VOLUME 13, ISSUE 12, DECEMBER 2024

Abstract: The financial services industry handles transactions amounting to trillions of dollars daily, necessitating a focus on cost-efficiency, transparency, and security. Prior to the integration of blockchain technology, intermediaries such as money transfer services, stock exchanges, and payment networks frequently encountered cybercrime. Blockchain technology, initially popularized by cryptocurrencies like Bitcoin, has since become a transformative force across various financial sectors. This technology enhances the industry by providing secure, transparent, and cost-effective transaction protocols through encryption and algorithms. This prose explores the significant advancements blockchain has brought to financial services, emphasizing its role in revolutionizing insurance, asset management, banking, and the stock market.

Keywords: Blockchain Technology, Financial Services, Cybersecurity, Transaction Transparency, Cost-Efficiency

Abstract: Traffic sign detection plays a pivotal role in enhancing road safety and enabling autonomous vehicles. Indian roads, with their unique multilingual signs and dynamic environments, present significant challenges due to diverse regional languages, fonts, and conditions. Addressing these complexities is essential for developing reliable navigation systems for autonomous bots and vehicles. This objective aims to design and implement a real-time traffic sign detection system for Indian roads using the YOLOv5 model deployed on a Raspberry Pi. The system integrates multilingual detection capabilities and dynamically displays decisions in a terminal interface, enabling autonomous bots to operate efficiently in unpredictable environments.  The methods in the dataset comprising multilingual Indian traffic signs were collected and annotated. The YOLOv5 model was trained with augmented data to enhance detection accuracy. The trained model was optimized for edge devices using TensorRT and Pytorch. A Raspberry Pi, integrated with a depth camera, processed real-time video streams for detection. Detected signs were mapped to pre-programmed actions, which were displayed in the terminal and executed via bot navigation. The Results of the system achieved high detection accuracy and low latency, even under challenging lighting and weather conditions. Multilingual OCR integration ensured robust detection of diverse traffic signs. Real-world tests demonstrated reliable navigation and responsive action execution. The project's significant contribution to traffic management, road safety, and autonomous vehicle technologies, addressing the unique challenges of multilingual environments. The scalable solution has implications for smart city initiatives and real-time navigation systems on Indian roads.

Keywords: YOLOv5, Autonomous Vehicles, Traffic Sign Detection, Multilingual OCR.

Abstract: The College Arrangement Cell (CPC) serves as a bridge between understudies looking for business and potential bosses. It rearranges the situation handled through organized back and assets, improving the chances of effective placements. Students create proficient profiles highlighting abilities and encounters. The framework interfaces understudies with work openings based on their capabilities. This call centers on the imperative part of understudy administrations in encouraging effective college arrangements. We are going examine the different assets accessible to understudies, counting scholarly exhorting, career advising, internship openings, and workshops aimed at upgrading employability. The session will moreover cover procedures for successfully interfacing understudies with these administrations, tending to common challenges, and cultivating a steady environment that empowers understudy engagement and victory. By highlighting best hones and victory stories, we point to improving mindfulness and utilization of understudy administrations, eventually making strides in situation outcomes.

Keywords: placement, cell, employers, employment, success, opportunities, job, students, work.

Abstract: This project presents a control system to enhance the performance of a solar panel. A dual-axis mechanism is developed that tilts and turns the solar panel to face the highest intensity of light. The system is designed in LabVIEW and implemented on the Arduino Microcontroller. The physical model of the system was built using servo motors, LDRs and wiper. The pilot plant was tested by applying a source of light from various directions and monitoring its response. The solar panel is able to face towards the highest intensity of light with high level of precision. A LabVIEW simulation interface is developed, allowing for comprehensive monitoring and visualization of key performance metrics, including solar panel voltage, current output, and battery status.

Keywords: Arduino Microcontroller, LDRs, Servo motor, Solar panel, Wiper, LabVIEW.

Abstract: The paper outlines the design and implementation of a wearable glove system specifically developed for CPR monitoring and vital sign measurement. This innovative system integrates multiple sensors to track compression rate and depth during CPR while simultaneously measuring critical health indicators such as ECG (electrocardiogram), body temperature, and blood pressure. The system offers real-time feedback through a mobile application, enabling first responders to optimize CPR quality and make data-driven decisions during emergency situations. The goal of the system is to enhance the effectiveness of CPR, ensuring that compression depth and rate align with established guidelines, ultimately improving patient outcomes. This comprehensive monitoring and feedback mechanism assists healthcare providers and emergency medical services (EMS) in delivering high-quality, life-saving care in critical moments.

Keywords: CPR monitoring, ECG(electrocardiogram), Body Temperature, Blood Pressure , EMS(emergency medical services)

Abstract: Automated Toll Collection System has gained significant momentum in recent years due to its ability to streamline and optimize toll payment processing for highways and bridges. This advanced system utilizes Global Positioning System (GPS) technology to accurately track vehicle locations and enable electronic toll collection without manual transactions. The system boasts high accuracy, offering customization to accommodate different vehicle types and toll fees. It is also highly flexible and scalable, making it capable of adjusting to fluctuating traffic volumes and changing toll rates. In this system, a GPS device is installed on the vehicle, which communicates with a centralized server. This server calculates the toll based on the real-time distance travelled by the vehicle using the Haversine formula. The toll is then automatically deducted from a pre-loaded digital wallet or charged to a designated seamless payment gateway linked to the vehicle owner’s account. By eliminating the need for cash transactions and toll booth stoppages, this system offers improved convenience for drivers, reduces traffic congestion, and contributes to lower environmental impact compared to traditional toll collection methods. Embracing this technology has the potential to revolutionize toll management and enhance overall transportation efficiency, improving user experience and reducing delays.

Keywords: Raspberry Pi, LCD Display, GPS Technology, Distance Travelled, Payment Gateway Web App.

Abstract: Management of attendance is a fundamental com ponent of classroom assessment. Traditionally, manual processes, such as roll calls or attendance sheets, which are time-consuming and susceptible to errors. This paper proposes a smart attendance system that uses facial recognition technology to improve and optimize attendance tracking in educational institutions. Using advanced techniques like convolutional neural networks which is an algorithm specifically for deep learning that uses layers to perform convolution, activation, pooling, and other processes. CNN is used for object recognition tasks, such as image classification, detection, and segmentation, the system captures student images using high-definition cameras and compares them with pre-recorded data to mark attendance accurately. The system au tomatically updates the attendance records in a central database for administrative use. This smart and real-time method reduces human intervention, minimizes time waste, and eliminates errors, offering a reliable scalable solution for attendance management. By integrating emerging technologies like computer vision, this approach not only improves the attendance process but also establishes a foundation for enhancing overall organizational efficiency.

Keywords: facial recognition, attendance system, automation, Convolutional Neural Network (CNN), computer vision.

Abstract: It is now hard to live in the society these days by women. They feel handicapped in such situations and require help to save them from such dangerous conditions. There are many technologies introduced for women, but unfortunately, words like kidnapping, eve teasing, and sexual harassment are still very much alive in the country. When women encounter such unsafety situations, establishing an automatic detection system that sends up an alert message along with the location of the police department is what has to be done. This may include abnormal sounds, shaking, fearfulness, and heartbeat. These could be detected using appropriate sensors and provided the alert message. This paper surveys the existing mechanism for location detection, communication sending, and parameter collection from the human body via sensors.

Keywords: Distributed Ledger Technology (DLT), Smart Contracts, Security, Transparency, Integrity, Voter Anonymity, Verifiability, Cryptographic Techniques, Consensus Mechanisms, Scalability, Democratic Processes.

Abstract: Facial detection and recognition are revolutionary technologies in computer vision designed to identify and verify individuals. These systems are used in a variety of areas, including security and personalized services. This article explores the techniques, challenges, practical uses, and ethical implications of facial detection and recognition.

Keywords: Facial Detection, Facial Recognition, Computer Vision, Deep Learning, Security, Privacy.

