The Retrieval-Augmented Generation (RAG) model significantly enhances the capabilities of large language models (LLMs) by integrating information retrieval with text generation, which is particularly relevant for applications requiring context-aware responses based on dynamic data sources. This research study presents a practical implementation of a RAG model personalized for a Chabot that answers user inquiries from various specific websites. The methodology encompasses several key steps: web scraping using BeautifulSoup to extract relevant content, text processing to segment this content into manageable chunks, and vectorization to create embeddings for efficient semantic search. By employing a semantic search approach, the system retrieves the most relevant document segments based on user queries. The OpenAI API is then utilized to generate contextually appropriate responses from the retrieved information. Key results highlight the system's effectiveness in providing accurate and relevant answers, with evaluation metrics centered on response quality, retrieval efficiency, and user satisfaction. This research contributes a comprehensive integration of scraping, vectorization, and semantic search technologies into a cohesive chatbot application, offering valuable insights into the practical implementation of RAG models.

This study presents a hybrid robotics automation system that optimizes real-time navigation, obstacle avoidance, and environmental mapping under difficult situations by combining AutoNav, LIDAR-based SLAM, and DenseNet with Leaky ReLU for robust motion planning. The main goals are to use AutoNav to enable autonomous navigation with optimal path planning, LIDAR-based SLAM to accomplish precise mapping and localization, and DenseNet and Leaky ReLU to improve motion planning and obstacle avoidance. Through the integration of various technologies, the study suggests an effective and flexible system for robotic operations in dynamic situations in real time. In order to provide the best trajectory planning and accurate obstacle recognition, the system constantly modifies motion planning based on real-time sensor data. Performance results show that the system outperforms individual parts, with a 95% gradient efficiency, a localization error of only 0.045 meters, and a pathfinding accuracy of 97.5%, the system's performance results illustrate its superiority over individual parts and highlight its real-time adaptability and optimization accuracy. For the future of robotics, this hybrid system offers breakthroughs in real-time decision-making and nimble autonomous robotic navigation.

Passengers' satisfaction with airlines is one of the important determinants of competitive advantage for airlines with globalization and customer-oriented aviation industries of today. Customer satisfaction directly impacts brand loyalty, customer retention, and profitability, becoming an important key performance indicator for airline operators. The research examines a dataset of over 120,000 passengers, evaluating various aspects of their flying experience such as inflight services, comfort, punctuality, and overall satisfaction. An in-depth analysis of the key factors for customer satisfaction is done based on several data analyses and using different machine learning techniques like Logistic Regression, K-Nearest Neighbors, Decision Tree, and Random Forest. Through these techniques, our results show that, among others, service quality, punctuality, and comfort are the essential requirements for customer satisfaction. Conclusively, this study offers actionable recommendations for airlines that are vital in improving passenger satisfaction, which is an important factor in developing effective customer loyalty in the highly competitive airline business. The K-Nearest Neighbors (KNN) model performed best with an F1 score of 0.93, excelling in balancing precision and recall. Other models like Decision Tree and Random Forest were also used, with Random Forest providing robustness due to its ability to handle large datasets without overfitting, while Logistic Regression gave interpretable results but had the lowest F1 score at 0.89.

Home automation systems (HAS), leveraging the power of the Internet of Things (IoT), are gaining significant attention for their potential to reduce costs, labor, and human error. As the demand for smart home technologies grows, effective energy management and cost reduction become increasingly important. This research explores the technical landscape of IoT-based HAS, focusing on remote control and management of home appliances through smartphones and dedicated applications. A comparative analysis of various HAS solutions will be conducted to evaluate their functionality, usability, and energy efficiency. Additionally, the study will examine the security and privacy implications of IoT-based home automation and potential barriers to adoption such as cost and complexity. By addressing these key issues, this research aims to contribute to the development of more effective and accessible smart home solutions.

Fake news, characterized by false information disseminated intentionally with malicious intent, has become a critical societal issue. Its impact spans political, economic, and social domains, fueled by the rapid proliferation of digital communication channels, particularly social media. To combat this menace, researchers have turned to automated mechanisms for detection, leveraging machine learning algorithms and curated datasets. In this exploratory research, the landscape of machine learning algorithms is employed in identifying fake news. Notably, the research focus on algorithms such as the Bidirectional Encoder Representations from Transformers (BERT) and Convolutional Neural Network (CNN) respectively. However, most of these studies rely on controlled datasets lacking real-time information from social networks—the very platforms where disinformation thrives. The findings underscore the need for research in social network environments, where fake news spreads most prolifically. Additionally, future investigations should extend beyond political news, considering hybrid methods that combine NLP and deep learning techniques. This study serves as a valuable resource for researchers, practitioners, and policymakers seeking insights into the evolving landscape of the ability to combat fake news effectively.

Cyberbullying, a pervasive issue in the current digital age, has prompted the need for advanced predictive models to identify and mitigate online harassment. This survey paper explores the landscape of cyberbullying severity level prediction using an ensemble-based deep learning approach for multimodal datasets. Delving into the realm of deep learning techniques and investigating their efficacy in discerning subtle patterns indicative of cyberbullying behaviour, the survey encompasses a comprehensive review of existing ensemble methodologies, highlighting their strengths and weaknesses in cyberbullying prediction. Diverse datasets, model architectures, and evaluation metrics employed in relevant studies are analysed, aiming to provide a thorough understanding of the current technological status. Additionally, difficulties and potential avenues for upcoming studies are discussed, fostering advancements in the development of robust predictive models to combat cyberbullying effectively. Researchers, practitioners, and policymakers looking for insights on the changing field of cyberbullying prevention using ensemble-based deep-learning methodologies will find this survey to be a valuable resource.

JCET (Jawaharlal College of Engineering and Technology) Companion, the innovative mobile app thoughtfully designed for JCET college community, introduces a comprehensive suite of indispensable features aimed at simplifying and enhancing campus life. At its core, the app provides a user-friendly event calendar intricately linked with a reminder system, ensuring students never miss vital dates or essential college events. The meticulously organized study material empowers efficient learning, while crucial announcements keep users informed. With seamless attendance tracking and notifications, students stay accountable and punctual. Homework management, to-do lists, fee handling through an integrated gateway, and efficient leave request management all find a home in this app, uncluttering the daily tasks that typically burden students. In essence, JCET Companion offers a centralized platform, fostering a sense of community and shared experience while ensuring everyone is consistently up to date, transforming college life into a well-organized and informed journey, marked by enhanced efficiency and connectivity for all its users.

With 1.07% of the country's overall GDP coming from fishing, the fishing industry has huge significance in India. The supply chain and overall exports to foreign nations will be improved by revolutionizing this sector of the economy. Consumers are nowadays very much concerned about their health and in knowing about the quality of the goods they purchase or consume, particularly when it comes to nutrition. Fish must be consumed within a certain time frame and under the right circumstances because it is a perishable food. The government officials must also keep an eye on illicit fishing, which is another serious problem that disrupts ecosystems in many different places. In other words, consumers, the government, and society in general demand transparency throughout the entire value chain of fish products. In this research, the use of blockchain using Ethereum-based smart contracts to trace fish packages back and forth throughout the entire fisheries value chain is explored.