Volume 14 | Issue 2 |

 Abstract

Escalating air pollution as a result of urbanization and industrialization is one of the most problematic issues affecting the environment and public health. Urban living requires stringent controls on emissions and effective management of growth trends. In this paper, we propose an emission control system for metropolitan cities called GreenGuard, which is a cloud-based emission monitoring system. This pollution emission control system incorporates IoT (Internet of Things) sensors, cloud computing, and data analytics to enable real-time air quality monitoring along with predictive insights for pollution control. As part of GreenGuard, IoT-empowered sensing devices are deployed throughout the city to monitor critical pollutants, including PM2.5, and PM10, CO, NO?, and SO?. The aforementioned sensors relay data to the cloud where sophisticated machine learning algorithms monitor air quality indicators and identify pollution hotspots. Environmental agencies, politicians, and citizens receive information and alerts through dashboards. Thus, giving them the ability to make decisions in realtime. GreenGuard's predictive analytics component is one of the most remarkable features of the project. It provides the ability to predict the level of pollution based on analyzing historical data along with meteorological conditions. Through this, authorities are able to take preventive measures by restricting traffic, controlling industrial emissions, and issuing public health warnings. It achieves all necessities for metropolitan cities like scalability, enhanced security, and improved accessibility using a cloud based platform. Therefore, making it an ideal solution for larger metropolitan cities. To evaluate the efficiency of the system, GreenGuard was implemented in a metro area through a pilot study. Findings showed successful integration with the environmental systems already in place and a strong ability to accurately calculate pollution levels. The ease of use of the systems interface along with the pollution report automation made pollution management strategies much more sophisticated. GreenGuard's predictive emission monitoring capabilities enable sustainable development within metropolitan areas, which leads to better public health. Addition of AI-powered analytics and wider geographic coverage would improve the results of the proposed system even further.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Emission Monitoring, IoT, Cloud Computing, Air Quality, Pollution Control, Smart City.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Anthrax, caused by Bacillus anthracis, is a highly contagious zoonotic infection with important connotations for animal as well as human health. Compartmental epidemiological models and fractional order differential equations are traditionally used models to analyse anthrax dynamics. These models tend to face nonlinearity complexities, so high computational methods are needed for exact solutions. This paper is a critical analysis of various neural network- based intelligent computing processes for the solution of anthrax disease models. Sophisticated techniques like Radial Basis Bayesian Regularization Deep Neural Networks (RB-BRDNN), Mayer Wavelet Neural Networks (MW-NN), and supervised neural networks (SNNs) are investigated in terms of their effectiveness for the solution of nonlinear differential equations. These models, when paired with optimization methods like Particle Swarm Optimization (PSO) and Bayesian regularization, enhance numerical stability and accuracy. The review points out the benefits of neural network- based methods in forecasting anthrax outbreaks and aiding disease control measures. Directions for future research are presented, focusing on hybrid AI models for real-time disease surveillance and intervention planning.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Anthrax disease, Neural network, fractional order, Single or multiple layers optimization schemes

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper presents a systematic literature review of reinforcement learning (RL) techniques, particularly deep reinforcement learning (DRL), applied to stock market price prediction. Through comprehensive analysis of recent research, we find that advanced algorithms such as Q-Learning, Double DQN, and Dueling DQN, especially when combined with sentiment analysis from news and social media, create powerful frameworks that address financial markets' complexity. Our review indicates that DRL approaches significantly outperform traditional methods in the literature, resulting in more adaptive and dynamic solutions for stock market forecasting. This paper synthesizes current research findings and identifies promising directions for future work in this rapidly evolving field.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

deep reinforcement learning, stock market prediction, Q-learning, Deep Q-Network, financial forecasting, systematic review, sentiment analysis

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This document explores the development and implementation of the "Women Safety Night Patrolling Robot in IoT," a cutting-edge solution designed to enhance the safety of women, particularly during nighttime. In light of increasing incidents of violence and harassment, this project leverages advanced technologies such as the Internet of Things (IoT), Raspberry Pi, cameras, and sensors to create an autonomous robotic system capable of patrolling designated areas. The robot is equipped to respond to sounds, providing real-time surveillance and transmitting critical information to a control center for immediate assistance in emergencies. By fostering a sense of security and independence, this initiative addresses the pressing societal challenges surrounding women's safety. Future enhancements may include the integration of artificial intelligence for improved threat detection, the expansion of the robotic network for comprehensive coverage, and adaptations for rural and underserved regions. Ultimately, this project represents a significant advancement towards creating a safer environment for women, empowering them to navigate public spaces confidently.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Women safety, Night patrolling robot, Internet of Things (IoT), Autonomous surveillance, Raspberry Pi, Real-time monitoring, Sound detection, Emergency response, Threat detection, Artificial intelligence (AI), Public safety

