VOLUME 13, ISSUE 7, JULY 2024

Abstract: In today's digital landscape, characterized by widespread cloud adoption, ensuring robust security measures is paramount for organizations of all sizes to protect sensitive data and maintain business integrity. However, small and mid-sized companies often face challenges in implementing comprehensive security solutions due to budget constraints and limited technical expertise. The paper presents an innovative approach to address these challenges by integrating open source into our cloud security assessment tool, which aligns with the methodologies outlined in the MITRA framework. By leveraging these frameworks, our tool provides comprehensive and cost-effective security assessments, allowing companies to identify and mitigate vulnerabilities within cloud environments efficiently. Through a user-friendly interface and clear recommendations for remediation, our tool empowers organizations to navigate the complexities of cloud security with confidence, ensuring that potential risks are addressed proactively. By harnessing the power of opensource frameworks and adhering to industry best practices outlined in the MITRA framework, we ensure accessibility and affordability, democratizing access to robust security measures for organizations of all sizes. Overall, our approach represents a significant advancement in cloud security assessment, offering practical solutions tailored to the evolving needs of small and mid-sized companies in today's digital landscape. Index Terms: AWS, Opensource, Security, MITRA Framework, PACU, Cloud Automation.

Abstract: Frequency hopping techniques are used in CDMA communication systems, where several hopping frequencies are allocated for each user within a specific frequency range for all users. The number of frequencies within a certain frequency range is fixed so that the interference noise is reduced.The frequency hopping algorithm for these frequencies varies from one user to another. In this paper, we propose a practical method for a frequency hopping system using a programmable hopping algorithm stored in ROM for the case of slow FHSS and fast FHSS, and for three users and eight frequencies , this system is designed using a cyclone II EP2C20F484C7 FPGA from ALTERA placed on education and development board DE-1 with the following parameters: -Clock frequency: FCLK=50MHz -Modulation type of signal is : 2FSK. -Frequency range: (0.011 Hz…10 MHz). -Frequency Resolution: (0.011 Hz). -Signal amplitude (5V). -Controlled parameters: values of hopping frequency, number of hopping frequencies, type of FHSS . -Update capability: changing hopping frequency algorithm, changing modulation type: BPSK, MFSK, increase frequency range up to 20MHz , changing data frequency and hopping frequency.

Keywords: FHSS, CDMA , FSK, FPGA, DDFS, SFHSS, FFHSS.

Abstract: The immutable, transparent, and decentralized nature of blockchain technology has found widespread application across various sectors including the Internet of Things, finance, energy, and healthcare. As the Big Data era unfolds, there's a growing demand for data sharing and exchange among companies and organizations to enhance services through data analysis and mining. However, traditional centralized data platforms encounter challenges such as privacy breaches, high transaction costs, and lack of interoperability. Integrating blockchain into this domain offers promising solutions by facilitating decentralized data storage and exchange, enabling access control, identity authentication, and copyright protection. Despite the emergence of numerous blockchain-based schemes for data sharing and exchange, there exists a gap in literature regarding comprehensive reviews and summaries of such endeavors. DataValue is a blockchain-based platform designed to revolutionize personal data control, providing users with enhanced benefits, privacy assurances, and a novel paradigm for data management in the digital era. With a core focus on user empowerment, DataValue introduces the concept of Tokens, allowing users to monetize their data and receive rewards in return. This innovative approach shifts the conventional data-sharing landscape, emphasizing individual ownership and control over personal information. Users on the DataValue platform enjoy robust privacy measures, gaining unprecedented control over the sharing and deletion of their data. The system introduces a digital marketplace where users can leverage their data for rewards, fostering a community-driven ecosystem. Additionally, DataValue extends beyond a transactional platform by incorporating educational resources on data privacy, providing insights into personal data usage, and facilitating connections within the community. This comprehensive suite of features represents a paradigm shift, transforming the digital economy by placing data ownership and user empowerment at the forefront of its design. DataValue stands as a beacon for a more transparent, user-centric approach to data management.