Abstract: This paper provides a comprehensive survey on virtual brain development using EEG (Electroencephalogram) and IoT technologies. As advancements in hardware, software frameworks, and Brain-IoT wearable sensors enable real-time brain data analysis, virtual brain research is rapidly advancing. These innovations enhance the creation of brain-IoT systems for monitoring and analysing brain activity, which offers promising applications in healthcare, neurotherapy, and cognitive research. This study explores key trends such as EEG-based IoT models, machine learning integration, and cloud computing platforms that support these advancements. The paper also addresses the need for energy-efficient infrastructure to support bandwidth demands in the IoT cloud, aiming to accelerate the future development of virtual brain technologies..

Keywords: Virtual mind, Brain Computer Interface, Electroencephalogram, wearable sensors, Internet of Things, Cloud.

Abstract: Stress is a natural reaction to various stress-inducing factors which can lead to physiological and behavioral changes. If persists for a longer period, stress can cause harmful effects on our body. The body sensors along with the concept of the Internet of Things can provide rich information about one’s mental and physical health. This project is based on the stress recognition algorithm using face images and Expressions which can recognize stress from images acquired with a general camera. Additionally, a CNN design that receives facial landmarks as input to take advantage of the fact that eye, mouth, and head movements are different from normal situations when a person is stressed.

Keywords: Stress detection, emotion detection, Internet of Things (IoT), machine learning.

Abstract: In response to global food security challenges and the necessity for sustainable farming practices, this paper introduces a Smart Agriculture Management System utilizing IoT and sensor technologies to enhance agricultural efficiency, productivity, and sustainability. The system comprises a network of crop sensors, soil moisture sensors, and humidity sensors that continuously monitor soil and crop health in real-time. By leveraging IoT connectivity, the system facilitates the collection and analysis of crucial data, enabling precise and timely decision-making for farmers. This architecture integrates cloud-based data storage and analytics platforms, processing and visualizing sensor data to provide actionable insights via user-friendly interfaces. Automated irrigation systems, governed by real-time soil moisture data, optimize water usage, thereby reducing waste and increasing crop yields. Additionally, predictive analytics, utilizing historical and real-time data, offer recommendations for fertilizer application and pest management, ultimately minimizing chemical usage and promoting crop health. Field trials affirm the system's efficacy in improving resource management, crop quality, and farm profitability. The implementation of smart technologies exemplifies the transformative potential of IoT and sensors in revolutionizing agricultural practices, fostering sustainability, and addressing the pressing challenge of feeding a growing global population.

Keywords: IoT, Sensor technologies, Pest management

Abstract: This robotic system combines advanced technologies to enhance military security and immediate medical access. It employs AI-driven face recognition for personnel identification, ensuring secure access in critical zones, and laser targeting to detect and track threats. Landmine detection technology allows safe navigation through hazardous terrains, while ultrasonic sensors enable autonomous obstacle avoidance. In emergencies, the robot detects soldier distress, sends an SOS alert, and autonomously provides access to first aid supplies. These integrated capabilities improve battlefield safety, reduce response times, and increase operational efficiency, making the system a versatile and reliable tool for modern military operations.

Keywords: Deep Learning, Face Recognition, Military Robotics and SOS alert.

Keywords: CNC machine, Arduino-Uno, CNC Sheild, G-code.

Abstract: This project aims to create an integrated automation system in response to the growing demand for innovative solutions in use of robotics in military security, this work endeavors to bridge existing gaps by introducing an enemy detection system with automatic weapon delivery system integrates advanced recognition, encryption, and navigation technologies to address security challenges. The system enables authorized personnel registration using a user module that captures multiple angles and encrypts the data with a password. A robot equipped with a web camera identifies authorized and unauthorized individuals through a trained dataset of images. The weapon delivery subsystem employs a line-following sensor for accurate navigation to predefined base stations automatically and includes a manual control mode to navigate through any location. This modular approach ensures adaptability in dynamic environments without human intervention.

Keywords: Enemy Detection System, Weapon Delivery, Line Following, Predefined Base Stations

Abstract: This brief presents an approach for a technique to systematically tradeoff accuracy in exchange for area, power, and delay savings in digital circuits is proposed: gate-level pruning (GLP).  The methodology is first demonstrated on adders, achieving up to 78% energy-delay-area reduction for relative error. It is then detailed how this methodology can be applied on a more complex system composed of a multitude of arithmetic blocks and memory: the discrete cosine transform(DCT), which is a key building block for image and video processing applications. Even though arithmetic circuits represent less than the entire DCT area, it is shown that the GLP technique can lead to energy-delay-area savings over the entire system for a reasonable image quality loss. This GLP approach can be Implemented using Verilog HDL and Simulated by Modelsim 6.4 c. Finally it’s synthesized by Xilinx tool.

Keywords: DCT, Verilog HDL, Xilinx tool.

Abstract: Industrial robots are prone to failure due to harsh working environments, which affects movement accuracy. The fault diagnosis of industrial robots has become an indispensable part of robot collaborative maintenance in intelligent manufacturing. Most existing diagnostic methods only use a single data source, and the diagnostic accuracy will be affected due to signal acquisition errors and noise interference. This paper proposes a multi-source data fusion and channel attention convolutional neural network (MD-CA-CNN) for fault diagnosis of multi-joint industrial robots. The network takes the time domain data and time-frequency domain data of the vibration signal, torque signal, and current signal of the six joints of the robot as input. Then, we realize the diagnosis of the faults by using a Softmax Classifier layer after the two parts of feature extraction and feature fusion. In addition, a channel attention mechanism is developed. It acts on the two parts of feature extraction and feature fusion, respectively. It assigns weights to different source data and weights to time-domain and time-frequency domain features.

Keywords: 360 degree camera, Tensor flow, Digital Image Processing, Conveyer Belt

Abstract: Approximate computing is a paradigm shift in energy-efficient systems design and operation, based on the idea that we are hindering computer systems’ efficiency by demanding too much accuracy from them. Interestingly, large number of application domains, such as DSP, statistics, and machine learning. Approximate computing is suited for efficient data processing and error resilient applications, such as signal and image processing, computer vision, machine learning, data mining etc. Approximate computing circuits are considered as a promising solution to reduce the power consumption in embedded data processing. This paper proposes an FPGA implementation for an approximate multiplier based on selective fractional part based truncation multiplier circuits. The performance of the proposed multiplier is evaluated by comparing the power consumption, the accuracy of computation, and the time delay with those of an approximate multiplier based on exact computation presented. The approximate design obtained energy efficient mode with acceptable accuracy. As compared to conventional direct truncation proposed model significantly influences the performance. Therefore, this novel energy efficient rounding based approximate multiplier architecture outperformed other competitive model. 

Keywords: FPGA,DSP,Approximate Multiplier

Abstract: This work proposes the design of a system to create and handle Electric Vehicles (EV) charging procedures, based on intelligent process. The Electric Vehicles charging should be performed in effective way. One of the significant challenges with widespread electric vehicle adoption is related to vehicle charging. Many potential EV drivers have range anxiety or don’t want to spend much time charging an EV battery on long trips. Although dynamic wireless charging may seem like something out of a science fiction movie, it could be a viable way to overcome vehicle charging issues. These wireless power transfer systems work while the vehicle is in motion, providing numerous benefits. Dynamic wireless charging for electric vehicles allows them to charge while moving with the help of copper coil. The addition of gate system with payment web application enhances accessibility and convenience to users. Battery heat detection through voltage and temperature sensor adds safety to this system.

Keywords: Copper coil, Web application, Voltage and temperature sensor

Abstract: Efficient crowd management in public transportation enhances passenger comfort, safety and operational efficiency. This project introduces a smart allotment system for managing crowds in public transport, focusing on real-time monitoring of bus capacity and bus stop crowd density. The system comprises two modules: the bus module and the bus stop module. The bus module uses an ESP32 microcontroller, IR sensors for passenger counting, and a DC motor for automated door control. Real-time seat availability is displayed on an LCD within the bus and shared with the bus depot via Zigbee communication.