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This research introduces a mobile-controlled river cleaning robot designed to address the growing challenge of water pollution. The robot, powered by an ESP32 microcontroller, serves a dual purpose: removing floating debris and monitoring water quality through a Total Dissolved Solids (TDS) sensor. By integrating a conveyor belt for waste collection and an IoT-based platform (ThingSpeak) for real-time TDS data visualization, this system offers a cost-effective, scalable solution for environmental protection. The robot operates using L298 motor drivers, DC motors, and a 12V power supply, with manual movement control. The TDS sensor provides continuous monitoring of water pollution levels, ensuring that pollution trends are tracked efficiently. The system's remote monitoring capabilities allow authorities to make informed decisions. This research demonstrates the feasibility of combining waste removal with pollution tracking, paving the way for smarter, automated solutions for cleaner water bodies

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Water Pollution, River, Mobile Controlled, TDS

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In today's rapidly advancing digital landscape, maintaining a strong online presence is essential for security-centric companies. Xproguard Pvt. Ltd. has developed a portfolio web application that effectively presents its range of security offerings through modern web technologies. Utilizing React.js, Next.js, Tailwind CSS, and Framer Motion, the platform ensures a responsive interface, enhanced SEO capabilities, and smooth user experiences. Key features include dynamic product displays, a real-time ranking mechanism, and personalized privacy policies, all aimed at boosting user interaction and fostering transparency. This paper explores the chosen technology stack, architectural design, and development process of the application, emphasizing its contribution to strengthening Xproguard's brand identity and commitment to digital innovation..

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

React.js, Next.js, Tailwind CSS, Framer Motion, TypeScript, Web Portfolio.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In the context of intelligent transportation systems, the detection of road irregularities like potholes in advance is crucial to improving public safety and maximizing maintenance. This paper introduces the creation of a real-time pothole detection system based on the YOLO (You Only Look Once) object detection algorithm. Utilizing the YOLO model's speed and accuracy, the system extracts video streams from road-facing datasets to detect and localize potholes with great accuracy. The app architecture includes phases like image acquisition, pre-processing, CNN-based detection, and post-processing to refine the results. With performance and scalability in its design, this solution provides a viable solution for municipal authorities and smart city programs to automate road condition monitoring, thereby saving time on manual inspection and enhancing urban mobility.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

YOLO, Pothole Detection, Image Pre-processing, Post-processing, Deep Learning, Python, OpenCV

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Air pollution in urban areas is increasingly driven by vehicle emissions, which release harmful gases include such things as carbon monoxide (CO), nitrogen oxides (NOx), hydrocarbons (HC), and particulate matter (PM). These pollutants pose significant risks to both environmental quality and public health, highlighting the urgent need for effective monitoring and control systems. This project presents the development of an automated Effective Air Pollution Monitoring System for Eco Balance, designed to detect exhaust gas levels in real-time as vehicles pass designated points. The system employs advanced sensors to monitor pollutant concentrations and utilizes a camera- based recognition system to capture the number plates of vehicles that exceed permissible emission levels. The collected data, including pollution metrics and vehicle details, is transmitted to the Regional Transport Office (RTO) for necessary enforcement actions. By promoting compliance with emission standards, this automated system aims to significantly reduce vehicle-related air pollution, fostering a cleaner and healthier urban environment.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Air Pollution, Vehicle Emission, Pollution Sensor, Camera-Based Recognition, Vehicle Identification, Regional Transport Office (RTO)

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The rapid expansion of the Information Technology (IT) sector has significantly contributed to the global e-waste crisis. Electronic waste (e-waste) consists of discarded electrical and electronic equipment, which, if improperly managed, poses severe environmental and health hazards. This review paper consolidates insights from various research studies, examining the challenges, technological innovations, circular economy approaches, regulatory frameworks, and socio-environmental impacts associated with e-waste management. It also highlights sustainable solutions, including Artificial Intelligence (AI)-driven recycling, blockchain-based tracking systems, and eco-design strategies, offering a roadmap for future advancements in the domain. By integrating data from multiple sources and case studies, this paper presents a holistic overview of current e-waste management trends and suggests actionable strategies for effective waste mitigation.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Advancements in E-Waste Management Systems and Pollution Control: A Comprehensive Review in the IT Domain

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Proper attendance record-keeping is critical in schools for tracking student participation and performance. Conventional approaches, including manual registers and RFID-based systems, are prone to errors, tampering, and inefficiencies. This research proposes a Fingerprint-Based Smart Attendance Management System Using IoT, which tracks attendance automatically using biometric verification. The system utilizes an ESP32 microcontroller coupled with a fingerprint sensor to scan and authenticate student identities. Attendance records are stored and analyzed in a Python-based system with real-time tracking through a web-based interface. Additionally, when a student has an attendance level of less than 75%, an automatic warning message is sent to their parents. The proposed system improves the accuracy, stops proxy attendance, and enhances overall efficiency in handling attendance. With the integration of IoT and biometric authentication, the system guarantees a secure, scalable, and user-friendly process for tracking attendance

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Attendance Monitoring System (AMS), Automated Attendance Tracking, Cloud-based Systems, Fingerprint Recognition, Internet of Things (IoT).

  License

Creative Commons Attribution 4.0 and The Open Definition