Abstract: In today's digitally-driven world, AI voice assistants have emerged as indispensable tools,seamlessly integrating into our daily lives. These intelligent virtual companions, powered by artificial intelligence and natural language processing, possess the ability to understand and respond to voice commands, transforming the way we interact with technology. This abstract delves into the realm of AI voice assistants, exploring their functionalities, applications, and the underlying technologies that drive their capabilities. We examine how these assistants can perform a wide array of tasks, from answering queries and sending emails to providing real time information and controlling smart devices. Moreover, we discuss the challenges faced by AI voice assistants, including privacy concerns and potential biases, and highlight the ongoing advancements that promise to shape the future of human-machine interaction. As AI voice assistants continue to evolve and become more integrated into our daily routines, they hold the potential to redefine convenience, efficiency, and accessibility in the digital age.

Keywords: Artificial Intelligence, NLP, Speech Recognition, Virtual Assistance.

Abstract: Audiobooks are ideal for anyone who, like the majority of us, likes to listen rather than read. It is just not possible to purchase and store them in your home on a bookshelf. Audiobooks are also a good method to relax your eyes and take a break from the continual stimulation of digital devices. Others can take advantage of them to save time. For example, keep up with books while doing different tasks at same time. It has the potential to not only alleviate problems for millennials, but also to be a highly useful tool for visually impaired people. The ability to transform any material into an audiobook is a true gift to civilization. Our technology can be put to use in the development of such tools. Text-to-speech and other read-aloud programs are widely utilized to assist students in developing their reading comprehension abilities. A PDF to audio system is a screen reader program that has been designed and developed specifically for the purpose of effective audio communication. International Organization for Standardization (ISO) established PDFs as an open standard document format for the aim of displaying and transmitting information securely (ISO). One of the most convenient formats for electronic communication and information transmission is the document format. It's critical if we want to improve accessibility for screen readers by including audio into our material. Among the features PDF documents provide are text links and buttons as well as audio and video files. Many languages may be supported by the PDF to audio technology, which will allow users to hear text being read aloud (spoken).

Keywords: Audiobooks, Communication, Text-to-Speech

Abstract: The “COMIPEDIA”: A creative platform that will help you to showcase your talent for writing, creating art, and editing for novels. An Indian platform that is a celebration of reading, writing, and creativity. It features comic novels from Indian content and cultures, as well as original works by talented Indian creators. Users can enjoy reading, writing, commenting, and interacting with other comic lovers on COMIPEDIA. A comic novel app encourages users to as well as write, it helps people interact and one gets praise when he/she showcases their talent, and their skills to people. Share their imagination, their world of magical words and creative art. A comic app represents an imaginary world created with one's creative mind. Comic novels with a touch of Indian culture sound interesting right?! A platform for creativity and explorers of creativity. A comic, novel, and short story platform is a website or an app that allows you to read, write, and share stories in different formats and genres. You can access a wide range of stories from various authors and genres, such as romance, fantasy, horror, comedy, etc. You can express your creativity and imagination by writing your own stories and getting feedback from other readers and writers. You can connect with a community of like-minded people who share your passion for storytelling and literature. You can discover new talents and inspirations from other writers and stories. Getting feedback from other writers can be very helpful for improving your writing skills and gaining new insights. It refers to the way writers connect with their audience, both interpersonally and intellectually. Interpersonal connection means acknowledging the reader’s presence, perspective, and expectations, while intellectual connection means guiding the reader through the argument, evidence, and implications of the text

Keywords: COMIPEDIA, comic novel, Praise, Showcase

Abstract: Land mine detection is vital throughout warfare to deploy armed vehicles with detection technology within the enemy territory. The increasing threats of terrorism have necessitated the development of advanced technologies for the timely detection of explosive devices. This study introduces a novel approach to landmine detection using wheeled mobile robots equipped with a sensor integration of metal detectors, IR sensors and ESP32 micro controller. The proposed system leverages the sensitivity of IR sensors to detect a temperature spike to enhance the efficiency and safety of landmine detection operations. The mine detection system comprises a lightweight metal detector mounted on a custom-designed mobile robot chassis. The metal detector is configured to identify metallic components commonly found in explosive devices. The mobile robot is equipped with autonomous navigation capabilities and, enabling it to cover large areas rapidly and transmit data to a ground control station. Moreover, an IR sensor is also used to detect heat spikes which are normally emitted by the buried mines.

Keywords: Metal Detector, IR, ESP32, Sensor Integration.

