally, our website features a user-friendly interface that is simple, interactive, and easy to navigate. We prioritize user feedback in our iterative design process to ensure effectiveness and usability. Our ultimate goal is to empower visually impaired individuals to shop independently and confidently in the digital world.

Keywords: E-commerce, visually impaired, online shopping, voice assistant

Abstract: This comprehensive literature review investigates the efficacy and advancements of form perfectors in correcting posture deviations, leveraging the innovative technologies of OpenCV and MediaPipe. Posture irregularities, prevalent across diverse demographics, significantly impact health and well-being. Form perfectors, encompassing mobile devices and exercise regimens, offer promising solutions for addressing these concerns. However, their effectiveness, mechanisms, and integration into practice necessitate critical evaluation. Employing a systematic approach, this review synthesizes recent research findings, highlighting the multifaceted applications of form perfectors. By integrating OpenCV and MediaPipe technologies, this study extends the traditional review framework, enabling detailed analysis of posture-related data, including skeletal tracking, joint angles, and movement dynamics. Through this lens, the review assesses the effectiveness of form perfectors in mitigating common postural deviations such as kyphosis, lordosis, and forward head posture. Furthermore, the review elucidates the theoretical underpinnings of form perfectors, elucidating biomechanical principles and sensorimotor feedback mechanisms. It explores the integration of OpenCV and MediaPipe within form-perfection frameworks, enabling real-time posture assessment and personalized interventions. Additionally, this review examines the role of machine learning algorithms in optimizing form perfectors' adaptability and efficacy, paving the way for intelligent and personalized posture correction solutions

Keywords: Posture correction, Form perfectors, OpenCV, MediaPipe, Skeletal tracking

Abstract: Amid the escalating global mortality stemming from the COVID-19 virus, researchers are dedicated to exploring technological innovations to bolster the efforts of healthcare professionals. Artificial Intelligence (AI) techniques are being harnessed to swiftly and accurately predict disease severity in pa- tients with comorbidities, thereby assisting healthcare providers in their evaluations. Presently, initial detection of comorbid patients relies on X-ray images. This study centers on the development of classification models, specifically DenseNet121 and NANSNetLarge. The performance of these models is sys- tematically compared against a predetermined threshold value. The proposed models leverage DenseNet121 and NANSNetLarge with ReLU activation function and softmax pooling, resulting in accuracies of 95% and 81%, respectively. Based on the findings, DenseNet121 emerges as an effective classification model. Index Terms: Comorbid, COVID-19, DeanseNet121, NANSNetLarge ReLU, Softmax pooling.

Abstract: The programmable logic controller (PLC) is a microprocessor-based system that accepts input data from switches and sensors. It processes that data by making decisions in accordance with a stored program, and then generates output signals to devices that performs a particular function based on the application. It was developed to automate the motor control process in a way that offered flexibility to make circuit design changes easier. The original purpose of the PLC was to allow electro-mechanical and electronic input devices to communicate with a computer that would perform logical operations on the input data and output a corresponding signal to some form of output device. A PLC is designed to check the input status, execute the program, and update the output status. It also uses a programming language based upon readily identifiable symbols common to motor control.

Keywords: PLC, Vibration Sensor, Motor Protection Circuit breaker, Switch mode Power supply, Reliable operation.

Abstract: Falls among individuals pose serious risks to their health and independence, underscoring the importance of effective fall detection solutions. This study aims to address this critical issue by proposing a novel approach that integrates Computer Vision and Deep Learning for Real-time fall detection and assistance. Traditionally, fall detection systems have relied on wearable sensors, which, despite their widespread use, often suffer from drawbacks such as false alarms and discomfort for the wearer. In response to these limitations, this project introduces an efficient solution by leveraging Computer Vision and Deep Learning. The core of this innovative system lies in the integration of the YOLOv8 (You Only Look Once) which is a cutting-edge, real-time object detection algorithm that uses Convolutional Neural Network (CNN) to predict the bounding boxes and class probabilities of objects in input images with Computer Vision. YOLOv8, a variant of the YOLO object algorithm series, has demonstrated superior performance in identifying various objects, and therefore has been used in detecting fall events, with remarkable accuracy and efficiency. By combining the strengths of YOLOv8 and Computer Vision, this solution offers improved accuracy and reliability in identifying fall events and also enhances the overall user experience by providing timely assistance and ensuring the safety and well-being of individuals.

Keywords: Computer Vision, Deep Learning, Microcontrollers, bounding boxes

Abstract: This paper presents a comprehensive Machine Learning Operations (MLOps) framework tailored for neural style transfer, focusing on modularity, maintainability, and scalability. Leveraging deep learning models, particularly VGG16, and inspired by seminal works like "A Learned Representation for Artistic Style," our framework integrates cutting-edge MLOps principles to enhance development processes and reproducibility. The implementation utilizes PyTorch for neural networks, FastAPI for backend optimization and MLflow, DVC, and Dagshub for detailed experiment tracking and version control. The frontend is developed with Streamlit, ensuring user-friendly interaction, while Docker guarantees deployment portability. Continuous integration and deployment are managed via GitHub Actions, with AWS ECS and Fargate providing scalability and reliability. Terraform is employed for Infrastructure as Code, enhancing system architecture agility. This end-to-end approach aims to improve model performance, streamline pipelines, and uphold reproducibility and sustainability in neural style transfer applications, pushing the boundaries of innovation in this domain. Our integrated MLOps framework demonstrates significant potential in advancing neural style transfer technology.