Keywords: ESP32, Microcontroller, IR Sensors, DC Motor, Zigbee module, LCD Display.

Keywords: Malware Detection, YARA Rules, Network Traffic Analysis, Real-Time Detection, Cybersecurity, Pattern Matching, Malware Analysis, Threat Identification

Abstract: Secured data communication is crucial in the modern era of digital interactions. And also introduces a secure cryptographic technique for multimedia communication, incorporating audio, text, and image transmission using advanced technologies such as Light Fidelity (Li-Fi), Zigbee modules, and a Telegram bot. For audio communication, the system utilizes Li-Fi to transmit encrypted audio signals between a speaker and a solar-powered receiver, ensuring both security and energy efficiency. Solar panels are employed to power the communication system, making it sustainable and reducing dependency on external power sources. For text communication, Zigbee modules provide a low-power, reliable method for transmitting encrypted messages between the transmitter and receiver. Finally, a Telegram bot is integrated to enable the secure transmission of encrypted images, offering a user-friendly interface. The system applies cryptographic algorithms to protect data integrity and confidentiality across all communication channels. The proposed solution provides a comprehensive, energy-efficient, and secure multimedia communication framework, suitable for diverse applications. Index Terms:   Wireless communication , Encrypted data, Decryption, Zigbee modules, Cryptography, Multimedia, Li-Fi, Solar Panel, , Data Security, Sustainable Communication.

Abstract: Passenger security in railways is a critical concern, with increasing incidents of robberies and delays in FIR registration. To address these issues, we propose R-Help, an Android-based mobile application enabling passengers to register complaints effortlessly. The system uses a real-time database to store and manage complaint data, ensuring streamlined tracking and resolution. Passengers can lodge complaints with minimal inputs, upload supporting evidence, and receive a unique complaint ID. The application forwards complaints directly to Railway Police Force (RPF) officers for prompt action. It also provides real-time status updates, enhancing transparency and user convenience. Unlike existing systems, R-Help addresses delays in FIR registration, particularly in emergencies like accidents and assaults, where time is crucial. By digitizing the process, it eliminates manual intervention and minimizes inefficiencies, making complaint redressal faster and more reliable. This solution aims to improve passenger safety and accessibility through a tech-driven approach.

Keywords: Railway Security, complaint registration, Complaint tracking

Abstract: This project presents the development of an EMG-controlled lower limb exoskeleton designed to aid individuals with hemiplegia in regaining mobility and enhancing rehabilitation outcomes. Utilizing an Arduino microcontroller, EMG sensors, and a DC motor, the exoskeleton responds to muscle signals, enabling intuitive control that mimics natural leg movement. An accelerometer sensor is incorporated for gesture recognition and fall detection, providing an added layer of safety by monitoring unintended movements and potential falls.

Keywords: EMG-sensors, Arduino UNO, H-Bridge, Hemiplegia.

Abstract: The paper aims to decrease the number of accidents that occur on curved roadways. To do this, a warning LCD Display that displays as a vehicle approaches from the other side of the bend serves as a message to the driver. The IR transmitter and receiver sensor, which is connected to the Arduino Uno microcontroller, is used to detect the vehicle. And Motor operated gates are fixed upon each sides for free passage of vehicles from one side to other side. On the winding roads in the ghat portion, this might save thousands of lives. By implementing a new technique, they come up with a plan to prevent accidents after determining their causes and effects. Two IR sensors make up the new method, which alerts the vehicle on the opposite road. Landslide is one of the hazardous and critical geographical process, which damages to civil infrastructure and property as well as causes loss of life. This paper is an attempt with regard to the expansion of a landslide susceptible approach by using Accelerometer Sensor. And Rain Sensor is used for detecting heavy rainfall. Upon detecting the landslide condition or Heavy Rains it warns on display as a message and closes gates on either sides of ghat till road condition gets normal.

Keywords: LCD display, Arduino Uno microcontroller, Accelerometer Sensor.

Abstract: Robotics is the division of engineering which deals with the manufacturing, production and application of robots. There are many types of robots like Ariel, ground, wheeled, industrial, mobile robots etc. Spider robot is a type of ground robot capable of walking. Current status of this project is that our robot can freely move along all axes . Till now our spider can be controlled by a wireless control remote. The robot can be used for both indoor and outdoor purposes. The project’s main hardware includes ESP 32, IP camera and servo motors. This robot ideal case is to work according to our instructions like rotating in all direction for video surveillance etc. The robot can be regarded as a basic prototype for a robot which works according to our instructions or can make its own decisions, based on the sensors output, and then executes those decisions using servo motors to change the position or to move in a require pattern

Keywords: Spider Bot, ESP32 Controller, Face Recognition Application, Proximity Sensor, Intruder Detection.

Abstract: This project focuses on developing a comprehensive system for ship detection, passenger monitoring, and maritime safety using Synthetic Aperture Radar (SAR) imagery and IoT-based automation. Initially the system  detects the ships using SAR images and employs an infrared (IR) sensor, connected to an ESP32 microcontroller, to count passengers boarding the ship. Once the passenger count exceeds a preset threshold, the system activates DC motors to automatically close doors.  underwater UV sensor detects obstacles, and a crack sensor monitors the ships structural integrity. To improve maritime security, the system incorporates RF modules to monitor border crossings and GPS tracking to trace the ship's location, even when network coverage is lost. Additionally, a sink detection mechanism is integrated to send alerts via Telegram if abnormal tilting or potential sinking is detected.​

Keywords: SAR images, RF Modules, ESP32 module, GPS, UV Sensors, IR Sensors, ADXL Sensors.

Keywords: Defect detection, DAM health diagnosis, multimodal sensors, water analysis, crack detection.

Keywords: Humanoid Robot, Healthcare, Sensors, Arduino Mega, Raspberry Pi 3B+, Deliver, Interact, Surgical instruments.

Abstract: Artificial Intelligence (AI) and it is one of the considerably important ways to improve cyber security. This investigation looks at the ways AI is used in the areas of anomaly detection, threat intelligence, and automated response to incidents. It also deals with issues such as adversary sponsorship, privacy violation, and lack of trained experts. The paper sights case studies, mentioning the advantages and disadvantages of using of Artificial Intelligence in the sphere of cybersecurity. AI offers great opportunities, but it is necessary first to resolve its weaknesses, and ethical issues related to its use.

Keywords: Artificial Intelligence, Anomaly Detection, Adversarial Attacks, Ethical AI, Machine Learning, Deep Learning.

Keywords: RFA Random Forest Algorithm, Back Propagation, Price prediction, Crop Growth, Improve Yield,Price,Plant Disease Classification

Abstract: The process of donating an organ can save lives by bridging the supply and demand for organs. However, the system's effectiveness is hampered by issues like a lack of transparency, ineffective logistics, and worries about data security. With its decentralized, unchangeable, and secure structure, blockchain technology provides a revolutionary way to get past these challenges. The potential of blockchain technology to transform organ donation through increased transparency, data integrity, and stakeholder trust is examined in this abstract. The lack of transparency in the donor-recipient matching process is one of the main issues surrounding organ donation. By establishing a decentralized ledger that documents each transaction, including donor registrations, organ availability, and recipient information, blockchain technology can solve this problem. Since these documents are unchangeable and time-stamped, all parties involved—including hospitals and regulatory.

Abstract: The sixth generation (6G) of wireless networks, which can meet the various demands of modern communication, heralds a transformative era marked by intelligent, self-configuring networks. This study examines how Quantum Machine Learning (QML), a keystone technology, will influence 6G network architecture in the future. Beyond the constraints of conventional methods, 6G networks can dynamically adapt to changing network states and user requirements in real-time by integrating machine learning (ML), quantum computing (QC), and QML. We perform an extensive review of ML, QC, and QML advancements, highlighting their potential applications and challenges in the context of 6G networks, by leveraging insights from 5G and Beyond 5G (B5G) technologies. In addition, we present a novel framework for 6G communication networks that addresses important issues in air interface design, network infrastructure, edge computing, and user optimization. It incorporates both QC-assisted and QML-based approaches. The transformative potential of quantum and QML-assisted technologies in reshaping wireless communication systems is highlighted in this paper. Keywords: 6G Communication Networks, Quantum Computing, Machine Learning, Beyond 5G, Parallel processing, Quantum communication, Cutting-Edge Networking, Revolutionary Network Paradigms, Isolated artificial intelligence.