Abstract: In the study of artificial intelligence, Visual Question Answering is becoming a more important subject since it sits at the critical nexus of Computer Vision (CV) and Natural Language Processing (NLP). In the fields of CV and NLP, VQA has emerged as a major research area due to its cognitive capability. The semantic information needed for image captioning and video summarization is already present in still photos or video dynamics; it just needs to be extracted and articulated in a way that makes sense to humans. On the other hand, VQA doubles the effort linked to artificial intelligence by requiring semantic information from the same medium to be compared with the semantics implied by a query expressed in natural language. Transformers model is applied to the CV field and combines the transformers based NLP algorithm to construct a VQA system, based on a large number of actual scene photographs [1-3] on the KAGGLE platform. The results of the experiment validate the usefulness of their model by demonstrating that it can provide accurate answers in a simple and ordered setting and that there is a definite discrepancy between the generated results and the real answers in a chaotic scenario. We have considered the Issues or challenges based on VQA research as per the current scenario.

Keywords: Visual Question Answering (VQA), Computer Vision (CV), Natural Language Processing (NLP), Long Short-Term Memory (LSTM), MDETR, Issues or challenges based on VQA and VQA in Ontology.

Abstract: The relentless growth of the internet, coupled with the unprecedented surge in e-commerce activities due to factors such as the global COVID-19 pandemic, has created an expansive digital landscape. However, this flourishing environment has attracted a commensurate increase in cyber threats, particularly concerning the theft of sensitive user information, such as credit card data from e-commerce platforms. This paper introduces an innovative approach by developing a sophisticated Deep Belief Neural Network (DBNN) for intrusion detection which was implemented using Python. This DBNN is seamlessly integrated with Snort, a renowned intrusion detection system, and fortified by the inclusion of a web application firewall. Snort boasts of a robust signature database which aided the identification and elimination of intrusions. A web application firewall is included to foil intrusions at the application layer using rules targeting SQL injection and DoS attacks. By so doing, sensitive customer information such as credit card information which has been a shortcoming with previous systems can be protected. A correlation coefficient of 0.78 between the latency and response time for the baseline and attacked states of the server shows the web application firewall’s ability to maintain the smooth running of the server during intrusion attempts through DoS attacks. In rigorous testing, the DBNN demonstrates a commendable 91.2% accuracy, affirming its efficacy in identifying and thwarting intrusion attempts. The study contributes significantly to knowledge by showcasing that this integrated defense strategy substantially enhances the security posture of e-commerce platforms. A significantly low false positive rate of 8.14% buttresses the effectiveness of the hybrid system in the face of evolving cyber threats in the contemporary digital landscape.

Keywords: Intrusion Prevention System, Deep Belief Neural Network, Denial of Service, E-commerce

Abstract: When compared to two-stage converters, this five-stage converter helps the inverter handle almost twice as much power. Design issues with power conditioning units for grid-connected solar photovoltaic systems include power quality, efficiency, dependability, implementation costs, etc. In order to solve the majority of the practical limitations of central DC source application, this article discusses a single DC-source-based five-level-doubling network high-resolution multilevel inverter topology with the right combination of switches. To boost efficiency and double inverter utilization, a five-stage high-resolution multilevel inverter solution is modified. This work also demonstrates the system's ability to handle reactive power and block faults. MATLAB/Simulink is used to extensively simulate the converter. The proposed concepts' effectiveness is confirmed by the laboratory prototype's experimental findings. A common PV array powers the main bridge, while separate sources power the auxiliary bridges. Even though these separated sources need far less electricity, The overall cost of the system reflects it. A low-gain PI controller has been used to eliminate these isolated sources. The dc source in this converter only feeds the main bridge. With the aid of transformers, all major bridges for grid-connected solar PV applications are combined and fed by a single PV array. During unbalancing, there won't be any mismatch because three DC buses are combined. As a result, the system will not stray from MPPT and will continue to provide power quality. Between the PV and the inverter, there is a boost converter. When compared to single-stage converters, this two-stage converter enables the inverter handle almost twice as much power.

