International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Smart Home Monitoring System for Early Childhood Using Computer Vision Technology
Get PDFOne of the most significant problems families face today is the proper handling of newborns; most parents can barely always keep a close eye on their babies. Baby monitors put the minds of many parents at ease by increasing the safety of their children; however, many currently available models lack certain features that should comply with safety regulations. This paper proposes an intelligent monitoring system for infants that can be integrated into smart homes to improve real-time monitoring through a computer vision technique. Therefore, the primary goal of a smart home presence detection system is to enhance children\u27s safety by accurately identifying their presence and identifying risks that may arise in real-life scenarios. It operates in real-time to ensure parents are always informed of their child\u27s safety. This approach employs YOLOv5, which is well-known, fast, and accurate, thus suitable for this task due to its impressive real-time object detection performance. The proposed system indicates a quick and efficient framework for keeping children secure in smart homes, presenting the potential of advanced computer vision techniques in the real world
An Efficient and Robust Deep Learning Approach for Vehicle Recognition using Light-weight Deep Network
Get PDFIn the realm of intelligent transportation systems, automatic number plate detection has emerged as a crucial research topic due to its wide range of applications, including traffic violation monitoring, support for autonomous vehicles, vehicle speed tracking, automated toll collection, stolen vehicle identification, and overall traffic management. The goal of automatic number plate detection is to accurately identify vehicles based on their number plates. This study proposes a hierarchical approach for detecting number plates. In the initial phase, a lightweight deep learning model, Mobile Net-SSD, is employed to detect number plates. Subsequently, the alphanumeric characters from the detected number plates are extracted using an Optical Character Recognition (OCR) technique. The model is, built on a convolutional neural network, and efficiently uses depth wise and pointwise convolution layers, making it suitable for mobile and embedded systems. Additionally, we introduce a dataset of 30,613 vehicle number plate images to foster further research. Experimental evaluations show that the proposed method achieves 95% accuracy on this dataset, significantly enhancing real-time number plate detection and making it suitable for large-scale implementations in smart cities and intelligent transportation networks
A Robotic Simulation for Aerial Monitoring and Disease Detection of Gladiolus Field
Get PDFAgriculture is an essential sector that is witnessing the integration of advanced technologies to improve productivity and efficiency. Aerial crop monitoring using drones has surfaced as a pivotal technology for precision agriculture, allowing farmers to collect detailed data regarding crop health, soil conditions, and pest infestations. A robotic farm monitoring system in simulation can provide an initial platform to test various automated services before deploying them in the real field. This paper presents an agricultural robotic simulator currently developed for the gladiolus field. Simulation has been designed using V-REP (now known as CoppeliaSim) and Robot Operating System (ROS). Autonomous path planning and navigation are achieved through Hector Simultaneous Localization and Mapping (SLAM) and Rapidly Exploring Random Trees (RRT). One of the most common and fatal diseases of the gladiolus plant named ’Fusarium yellow’ has been successfully detected through image processing. This simulation is specifically designed to save resources and reduce the time and cost of developing and testing real-time autonomous aerial robotic systems and test algorithms for crop monitoring. Usability evaluation of the developed system through user survey shows positive results
A FEM Analysis of BLDC Ceiling Fan with Different Slot-Pole Combinations
Get PDFBLDC motors have recently made significant advancements in the automation industry. Due to their high efficiency and power density, they are widely used in everyday applications such as fans, electric bikes, rail transit, and automobiles. The slot-pole structure is a key factor influencing motor design. This research explores various slot-pole combinations to enhance performance.
For ceiling fan applications, a balanced and highly efficient stator with concentrated winding has been designed based on different slot-pole configurations. Two commonly used combinations—18-slot/16-pole and 12-slot/14-pole—were analyzed. However, these configurations result in high cogging torque and a low winding factor, reducing the efficiency of BLDC ceiling fans.
To overcome these issues, a 24-slot/22-pole combination is proposed. This design improves torque production, power efficiency, and magnetic flux density while reducing cogging torque and increasing cogging frequency. The effectiveness of this structure is evaluated using the finite element method (FEM) in Ansys Electronics Desktop softwar
Reducing the Environmental Impact of Leather Production and Assessing the Potential of Cactus-Based Vegan Leather
Get PDFGlobal warming and the environmental and health risks linked to animal-based leather products have increased the demand for sustainable alternatives. Vegan leather has gained attention as a promising solution to these issues, encouraging eco-friendly fashion. To reduce its environmental impact, the leather industry is shifting from animal-derived to plant-based materials. Traditional leather production involves slaughtering over a billion cattle each year, releasing harmful substances like chromium and lead that pollute water sources and threaten public health. This study explores the potential of cactus-based vegan leather as an eco-friendly substitute for conventional leather. The process involved harvesting mature cactus pads, drying them in the sun, and transforming them into a sturdy material that mimics the properties of real leather. Mechanical tests showed that cactus leather offers similar durability, flexibility, and aesthetic appeal to traditional leather. The results emphasize the environmental, economic, and functional advantages of cactus leather, positioning it as a scalable alternative to reduce the negative ecological effects of animal-based leather production
Management of Speech Impairment Disorders in Aphasia Patients using Digital intervention with Multilingual Regional Dialects
