Volume 12 | Issue 5 |

 Abstract

Health plays a very crucial part in our life. Like the quote says "Health is Wealth" if we have good health then it will lead to prosperous life. Therefore, we need to take care of our health no matter what. Our health should not get affected neither physically nor mentally. As we know that we cannot meet the doctor on daily basis. Looking at current scenario, life is very hectic we don't have time to make doctor's appointment. So to make it easier for us to communicate the doctor's we have created healthcare chatbots. Due to chatbots the person can ask any health related questions or doubts they are facing at that movement point of time and the chatbot will answer it. If we take a look at people they don't prioritize their health, which may lead to severe diseases. This Health care chatbot will make them understand the disease by studying the symptoms then predicting the disease. It is no charge service that will help user to get health related information in no time. Hence, Healthcare chatbot is used to understand and analyze human emotions.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Natural Language Processing, Decision Tree, Support Vector Machine, DialogFlow.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Teachers play a pivotal role for education of all children. Favourable and positive attitude of teachers towards children with disabilities is a major aspect of teaching-learning process and also for the growth and development of children with disabilities in the inclusive classroom. Hence the aim of this paper is to examine the attitudes of primary school teachers towards inclusive education. A sample of 120 primary school teachers was used for this purpose. The sample was chosen from the district of Uttar Dinajpur, using the mixed method technique. The researcher conducted a descriptive survey study.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

KEYWORDS: Primary school teacher, attitude, inclusive education.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The growing popularity of electric vehicles (EVs) calls for the creation of effective and user friendly infrastructure for charging them. The automatic wireless power hub for EVs that is suggested in this study provides a simple and convenient charging experience.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Automatic wireless power transfer (AWPT) ,Electric vehicle (EV) charging, Wireless EV charging, Inductive charging (if applicable)

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Abstract: Street lighting constitutes a significant portion of total energy consumption in urban areas. This paper proposes a novel approach to street lamp control systems, emphasizing remote monitoring to mitigate maintenance costs and energy usage. The study aims to introduce an efficient street lighting system capable of substantial energy reduction. Currently, many countries employ conventional street lights operating solely based on light intensity, often utilizing energy-intensive fluorescent lamps. In contrast, this study advocates for a smart lighting system incorporating cutting-edge Light Emitting Diode (LED) technology and sensor networks driven by microcontrollers. A comparative analysis between the proposed smart lighting system and conventional street lighting systems is presented, focusing on energy consumption. The system's architecture is simulated using the Proteus environment interfacing with microcontrollers. The results indicate a significant reduction in energy consumption with the implementation of the proposed smart lighting system. Additionally, the system's automation features, including automated on/off cycles synchronized with vehicle movement times, further optimize energy efficiency. Overall, this research presents a promising avenue for enhancing urban energy sustainability through intelligent street lighting systems, potentially yielding substantial environmental and economic benefits.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Keyword: Smart Street Lighting, Energy Efficiency, LED Technology, Sensor Networks, Microcontroller Integration, Remote Monitoring, Automation, Energy Consumption Reduction

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Advanced Heart Disease Prediction: Harnessing Hybrid Machine Learning" explores the fusion of traditional statistical methods with cutting-edge machine learning techniques to enhance the accuracy and efficacy of heart disease prediction models. This abstract outlines the integration of diverse data sources, including medical records, genetic profiles, and lifestyle factors, into a comprehensive predictive framework. By leveraging hybrid machine learning approaches such as ensemble methods and deep learning architectures, the proposed system achieves superior performance in identifying individuals at risk of developing advanced heart disease. Through a rigorous evaluation process on real-world datasets, the effectiveness and robustness of the hybrid model are demonstrated, underscoring its potential to revolutionize cardiovascular risk assessment and improve patient outcomes

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Heart disease, Machine learning (ML), genetic profiles, medical records, prediction models

