DON'T THROW: A Sustainable Waste Management and Recycling Ecosystem using Digital Innovation
Identification of Fake Indian Currency using an Android App
AI-Driven Drug Pill Recognition System: A CNN-Based Android Application for Visually Impaired and Senior Citizens
Healthcare Chatbot using Machine Learning and Natural Language Processing
Balancing Pixels and Play: Assessing the Physical and Mental Health Impacts of Children's Video Gaming
Development of Mobile App for the Soil Classification
Applications of Wearable Technology in Elite Sports
Using the Arduino Platform for Controlling AC Appliances with GSM Module and Relay
Emerging Technologies in Interaction with Mobile Computing Devices – A Technology Forecast
Evaluation of Mobile Banking Services Usage in Minna, Niger State
Smartphone Applications–A Comparative Study BetweenOlder And Younger Users
Technological Diffusion of Near Field Communication (NFC)
Touchscreen and Perceived Usability: A Comparison of Attitudes between Older and Younger Mobile Device Users
A Review on Routing Protocols for Mobile Adhoc Networks
Applications of Wearable Technology in Elite Sports
The "DON'T THROW" research is an innovative solution addressing inefficiencies in waste management and recycling. Designed as a dual-app system for users and scrap dealers, it integrates digital tools to streamline scrap collection, reduce environmental impact, and promote resource optimization. Users can schedule scrap pickups at their convenience, with their orders routed to nearby professional dealers. Dealers benefit from a steady income by leveraging the app's network. Additionally, small and medium-sized enterprises are integrated into the system for scheduled scrap collection, ensuring a steady revenue model for the company. Future enhancements include an e- commerce platform, enabling users to exchange scrap for goods, thus fostering a circular economy. This paper explores the architecture, modules, and potential applications of "DON'T THROW" in transforming the waste management industry.
This paper seeks to address the problem of counterfeit Indian currency, which creates financial risks and damages trust. Through the application of machine learning and mobile applications, it provides a trusted solution for authenticating currency, improving financial security, and minimizing fraudulent transactions. The Android application enables users to register, login, and take pictures of currency bills using their phone's camera and the user can even upload image of currency bill from the gallery. A machine learning model which is trained using CNN algorithm is used to scan the image and identify whether the currency is authentic or forged. This quick verification process enables users to fight counterfeit currency. The app, built with Kotlin, ensures a smooth interface for easy access and use. Overall, this Android app offers a potential solution to the pervasive issue of counterfeit currency circulation.
As individuals age, challenges such as declining vision and memory can increase the risk of medication errors, particularly among the elderly and visually impaired. To address this issue, this research presents a deep learning-based Android application for accurate and accessible drug pill recognition. The system leverages a contrast-enhanced Convolutional Neural Network (CNN) trained on a diverse pill image dataset, achieving a test accuracy of 98%. Integrated with a REST API, the model enables real-time image classification via a smartphone camera. The application further enhances usability through voice-assisted feedback and visual pill details, promoting autonomy and medication adherence. This AI-driven solution bridges the gap between healthcare and technology, offering a practical tool to reduce medication errors and improve the quality of life for users with visual and cognitive impairments.
Healthcare is a fundamental necessity and a basic right of every human. Major advancements, like the development of healthcare chatbots, are transforming the healthcare industry. They help individuals who cannot consult doctors for every minor ailment by providing timely assistance. By helping users assess health concerns and providing relevant information, chatbots reduce unnecessary doctor visits. The purpose of this study is to create a healthcare chatbot that leverages advanced technologies such as Natural Language Processing (NLP) to efficiently process user inputs. It guides users through a series of questions to identify their symptoms and uses Machine Learning (ML) to suggest possible health conditions. The system incorporates an ensemble learning approach using majority voting among K-Nearest Neighbors (KNN), AdaBoost, and Multi-Layer Perceptron (MLP), achieving an accuracy of 96.47%. Additionally, it offers personalized recommendations such as disease descriptions, precautions, diet plans, exercise plans, medications, and suggests doctors based on the user's location, providing essential details to help them find the right healthcare professional. By relieving the burden on doctors for minor health concerns, the chatbot contributes to a more streamlined healthcare system, ensuring healthcare resources are allocated effectively for serious medical cases and enabling users to manage their health with a virtual assistant available around the clock.
This article examines children's video gaming and its physical and mental health impacts. Over six decades, games have advanced to immersive 3D environments, with 90% of children gaming on various devices. Excessive gaming fosters sedentary lifestyles, obesity, musculoskeletal issues, and sleep and vision disruptions. Mentally, it can lead to addiction, social withdrawal, anxiety, depression, and isolation, as lonely children use gaming to cope. While some argue games promote relaxation, motivation, and learning through immersion, these benefits are negated when health suffers. The article concludes that parents must monitor and limit gaming to safeguard children's well-being, academic performance, and social development.