Keywords: Machine Learning Operations (MLOps), neural style transfer, deep learning, model deployment, reproducibility, scalability, maintainability

Abstract: Agriculture plays an important role in the growth of a country; also, economic growth relies on the quality of the crops produced which is proportional to the diseases occurring on it. The problem occurs when the leaves of the plants get affected by multiple diseases, which requires a solution by accurately detecting the disease. Here we will be taking tomato leaves with multiple diseases into consideration. The research is based on CNN based architecture VGG16 which helps to achieve accuracy above 92% when performed on tomato leaves dataset which consist of eleven classes. PlantVillage and Tomato Leaf Diseases are two dataset sources for the collection of images for the model.

Keywords: Convolution Neural Network, VGG16, Tomato leaf diseases detection, Tomato leaf diseases classification

Abstract: Mulching has a long history as a practice of increasing soil moisture, controlling plants, controlling soil temperature, and providing a microclimate for plants. To improve crop production, there are many ways to increase efficiency and reduce the amount of water needed to grow crops. But paper mulch (also known as agricultural film) is one of the best ways to cover the soil and provide necessary aeration around your crops. There are many types of mulch, but plastic mulch is known to require less effort, so we decided to create an automatic mulch laying machine that also has a drip attachment. Moisture management in arid regions is important for crop growth. Covering the film close to the roots of the plant is to eliminate the growth of the plant and at the same time it can retain moisture and not lose soil, but this process will require spending a lot of money and time. Therefore, the "perforated mulch laying machine" will reduce labor costs and time and can complete the job of laying mulch and drilling holes in the ground at the same time.  Mulching film laying machine consists of body, main machine, cutting machine, punching machine, drip ring and punching machine. The machine spreads the mulch onto the prepared planting bed along with the drip line. This will place the cover on the mattress without damaging it and also ensure the hole is the correct size. This product can be widely used in agriculture to grow tomatoes, tomatoes, melons and other hybrid plants. Reducing investment costs and mulch placement time by using the simplest method will not cause trouble for farmers. We can control it via Bluetooth using the DC motor, Bluetooth module, ESP 32 and IoT audio to monitor the temperature, humidity and battery.

Keywords: Mulch Laying, Punching holes in one way, Moisture and Temperature Management, perforated mulch laying machine.

Abstract: Wireless sensor networks has revolutionized the environmental monitoring field, enabling collecting and analyzing real-time data over large geographic areas! A novel Wireless Weather Station is presented utilizing Long Range (LoRa) technology for transmitting data remotely. The system integrates different environmental sensors like temperature, humidifying, pressure, and rain sensors, along a LoRa transceiver module! The data is wirelessly transmitted to a central database for analysis and visualization. The hardware and software architecture of the weather station are described, detailing sensor integration with LoRa technology. Further, the results of field tests are presented to evaluate system performance, including data accuracy, transmission range, and power consumption. Our discoveries show the Wireless Weather Station's effectiveness and reliability using LoRa technology, showcasing its deployment potential in environmental monitoring applications widely! This research drives the IoT-based weather monitoring systems advancement, providing cost-effective solutions for collecting and analyzing environmental data in remote or inaccessible areas. Keywords: LoRa, Weather Monitoring, Intenet of things.

Abstract: Handwritten Character Recognition of Kannada Language using Convolutional Neural Network is the project aimed at preserving the handwritten script in digital format, particularly for Kannada language, since Kannada is a language that is spoken by almost all of the residents of Karnataka. Kannada language has 49 base characters which include 15 vowels and 34 consonants. The project focuses on converting handwritten characters or sentences by recognizing them and converting them into digital format using Convolutional Neural Network (CNN) technology. To determine the model’s effectiveness, it must first be trained, then validated and ultimately tested. The model gave a prediction performance of 97 % for the testing set. This result highlights the potential of this particular project to significant improvements in the accessibility to historical records and the streamlining of administrative processes through the successful implantation of the handwritten character recognition system.

Keywords: Convolutional Neural Network, Handwritten Character Recognition, Artificial Intelligence, Optical Character Recognition.

Abstract: Automatic trading, also known as algorithmic trading, represents the pinnacle of technological advancement in financial markets. Through the utilization of sophisticated algorithms, automatic trading systems execute trades with unparalleled speed and efficiency, operating 24/7 across global markets. These systems remove the human element from decision-making, eliminating emotional biases and executing trades based solely on pre-defined rules and criteria. By leveraging historical data, technical indicators, and statistical models, automatic trading systems can identify and capitalize on market opportunities that may be imperceptible to human traders. However, with the potential for high- speed execution comes inherent risks, including technical glitches, data inaccuracies, and susceptibility to unforeseen market events. Consequently, successful implementation of automatic trading requires meticulous development, rigorous testing, and ongoing monitoring to ensure optimal performance and risk management. Despite these challenges, automatic trading continues to revolutionize the financial landscape, offering both institutional and retail investors unprecedented access to sophisticated trading strategies and opportunities.

Keywords: Algorithm, Automatic, Flutter Framework, Risk Management, Stock Market, Strategies, Trading Bots.

Abstract: A hexapod robot is a type of multi-legged robot with six legs that is designed to mimic the locomotion and movement patterns of insects or spiders. The need for hexapod robots arises from their ability to navigate and interact with their environment in ways that traditional wheeled or tracked robots cannot. Hexapod robots can be used in many applications, including educational tools for teaching robotics and programming concepts, entertainment and hobby robotics, and even practical applications such as search and rescue operations in rugged terrains where wheeled or tracked robots cannot operate. The complexity of hexapod robots can vary significantly, ranging from simple hobbyist projects to advanced research platforms. Advances in robotics and control systems have led to the development of hexapods with impressive capabilities such as walking on uneven surfaces, climbing stairs, and even performing complex tasks requiring manipulation and object interaction. Biomechanics are at the heart of the biomimetic embodiment of a hexapod robot because legs are the most important part of the robot and they have to follow various locomotion patterns dictated by the locomotion control system.