Abstract: An AC dust detection filter is an essential part of modern air conditioning systems designed to improve indoor air quality and system efficiency. It captures dust, pollen, and other particulate matter that can accumulate over time, preventing them from circulating through the air. Many of these filters feature integrated sensors that monitor the level of dust buildup and can trigger alerts or automatic cleaning cycles when maintenance is needed. By preventing the clogging of internal components, these filters contribute to the AC’s overall performance and longevity, ensuring that the system operates at peak efficiency. Additionally, by reducing dust accumulation, they help in minimizing the risk of respiratory issues and allergies, offering a healthier living or working environment. AC dust detection filters are particularly beneficial in areas with high dust levels or in homes with pets, where dust and allergens tend to accumulate more rapidly.

Keywords: Include at least 4 keywords or phrases.

Abstract: Acute respiratory Disease (ARD) is a viral respiratory disease caused by Severe acute respiratory syndrome (SARS), associated coronavirus. It was first identified at the end of February 2003 during an outbreak that emerged in China and spread to 4 other countries. WHO coordinated the international investigation with the assistance of the Global Outbreak Alert and Response Network (GOARN) and worked closely with health authorities in affected countries to provide epidemiological, clinical and logistical support and to bring the outbreak under control. ARD is an airborne virus and can spread through small droplets of saliva in a similar way to the cold and influenza. It was the first severe and readily transmissible new disease to emerge in the 21st century and showed a clear capacity to spread along the routes of international air travel. SARS can also be spread indirectly via surfaces that have been touched by someone who is infected with the virus. Most patients identified with SARS were previously healthy adults aged 25–70 years. A few suspected cases of ARD have been reported among children under 15 years. The case fatality among persons with illness meeting the current WHO case definition for probable and suspected cases of ARD is around 3%. This ARD is of different type, to determine the exert type one is suffering from amongst the various diseases is what we intend to achieve in this research. We shall search out the various types of Acute Respiratory Deseases, search out their various types of symptoms/Signs, determine their Distinctions, know their % relevance, and compare the relevant ratios, using Fuzzy Cluster Means (FCM) Algorithm for clustering of the signs, SQL which we employed for the database query and MysQl Server (PHPmyAdmin) which we used as the data backend (database).

Keywords: Fuzzy cluster means (FCM); Algorithm; Model, Computing, Architecture, SARS-COV-2; SARS-COV-2 (COVID-19); SARS-COV; MERS-COV; HCOV-NL63, Influenza

Abstract: There has been a spike in digital bullying in online groups and similar online public platforms such as Twitter in recent years. These incidents have been seen to have a negative impact on the victim's social, democratic, and economic well-being. Despite its well-documented adverse effects, leading online communities have done little to fix it, citing the sheer size and diversity of such comments and, as a result, the impractical number of human moderators required to achieve the task. we develop this automated digital bullying in online group identification on Twitter from the standpoint of the suspects, focusing on two factors- accidents and prudes. Bullying tweets are ordered into 5 types- offensive language, abusive language, ethnic, sarcasm and neither, In addition, each tweet is labeled as one of these kinds of non-shaming. Our objective is to automatically categorize tweets into the five types listed above. For each of the types, the data cleaning and feature-based steps are applied to both the named training set and the evaluation set of tweets. Finally, a web application for muting shamers attacking a victim on Twitter was designed and implemented based on the categorization and identification of bullying tweets.

Abstract: Flood is one of the most disruptive natural hazards, responsible for loss of lives and damage to properties. A number of cities are subject to monsoons influences and hence face the disaster almost every year. Early notification of flood incident could benefit the authorities and public to devise both short and long terms preventive measures, to prepare evacuation and rescue mission, and to relieve the flood victims. Geographical locations of affected areas and respective severities, for instances, are among the key determinants in most flood administration. Thus far, an effective means of anticipating flood in advance remains lacking. Existing tools were typically based on manually input and prepared data. The processes were tedious and thus prohibitive for real-time and early forecasts. Furthermore, these tools did not fully exploit more comprehensive information available in current big data platforms. Therefore, this project proposes a novel flood forecasting system based on fusing meteorological, hydrological, geospatial, and crowd source big data in an adaptive machine learning framework. Data intelligence was driven by state of the-art learning strategies. Subjective and objective evaluations indicated that the developed system was able to forecast flood incidents, happening in specific areas and time frames. It was also later revealed by benchmarking experiments that the system configured with an MLP ANN gave the most effective prediction, with correct percentage, Kappa, MAE and RMSE of 97.93, 0.89, 0.01 and0.10, respectively.

Keywords:

• Flood forecasting
• Natural hazards
• Monsoon influences
• Early notification
• Preventive measures
• Evacuation and rescue
• Geographical locations
• Big data
• Machine learning

Abstract: Fingerprint-based biometric systems are vulnerable to attacks involving altered or forged fingerprints. This paper introduces a robust machine learning model for detecting altered fingerprints, utilizing the SOCOfing dataset containing 6,000 real and 49,270 altered fingerprint images. The model employs a convolutional neural network (CNN) to extract critical features such as ridge patterns, minutiae points, and texture details, achieving high accuracy and reliability. Our results demonstrate significant improvements in biometric security, paving the way for advanced applications in forensics and authentication systems. The findings also highlight the importance of AI-based security solutions and propose methods to scale the model for real-world applications. Future studies can focus on optimizing CNN architectures and integrating hybrid models for increased robustness.

Keywords: Altered Fingerprints, Machine Learning, SOCOfing Dataset, Convolutional Neural Networks, Biometric Security

Abstract: The project is a multi-pronged platform for India to preserve and demonstrate its rich cultural past together with the modernization of technologies. The implementation of Augmented Reality for tourist purposes [8][9][10] led to the design of the platform that offers virtual reality tours of historical monuments and cultural landmarks, and thus, teaches the public the history of such locations and their historical significance. An artisans' space is part of a cultural marketplace scheme, which is partially based on community tourism paradigms [6][7], of designing a cultivation estate from where local artists can showcase their authentic, handcrafted works and generate revenues from their skills; thus, “community restoration and crafts delivering possibilities” has become a reality. Concepts of engageable learning and motivation through gamified experiences [3][4] make India's heritage learning into an interactive and pleasurable experience. Additionally, an AI-driven cultural chatbot, together with the developments in AI and NLP [1][2], permits to have an uninterrupted communication with smart gadgets about the country's culture and the event's history, which contributes to the discovery of historical information unique and authentic. Through the combination of AR, e-commerce, gamification, and artificial intelligence, India has devised a novel and comprehensive method for the preservation of its cultural heritage filled with many layers, which will touch the hearts of the future generations to a higher degree of comprehension and unflappable dedication.

Keywords: AR, 360° Virtual Tours, Gamification, Interactive Learning, Cultural Chatbot, Artisans Marketplace, Heritage e-commerce, AI Insights, Immersive Education, Virtual Tourism.

Abstract: Morse code, a communication method based on sequences of dots and dashes, plays an important role in various communication systems, especially in emergency situations and assistive technologies. This paper presents a simple yet effective Morse code decoder system using an Arduino UNO, a 16x2 LCD with an I2C interface, and a laptop for input. The proposed system decodes Morse code signals sent from a laptop and displays the corresponding text on the LCD. The aim of this work is to develop an efficient and cost-effective solution for both communication and assistive purposes.