Abstract: Agricultural productivity is something on which the economy highly depends. This is one of the reasons that disease detection in plants plays an important role in the agricultural field. Having a disease in plants is quite natural. If proper care is not taken in this area then it causes serious effects on plants due to which respective product quality, quantity, or productivity is affected. For instance, little leaf disease is a hazardous disease found in (chili, banana, potato, and tomato) plants. Detection of plant disease through some automatic technique is beneficial as it reduces the large work of monitoring big farms of crops, Employing automated techniques for detecting plant diseases is beneficial, as it greatly reduces the extensive labour required to monitor large agricultural fields. The leaf diseases often manifest their symptoms on the leaf area during the early stages of infection. These infections can be analyzed and classified automatically using computer vision and machine vision systems, which employ image-processing techniques to interpret the information. The paper gives a brief review of major plant diseases that show symptoms in leaves and explains in details by involving image processing techniques.

Keywords: Leaf disease, Digital image processing, Color classification, Pattern classification.

Abstract: The convergence of robotics, Internet of Things (IoT), cloud computing, and machine learning is revolutionizing the concept of virtual doctors. This paper explores the integration of robots as nurses, IoT devices, and cloud-based systems to create an advanced virtual doctor platform.Robotic nurses are designed to assist with routine tasks, patient monitoring, and interaction, while IoT devices collect real-time health data from patients. This data is transmitted to cloud-based systems where machine learning algorithms analyze it to provide accurate diagnostics and personalized treatment recommendations. The study examines the benefits of this integrated approach, such as enhanced patient monitoring, increased accessibility to healthcare, and improved efficiency in medical services. Additionally, the paper addresses the technical challenges, including data security, interoperability of devices, and the accuracy of machine learning models. The findings suggest that this multi-faceted approach has the potential to transform healthcare delivery, particularly in remote and resource-limited settings, by offering comprehensive and continuous medical

Keywords: SSL Stripping Attacks, Elliptic Curve Cryptography (ECC), Advanced Encryption Standard (AES), Authenticated Encryption, Key Exchange, Data Integrity

Abstract: The goal of this project is to use laptop vision and augmented reality technologies along with TensorFlow, PyTorch, and OpenCV to develop a web application for an AR virtual becoming room. Typically, the recommended tool is made for the web-based environment [13]. The primary necessity for detecting, identifying, and tracking human body actions is to interact in actual-time with the recommended software content material, which include digital garb, with the use of a digital camera. The vital and primary person interfaces on this utility are the garment catalog, garment information, and digital camera preview [13]. Furthermore, real-time popularity and detection of the skeleton joint positions in human beings is finished thru the software of a human frame detection and motion monitoring model. In evaluation to other tasks and demonstrations presently in life, our model illustrates the stay pictures to check the outcome of categorization via an accurate evaluation of the anticipated and real effects concerning the accuracy price of every person in real time. In precis, a human body detection and movement monitoring model is included into the improvement of an augmented reality (AR) digital becoming room net software for clients [1].

Keywords: Machine learning, Pytorch, OpenCV, TensorFlow, Augmented Reality, Real- time recognition.

Abstract: Identification of blood groups plays a vital role in the medical field for any treatment, ensuring compatibility in transfusions and other procedures. Currently, this task is typically performed manually in laboratories, a time-consuming process that requires skilled experts. To address the constraints and limitations of conventional blood group prediction methods, MATLAB techniques have been developed. These techniques incorporate image processing, including segmentation processes, to classify blood groups efficiently. By collecting blood samples and processing them through image classification with feature extraction, the variety of blood types based on ABO and Rh systems can be accurately identified. This advanced methodology mitigates the drawbacks associated with traditional methods, primarily reducing manual errors and enhancing speed and accuracy. The implementation of these techniques allows for the rapid and precise classification of blood groups, which is crucial in medical emergencies and routine diagnostics. The integration of image processing with artificial intelligence significantly enhances the reliability and efficiency of blood group determination. This technological advancement not only ensures faster results but also reduces the dependency on human expertise, minimizing the risk of errors. Consequently, this innovative approach represents a significant improvement over conventional methods, providing a robust solution for the timely and accurate identification of blood groups. This development is particularly beneficial in critical situations where time is of the essence, ensuring that patients receive the correct blood type promptly, ultimately saving lives and improving healthcare outcomes.

Keywords: Blood group type, feature extraction, Histogram, Image processing, MATLAB, Segmentation.