Abstract: The project introduces “ Implementation of Smart Gas Management ”. The problem of gas leakage and fire is often encountered in our day-to-day life. Leakage of this gas raises the risk of building fire, suffocation or an explosion. As soon as gas leakage will be detected, user will be notified by using LCD display and turn off gas valve automatically. The buzzer starts beeping whenever gas is detected. The issue of fire at kitchen can be monitored with the help of flame sensor, user will be notified by using LCD display and turn off gas valve automatically. The buzzer starts beeping whenever fire is detected. When the milk spills on stove, the liquid sensor detects and the stove knob will be turn off. The Sound Sensor will detect the whistle count after completion of the whistle the stove knob will turn off automatically. In addition to these, it is often found that a person forgets to book gas cylinder due to his/her busy schedule. With the help of load sensor, the gas cylinder weight can be monitored and when the cylinder gets empty, they can book a gas cylinder. Keyword: Flame Sensor, Gas Sensor, Sound Sensor, Load Sensor

Abstract: Hostile discourse, characterized by discriminatory language, expressions of hate, or overt aggression based on individual or group identity, presents a formidable challenge in online communication. This article is an in-depth study of hate speech research, specifically the definition and classification of hate speech in text. Through a comprehensive review, the research explores various techniques, ranging from classical machine learning algorithms to advanced deep learning models such as convolutional neural networks, short-term memory networks, gated recurrent units, and transformer-based architectures, with a special focus on bidirectional LSTM with self-generating mechanisms and feedforward neural networks. Moreover, the paper offers practical insights for effective model development, emphasizing the necessity of harnessing large-scale social media datasets, ensuring data balance for representative training, implementing regularization techniques for improved generalization, and incorporating a validation set for accurate performance evaluation. By combining theories from a variety of research methods and using an integrated approach from diverse models, this study aims to provide researchers and practitioners with a conceptual framework for developing powerful models that are effective. In summary, this article highlights the importance of adapting technology to the dynamic field of online communication, with the overall goal of promoting security and benefiting diverse communities..

Keywords: Hostile Discourse Detection, Hate Speech, Machine Learning Models, Data Preprocessing, Model Training, Ensemble Approach

Abstract: AI-Enabled Home Security and Automation with Facial Recognition and Anomaly Detection, based on Arduino Uno, is a comprehensive project that employs a range of sensors and devices for enhanced safety, security, and convenience. It incorporates a fire sensor for early fire detection, triggering a water pump via a relay for fire suppression, and a gas sensor for LPG detection, which automatically opens windows through a DC motor to vent the gas. The Light Dependent Resistor (LDR) sensor distinguishes between day and night, controlling indoor and outdoor lighting accordingly. A voice reader module offers voice-activated control for lights and fans. A temperature sensor regulates the room's temperature by activating a fan through a relay, ensuring comfort. An integrated camera with facial recognition capabilities enhances security, automatically unlocking the door for known individuals and awaiting homeowner instructions for unknown persons. An IR sensor detects occupancy, turning off lights and fans if no residents are present, optimizing energy efficiency. This multifaceted project combines safety, energy efficiency, and security features, making it a sophisticated and user-friendly home automation system. Key terms: Automation, Security, Facial Recognition, Anomaly Detection, Sensors

Abstract: This paper presents an innovative approach to enhance the recognition of human hand postures within the realm of Human-Computer Interaction (HCI) applications. The primary objectives are to streamline computing processes, minimize user effort, and enhance comfort in hand posture manipulation. The authors introduce a novel application designed for computer mouse control, leveraging a sophisticated algorithm and hand feature selection methodology. Through rigorous testing, the application demonstrates commendable performance in terms of time efficiency. Moreover, the integration of hand postures with a voice assistant further enhances user experience, facilitating smoother system operation. Overall, this research offers promising advancements in HCI by amalgamating intuitive hand gestures with intelligent technological solutions.

Keywords: Human-Computer Interaction(HCI), Gesture Recognition, Opencv, Mediapipe, Mouse Control, Machine Learning.

Abstract: Face recognition technology has emerged as a smart solution for addressing various contemporary needs, including empathy and identity verification. It combines the unique aspects of biometric methods, which seek to establish individual identity through bodily characteristics, with the familiar capabilities of visual recognition systems. This project is designed to streamline the process of maintaining daily attendance records for students. The system operates by recognizing the faces of students and automatically saving their attendance status in a database.

Keywords: Face Recognition, Attendance system and Bio-metric, etc.

Abstract: Swimming has become an important sport for children and adults. Although it is a form of entertainment, it is life-threatening. According to the World Health Organization, drowning is a major threat that claims the lives of 372,000 people worldwide each year. In low- and middle-income countries, 90 percent of deaths are caused by malnutrition. The main purpose of this system is to create a swimming pool with safety measures that can predict children's poolside activities when adults are not present. This system is used to prevent drowning due to alarm. The system can be used in schools, restaurants, apartments, water parks and other places. The condition of respiratory failure caused by immersion or submersion in water is often called drowning. Most drownings happen unpredictably and no one knows it. Drowning can cause breathing problems and lead to sudden death. According to research, drowning is considered the third leading cause of death and injury worldwide. Approximately 360,000 people drown each year worldwide. The condition of respiratory failure caused by immersion or submersion in water is often called drowning. Most drownings happen unpredictably and no one knows it. Drowning can cause breathing problems and lead to sudden death. According to research, drowning is considered the third leading cause of death and injury worldwide. Approximately 360,000 people drown each year worldwide. The groups most affected by drownings are children, men and individuals. Considering that an estimated 567,090 people died from drowning in 2015, drowning is considered a major public health problem. In 2015, approximately 9% of them suffered drowning injuries. Two of them are teenagers around the age of 14 or younger. Between 2005 and 2014, there were an estimated 3,536 non-boating-related drowning deaths in the United States. Approximately ten people die every day from accidental drowning. Two of them are children 14 years old or younger. Approximately 3,650 people lost their lives by drowning. In addition, every year 332 people drown in accidents even while at sea.