Abstract: As per the recent Indian Economic Survey, agriculture in India employed over half of the workforce available. Consequently, it is crucial to recommend crops those are most suitable for varying soil types and environmental conditions to promote sustainable agricultural practices. This goal can be achieved by utilizing ML, including DL algorithms for managing complex datasets and natural language processing techniques. This paper gives an overview and complete insight about studies and works done on soil analysis and crop recommendation systems to give idea about better algorithms for crop recommendation systems using the latest Machine learning also DL algorithms for better accuracy and efficiency, highlighting their significance, effectiveness, and practicality in crop recommendation systems, with the relevant datasets.

Keywords: Crop recommendation, Crop prediction, Fertilizer recommendation, Yield prediction, Rainfall prediction Soil analysis, Machine learning, KNN, Random Forest, Decision Tree.

Abstract: This project aims to create an interactive and engaging platform for visualization of data structures and algorithms (DSA) to enhance learning and understanding. Key features include simulation of real-world problems. It demonstrates a practical application of the algorithm, such as routing. Network routing and social network analysis [1][2]. Built-in chatbots support user browsing, while discussion boards promote community interaction and collaborative learning. [4] Gamified learning elements such as quizzes and mini-games combined with a leaderboard system prompt user to deepen their understanding, debugging tools with memory visualization, algorithm comparison methods [8], playback controls (play, pause, rewind, next) and other additional features for users to explore DSA on their own. It can allow users to create, edit, and save notes during a session. It supports personalized learning, combining interactive learning tools, gamification, and integrating real-world problems. The platform is transforming the way users understand and engage with data structures and algorithms to better support students and professionals.

Keywords: DSA Visualization, Gamified Learning, Algorithm Comparison, Memory Debugging, Interactive Education, Real-World Simulations, Personalized Learning, Quizzes, Chatbot, Community Forum.

Abstract: Systems for detecting and recognizing traffic signs are now crucial parts of intelligent transportation systems, especially for driver-assistance and autonomous cars. In this study, an embedded platform-based traffic sign detecting system that is both economical and effective is designed and implemented. The suggested system makes use of essential parts like an Arduino Uno, ESP32-CAM, and infrared sensors in addition to supplementary hardware including a 4WD car chassis kit, 18650 batteries, and an L293D motor driver shield. Real-time traffic sign recognition is made possible by the combination of technology and software, which can improve traffic control and road safety. The system's capacity to accurately identify and recognize traffic signs is demonstrated by the testing findings, which makes it appropriate for low-cost autonomou

Abstract: Food security, economic stability, and public health are all greatly impacted by food safety and quality. In addition to causing serious illnesses, spoiled or infected food contributes significantly to food waste. Innovative approaches that integrate affordability, accuracy, and efficiency are needed to address these issues. The creation and deployment of Internet of Things (IoT)-based food quality monitoring systems that use inexpensive sensors to identify early spoiling indicators are the main topics of this review. In particular, the MQ4 methane sensor's interaction with NodeMCU and Wi-Fi modules offers a reliable way to keep an eye on gases released during food decomposition, such as ethanol and methane. In order to guarantee food safety, these devices provide real-time data to cloud-based platforms like the Blynk app, allowing for remote monitoring and prompt response.

Abstract: The IoT-based smart cradle introduces a paradigm shift in infant care, integrating cutting-edge technology to provide a comprehensive solution for modern parents. This cradle is equipped with an array of sensors that constantly monitor the baby's well-being. From tracking ambient temperature to sensing heartbeat and sound levels, the cradle gathers real-time data, offering parents valuable insights into their child's health and comfort. Caregivers gain remote access to the cradle's functionalities, which enables them to observe various aspects of the infant's surroundings and environment. This work aims to provide better monitoring of the infant by utilizing Machine Learning models for the classification of the infant's emotions as well as for intruder detection. This seamless integration of the cradle with IoT technology ensures that parents receive instant alerts and notifications in case of any anomalies, fostering a heightened sense of security.

Abstract: In the evolving landscape of software development, architectural decisions significantly impact application scalability, maintainability, and operational efficiency. Monolithic and Microservices architectures are two dominant paradigms, each offering distinct advantages and posing unique challenges. While microservices provide modularity and scalability, their complexity often leads organizations to reconsider monolithic designs for certain scenarios. This paper critically examines both architectures, exploring their strengths, limitations, and trade-offs. Through case studies and comparative analysis, it highlights contexts where reverting to a monolithic approach aligns better with opera-tional goals. Additionally, the paper outlines a structured framework for transitioning between these paradigms and discusses emerging hybrid architectural models that blend simplicity with scalability. By offering a balanced perspec-tive, this work equips practitioners with actionable insights to make informed decisions tailored to their technical and business needs.

Keywords: Software Architecture, Monolithic Architecture, Microservices Architecture, Distributed Systems, Modular Design

Abstract: This paper presents a solution to improve fruit yield monitoring and sales in agriculture by combining the ESP32CAM module with Telegram bot technology. The system uses the ESP32CAM to capture real-time images of fruit, which are then analysed with machine learning algorithms for accurate counting and quality assessment. The images are uploaded to a cloud server, where advanced analytics estimate the yield and predict the best harvest times. This approach helps farmers make better decisions about when to harvest and manage their inventory. The Telegram bot acts as an easy-to-use interface for farmers and customers, allowing smooth communication and realtime updates on inventory, sales, and yield information. Farmers can use the bot to manage their stock, get notifi-cations about fruit quality and quantity, and directly sell to consumers, removing intermediaries and improving prof-itability. By automating the processes of monitoring yield, assessing quality, and handling sales, this system cuts down on manual work, boosts efficiency, and creates a direct link between farmers and customers. Using machine learning, realtime communication, and cloud-based analytics, the system offers a modern and scalable solution to problems in agriculture, paving the way for future advances in precision farming and direct sales to consumers.

Keywords: Road safety, Fruit yield monitoring, ESP32CAM module, Telegram bot, Machine learning algorithms, Image processing, Real-time data, Cloud-based server, Yield estimation, Sales management, Agriculture technology, Precision farming, Scalable solution.

Abstract: Cloud computing has transformed the Internet of Things (IoT) as it offers easily scalable, flexible, and affordable solutions for storage and processing data. From our study, we found that the integration of cloud computing and IoT, its advantages and disadvantages evolution in future was discussed. Finally, this paper tried to cover up the literature involving these areas retroactively through their past to present studies up to 2021 and a conducive material has been developed for obtaining new insights from researchers who are going further work on some other or extended versions. Through discussing these and conducting a broad literature review as well as comparing current implementations, in this paper we explore the way in which cloud-based platforms can augment capability offered by IoT and facilitate prominence of data management, security and interoperability issues. Our discovery indicates that although cloud computing still advances IoT capabilities, it also adds extra challenges which require more future research and efforts to be settled.

Keywords: Cloud Computing, Internet of Things, Cloud based IoT, Integration.

Abstract: Li-Fi (Light Fidelity) is a modern wireless communication technology that transmits data using light instead of radio frequencies. Compared to conventional Wi-Fi, it provides more energy economy, improved security, and quicker communication speeds. This study reviews Li-Fi data transmission system architecture, with particular attention paid to key elements such as photodiodes for data reception and LEDs for data transmission. To demonstrate how data is encoded into light signals, various modulation techniques are covered, such as pulse width modulation and on-off keying. Important design factors like ensuring line-of-sight between the transmitter and receiver and controlling interference from other light sources are also covered in the study. The possible uses of Li-Fi are being investigated in domains such as indoor networking, healthcare, the Internet of Things, and vehicle communication. Li-Fi has drawbacks like poor coverage and sensitivity to ambient light, despite offering faster bandwidth and greater security. To overcome these obstacles, future research directions are highlighted in the paper's conclusion.

Keywords: Li-Fi Technology, Wireless Communication, Visible Light Communication (VLC), Light Fidelity (Li-Fi), LED Modulation, Photodiodes, Data Transmission, Modulation Techniques, On-Off Keying (OOK), Pulse Width Modulation (PWM), Orthogonal Frequency Division Multiplexing (OFDM), Line-of-Sight Communication, Ambient Light Interference, High-Speed Connectivity, Energy Efficiency, Indoor Networking, Internet of Things (IoT), Vehicle-to-Vehicle (V2V) Communication, Electromagnetic Interference (EMI).

