Authors - Seema Tripathi, Nikita Bhardwaj, Shivani Bansal Abstract - Voice recognition technology has evolved into a cornerstone in contemporary applications, from virtual assistants and intelligent homes to biometric security and healthcare. Its potential to facilitate unobstructed human-computer interaction has hastened the need for more precise and more robust systems. GMM and HMM traditionally paved the way for voice processing. However, deep learning architectures—namely Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformer-based models—have revolutionized the field by achieving unprecedented performance and flexibility. This research paper provides a comparative study of major deep learning models for voice recognition, critically evaluating their design rationales, merits, and shortcomings Some major challenges like scarcity of data, noise tolerance, computational efficiency, and interpretability of models are discussed. The paper also offers the perspectives of the future trends in work like the inclusion of self-supervised learning, light-weight models for edge devices, and multimodal systems that will influence the next voice recognition generation. The goal of this work is to offer an end-to-end perspective of what exists currently and stimulate future work in this very dynamic field.
Authors - Vipul Lanjewar, Sourish Joshi, Sujata Joshi, Menachem Domb Abstract - AI is changing supply chain, transport, and logistics using neural net-works to improve decisions. It helps with real-time analysis, route planning, and demand prediction. A bibliometric analysis with Scopus data was performed, using VOSviewer and Biblioshiny to track trends, citations, and new themes in AI for these fields. The focus was on areas like warehouse automation, self-driving logistics, and smart transportation, while also tackling data security and ethical issues. By finding key research and gaps, this paper shows how AI can shape the future of these industries.
Authors - Anshika Srivastava, Rojalin Patri Abstract - This study explores whether arms and armed forces increase the probability of armed conflict within a country. Though several studies in literature have highlighted the cases where arms and armed forces have influenced armed conflict within a country, none of them have provided empirical evidence to support this phenomenon. This study attempts to bridge the gap by providing a quantitative analysis across 45 countries over 28 years and further substantiates the arguments laid in qualitative studies. Random effect panel logistic estimates and year-wise logistic estimates have been used to capture the overall as well as year-wise significance of arms and armed forces on armed conflict within the country, respectively. Similarly, when the number of armed forces increase by one million, the odds for armed conflict becomes 3.97 times more and when military expenditure increase by 1%, the odds for armed conflict becomes 9.06 times more than before. These insights point towards the fact that arms, armed forces and militarism don’t necessarily help reduce violence.
Authors - Kalyani Yede, Deepak Sharma Abstract - Work-life balance is of utmost importance to career workers managing the challenges of contemporary work environments and family duties. This research employs secondary data to investigate the determinants of work-life balance, its impact on worker satisfaction, productivity, and health, and organizational support as a facilitator of balance. The study finds that flexible work arrangements, supportive management, and organizational policies all contribute strongly to helping employees balance work and personal life. Excessive workload and a lack of support, on the other hand, lead to job dissatisfaction and stress. The study emphasizes a need for cooperative efforts between employers and employees to create a good work-life balance. This study offers useful insights to organizations that want to enhance organizational performance and employee well-being by implementing focused work-life balance programs.
Authors - Namrata Patil, Pravin Desai, Ashvini Patil, Pragati Patil Abstract - In the context of multimedia content of huge scale, effective and efficient video summarization has become more and more important for improving web browsing experiences and information overload. In this paper, we introduce a new video summarization method by modeling it as a sequential decision-making problem. A Deep Summarization Network (DSN) is proposed for predicting the probability of considering each video frame in terms of its possible contribution to the final summary. For training the DSN, we suggest an end-to-end deep reinforcement learning system that works in a fully unsupervised way, without requiring annotated labels or human intervention. Our approach has its foundation in a well-crafted reward function that assesses generated summaries along two primary dimensions: diversity and representativeness. These elements are designed to ensure that the chosen frames not only convey the main content of the video but also encompass a good number of visual and contextual variations. The DSN is trained to maximize these rewards, resulting in brief, informative, and non-redundant summaries. Extensive experiments are performed on two standard datasets to confirm the efficacy of the new method. The experimental results show that our method is capable of rendering competitive performance compared with state-of-the-art methods, especially under unsupervised scenarios, thus revealing excellent potential to be applied in real-world systems for large-scale video analysis and multimedia retrieval.