Keywords: - Microcontroller, Load cell, PIR Sensor, Lifting Mechanism.

Abstract: The ever-increasing urbanization and the proliferation of vehicles have led to a critical challenge in metropolitan areas: finding available parking spaces efficiently. This paper gives an idea about IoT-based Smart Parking System with Slot Reservation to address the above issue. The system leverages the power of the IoT to monitor and manage parking spaces in real-time, offering users the ability to reserve parking spots in advance, the suggested setup comprises of several key components, including a network of IoT sensors placed in parking lots, a centralized server, and a user-friendly website or mobile application. These IoT sensors are strategically installed in parking spaces and continuously monitor their status. They detect the presence or absence of vehicles, ensuring accurate and up-to-date information about parking availability. The collected data from the provided sensors is transmitted to the centralized server, which processes and updates the information in real-time. The heart of the setup stays in the website, which allows users not only check the parking space’s accessibility in their vicinity but also reserve a spot before arriving at the parking lot. Users can view a map displaying all available parking spaces and select the one that suits their needs. Our project also contains automated ticketing system from which user will get a booking detail along with QR code to their email id. Once a parking spot is reserved, it becomes temporarily unavailable for other users, ensuring that the user has a guaranteed space upon arrival.

Keywords: IoT, Smart Parking, Slot Reservation, Receive QR Code.

Abstract: Across the India 68 million tons (50 kg per person) of edible food is wasted annually by restaurants, grocery stores, event venues, and households. This wastage contribution to environmental problems and is ethically troubling, especially when millions go hungry. Our innovative Bhoojana Vibhajana Website facilitates direct connections between generous donors and those who in need. By seamlessly channeling surplus food to those in need, we strive to create a more compassionate and inclusive society, reducing hunger.

Abstract: The world has drastically changed in recent years, with a shift toward the use of electric vehicles, which are both more comfortable and cost-effective than standard gasoline or diesel-powered automobiles. Although the number of electric vehicles produced has expanded significantly, the demand for charging stations for these vehicles has not kept up with supply. The majority of foreign nations have adopted electric vehicles in significant numbers, and as a result, household power bills have soared due to the need to charge these vehicles. For instance, the E-vehicle requires charging for more than eight hours, which quickly drives up the monthly electricity bill to $190. To lower the cost of your electricity bill, you can employ renewable energy as a power source

Keywords: EV-Electric Vehicle, Arduino-controller, LDR, GSM, MPPT controller.

Abstract: The design of Automatic vending machine. The Primary goal is to dispatch new Innovation applications in the public eye. Vending machines that dispense different types of products. Here we use a servo motor to dispense the item along with Raspberry Pi. To overcome the physical cash we are building a digital payment based on QR code (paytm UPI).The customer can select the product before scanning the QR code. After the successful payment process the particular servo motor will rotate and dispense the item. Keyword: Raspberry Pi, Servo motor,IR Sensor, Payment through QR code.

Abstract: This project presents a comprehensive deep learning method aimed at enhancing prevention of smuggling activities, forest fire detection, and emergency response through an integrated system. Utilizing Arduino Uno with an Atmega328 microcontroller, IR and Fire Sensors, and Electric Shock Plugin, the system detects wildfires, monitors animal movements, and prevents boundary crossings with controlled electric shocks. Image analysis is conducted using OpenCV and Python 3, while a Wi-Fi Module facilitates communication. Integration with the Telegram mobile application ensures real-time alerts to nearby residents. The Arduino IDE supports seamless hardware programming. By combining machine learning models, a Buzzer, and a versatile software architecture, the project promotes sustainable coexistence between wildlife and human habitats.

Keywords: Deep Learning, smuggling activities, Forest Fire Detection, Emergency Response.

Abstract: In the contemporary manufacturing landscape, the demand for multipurpose machine and is used for multiple operations in the field of mechanical engineering . The Scope of the project involves on the development and implementation of an automated system for sheet metal cutting and welding. There are sheet metal operations which also involves joining as a subsequent process. The system integrates automation & robotic technology to automate the traditionally labor-intensive processes of cutting and welding metal sheets

Abstract: This project is designed to control a robot with voice commands. An Android application with a microcontroller is used to complete the required tasks. The connection between the Android application and the vehicle is provided via Bluetooth technology. The robot is controlled by buttons in the app or commands from the user. Two DC servo motors connected to the microcontroller on the receiver side facilitate the movement of the robot. The command from the mobile application is converted into a digital signal via the Bluetooth RF transmitter and sent to the appropriate distance of the robot (approximately 100 meters). At the end of the receiver, the data is determined by the receiver and fed to the microcontroller, which ensures smooth operation of the DC motor. The purpose of the voice-controlled robot car is to perform tasks by listening to the user's commands. In order for users to work effectively on the robot, prior preparation is required. Similarly, program code is used to give instructions to the controller.

Keywords: Robot, Design, Fabrication, Sensor, Automation.