Abstract: This project is dedicated to developing an advanced system for the detection and moder- ation of hate speech on a social media platform. It involves data collection, pre- processing, and the application of deep learning algorithms to train a model. The system utilizes a database for efficient data storage and systematically evaluates comments on user- generated content. When it identifies offensive or hateful comments, it offers users the choice to either remove or keep them, while also allowing users to report profiles engaged in inappropriate behavior. The primary goal of this project is to improve content moderation on the social media platform, fostering a more inclusive and respectful online environment.

Abstract: A secure environment is unattainable without the implementation of encryption technology. Given that images constitute a significant portion of multimedia data, safeguarding them is crucial in the modern context. The major challenge lies in how we can effectively protect our data. Encryption involves transforming a piece of information by encoding it such that only authorized individuals can decode, read, and understand it. This protects the information from unauthorized access by malicious entities. The encryption process involves subjecting the data to a series of mathematical transformations, producing an alternative form of the original data. This sequence of mathematical operations is known as an algorithm. In this paper, we have conducted a survey of various research papers and reviewed existing encryption techniques. Based on our survey, we also discuss the concept of two-way encryption, analyzing it in conjunction with the Data Encryption Standard (DES) for improved security.

Keywords: Encryption, Encoding, multimedia, confidentiality, integrity, authenticity, cryptography.

Abstract: Load balancing in cloud computing environments is a critical area of research that ensures efficient resource utilization, minimized response times, and improved overall system performance. This survey paper provides an extensive review of various load balancing strategies and algorithms employed in cloud computing, categorizing techniques into heuristic, meta-heuristic, hybrid, and machine learning-based approaches. The problem involves distributing dynamic workloads across diverse computing resources to prevent bottlenecks and ensure efficient processing. Numerous algorithms have been developed to address this issue, each with specific strengths and weaknesses. Key studies, including recent advancements and emerging trends, are highlighted to offer a comprehensive understanding of the state-of-the-art in load balancing for cloud computing. The results demonstrate the effectiveness of various algorithms in enhancing cloud performance, with reinforcement learning-based approaches and hybrid algorithms showing particular promise. This survey underscores the importance of developing advanced techniques to address evolving challenges, with future research directions focusing on integrating AI and machine learning for more adaptive solutions.

Keywords: Load balancing, Cloud computing, Heuristic approaches, Machine learning, Resource utilization

Abstract: The start of 6G wireless communication letters a transformative leap in connectivity, offering unparalleled rapidity, ultra-low latency, and massive capacity. Central to this evolution is cooperative communication, which leverages collaborative strategies among multiple nodes to enhance network performance. This paper provides a comprehensive exploration of the functionalization, evolution, challenges, and applications of cooperative communication within 6G networks. By examining the underlying principles, potential benefits, and inherent challenges, we aim to shed light on the critical role cooperative communication will play in the advancement of wireless technology. Our analysis underscores the transformative impact of these collaborative approaches, highlighting their potential to address key issues in connectivity, reliability, and efficiency, thereby paving the way for a more robust and versatile 6G network infrastructure.

Keywords: Cooperative Communication, 6G, Wireless Communication, Wireless Networks

Abstract: Breast cancer remains one of the leading causes of mortality among women worldwide. Early detection through screening is pivotal in improving survival rates and treatment outcomes. Over recent years, machine learning (ML) algorithms have emerged as powerful tools in enhancing breast cancer screening processes. This review paper provides a comprehensive analysis of the state-of-the-art ML algorithms employed in breast cancer screening. We explore various supervised, unsupervised, and reinforcement learning techniques, assessing their effectiveness in image analysis, risk prediction, and diagnostic accuracy. Key contributions include a detailed examination of convolutional neural networks (CNNs) in mammogram analysis, the role of support vector machines (SVMs) and random forests (RFs) in feature extraction and classification, and the application of ensemble methods in improving prediction robustness. Additionally, we discuss the integration of ML algorithms with clinical workflows, highlighting challenges such as data heterogeneity, interpretability, and ethical considerations. Through this analytical review, we aim to provide insights into the current landscape of ML applications in breast cancer screening, identify gaps in existing research, and suggest directions for future studies to enhance the efficacy and reliability of these technologies in clinical practice. Index Terms: Deep Learning, Breast Cancer, Machine Learning (ML) Algorithms, Convolutional Neural Network, Support vector Machine

