Volume 14 | Issue 2 |

 Abstract

With growing environmental concerns and the need for sustainable solutions in urban transport, electric vehicles (EVs) are becoming a more admired and environment-friendly alternative to cars that are powered by conventional fuel. Although, the adoption of EVs is still limited by challenges like range anxiety--drivers' concerns about running out of battery power on longer trips--and a lack of accessible charging stations, especially in cities. Addressing these issues requires innovative approaches that make EVs more convenient for everyday use while also supporting clean energy sources. This project proposes a solar-powered dynamic wireless charging (DWC)system for electric vehicles, using inductive power transfer (IPT) technology embedded in road infrastructure. The system enables EVs to charge continuously while driving, reducing range anxiety and improving charging accessibility by eliminating the need for frequent stops. By utilizing solar energy, this solution lessens the dependence on conventional power sources, promoting EV adoption as part of a greener transportation network. Working in collaboration with urban planners and engineers, the project aims to integrate this charging system directly into city roads, turning them into dynamic charging networks and contributing to reduced greenhouse gas emissions. This initiative envisions a future where electric vehicles can recharge seamlessly during travel, supporting a more sustainable and efficient urban transport system.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Electric Vehicles (EVs), Dynamic Wireless Charging (DWC), Inductive Power Transfer (IPT), Wireless Power transfer (WPT), Electromagnetic Field

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The Android-Based Depression Detection System Using Natural Language Processing (NLP) takes an innovative approach to mental health, monitoring users' online behaviour for signs of depression using cutting-edge technology. In today's digital world, when people are increasingly turning to online platforms for entertainment, education, and distraction, their interactions with content may reveal subtle details about their mental health. Through normal online behavior's, this Android application aims to detect early indicators of sadness, which frequently show up in user behavior and content selections before they are consciously recognized. The system's purpose is to encourage people to actively seek mental health care by providing a platform for preventive mental health. The application encourages early intervention by producing actionable insights and suggesting mental health resources and support systems, as opposed to waiting until depression symptoms worsen or become apparent. Additionally, anonymized data analysis permits academics and mental health practitioners to collect data for extensive studies and interventions while guaranteeing privacy and confidentiality. By combining user-centric technology with mental health research, the initiative aims to improve individual well-being while also reducing the stigma attached to mental health.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Natural Language Processing Algorithm (NLP), Depression Detection, Mental Health Monitoring Mental Health Monitoring System, Behavioral Analysis, Sentiment Analysis, Machine Learning, BERT Model.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Prepaid Energy Meter Using GSM and Raspberry Pi. This hardware and software hybrid solution is designed to revolutionize electricity distribution by eliminating overbilling, preventing meter tampering, and addressing electricity theft. With a prepaid model, users must pay for electricity in advance, enabling better energy management and reducing wastage. The system integrates a GSM module for instant communication, sending SMS alerts to users regarding energy consumption, balance updates, and potential theft incidents. If theft is detected, the system notifies both the consumer and utility authorities. This IoT-based smart energy metering solution modernizes traditional energy meters, making them more efficient, secure, and transparent.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Prepaid Energy Meter Using GSM & Raspberry pi, Prepaid Meter, Raspberry pi Pico w, Energy Optimization, GSM Module, IoT, Smart Metering, Energy Management, SMS Alerts, Energy Theft Detection, Prepaid Billing, Remote Monitoring, Load Disconnection, Digital Meter, Smart Grid, Consumer Awareness