Abstract: Automated cheque processing has become increasingly important in the banking and financial sectors. With the growing volume of cheque transactions, manual processing has become inefficient, error-prone, and time-consuming. Automated systems have emerged as a solution to streamline the cheque processing workflow, improve accuracy, and reduce operational costs. In today's financial landscape, the automation of cheque processing has emerged as a critical need for enhancing operational efficiency and accuracy in banking institutions. The transition from manual to automated cheque processing systems has become imperative to meet the demands of a rapidly evolving financial ecosystem. The automated cheque processing system employs advanced image recognition and machine learning algorithms to capture, extract, and validate crucial information from the scanned checks. Through optical character recognition (OCR), signature verification, and fraud detection techniques, this system enhances the accuracy and security of cheque processing while minimizing human intervention. Neural network-driven deep learning algorithms are used to automatically extract pertinent data from checks, including account numbers, amounts, and payee information. These algorithms have overcome the difficulties presented by different handwriting styles by undergoing intensive training on big datasets, enabling them to interpret handwritten text and signatures with accuracy. In conclusion, deep learning based automatic check processing provide a revolutionary way to modernise financial transactions while enhancing dependability, and efficiency.

Abstract: "Design and Fabrication of a Receptionist Robot" aims to develop an automated system capable of performing various front-desk tasks to enhance operational efficiency and visitor experience. The robot is designed with a humanoid appearance and equipped with advanced sensors and artificial intelligence for natural language processing, enabling seamless interaction with users. The fabrication process involved selecting high-quality materials and precise engineering techniques to ensure durability and functionality. The resulting robot effectively greets visitors, provides information, and manages appointments. The successful implementation demonstrates the robot's potential in service roles, highlighting significant improvements in customer service efficiency. Future scope includes enhancing the robot's capabilities with advanced AI features, such as emotion recognition and multilingual support, and expanding its application to other service industries.

Keywords: Receptionist Robot, Artificial Intelligence, Autonomous Navigation, Customer Service, Human-Robot Interaction, Front Desk Automation, Sensor Technology.

Abstract: Amid the escalating global mortality stemming from the COVID-19 virus, researchers are dedicated to exploring technological innovations to bolster the efforts of healthcare professionals. Machine Learning techniques are being harnessed to swiftly and accurately predict disease severity in patients with comorbidities, thereby assisting healthcare providers in their evaluations. Presently, initial detection of comorbid patients dataset 273 patients. So basically in the patients dataset the parameters we have are Unnamed, Sex, BP_high, BP_low, RR, Temp, SpO2, Covid, Age. The models used for this project are lasso logistic model which is used for regression model can predict COVID-19 outcomes using clinical data. It identifies key factors for prognosis and avoids overfitting. Researchers use metrics and feature analysis to assess its effectiveness. This approach helps develop data-driven tools for personalized medicine in COVID-19 patients. And Artificial neural networks can analyze COVID-19 data to predict patient outcomes. They learn from patient details to personalize care and support clinical decisions. Challenges include choosing the right data, designing the model, and making it work for new patients. Careful planning is needed for reliable ANN models in COVID-19 research.

Abstract: Asthma, a prevalent chronic respiratory disorder, affects millions worldwide, necessitating accurate and timely diagnosis for effective management. Recent advancements in artificial intelligence (AI) have facilitated the development of non-invasive diagnostic tools, particularly in analyzing respiratory sounds. In this paper, we propose a novel asthma recognition system utilizing Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs) for analyzing respiratory sound data. The proposed system begins by preprocessing raw respiratory sound recordings to extract relevant features. These features are then fed into a CNN-LSTM architecture, which effectively captures both spatial and temporal dependencies in the data. The CNN component learns hierarchical feature representations from spectrogram-like input representations of respiratory sound, while the LSTM component learns temporal patterns and dependencies. We conduct experiments on publicly available respiratory sound datasets to evaluate the performance of the proposed system. We compare our approach with existing methods and demonstrate its superior performance in terms of accuracy, sensitivity, and specificity in asthma recognition. Furthermore, we analyze the interpretability of the CNN-LSTM model to provide insights into its decision-making process, enhancing its trustworthiness in clinical applications. Additionally, we discuss the scalability and deployment feasibility of the proposed system in real-world healthcare settings. Our findings suggest that the CNN-LSTM-based asthma recognition system offers a promising avenue for accurate and automated asthma diagnosis using respiratory sound data. By leveraging deep learning techniques, this system has the potential to improve diagnostic accuracy, reduce healthcare costs, and enhance patient care in asthma management. patients. Key Words: Asthma, Respiratory Sound, Healthcare, Machine learning

Abstract: The utilization of croaker-computer commerce bias in the operating room (OR) necessities the development of novel modalities that facilitate medical image manipulation while maintaining sterility, facilitating croaker’s attention span, and enabling quick reaction times. This concept introduces “Gestix”, a vision-based hand gesture recognition and prisoner system that can navigate and manipulate photos in an electronic medical record (EMR) database in real-time by interpretingthe gestures of stoners. Through picture input, navigation and other movements are translated to instructions based on their temporal circles. During a brain vivisection operation, “Gestix” is tried. This interface achieved a quick and intuitive reaction, simple commerce, and prevented the surgeon from shifting their posture or shifting their concentration throughout the in vivo experiment. Information gathered from two usability assessments.

Keywords: Gestrix, croaker-computer, Sterile, Navigation.

Abstract: In today's fast-paced digital world, integrating Artificial Intelligence (AI) into cybersecurity practices is crucial for making auditing processes better and faster. This paper explores how AI automation is changing cybersecurity audits, showing its many impacts. By looking at current research, we see how AI can improve traditional cybersecurity methods by spotting threats before they become big problems, reacting quickly to any issues, and making organizations stronger against new cyber dangers. AI-driven cybersecurity audits use fancy computer programs to look at lots of data in real time, finding complex patterns and weird things that might be threats. Using AI's smart predictions, organizations can stop problems before they happen. Moreover, we discuss how AI and cybersecurity work together, showing how AI tools make security better and audits easier. By using special AI programs like threat-spotting systems, organizations can find, stop, and fix cyber threats in a smarter way. This paper also explores how AI makes audits better, making sure they are accurate and complete. By letting computers do the boring parts of audits, auditors can focus on the important stuff like checking for risks and making sure rules are followed. Lastly, we explain the important rules and privacy things organizations need to think about when using AI for cybersecurity audits. This paper shares useful ideas for people who work in this field, make rules, or study it.