Authors - Janwale Asaram Pandurang, Minal Dutta, Savita Mohurle Abstract - The machine learning algorithms used for the automated predction of esophageal cancer, a highly destructive disease that frequently exhibits at an advanced stage because it lacks early symptoms, is examined in this work. A huge dataset including clinical, demographic, and diagnostic information is used in the study to relate the classification algorithms of logistic regression and decision trees. With a incredible accuracy of 99.75% compared to 64.87%, the Decision Tree model clearly beaten Logistic Regression. Its capability to recognise complex, non-linear relationships in the data is responsible for Decision Tree's better performance, which makes it a useful tool for early cancer detection. The study identifies the need for validation on a variety of datasets and techniques to reduce overfitting, even as the results illustrate how machine learning may improve diagnostic accuracy. Improved clinical processes and better patient outcomes are made possible by us research's successful development of scalable, interpretable, and effective diagnostic tools.
Authors - Jatin Kumar Sangewar, Chandan Kumar Sangewar, Gaurav Kumawat, Chirag Joshi Abstract - In this research paper, we introduce a novel approach to improving research paper recommendation systems using the Universal Sentence Encoder (USE) to analyze and understand the textual content of academic papers, such as their title, abstract, and publication year. Our ultimate objective in the proposed methodology is to greatly enhance the accuracy and personalization of paper recommendations in favor of scholars, researchers, and students. Our research provides a thorough system architecture review, extensive experimentation with regard to state-of-the-art benchmarks, as well as an assessment of its probable impact on the world of academia. In addition to the technicalities of our method, we explore the larger research paper recommendation system context. This involves a close look at the issues that plague these systems, including data sparsity and the cold start problem, and the potential directions they offer for enhancing academic discovery. We also look at possible futures for the discipline, including the incorporation of user profiling, collaborative filtering methods, and ethical considerations into the building of these systems. The goal of this study is to push the field of research paper recommendations into a new generation based on the use of state-of-the-art Natural Language Processing and Machine Learning methods while ensuring a commitment to enhancing the academic experience. The new use of the USE model in this system offers intriguing possibilities for making more accurate and user-specific recommendations, which will eventually enable a more productive and efficient academic experience for users in general.
Authors - Naina Kokate, Aoudumber D. Londhe, Priyanka Swapnil Raikar, Nikeeta Pande, Sanjana Sanjiv Nikam, Nethra Nadar, Indranil Nayak, Rhia Nevgi, Neil Oswal Abstract - This project demonstrates about working of Peltier module with an new approach, we have tried making a smart way of using it by making a smart water temperature modulation bottle. The targets we wanted to achieve through this project was to make it energy efficient along with cost effective. the dual purpose of heating and cooling to be done as per our wishes. the main components which are used in this project are TEC1-12706 Peltier module, W1209 digital thermostat, two heatsinks and two fans. the project can be used for personal as well as professional fulfilling of needs such as getting water to a certain temperature or maintaining a medicine at a given temperature. the project can work on both battery and electricity.
Authors - Ketaki Paranjape, Rajasi Barapatre, Sandhya Arora Abstract - This study conducts a statistical analysis of the Israeli-Palestinian conflict to uncover patterns and relationships that characterize the dynamics of hostilities. The research examines critical questions about the association between event location, age, citizenship, and types of ammunition, employing statistical methods such as Z-scores, Chi-square tests, and F-tests on a comprehensive dataset. Key findings include significant regional variations in participation in hostilities, with Gaza showing the highest levels of engagement, and the predominance of the 21–30 age group in active involvement. Additionally, asymmetrical impacts were observed, with Palestinian civilians primarily affected by Israeli security forces, and Israeli civilians targeted by Palestinian actors. Analysis of ammunition usage reveals targeted engagement against younger age groups and highlights the varied means of violence in the conflict. These findings provide valuable insights into the conflict's demographic and regional dimensions, offering a foundation for data-driven conflict resolution strategies and humanitarian interventions.
Authors - Kalyani Yede, Deepak Sharma Abstract - This study looks into the effect of work-life balance on IT professionals in Pune, India, through analysis of determinants that affect this balance and measures to enhance it. A thorough review of literature demarcates important areas for study, such as the organizational policy, socio-cultural determinants, and perceptions. The research will fill the gap between research and practice by presenting culturally responsive suggestions to organizations looking to improve employees' job satisfaction and productivity. The research will, with a mixed-methods design, offer insights for policy-making and enhancing the quality of life of IT professionals.