Abstract: The rapid proliferation of social media platforms such as Twitter creates a fertile ground for misinformation and fake content. The detection of fake tweets is a highly complex challenge because of the short length, diverse topics, and linguistic nuances that these short messages carry. The present research introduces Article Authenticity Analyzer (AAA), a novel system, for effective identification and classification of fake tweets. The proposed analyzer integrates advanced NLP techniques, user behavior analytic, and social network analysis to provide a holistic detection framework. The system extracts contextual and semantic features from tweet content by leveraging transformer-based models like BERT, whereas user behavior analysis evaluates credibility based on metadata such as account age, posting frequency, and network interactions. Graph based techniques are used to uncover coordinated misinformation campaigns. The AAA achieves state-of the-art performance with an accuracy of 92% and demonstrates robustness across multiple datasets. This paper discusses the methodology, experimental setup, and real-world implications of deploying the AAA in combating fake news on social media platforms.

Abstract: Driver safety occupies a top priority in the automotive industry, where poor visibility during heavy rains often results in accidents. This article proposes an automated wiper system using a rain sensor such that it can detect rain and adjust the speed of the wipers automatically without requiring human intervention. The system comprises an Arduino, rain sensor, and a servomotor; it shall measure humidity and activate trigger signals for wiper operation when that value goes higher than the maximum set point. That is, the Arduino system can process sensor data to give commands to the servomotor that triggers wiper speed based on the intensity of rainfall. This rain sensor is mounted in the windshield, and all components will be operated through the car battery.

Abstract: This review examines the vital role of interface materials in solar photovoltaic (PV) systems and lightemitting diodes (LEDs), emphasizing their critical functions in thermal management, electrical connectivity, adhesion, and environmental resilience. As renewable energy and solid-state lighting technologies evolve, the demand for advanced interface materials to enhance performance and durability grows.In solar applications, interface materials such as silicone-based compounds, epoxy adhesives, and phase change materials (PCMs) are crucial for dissipating heat and ensuring the longevity of solar panels. These materials excel in handling temperature fluctuations, safeguarding efficiency. In LEDs, conductive adhesives and metalized films are key to forming strong electrical connections and efficiently transferring heat from semiconductors, optimizing light output and performance in compact systems. The review also explores the environmental endurance of these materials, focusing on their ability to withstand UV exposure, thermal cycling, and harsh conditions. Advanced options, including nanomaterials and smart materials, show promise for improving thermal and electrical properties at critical interfaces. Integrating contemporary research and innovations, this paper highlights interface materials as pivotal in driving energy efficiency and operational longevity. It underscores their role as enablers of sustainable energy solutions and nextgeneration lighting technologies, advocating for continued research and development in this transformative field. Key Words: Perovskite solar-cells, Power conversion efficiency Hole transport layer,Electron transport layer ,Buffer layer ,Photovoltaic devices.

Abstract: The objective of this research is to analyze the significance of big data and predictive analytics through a thorough literature review within investment banking. We look further into how investment banks use these technologies for risk control, market forecasting, managing clients’ portfolios and preventing fraud. The problem sets out implementations at large institutions and considers gaps in the market for such implementations including data quality constraints, technology limitations, regulation issues, and skills gap. The evidence shows that although there are challenges with implementation, the broad use of big data and predictive analytics improves the effectiveness and efficiency of decision-making processes in investment banking. The paper provides a vision of further development of the market in AI technologies adoption in that area of research and practice.

Keywords: Big data analytics, predictive analytics, investment banking, risk management, machine learning, artificial intelligence

Abstract: Mental health disorders, anxiety disorder, depression, and even stress, are seen rising among adults compared to preceding generations. The factors that influence adult mental well-being issues are examined for alternative measures to enhance such adult mental well-being through this review. Recently, in the pursuit of care provision support systems include therapy, counseling, workplace mental health initiative, and internet-based programs. The review also covers barriers which include stigma, cost, and limited access. Conclusion The review concerning the systems concludes advising improvements of the support structures for mental health that are universal, accessible, and user-friendly enough to alleviate the growing concern about adult mental health.

Keywords: Mental Health, Machine learning, Deep learning, KNN, Random Forest, Decision Tree, Naive Bayes, SVM.

Abstract: This project aims to develop a deep learning-based text classification system that predicts the domain of a given article using the 20 Newsgroups dataset, which consists of news articles categorized into various topics. The goal is to classify articles into broader domains such as 'Technology,' 'Sports,' 'Politics,' and 'Religion,' based on their content. The model employs an LSTM network, a form of RNN, because it is well-suited to handle sequential data like text and capture long-term dependencies in the content. The project first preprocesses the data by tokenizing the text, padding sequences to have uniform input size, and one-hot encoding the target labels. Next, the LSTM network is trained so that it may recognize the text's patterns and features and be able to map it into a predefined category. The model was evaluated in terms of accuracy, precision, recall, and F1-score. Also, the batch size and number of epochs were readjusted according to hyperparameter tuning for increased accuracy. Through training, the model can predict the category of any unseen article. The result is mapped to its corresponding domain using a predefined dictionary. The system also maintains the functionality of saving the trained model, tokenizer, and label encoder so that the same model can easily be loaded for further predictions. This text classification system can be applied in areas such as news aggregation, content categorization, and information retrieval where automatic sorting of articles into relevant domains is required. In addition, the project explores the possibility of improving text classification using LSTM networks on domains with large unstructured text data, thereby contributing to the advancements in NLP and deep learning applications in real-world scenarios.

Keywords: Text Classification, Deep Learning, LSTM , 20 Newsgroups Dataset, Recurrent Neural Networks (RNN), Content Categorization, Tokenization Sequence Padding.

Abstract: Communication of individuals with speech deficits mostly depends on sign language which isn’t known to a large number of the general people. And generally it becomes tedious to communicate with a person having only the knowledge of a regional language. This makes different forms of effective communication very challenging. In order to solve this problem, we present an assistive device that converts hand movement into sound and text which can be spoken and read by the speech impaired person, thus enabling interaction with everyone and society at large. Such a system consists of a glove with flex sensors that detects change in resistance applied to certain hand gestures. All these signals are received by an Arduino UNO microprocessor which is programmed to understand these gestures and outputs speech based on these gestures with the aid of a text-to-speech TTS module. In order to make it accessible to more regional areas we used google-text-to-speech(GTTS) module.For making it available for more regional areas we used google-text-to-speech(GTTS). Moreover, the system can use the converted text for visual communication which increases the scope of application of the device. This approach uses recognition of hand gestures and text to speech synthesis to enable speech impaired to communicate in a cheap and efficient way. The device is easy and straightforward which in turn helps to promote diversity and improve the living standards of the users.

Keywords: Speech impairment, sign language, gesture recognition, flex sensors, Arduino UNO, Text-to-Speech (TTS), Google Translate API, LCD display, multilingual communication, assistive technology, communication aid, speech-impaired individuals, accessibility, sign language translation, portability, assistive devices.

Abstract: The financial services industry handles transactions amounting to trillions of dollars daily, necessitating a focus on cost-efficiency, transparency, and security. Cybersecurity is the biggest threat to this industry and Blockchain is the only answer to protect data in the growing FinTech space. Prior to the integration of blockchain technology, intermediaries such as money transfer services, stock exchanges, and payment networks frequently encountered cybercrime. Blockchain technology, initially popularized by cryptocurrencies like Bitcoin, has since become a transformative force across various financial sectors. This technology enhances the industry by providing secure, transparent, and cost-effective transaction protocols through encryption and algorithms. This prose explores the significant advancements blockchain has brought to financial services, emphasizing its role in revolutionizing insurance, asset management, banking, and the stock market. With rapidly increasing use of LLMs in financial sector, blockchain is in the center of data protection and security for this industry in all directives.