Keywords: Artificial Intelligence, Cybersecurity Audit, Audit Automation, Revolutionizing Security Audit

Abstract: The sending/receiving of data (data communication) is the most power consuming in wireless communication, wireless sensor networks (WSN), bio medical devices and data storage since the electronic components at transmitter end are depending on batteries not generally rechargeable characterized by limited capacity. Data compression is among the techniques that can help to reduce the amount of the exchanged data between wireless sensor nodes in bio medical devices resulting in power saving. Nevertheless, there is a lack of effective methods to improve the efficiency of data compression algorithms and to increase transmission reception energy efficiency. In this paper, we proposed a novel lossless compression approach for ECG data compression using Transition Inversion based Run Length Encoding algorithms. TIE -RLE is an optimization of the RLE algorithm, which aims to improve the compression ratio. This method will lead to less storage cost and less bandwidth to transmit the data, which positively affects the sensor nodes’ lifetime and the network lifetime in general. The proposed scheme increases run length of number zeroes and reduces reduced number of  one's transmission which reduces power consumption and increases compression ratio of ECG transmission and storage. The proposed architecture is implemented using verilog HDL and simulation/synthesize was done in Modelsim and Xylinx vivado tools.

Keywords: renewable and non-renewable, walking or jogging, generate power, piezoelectric sensor, noiseless and pollution-free.

Abstract: The development of an advanced spying robot equipped with metal detection capabilities, aimed at enhancing security and surveillance operations in various environments. At the heart of the system lies the ESP32 microcontroller, acting as the central processing unit to coordinate the robot's functions and interactions. Camera module is used for surveillance. Leveraging cutting-edge technologies, including dedicated sensors and communication modules, the spying robot offers a comprehensive solution for detecting metallic objects and ensuring effective surveillance. One of the standout features of the spying robot is its dedicated metal sensor, enabling it to identify metallic objects within its surroundings. This capability enables the robot to detect potential threats or target specific items of interest, enhancing security measures in diverse scenarios. Complementing the metal detection capability is the integration of an ultrasonic sensor, providing proximity detection to navigate obstacles and ensure safe traversal in various environments. The locomotion of the spying robot is powered by four DC motors, offering agile maneuverer ability across different terrains and environments. A enabling precise movement and swift response to commands. With integrated WiFi connectivity and compatibility with the Blynk IoT platform, the spying robot enables remote monitoring and control, enhancing its versatility and usability in various surveillance applications.

Keywords: Metal detection, Spying, Surveillance, Object detection, ESP32, Camera module.

Abstract: This People usually communicate with words, either by speaking or writing. But for deaf individuals, sign language becomes their main way of sharing information. Without someone to interpret, they face challenges in connecting with others. Sign language uses visual patterns to convey meaning, and it's not only essential for the deaf but also helpful for those with Autism Spectrum Disorder (ASD).However, there's a gap in communication between deaf individuals and the rest of society because many people don't understand sign language. To address this issue, a solution is proposed – a system that uses a camera to capture hand gestures. This system, powered by a neural network, interprets these gestures and turns them into spoken words. It's like teaching technology to understand and speak the language of sign.Sign language is crucial for those who have difficulty hearing or speaking, but it's often challenging for others to interpret. This proposed system aims to eliminate the need for an interpreter by using advanced technology. The process involves capturing hand gestures, enhancing accuracy through image processing techniques, and finally, converting the signs into spoken words using a speech synthesizer. In simpler terms, it's like creating a smart system that helps bridge the communication gap between deaf individuals and the rest of the world.

Keywords: Sign, Text, Voice, Video

Abstract: The emergence of instant messaging apps such as WhatsApp has transformed communication and resulted in an enormous amount of conversational data being collected. By analyzing this data, important insights about user behavior, preferences, and new trends can be found. In this research, we suggest a novel method for applying machine learning (ML) techniques to the analysis of WhatsApp chat trends. Utilizing natural language processing (NLP) techniques, our suggested method preprocesses WhatsApp chat data and extracts pertinent information. We use named entity recognition to find important entities referenced in chats, topic modeling to find recurrent themes, and sentiment analysis to determine the emotional tone of discussions. We also use machine learning classifiers to group conversations according to other parameters like subject, sentiment, and participant demographics. We undertake trials on a huge dataset of WhatsApp chats covering a variety of themes and user demographics in order to verify the efficacy of our technique. We assess the precision of our topic modeling, sentiment analysis, and classification algorithms, showcasing their capacity to extract significant insights from chat data. Our findings demonstrate how our ML-based WhatsApp chat trends analyzer can be used to extract insightful information from conversational data. This study adds to the expanding body of knowledge in conversational analytics and has applications in sociolinguistics, social media marketing, and customer service optimization, among other areas. Our effort intends to bridge the gap between raw conversational data and actionable insights by offering a comprehensive framework for WhatsApp chat research. This will improve our understanding of digital communication patterns and their wider social consequences.

Keywords: Data Analysis, Named Entity Recognition, Machine Learning, Classification Algorithms, and Natural Language Processing.