Get PDFSpeech is a zestful, and intricate activity that enables people to express ideas, emotions, and thoughts. We are able to render our views because of this neural activity. It is a significant process for learning and personal development that every individual deserves to develop, including those with special needs and who are on a journey to learn how to communicate. Children frequently suffer from speech disorders. This entails them at the risk of experiencing social, intellectual, and academic challenges that may persist and affect them in their adolescence and adulthood. In this context, we present a speech therapy solution for special children, to assist kids with speech and language impairments in improving their language skills. The proposed app can act as a useful management tool and rehabilitation system for people with aphasia disorder and their caretakers including parents, guardians, and teachers. This innovative app offers a vast number of features and practice sessions to develop language skills and overcome communication impairment problems. It also supports multiple regional languages, including English, Urdu, and Sindhi allowing users to switch between native languages effortlessly through the settings. The developed app is equipped with a dynamic accuracy assessment, and progress-tracking system, notifying the parents or guardians when practice sessions are missed, ensuring that language development remains consistent and effective. The major novelty of this work is that it has considered regional aphasia patients and their language needs. In contrast to the existing developed therapeutic tools which are mainly oriented towards resource-rich languages, the proposed work aims to address regional languages. The proposed speech therapist App for children can be a powerful tool for parents, caregivers, and educators, providing a fun and interactive way for children to improve their speech and language abilities. The developed solution also offers benefits in the context of enhanced patient involvement, motivation throughout their learning journey, greater flexibility, and accessibility in contrast to in-person therapy, immediate feedback, and careful progress monitoring that makes it easier to assess and modify treatment sessions
Heart Sense: A novel IoT integrated Deep Learning Based ECG Image Analysis for Enhanced Heart Disease Prediction
Get PDFThe increasing advancements in the healthcare networks leveraging the unmatched capabilities of the Internet of Things for various fatal disease prediction and remote health monitoring that proved to be very beneficial in providing timely and accurate healthcare services to patients. Patients who are suffering from chronic diseases like blood pressure, kidney diseases, and heart diseases need treatment on time to avoid sudden deaths due to these ailments. To avoid this serious scenario, we have presented a novel approach for predicting heart diseases based on the Internet of Things. By leveraging the combined abilities of The IoT and Deep learning we have proposed an advanced approach that will able to predict heart diseases with increased accuracy and precision in comparison to the existing approaches along with providing timely notifications to both patients and the medical professionals to deal with the situation at hand most effectively.
We will be receiving real-time health data from the sensors which will be a wearable IoT device in our case. This collected data contains the continuously monitored information of the patient’s ECG using an ECG sensing system that is sent to the cloud for precise disease prediction. We will also be employing the patients ‘electronic health records which will contain ECG images to increase the accuracy of our results. The Deep Learning model called the transformer will be used in the proposed approach for the precise prediction of cardiovascular disease in real-time. Both the healthcare professionals and the patients are provided with the relevant information if an ailment is predicted for effective healthcare monitoring and treatment. The proposed model has better results than the existing approaches for the prediction of heart disease in terms of accuracy which is 99.8%
Barriers to AI Adoption in Education: Insights from Teacher\u27s Perspectives
Get PDFA
rtificial intelligence in education is capable of offering significant benefits in the form of content generation, personalized learning, assistance in administration, and analytical reports. Despite the benefits, the integration of AI in education faces several challenges hindering its integration. The barriers to AI adoption in education are critical to explore, as they affect the incorporation of innovative educational technologies. The study aimed to explore the perceived barriers to suggest practical recommendations to enable educators to embrace innovative AI technologies for teaching. This study employed a qualitative research design with a descriptive research approach. A purposive sampling method was applied to select public and private sector educators from schools, colleges, and universities in Pakistan. Data were collected using an open-ended questionnaire designed using Google Forms. Data were analyzed using thematic analysis to recognize and categorize patterns and themes in responses, gaining a thorough understanding of the key barriers to AI adoption. The insights revealed that integrating AI in education inherits barriers in user experience, technological, and skills limitations, content reliability, privacy and security concerns, and overdependence on AI a risk to reduce creativity and learning. To overcome the barriers, clear ethical guidelines and policies, a balanced integration of AI with pedagogy, AI literacy training, and support to enable teachers to effectively use AI in education are recommended
Performance Analysis of Motorbike Engine Using Bioethanol Gasoline Blends
Get PDFThe increasing demand for sustainable energy and reduced reliance on fossil fuels has driven the exploration of alternative fuel options. This study aims to evaluate the performance of a motorcycle engine using bioethanol-gasoline blends. Simulations were conducted using AVL Boost software. By applying AVL Boost in innovative ways, the research provides new insights into improving the performance of motorcycle engines powered by bioethanol-gasoline blends, contributing to more eco-friendly transportation. A numerical model of a single-cylinder engine was developed, and various fuel blends were tested to assess performance characteristics at engine speeds ranging from 1000 to 4000 RPM. Single-cylinder spark ignition engines are commonly used in many types of motorcycles. The results showed that the E20 blend achieved a 4% increase in power and improved performance characteristics during tests on engines running on lower ethanol blends
A Data-Driven Review of Machine Learning Techniques for E-commerce Product Recommendation Systems
Get PDFIn today’s digital economy, recommendation systems are essential for enhancing customer experience and driving e-commerce growth. This study presents a comparative, quality-ranked review of machine learning-based product recommendation techniques, evaluating five key approaches: association rule mining, content-based filtering, collaborative filtering, knowledge-based systems, and hybrid models. Using a systematic literature review of 44 peer-reviewed publications across major publishers, the analysis includes geographic and publisher-wise trends and a structured quality assessment rubric. Results highlight hybrid systems as the most promising strategy, offering superior accuracy, diversity, and personalization while addressing cold-start, sparsity, and scalability challenges. Each technique’s strengths, limitations, and practical deployment considerations are critically examined to support evidence-based decision-making. The study concludes by recommending hybrid approaches tailored to domain-specific needs, offering actionable insights for both researchers and industry practitioners seeking effective and adaptable recommendation systems