Keywords: Blockchain, Financial Services, Cybersecurity, Data Protection, Transaction Transparency, Cost-Efficiency, LLM Security

Abstract: In today’s technological landscape, artificial intelligence (AI) has become prominent in various fields, including cyber security. While AI has strengthened security measures and protected networks, hackers increasingly target AI-generated cyber threats and autonomous hacking systems. This shift has made it more challenging for traditional defences to remain effective, as attackers utilize AI to launch and execute cyber-attacks and identify vulnerabilities to exploit. This work aims to describe how AI has evolved in the context of cyber threats and what types of hacking an AI system can perform autonomously while exploring the potential of AI in cyber security. Additionally, it analyses the ethical dimensions surrounding AI as a double-edged tool and examines some defence strategies that can be implemented against AI-driven attacks. Cyber security professionals are better positioned to develop systems to combat autonomous hacking by understanding the current risks and potential mitigation measures.

Abstract: The research analyses the role of machine learning technology in facilitating process transformations between predictive analytics production and high-level automation across different application areas. The research analyses market prediction software and algorithm-controlled automation across different sectors that operate through learning platforms accepting data inputs. The basic technological element of machine learning operates as an essential element to enhance organizational performance with better executive decision quality. Advancements during the twenty-first century propelled rapid algorithm development because of improvements in automated vehicles, language translation solutions, and computer systems. The merger of data mining technology with artificial intelligence creates a full-scale transformation that impacts manufacturing system operations. Algorithmic processing by virtual platform vendors permits them to create predictive analytics software solutions through dataset examination. These information systems achieve higher efficiency by improving data collection operations combined with superior processing capabilities. Artificial intelligence focuses particularly on machine learning as a system that enables computers to develop knowledge autonomously by advancing their functions through automation and without direct human code instructions. Algorithms achieve greater strength in row-based learning methods because pattern-finding programs produce business-wide prediction forecasts. Industrial sectors transformed their operations through this technology to make business organizations capable of automation while achieving enhanced predictive processing. The popularity of machine learning spans entertainment, along with industrial and commercial domains, because programmers require limited skills to run it on various applications. Artificial intelligence systems and machine learning systems merge to create basic industrial reorganization as companies implement them in their manufacturing operations. The current global market competition enables organizations to excel operationally through AI and helps them overcome essential operational obstacles. Industrial operations during past periods managed control regulation by using traditional methods in combination with a human workforce.

Keywords: Machine Learning, Deep Learning, Predictive Analysis, Artificial Intelligence.

Abstract: In this work, we propose DRLEER (Dynamic Reinforcement Learning-Based Energy-Efficient Routing), a novel routing protocol designed to maximize energy efficiency and prolong the operational lifespan of Internet of Things (IoT) networks. DRLEER aims to minimize energy consumption while optimizing data delivery by employing a dynamic Reinforcement Learning approach to routing decisions. The protocol comprises three key phases: network design and Cluster Head (CH) selection, clustering, and energy-aware data transmission. During the first phase, DRLEER calculates Q-values for CH selection by considering both hop count and initial energy, allowing the network to identify the most appropriate CHs for efficient communication. Subsequently, in the clustering phase, CHs broadcast invitation messages to nearby nodes, while nodes farther from the base station associate with the closest clusters. This process results in an optimally organized network structure. The final phase utilizes Reinforcement Learning to enable energy-conscious routing decisions based on residual energy and network conditions. An energy threshold is defined to control CH replacement and maintain the stability of the network. Simulation results show that DRLEER significantly outperforms existing protocols, extending network lifespan to 5866 rounds, reducing average end-to-end delay to 55ms, and conserving energy with an average consumption of 2.75 per round. Furthermore, DRLEER successfully delivers 14.2 × 10^5 packets, demonstrating its ability to efficiently handle data delivery under energy constraints. Overall, DRLEER provides a scalable, adaptable, and energy-aware solution for IoT routing, extending network service life and conserving resources through a low-power Reinforcement Learning framework

Keywords: IOT, WSN , Deepa Reinforcement Learning , Energy Efficiency

Abstract: Early artificial intelligence (AI) adoption and a weakness in organizational execution represent two elements that shape practical examples of AI-assisted clinical workflow optimization. Some institutions are realizing operational efficiencies, short-term reductions in clinical error rates, and enhanced patient experience even amid talent shortages. Initial improvements align with the actual diagnostic or treatment pathway being executed and the real-world clinical and technical capabilities enabled by the AI initiative. Data-driven medicine on the other hand, with its call for evidence-based, structured data-driven access to clinical decision support tools at the time and place of need, as well as automated alerts and reminders, remains a vision yet to be fully realized. Institutions with the right elements in place can expect workflow enhancements provided clinicians are willing and able to trust their clinical judgment more than the underlying models and embrace delegation. While some hospitals have implemented data-mature and user-centered data-driven medicine for the first three years for diagnostic support and decision-making, AI-supported routing and triage, multispecialty treatment planning, and high-urgency multidisciplinary approval have remained aspirational. In other words, the implementation readiness of AI-supported workflow optimization in these hospitals remains in flux, with elements switching between enablers and barriers. Expectation alignment, however, has improved markedly during the same period. Work that focuses on the evolution of clinical governance, data infrastructure, training needs across clinician groups, user-centered design, and operating model readiness is therefore directly relevant to translating AI ambition into execution.

Keywords: Artificial intelligence in healthcare,Clinical workflow optimization,AI adoption in clinical settings,Early-stage AI implementation,Healthcare process automation,Clinical decision support systems,Machine learning in healthcare operations,Workflow efficiency improvement,AI-driven clinical productivity,Health information systems integration,Clinical operations management,Digital transformation in healthcare,Care delivery optimization,Provider workload reduction,AI impact on clinical practice.

Abstract: Credit risk scoring systems are among the most crucial decision-making models developed by banks. These models have become mandatory in many jurisdictions because of regulatory requirements that promote risk-sensitive capital charge computations. However, legal requirements and the need for better customer relations now make credit-scoring evaluation systems necessary and increase demand in the market. Regulators require understandability of prediction models, banks are interested in interpretability to create customer relations and meet consumer-protection laws, and customers want to understand why they were rejected, especially in cases of marginal evaluation. Additionally, explainable artificial intelligence (xAI) models support the model-monitoring processes of banks and help the implementation of explainable credit assessment. The complex nature of the model-jungle makes it impossible for users and auditors to be aware of limitations, risks, and adequacy in risk management therefore clarity on how the models and systems become really interpretable is required. Existing xAI credit scoring evaluation models, explainable AI (xAI) model families, and classes of post-hoc explanation techniques are examined to present a taxonomy of approaches. Based on the analysis, a set of operational and cognitive evaluation measures and compliance-oriented explainability tests are proposed. Finally, incorporation of these concepts into model deployment, xAI governance, and overall software life-cycle management in banks is outlined.

Keywords: Credit Risk Scoring Systems, Explainable Artificial Intelligence, Explainable Credit Assessment, Regulatory Compliance In Banking, Model Interpretability, Customer-Facing Credit Decisions, Consumer Protection Laws, Risk-Sensitive Capital Requirements, XAI Model Taxonomy, Post-Hoc Explanation Techniques, Credit Scoring Evaluation Frameworks, Model Transparency, Operational Explainability Metrics, Cognitive Evaluation Measures, Compliance-Oriented Explainability Tests, Model Monitoring And Validation, XAI Governance Frameworks, Banking Software Lifecycle Management, Risk Management Transparency, Interpretable Financial Models.