Abstract: This survey paper systematically investigates a drone-assisted intelligent system capable of detecting metallic abnormalities. Our solution utilizes multiple types of high-precision sensors along with machine learning-based algorithms to operate autonomously and examine metallic items or any possible metallic anomalies in the environment. The utilization of those technologies on a drone platform is more flexible, simple and efficient solution for industries like infrastructure monitoring, environment, and security. The system assists in improving the rate of detection while eliminating the need for human inspections. As our drone will be using a HD camera for live videography that will be transmitted to the mobile screen with the help of an app. This improvement will be a great step towards ensuring that both safety and workflow are perfect. Through a series of experiments that illustrate this method, we show the ability of this strategy to change the approach to detect and manage the metallic anomalies.

Keywords: Phase sequence changing, PLC Programming and data checking.

Abstract: The problem of landslides has been reported across the globe. When this happens, it leads to losses due to the destruction of properties and even sometimes death. However, there are no proper ways of alerting residents before such events occur so this is to minimize the eventual impacts. Landslides happen especially due to huge rainfall which causes considerable communication damage, loss of life, and damage to agricultural and forestlands human beings and animals depend on the Environment. Suddenly a Landslide occurred in our area and we were unable to save. The only solution to Landslides is the development of systems to predict, detect, and take preventive measures using advanced technology. A method is used to collect and analyze data during the system analysis phase. The implementation of the system will cause a reduction in losses and deaths caused by Heavy Rainfall.

Abstract: In this research, we have proposed a machine learning model that works on Random Forest Classifier, which extracts the MFCCs(Mel-Frequency Cepstral Coefficients) from baby cries and utilizes these features for predictions such as hungry, belly-pain, burping, tired and discomfort. This research can help the parents, caregivers to determine the exact reason behind the crying baby and suggesting the necessary actions to be taken further depending upon the baby cry.

Keywords: MFCCs(Mel-Frequency Cepstral Coefficients), FFT(Fast Fourier Transform), ML(Machine Learning), DL(Deep Learning), LSTM(Long Short Term Memory).

Keywords: Location-based service, GPS, time and attendance system, sending SMS, android applications.

Abstract: Alzheimer’s disease (AD) is a chronic, irreversible brain disorder, no effective cure for it till now. However, available medicines can delay its progress. Therefore, the early detection of AD plays a crucial role in preventing and controlling its progression. The main objective is to design an end-to-end framework for early detection of Alzheimer’s disease and medical image classification for various AD stages. A deep learning approach, specifically convolutional neural networks (CNN), is used in this work. Four stages of the AD spectrum are multi-classified. Furthermore, separate binary medical image classifications are implemented between each two-pair class of AD stages. Two methods are used to classify the medical images and detect AD. The first method uses simple CNN architectures that deal with 2D and 3D structural brain scans from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset based on 2D and 3D convolution. The second method applies the transfer learning principle to take advantage of the pre-trained models for medical image classifications, such as the VGG19 model. Due to the COVID-19 pandemic, it is difficult for people to go to hospitals periodically to avoid gatherings and infections. As a result, Alzheimer’s checking web application is proposed using the final qualified proposed architectures. It helps doctors and patients to check AD remotely. It also determines the AD stage of the patient based on the AD spectrum and advises the patient according to its AD stage. Nine performance metrics are used in the evaluation and the comparison between the two methods. The experimental results prove that the CNN architectures for the first method have the following characteristics: suitable simple structures that reduce computational complexity, memory requirements, overfitting, and provide manageable time. Besides, they achieve very promising accuracies, 93.61% and 95.17% for 2D and 3D multi-class AD stage classifications. The VGG19 pre- trained model is fine-tuned and achieved an accuracy of 97% for multi-class AD stage classifications.

Keywords: Medical image classification · Alzheimer’s disease · Convolutional neural network (CNN) · Deep learning · Brain MRI.

Abstract: Social networking platforms have become an essential means for communicating feelings to the entire world due to rapid expansion in the Internet era. Several people use textual content, pictures, audio, and video to express their feelings or viewpoints. Text communication via Web-based networking media, on the other hand, is somewhat overwhelming. Every second, a massive amount of unstructured data is generated on the Internet due to social media platforms. Video emotion analysis is one of the hottest topics in the video understanding community to cognize the emotion in videos for affective computing, video recommendation, and so on. Currently, many studies tend to employ different deep structures to model video contents for this task. In fact, audiences responses (e.g., physiological signals and comments) are also important since they are directly related to video emotional content and can reflect the emotions in videos.  

Abstract: In today's rapidly evolving digital landscape, the security and integrity of software applications are paramount. As technology progresses, so do the intricacies of cyber threats, highlighting the critical importance of identifying and resolving vulnerabilities. Addressing this need, we present "3D Face Reconstruction and Deepfake Detection," a project marking a significant advancement in the fields of computer vision and deep learning. We employ Volumetric Convolutional Neural Networks (CNNs) to reconstruct 3D facial models with precision and accuracy, leveraging the feed-forward properties of CNNs to ensure stability and efficiency. This innovative approach enhances the quality of 3D reconstructions, showcasing the potential of deep learning in solving complex real-world problems. Equally important, our project integrates an advanced deepfake detection system using MesoNet, which efficiently identifies synthetic facial images and ensures the authenticity of the reconstructed 3D models. By leveraging a custom dataset that combines various standard datasets, our deepfake detection model achieves high accuracy and robustness, minimizing false positives and negatives. The dual focus on 3D face reconstruction and deepfake detection exemplifies the power of machine learning in capturing intricate facial features and structures while simultaneously safeguarding against digital threats. "3D Face Reconstruction and Deepfake Detection" represents a pivotal step at the intersection of technology and innovation, redefining the processes of 3D face reconstruction and deepfake detection, and making a significant contribution to the fields of computer vision, digital security, and 3D modeling.