Abstract: Recognizing human activity is essential to improving interpersonal relationships and interactions between people because it provides important insights about a person's identity, personality, and psychological condition. The difficulties in the field are shown by how difficult it is to appropriately extract this information. Research in artificial intelligence and machine learning is primarily focused on the ability of humans to perceive actions, which is propelling developments in a wide range of applications. Robust activity recognition systems are required for a variety of applications, including robots, human-computer interaction, and video surveillance. Recognition of human activity has become an important area of research in image and video analysis. Numerous research has examined this subject over time, emphasizing both its importance and the continuous search for better approaches. In this regard, we suggest a unique method to improve the accuracy of human action and activity recognition using OpenCV, Convolutional Neural Networks, and Graph Neural Networks based on deep learning. Our approach uses CNN and GCN algorithms, which are excellent at finding features and patterns in pictures and video sequences, to train a large dataset. This is enhanced by OpenCV, a potent real-time computer vision technology, which makes the identification system's implementation easier. Our method seeks to achieve high precision in identifying and categorizing different human actions by combining CNN, GCN and OpenCV, advancing fields like security, UI design, and autonomous systems.

Keywords: CNN, GCN, deep learning, OpenCV, human action/activity recognition.

Abstract: This paper presents a novel clustering scheme for optimizing energy consumption in Flying Ad Hoc Networks (FANETs) using a Secure and Hybrid Bio-Inspired Optimization (SHBIO) method, integrating Binary Whale Optimization Algorithm (BWOA) and Ant Colony Optimization (ACO). The proposed approach involves calculating the optimal number of cluster heads (CHs) based on coverage demand and bandwidth balancing. By considering UAV energy, inter-cluster and intra-cluster distances, and load balancing, the method selects optimal CHs. Clusters are maintained efficiently, and the nearest high-energy node is chosen for communication. Performance metrics such as end-to-end delay, network lifetime, throughput, packet delivery ratio, and packet loss were evaluated. Results demonstrate that the SHBIO-BWOA_ACO method significantly outperforms previous methodologies, achieving lower energy consumption, higher throughput, and improved network performance.

Keywords: Flying Ad Hoc Networks (FANETs), Binary Whale Optimization Algorithm (BWOA), Ant Colony Optimization (ACO), energy consumption, clustering, network performance, packet delivery ratio, throughput, end-to-end delay.

Abstract: This survey explores the secure and hybrid bio-inspired optimization techniques for Flying Ad-Hoc Networks (FANETs), addressing the limitations of traditional methods in dynamic and complex environments. Novel bio-inspired algorithms, such as clustering schemes and routing protocols, are proposed to enhance adaptability, robustness, and energy efficiency. Despite advancements, FANETs face significant challenges in security and performance. This study reviews recent developments in bio-inspired optimization, analyzing their efficacy and highlighting novel approaches like BICSF and multi-hop clustering algorithms. The proposed algorithms demonstrate improvements in secure communication and efficient resource utilization. The survey concludes that bio-inspired techniques offer promising solutions for optimizing FANETs, paving the way for future research to address existing gaps and enhance the overall performance and security of these networks.

Keywords: Bio-inspired optimization, clustering schemes, routing protocols, FANETs, secure communication, energy efficiency, dynamic networks.

Abstract: The increasing prevalence of chronic diseases and aging populations has created significant challenges for healthcare systems worldwide. To meet these challenges, there has been a growing interest in leveraging advanced technologies, such as data fusion and cloud storage, to enable more efficient and effective healthcare services. The design methodology employed for this innovative system is object-oriented analysis and design, providing a structured and systematic framework for the development process. Furthermore, the utilization of the Python programming language enhances the system's efficiency, scalability, and maintainability. By integrating a data fusion model, the system combines data from multiple sources to provide a more accurate and holistic view of patient health, thus enhancing the diagnostic process. This fusion of diverse data types, coupled with the robust CNN architecture, ensures a high level of precision and reliability in disease detection. This dissertation highlights an approach to conducting checks on various chronic diseases, including malaria, typhoid, heart disease, diabetic retinopathy, liver disease, and fetal health, utilizing Convolutional Neural Networks (CNN). The developed model exhibits an exceptional accuracy rate of 99.98%, underscoring its effectiveness in disease detection. The findings of this research represent a significant leap forward in leveraging advanced technologies for precise and comprehensive chronic disease diagnostics, with implications for improving healthcare outcomes and patient well-being.