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Heart disease remains a leading cause of morbidity and mortality worldwide, necessitating effective and early diagnostic tools. Machine learning (ML) techniques have emerged as powerful tools for predicting heart disease, offering potential improvements in accuracy and efficiency over traditional methods. This systematic review evaluates the performance and applicability of various ML models in heart disease prediction. We conducted a comprehensive literature search, selecting studies that applied different ML algorithms, including decision trees, support vector machines, neural networks, and ensemble methods, to heart disease datasets. Key performance metrics such as accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC) were extracted and analyzed. Our findings highlight the strengths and limitations of each model, with ensemble methods and neural networks generally outperforming others in terms of predictive accuracy. However, challenges such as data quality, interpretability, and clinical integration remain significant. This review underscores the need for standardized evaluation frameworks and the incorporation of domain-specific knowledge to enhance the reliability and adoption of ML models in clinical practice for heart disease prediction. Future research should focus on improving model transparency and developing robust, generalizable solutions to facilitate widespread clinical application.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Heart disease, Machine learning (ML), neural networks, disease prediction, clinical application.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This research investigates the development of an AI-powered companion designed to provide emotional support to individuals facing challenging circumstances. The AI system interprets and responds to emotional cues through a sophisticated workflow that converts user input into contextually relevant interactions. The process involves generating empathetic textual responses to user inputs, transforming these responses into natural-sounding speech, and synchronizing the digital human's lip movements with the audio to enhance interaction realism. This seamless integration of speech synthesis, and lip synchronization aims to create an immersive and supportive user experience. This study contributes to the field of AI-driven emotional support by demonstrating the potential of advanced technologies to deliver meaningful and human-like interactions, promoting mental well-being and offering a novel approach to digital emotional assistance.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Emotional Support Virtual Assistant (ESVA), Artificial Intelligence in Emotional Well-being, Digital Human Avatar, AI-driven Companionship,Artificial Intelligence

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In the age of rapid technological developments and advancement, conventional Learning Management Systems (LMS) often struggle to meet the ever-changing needs of learners. the emerging technologies of AI and Machine Learning and bigdata are able to provide various kind of analytics including descriptive, diagnostic, predictive, and prescriptive analytics, as well as recommender systems and adaptive learning techniques. These analytics are useful for understanding, interpreting, prediction, decision making and building recommended system. By harnessing machine learning techniques, the shortcomings of traditional Learning Management Systems (LMS) platforms can be addressed. By incorporating the prescriptive analytics, Learning Management Systems (LMS) can be tailored made with recommendations to students, faculty by facilitating proactive interventions that are based on historical data patterns. The prescriptive analytics not only empowers teachers with insights for resource optimization and instructional strategies but also fosters an adaptive educational ecosystem that evolves alongside the diverse needs of learners and educators. This paper provides the recent developments on Learning Management System (LMS) and the role of ML techniques to provide Learning analytics aiming to revolutionize the learning experience.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Prescriptive Analytics, Learning Management System, Machine Learning, Personalized Recommendations, Educational Ecosystem.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The Animal Intrusion Detection System, employing the YOLO v5 Algorithm, presents an innovative solution to safeguard farm animals and mitigate losses due to predation in agricultural settings. In response to the challenges faced by traditional monitoring methods, this system offers swift, accurate, and automated detection and classification of farm animals. Leveraging the advanced capabilities of the YOLO v5 Algorithm, the system provides real-time monitoring and alerts, empowering farmers to respond promptly to potential threats. This paper provides a detailed exploration of the system architecture, including the integration and customization of the YOLO v5 Algorithm for animal intrusion detection. The implementation process, encompassing data preprocessing, model training, and system optimization, is discussed to achieve optimal performance in farm environments. Furthermore, the practical implications and benefits for modern agriculture are elucidated, including enhanced farm security, reduced losses, and improved resource allocation. By providing actionable insights and real-time alerts, this project empowers farmers to proactively manage animal intrusions, optimize farm operations, and enhance productivity and sustainability in the agricultural sector.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Object Detection, YOLO v5, Animal Intrusion, Machine Learning, Animal Detection, Single Stage Object Detection Algorithm.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper aims to understand the relationship between Resilience and Emotional Intelligence among High School Students. A Quantitative approach has been adopted in this research by taking data from 194 participants who were High School Students (adolescents) from 13 to 19 years using two instruments. For Resilience, The Resilience Scale by Wagnild and Young was used and to measure Emotional Intelligence, The Shutte Self- Report Emotional Intelligence Test. Results showed a positive and strong relationship between Emotional Intelligence and Resilience among High School Students through Pearson- Moment Correlations using SPSS (r= .621, p= <.001) exhibiting a signification correlation and implying that a High score EQ means exhibiting higher Resilience in the face of adversity. Results also showed that there is a difference in levels of Emotional Intelligence and Resilience of students who belong to the same age bracket (15 years) but are in different grades (IX and X) (Data on Table 2). Mean and Standard Deviation of all 194 students was 118.26 and 14.53, respectively. The study has contributed to the field of Psychology and Sciences by strengthening evidence that exists on the relationship between Resilience and Emotional Intelligence among High School Students and that school grade influences the levels of Resilience and Emotional Intelligence among students. Thus, establishing evidence that grade/division plays a role in Emotional Intelligence and Resilience.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Emotional Intelligence. Resilience. High School Students, Quantitative Approach.

  License

Creative Commons Attribution 4.0 and The Open Definition