Abstract: Topic modeling is a very efficient data mining technique for mining text, latent data identification, and establishing links between text documents and data. Many studies in this field have been published by researchers, and these findings have been implemented in linguistic science, software engineering, political science, and medicine, among other fields.

Keywords: Topic Modeling, Latent Dirichlet Allocation, Machine Learning, Applications.

Abstract: Data mining and opinion mining used by organization in gaining customers and increasing sales. Online Customers take keen interest in creating system can take the comments and review of people on a certain product as input, and after applying properly developed mathematical model for predicting the reliability rate of a product, gives the anticipated results on the sale of one to ten. The mathematical model requires a properly designed methodology that can search in the historical data of each component and the newly collected data, the number of fake feedbacks created by competitors and general public by searching for the IP address of each of these reviews that influences the success and failure rate of the product. If same type of comments (negative feedback) comes from an IP address, it is blocked from the website. The final output is displayed based on multiple threshold calculations of the already given parameters and the results obtained from public platform on social media. The admin is responsible for adding new word to the database, adding information about the product and the specifications.

Abstract: Today’s era is the era of digitalization. Having smart phones and desktops is no less than having the world on our fingertips. Our lifestyle is involving being busy day by day. That busy, that people even find it a load to even type something to perform a task. So here comes virtual assistant at rescue. Just speak to it and the task is done. From sending a hello on WhatsApp to your friend to sending a full fleshed email to your boss virtual assistant will do it all for you. With time voice search is dominating over text searching. But what are virtual assistants? A software program that helps us perform our daily task just by speaking to it is a virtual assistant. A waking word is necessary to activate the software. This system can be used efficiently on desktops. The premise behind starting this project was that the data present on the web is sufficient and is openly available that can be used to build a virtual assistant that can make and perform intelligent decision for the user. They are intelligent computer programmes that recognise human natural languages via voice commands or text and perform tasks for the user. In this project, we will use a Python library to create your own voice assistant Index Terms – Python, Artificial Intelligence, Natural Language Processing, Speech Recognition ,Speech To Text ,Text To Speech, Python Libraries

Abstract: This study examines the planning and execution of a web-based application with the goal of enhancing user engagement and product management through several modules made specifically for various user roles. The system differentiates between the roles of ADMIN and USER, providing different levels of access and features to guarantee effective management and intuitive navigation The gateway is the Login module, which includes a mechanism for selecting a role and safe authentication using a username and password. While the USER role can only be used for browsing, the ADMIN role offers complete control over the system, including the ability to update product statuses. The New User module streamlines the process of creating an account for new users by providing a comprehensive registration form that gathers necessary personal data, including name, phone number, and email address. This guarantees smooth onboarding and incorporation inside the program. Product information, including categories, subcategories, pictures, costs, and features, is centralized in the Product module. Users with ADMIN access can add, remove, or change product details with complete control over product management. Conversely, USERS are able to examine and view the products that are offered.The Search module improves the user's buying experience by enabling users to conduct more focused searches based on name, price, category, and subcategory. This feature is intended to make the process of finding the right product easier while taking user preferences and financial limitations into account.This paper offers a thorough analysis of the architecture and operation of each module, showing how the system guarantees effective administration for administrators and a smooth surfing experience for users.

Keywords: IoT Enabled Crop Prediction and Irrigation Automation System Using Machine Learning Learning

Abstract: Health records maintaining has become the most important part in today’s medical field. While the time of emergency, it would be difficult for the doctor to know the previous health history of the patient to continue with further treatments. This project presents a health record system where a doctor can enter patients health and emergency information into our servers and it can be accessed by the doctor during the time of emergency. The main aim of this paper is to distribute patient’s data securely in data servers and performing the Quick Response Code with cryptosystems to perform statistical analysis on the patient data without compromising the patient’s privacy & give quick access to user.

Abstract: Facial A new design of pet feeder is proposed which can be controlled by interactive remote controller which helps to get rid of the manual settings of the previous versions of pet feeder. This design contains many new features as compared to the previous versions. In this design user can adjust the feed time, time gap between consecutive feeds and the quantity of feed served. This design also contains the call for pet at feed time, refill alert, dual power supply with battery charger, Massage alert system for owner in case of pet don’t get it’s feed, safety lock for container, sensor based system to serve previously served feed in case of left feed and the priority feeder with dual option of serve as by owner can opt for multi time and pet can opt for 1 time between feed time gap. Keyword: Microcontroller, Image Processing, H-Bridge, Python, Sensor, Servo motors, Message.

Abstract: The World Wide Web is a vast repository of knowledge from many diverse sources. Data, which is the most significant entity on its own, is particularly vital in the worlds of data science, computer vision, artificial intelligence, machine learning, and deep learning. Since data has already had a significant impact on so many organizations worldwide, it will always occupy center stage in the technology world. Web scraping was used to obtain data in the best possible form. The globe is chasing after the data supplied on the internet since it is so useful. Web scraping is a practice that has existed for some time and is still useful today. There are numerous forms and access methods for information on the internet. Web-based indexing or semantic processing of the material may therefore be laborious. The method that seeks to solve this problem is called web scraping. Using web scraping, unstructured web data can be converted into structured data that can be kept in a central database or spreadsheet for analysis. A few common web scraping techniques include traditional copy-and-paste, text wrapping and regular expression matching, HTTP programming, HTML parsing, DOM parsing, web-scraping software, vertical aggregation platforms, semantic annotation identifying, and computer vision webpage analysers. This comparative analysis of Web scraping tools and the techniques involved in it intends to increase the readers' awareness of this technology and aid in their quest for knowledge.

Keywords: Data science, computer vision, artificial intelligence, machine learning, deep learning, web scraping