Keywords: Smart Health Care, Data Fusion, Chronic Diseases, Convolutional Neural Network

Abstract: Keeping track of attendance while engaging students in the classroom may be tough, especially when the class is big. The conventional method of calling pupils' names is tedious and time-consuming, and proxy attendance is always a possibility. To address this problem and maintain track of students' attendance, a smart attendance management system (SAMS) using face recognition and location has been presented. The traditional method is replaced with a mobile application, which eventually reduces the use of pen and paper. The application needs to be installed on the mobile by the student. The application will serve as a user interface that can be accessed by teachers, students, and admins. Overall attendance can be viewed by students using face recognition, and their statistical data is also presented in the application. Each student can be tracked using a unique user ID, and the student's presence can be recognized using GPS coordinates, typically longitudes and latitudes.

Keywords: Smart Attendance, Face Recognization, Gio Location.

Abstract: Artificial intelligence (AI) is transforming a number of industries, including business, healthcare, robotics, and the arts. Artificial Intelligence (AI) in robotics improves automation and precision, enabling safer and more effective manufacturing and logistics operations. AI helps the healthcare industry by enhancing patient outcomes and accessibility through telemedicine, personalised treatments, and enhanced diagnostics. AI produces creative works in the art world that subvert conventional ideas of authorship and creativity. Companies use AI to improve operational efficiency, data-driven insights, and personalised marketing. AI has the potential to revolutionise society, but it also presents ethical issues that need to be carefully managed. These issues include algorithmic prejudice, data privacy, and employment displacement.

Keywords: Artificial Intelligence (AI), Robotics, Healthcare, Art, Business, Automation, Diagnostics, Personalised medicine, Creative AI, Data-driven insights, Ethical consideration, Algorithmic bias.

Abstract: Most of the educational institutions in Kenya are unable to facilitate full functional services of e-learning using conventional e-learning systems due to various reasons such as providing the necessary information and communication technology support. Rapid advancement of technology has prompted the institutions to enhance teaching and learning. Cloud computing has become an emerging and adoptable paradigm in education around the globe over the years with its promising benefits such as reliability, scalability, flexibility and reasonable cost to provide more effective e-learning systems. This study sought to develop an implementation framework for cloud-based learning in technical and vocational colleges in Kenya with the aim of enhancing educational accessibility, improving instructional quality and fostering technological readiness for an innovative and sustainable e-learning environment. The specific objectives were; to determine the e-learning systems implemented in technical and vocational colleges in Vihiga County; to evaluate the factors influencing implementation of cloud-based e-learning systems in Technical and vocational colleges in Vihiga County; and to develop an implementation framework for cloud-based e-learning systems for technical and vocational colleges. The study was premised on Technology-Organization-Environment framework and Unified Theory of Acceptance and Use of Technology. The study adopted descriptive research design and mixed methods approach. Purposive and stratified sampling were used when selecting the sample size of 91 respondents drawn from the target population of 951 consisting of administrators, trainers from different departments and information and communication technology trainees using published tables. Questionnaires and interview schedules were the main data collection instruments. Content validity was used besides pilot study to measure the validity of the instruments while reliability was measured through the test-retest procedure using Cronbach's alpha coefficient. Quantitative data was analyzed using descriptive and inferential statistics while qualitative data was analyzed using thematic analysis. The results of quantitative analysis were presented using frequency tables, charts and graphs. The study established that the utilization of conventional e-learning systems in technical and vocational colleges in Vihiga County was below average and there was a gap in cloud-based e-learning systems implementation. The institutions had inadequate information and communication technology infrastructure and internet connectivity, inadequate technical capacity and policies to effectively implement cloud-based e-learning. The study developed a cloud-based e-learning systems implementation framework for technical and vocational colleges premised on cloud-based infrastructure, institutional readiness and user characteristics as the main influencing factors. The study concluded that the existing e-learning systems were insufficient to facilitate quality and reliable e-learning delivery.