Abstract: Artificial intelligence (AI), mixed with advanced big data analytics methods, has the potential to play a pivotal role in enhancing efficiency and accuracy in multiple tax processes, from data management and fraud detection to pricing optimisation and performance assessments. However, the use of these new technologies must respect the ethical principles of transparency, accountability, and explainability in order to secure their acceptance by both internal and external stakeholders, ensure compliance with increasingly stringent financial regulations and well-founded tax decisions, and ultimately facilitate a more equitable tax regime. A Responsible AI framework is articulated for an area typically overlooked in the discussion of the ethical use of AI in other fields: its application in government analytics and compliance systems for tax agencies, natural and legal persons subjected to taxation, and internationally coordinated data-sharing agreements. These institutions frequently combine their own datasets with information sourced externally through digital interceptions, companies and organisations mandated to carry out withholdings or disseminate internationally belonging to third parties, data of a fiscal nature of a different nature that guarantees compatibility in the absence of a tax treaty, and other types of financial data. Given the sensitive nature of tax-administrative data and the legal obligations in force for tax agencies, the AI systems developed should respond adequately to the three dimensions of Responsible AI: securing ownership of data and results; avoiding biases during the design stage and in the response stage; and guaranteeing control and security of the systems' outputs.

Keywords: Responsible Artificial Intelligence, Tax Analytics Systems, Government AI Governance, Ethical AI Frameworks, Tax Compliance Automation, Big Data Analytics In Taxation, Fraud Detection Technologies, Pricing Optimization Analytics, Performance Assessment Models, Transparency And Explainability, Accountability In AI Systems, Regulatory Compliance In Taxation, Equitable Tax Regimes, Public Sector AI Applications, International Data Sharing Agreements, Tax Administrative Data Management, Bias Mitigation In AI, Data Ownership And Stewardship, Secure AI Outputs, Trustworthy Government Analytics.

Abstract: Over the past decade, security incidents, service outages, and a rise in malicious attacks against Cloud services have highlighted the need for continuous security assurance both during Cloud service development and operation. The adoption of Artificial Intelligence (AI) in any aspect of society is an emerging trend, and Cloud services are no exception. AI-based processes are continuously being deployed to enable organizations to confront the growing number of sophisticated cyber threats targeting Cloud environments. The easy adoption and scalability offered by AI and machine learning-based algorithms make them ideal for Cloud environments. A Cloud Security Reference Architecture (Cloud-SRA) and Cloud Security Assurance are critical for CI/CD and DevSecOps to ensure that security is a major requirement to be met before Cloud service deployment. Various Industry Use Cases have been published by the leading Clouds Service Providers (CSPs) demonstrating the effectiveness of AI in protecting their Cloud offerings. Continuous detection and response is one of the key approaches to application and security service reliability, and AI-based algorithms are being deployed to achieve it. The challenging issue of vulnerability and misconfiguration detection is being addressed through AI methods. Security forensics is yet another area that is facing a huge demand due to the number and severity of breaches occurring, and Cyber security stakeholders are adopting AI in many aspects, aiming to improve time detection/duration of impacts and enabling a holistic approach. In the rapidly changing technology landscape of the Cloud, automated support in the detection of security configuration policy compliance is evolving to remain relevant.

Keywords: AI-Driven Cloud Security, Cloud Security Assurance, Cloud Security Reference Architecture, DevSecOps Security Integration, CI/CD Cloud Security, Continuous Security Monitoring, AI-Based Threat Detection, Cloud Incident Response, Vulnerability Detection Automation, Cloud Misconfiguration Analysis, Security Forensics In The Cloud, Automated Compliance Monitoring, Cloud Configuration Policy Enforcement, Machine Learning For Cybersecurity, CSP Security Use Cases, Scalable AI Security Solutions, Cloud Service Reliability, Proactive Cloud Defense, Cyber Threat Mitigation, Adaptive Cloud Security Systems.

Abstract: Precision agriculture is considered one of the key solutions to satisfy world food demand by 2050. To achieve precision at the smallest farming unit, data collected, processed, and analysed to produce fit-for-use knowledge must be visible, sharable, and accessible among all stakeholders. Cloud computing technology on the foreshore has penetrated all segments of everyday life, not sparing the agriculture segment, making visible the nondirectional flow of information in real time. Cloud computing generally provides scalable infrastructure, powerful storage, data-sharing facilities, low operational costs, and powerful analytics, metering AI/ML model development and inference more affordable and enabling artificial intelligence and machine learning development and inference at regional scales. Its challenges include single-point failure, low-quality service, latency, and resource dependency. Conclusively, precision agriculture at the farm and field levels can also benefit from clustering agriculture stakeholders’ data on the cloud and making the data accessible to eminent researchers and agriculture domains using various algorithms to develop AI/ML models. The planned architecture helps shed light on the logical flow of information from the sensor to decision representation. It includes key functional modules, components required for data ingestion, integration towards data lakes, model training nested in the cloud, deployment in different environments for inference, and governing data with respect to modelling, privacy, and security of stakeholders’ data in the cloud. To satisfy world food demand by 2050, precision agriculture is considered one of the key solutions. Precision requires collecting, processing, and analysing data to produce fit-for-use knowledge that is visible, sharable, and accessible among all stakeholders. Cloud-computing technology on the foreshore has penetrated all segments of everyday life, not sparing agriculture, and enabling a non-directional flow of real-time information. Cloud computing generally provides scalable infrastructure, powerful storage, data-sharing facilities, low operational costs, and powerful analytics, making artificial intelligence and machine learning development and inference at regional scales more affordable. The technology’s challenges include single-point failure, low-quality service, latency, and resource dependency. Precision agriculture at the farm and field levels can benefit from clustering agriculture stakeholders’ data on the cloud and making the data accessible to eminent researchers and agriculture domains.

Keywords: Precision Agriculture, Cloud Computing In Agriculture, Smart Farming Systems, Agricultural Data Analytics, IoT Sensors In Farming, Real-Time Farm Data, Agricultural Data Sharing, Scalable Cloud Infrastructure, AI And ML In Agriculture, Farm-Level Decision Support, Data Ingestion Pipelines, Agricultural Data Lakes, Model Training And Inference, Edge–Cloud Agriculture Architectures, Food Security 2050, Stakeholder Data Accessibility, Agricultural Data Governance, Privacy And Security In Agri-Data, Latency And Reliability Challenges, Digital Agriculture Ecosystems.

Abstract: Manufacturing industries are embracing smart solutions to achieve operational excellence by enhancing controllability, visibility, and flexibility. An intelligent quality control system with autonomous capabilities is a critical enabler of smart manufacturing. The autonomous quality control mechanism integrates edge artificial intelligence and cloud orchestration—AI-based applications for real-time anomaly detection and predictive analysis, AI-enabled cloud services for system orchestration, and edge-cloud data governance. The effectiveness of the proposed approach is demonstrated in a case study involving a complex process using Internet-of-Things devices for data acquisition. Understanding the complex, repetitive, and noisy nature of manufacturing processes with advanced machine-learning algorithms often requires substantial data-analytics infrastructure. Moving all data to the cloud for processing and storing is not feasible for operational efficiency when the core functions are repetitive, time-sensitive, and performance-critical. Solutions deployed on edge devices provide limited performance and efficiency due to challenged computing resources. An edge–cloud quality-control framework with real-time anomaly detection and predictive analytics capabilities is proposed. AI-based applications with active learning on the edge provide constant real-time services to detect data anomalies in quality features from quality-control check points. AI-enabled cloud services orchestrate the entire system by continuously monitoring operational conditions and storing all data, validating the use of predictive-quality-control analysis.

Keywords: Smart Manufacturing Systems, Autonomous Quality Control, Intelligent Quality Inspection, Edge Artificial Intelligence, Cloud-Based AI Orchestration, Edge–Cloud Integration, Real-Time Anomaly Detection, Predictive Quality Analytics, Industrial Internet of Things (IIoT), AI-Driven Process Monitoring, Active Learning at the Edge, Manufacturing Data Governance, Distributed AI Architectures, Time-Critical Industrial Analytics, Operational Excellence Enablement, Scalable Quality-Control Frameworks, Edge–Cloud Data Pipelines, Performance-Critical AI Systems, Intelligent Manufacturing Operations, AI-Orchestrated Industrial Systems.