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Maintaining Road infrastructure is crucial for transportation safety, yet potholes and humps continue to be main hazards. Traditional manual inspection methods are inefficient and resource-intensive. This paper presents an automated system using Raspberry Pi, Pi Camera, and a machine learning model to detect road irregularities in real time. By leveraging computer vision techniques, the system identifies and classifies potholes and humps, enabling timely alerts to drivers and maintenance teams. The proposed solution is energy-efficient, cost-effective, and user-friendly, making it a valuable asset for smart cities and intelligent transportation networks.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Pothole detection system, Road monitoring automation, Smart transportation, Raspberry Pi-based anomaly detection, Real-time Road condition tracking, Computer vision in transportation, Energy-efficient monitoring, Cost-effective Road analysis.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Cognitive Behavioral Therapy (CBT) is a widely used intervention for managing stress, but traditional delivery methods face challenges in accessibility and resource constraints. The integration of Machine Learning (ML) and Artificial Intelligence (AI) into CBT offers innovative solutions to make these interventions more accessible and personalized. This review examines current applications of ML in CBT for adult stress management, exploring key benefits such as treatment personalization, outcome prediction, and process automation. We discuss challenges and future directions for ML-driven CBT, particularly in the context of the ongoing global stress crisis exacerbated by events like the COVID-19 pandemic. This paper synthesizes findings from various studies, highlighting the potential of ML in enhancing the effectiveness and reach of CBT interventions for stress management.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Cognitive Behavioral Therapy (CBT), Machine Learning (ML), Stress Management, Artificial Intelligence (AI), Mental Health, Adaptive Therapy, Chatbots, wearable Sensors, Natural Language Processing (NLP), Predictive Modelling.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Due to the rise in automobiles, climate change, and population density, there are now an alarmingly large number of potholes in the world. Understanding the physical features of potholes and their surroundings, such as the surfaces they appear on, the size and depth of common potholes, and the kinds of wear and tear that might result in pothole formation, is usually necessary for their identification. It would also require familiarity with technologies like deep learning and machine learning techniques that are frequently used for pothole identification. Poor road conditions are one of the major causes for road accidents. Developing countries in particular are witnessing in- creased accident rates due to these poor road conditions. Potholes, deep ridges, missing pitches, improper speed breakers, poorly constructed manhole covers and slabs all combine to greatly increase the probability of serious accidents thus transforming roads into obstacle courses. In this study we have developed a model to detect unwanted potholes, deep ridges and speed breakers using computer vision and machine learning tools. We have developed a customized dataset (called Bumpy) that we use to train our machine learning algorithms. In this paper we propose a method where we use the Tensorflow pre-trained model to detect the potholes, deep ridges and speed breakers. Our experimental results demonstrate high accuracy although there are many obstacles on the road.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Pothole Detection , Speed Breaker detection , Machine learning algorithms, Convolutional neural network , Road safety .

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

For people with physical disabilities, improving mobility and independence requires the development of sophisticated, automated, and reasonably priced wheelchairs. Conventional powered and manual wheelchairs frequently have drawbacks in terms of cost, usability, and environmental adaptability. In order to provide better performance at a lower cost, this paper describes the design and development of a new generation of automated wheelchairs that incorporates cutting-edge technologies like robotics, smart sensors, and energy-efficient systems. With automated navigation, obstacle avoidance, and adjustable user control, the suggested wheelchair offers improved usability and terrain adaptability. The goal of this wheelchair is to close the gap between high-tech solutions and affordability by using creative design and effective manufacturing techniques, which will increase accessibility for a larger group of users.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Arduino Mega, Motor Driver, Bluetooth model, joystick, GPS Module, Ultrasonic sensor

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In this paper the aims is to develop smart and real time monitoring for detecting and locating faults in underground power cables. Traditional methods of fault detection often involve manual inspection and are time-consuming, leading to prolonged power outages and costly repairs. This system leverages the Internet of Things (IoT) to automate and improve the accuracy of fault detection processes. The proposed solution utilizes a network of IoT-enabled sensors deployed along underground cables to monitor various parameters such as voltage, current, and temperature. In the event of a fault, the system detects anomalies in where advanced algorithms analyse the fault type and severity, providing detailed insights for maintenance crews. The paper aims to enhance the reliability of power distribution networks, reduce downtime, and minimize operational costs associated with manual fault detection. By incorporating IoT technology, this system represents a advancement in the field of electrical fault management, offering a scalable and cost-effective solution for modern power infrastructure.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Underground, Fault, Detect, Money

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In today's modern world the use of vehicles has become an essential part of our lives. It has not only increased the number of vehicles but also vehicle theft and accidents. This affects owners, and public safety in all countries. Drunk driving and negligence such has avoiding use of seat belts has resulted in increased number of accidents and loss of lives. In order to prevent vehicle theft, latest systems based on innovative technologies must be implemented. This paper introduces the design and implementation of a vehicle anti-theft facial detection system along with alcohol detection and other safety measures. Our vehicle anti-theft facial detection system works on vehicle safety by avoiding unauthorized users to access the vehicle. Only the owner approved user can get the access and unlock the safety door. Further consumption of alcohol of the user is detected through alcohol detector and the system only proceeds further if alcohol is not consumed by the driver. Final step is the mandatory use of seatbelts without which the vehicle won't start. This initiative looks forward to implement this system in vehicles to reduce number of vehicle thefts and accidents in future.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

VEHICLE ANTI-THEFT FACIAL DETECTION SYSTEM ALONG WITH ALCOHOL DETECTION AND SAFETY MEASURES

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper talks about a smart mirror built using a Raspberry Pi and facial recognition technology. The mirror doesn't just show your reflection--it also gives you useful information like the weather, time, news, and reminders. It uses a Raspberry Pi computer to run the system and OpenCV software to recognize faces in real time. A camera hidden behind the mirror can recognize who is standing in front of it and show personalized content without needing any buttons or touch. This smart mirror is designed to make daily life easier and shows how Internet of Things (IoT) technology can be used at home. The project uses affordable parts and free software to create a helpful, easy-to-use device.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Smart Mirror, Raspberry Pi, Face Recognition, IoT, Home Automation

  License

Creative Commons Attribution 4.0 and The Open Definition