Keywords: E-Learning, E-Learning Systems, Conventional E-Learning Systems, Cloud-Based E-Learning Systems, Cloud Computing, Framework

Abstract: The artificial intelligence makes significant use of face recognition. In this study, we employ cutting-edge technology to recognize the many faces included in the image. Locating missing children in cities, towns, etc. and tracking down offenders who have escaped from prison. By uploading photos of criminals from the criminal department's database as well as more recent photos of criminals arrested in recent crimes, this project makes it easy for the crime branch to identify offenders. In the proposed research, we will identify faces in photos using machine learning techniques including HAAR (High Altitude Acute Response), facial landmarks, and CNN (Convolution Neural Network algorithm). This algorithm can operate in real time and can recognize faces in photos regardless of their size or position. The user's old image and fresh image are submitted into this system, which then determines whether or not the two images match. This technology will make our society more secure while reducing crime.

Abstract: Farmers are the backbone of Indian Society. They grow the needed staple food for us. Sometimes due to confusions, they are not able to know about range of crops grown in nearby places because of which they land up in trouble which leads to heavy debts or suicidal of the farmers. So, to provide such information to the farmers in helping them, get to know the kind of crops grown in their nearby places and also grow a variety of crops which would yield in quality crops and profit, a web-based application is developed. This application will help the farmers or users to predict the ratio of different crop grown, so that farmer will be able to analyse the situation and harvest according to ratio already specified. In this application, location based as well as crop-based search are done so that maps will display and it will be easy to know the ratio of crop harvested and also predict the price of particular crop in specified location. It also allows searching the nearby areas to guide the farmers in step-by-step process for particular crop harvesting and also enable them to chat with relevant specialists to get useful information.

Keywords: Crops, predict, location based, harvesting.

Abstract: Reversible or information lossless gates have applications in nano-technology, digital signal processing (DSP) and in communication The power consumption is one of the biggest challenging issues for designing of VLSI circuits within the advanced technology. The reversible logic is one among the best approaches for low power application The main objective of this paper is to design and implementation of a magnitude comparator using reversible logic approaches. In this paper a 16-bit and 32-bit magnitude comparator are implemented with using reversible logic gates. The simulation of 16-bit and 32-bit magnitude comparator is carried out using Verilog HDL coding in Xilinx Software. Simulation results provide significant improvement in power consumption for 16-bit and 32-bit magnitude comparator using the proposed reversible logic gates method. Therefore, the proposed scheme can provide a significant improvement in comparator circuit in chips for future generation of VLSI blocks.

Keywords: Reversible, Verilog HDL, Xilinx, BJN gate, Power consumption.

Abstract: With the appearance of blockchain technology, it is currently conceivable to address different dispersed framework security issues in beforehand crazy methods. The decentralization of blockchain's evenly disseminated records is a critical part of this capacity. Through the organization of cryptographic frameworks, such decentralization has to a great extent superseded unified power's security functionalities. All in all, the major part that makes blockchain technology suitable is public or uneven cryptography. The blockchain experience has as of late opened the entryway for the healthcare business to integrate these know-hows into their electronic records. This reception permits the utilization of unbalanced cryptography, for example, hashing, carefully marked exchanges, and public key framework, to store and impart symmetric patient records to the legitimate coalition of emergency clinics and healthcare suppliers in a safe decentralized framework. These include expert patient perception software, drug following software, and electronic wellbeing records (EHR). It is pivotal to take note of that the main edge of the right insight morals is the healthcare professionals' moral mindfulness.

Keywords: Blockchain Technology, Internet of Things, Healthcare, Data Science

Abstract: With digitization we achieve the electronic form of the document as a copy of physical document. The electronic form of document increases the life of document and also the accessing capabilities. Most of the organization are moving towards digitization no matter what kind of document it may be. Digitization is one time process unless and until the document get altered or modified, thus we have DMS system also know as Document Management System to work with us. In this paper we are focusing how to develop the DMS system so as to digitized, maintain and access the document from any place anytime with appropriate access using block chain technologies. Further we also focuses on the security aspects of DMS system.

Keywords: Document, Document Processing, Security, Authorized Access, Document Retrieval, Digital transformation, Digitization, Workflow, block chain.