Bitcoin, as a decentralized digital currency, has undergone extreme price fluctuations over the years. Predicting its future price presents a significant challenge due to its volatile nature and susceptibility to various external factors, including market sentiment, regulations, and technological developments. This research aims to build an advanced forecasting model to predict Bitcoin’s price movements accurately. We leverage historical price data and apply cutting-edge machine learning techniques, including Long Short-Term Memory (LSTM) networks and Gradient Boosting Machines (GBM). By comparing these methods (...) with existing models, we evaluate their performance in predicting Bitcoin’s future prices, which is vital for traders, investors, and financial institutions in making informed decisions. (shrink)

Closed-Circuit Television (CCTV) systems are essential in modern security setups because they provide continuous surveillance, acting as both a deterrent and a critical tool for monitoring and evidence collection. Unlike human guards who can be limited by fatigue and blind spots, CCTV cameras offer consistent, 24/7 coverage of key areas. They fill gaps in the current security system by enabling real-time monitoring and recording incidents for later review, ensuring that potential security breaches are detected and addressed more effectively. This enhances (...) overall security effectiveness and reduces the reliance on human intervention. The integration of Artificial Intelligence and Machine Learning (AIML) techniques with existing CCTV networks presents a promising approach to address critical challenges in urban environments. This project examines how AIML can be leveraged for crowd management, crime prevention, and work monitoring using CCTV infrastructure. For crowd management, AIML enables automated crowd counting and density estimation, facilitating efficient allocation of resources during events and emergencies. In crime prevention, AIML algorithms analyze video feeds in real-time to detect suspicious activities and identify anomalies, aiding law enforcement in proactive interventions. Additionally, AIML enhances workplace monitoring by tracking productivity metrics, ensuring compliance with safety protocols, and optimizing operational workflows. Through these applications, AIML empowers cities and organizations to improve public safety, enhance operational efficiency, and make data-driven decisions based on insights derived from CCTV footage. The integration of AIML with existing CCTV networks represents a transformative advancement in urban surveillance and management practices, offering scalable solutions for diverse urban challenges. (shrink)

This project focuses on estimating reservoir inflows by integrating rainfall data, soil moisture levels in the catchment area, and releases from upstream reservoirs, coupled with an automated gate control system to prevent flooding in the basin. Utilizing hydrological models, the methodology predicts runoff from rainfall, adjusted for current soil moisture to enhance accuracy. Real-time data from upstream releases further refines inflow predictions. The automated system leverages predictive analytics and real-time monitoring to optimize gate operations, ensuring moderate water releases to maintain (...) safe reservoir levels and mitigate downstream flooding. This approach aims to enhance flood management and sustainable water resource use through advanced modelling and automation. (shrink)

Phishing attacks are an increasingly common cyber threat that exploit the trust users place in genuine websites by mimicking their look and feel. This research proposes a novel AI-based detection system designed to identify phishing domains that imitate authentic websites. Our approach leverages machine learning algorithms to analyze visual similarities, domain patterns, and metadata between phishing and legitimate sites. Through this method, the system detects phishing attempts before users are deceived. Key results indicate a high detection accuracy and a reduction (...) in false positives, which demonstrate the potential of this method for enhancing cybersecurity. Future improvements in realtime detection and integration into security protocols are discussed. (shrink)

Image captioning has seen remarkable advancements with the integration of deep learning techniques, notably Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, for generating descriptive captions for images. Despite these improvements, capturing intricate details and context remains a challenge. This project introduces an enhanced image captioning model that integrates transformers with an attention mechanism to address these limitations. By leveraging CNNs for feature extraction and LSTMs for sequence generation, while utilizing transformers to apply sophisticated attention to significant image (...) regions, the proposed model aims to generate more contextually rich and coherent captions. Experimental results indicate that incorporating transformers with attention mechanisms leads to a significant enhancement in caption accuracy and descriptiveness, surpassing traditional CNN-LSTM models. This advancement is particularly beneficial in various applications, including assistive technologies for the visually impaired, content-based image retrieval systems, automatic image annotation for digital asset management, and improved human-computer interaction. This approach represents a substantial step forward in achieving more precise and detailed image captioning, with potential impacts across numerous fields. (shrink)

Heart disease is a major challenge for global health, along with high morbidity and mortality. The earlier it is diagnosed, the better the outcome of the patient given timely intervention. This project employs a form of machine learning to train and create a risk assessment model of heart disease from the user-submitted data. The model employs the Random Forest algorithm, one of the most accurate robust algorithms available. We will use a dataset having patient records, such as age, gender, blood (...) pressure, and others. Other medical indicators. Therefore, data preprocessing and feature selection will be applied to enhance the model performance. The main idea is to design an interactive web application which can provide easy access to predict heart disease risk assessment. Users input health parameters, and the application, developed with Streamlit, indicates an immediate prediction for heart disease risk. The interface can be accessed by anyone without technical backgrounds. After the submission, it will process the data through the machine learning model, and risk assessment will be shown. This immediately outcome gotten from this type of risk assessment may prove to be an early warning for patients as they are encouraged to seek medical evaluation in appropriate times. This project, therefore, aims to bridge the gap that exists between advanced machine learning and an actual setting of practical healthcare where users can be well cared for proactively with their hearts and in an effort to ease the burden of heart diseases through early detection and intervention. (shrink)

Effective water management is vital for sustainable agriculture. This project introduces an IoT-based, AI-driven irrigation system that optimizes valve control using real-time soil moisture data. Soil moisture sensors continuously assess root zone moisture and relay this data to an AI framework, determining precise irrigation needs. The system autonomously adjusts valves according to environmental conditions, minimizing water waste and enhancing crop hydration. Machine learning algorithms, notably the random forest algorithm, analyze soil moisture and weather variables to inform irrigation schedules.

In a country as linguistically diverse as India, the demand for localized video content is rapidly increasing. Dubbing English videos into Indian languages, such as Hindi, Tamil, Telugu, and Bengali, is critical to making content accessible to wider audiences. This paper presents a software solution that automates the dubbing process using a combination of technologies like Automatic Speech Recognition (ASR), Machine Translation (MT), andText-to-Speech (TTS). The process begins by converting English audio into text using ASR, followed by translation into the (...) target Indian language through advanced Natural Language Processing (NLP) models. The translated text is then synthesized into natural-sounding speech using TTS engines like Google Text-to-Speech (gTTS). Finally, the dubbed audio is synchronized with the original video to ensure proper lip-sync and timing. This automated approach streamlines the dubbing process, reducing time and cost while maintaining translation accuracy, voice quality, and synchronization. The software offers an efficient solution for content creators, businesses, and educators looking to expand their reach across India’s multilingual population. (shrink)

Substation maintenance is a critical aspect of ensuring the reliable operation and longevity of electrical power systems. This process involves a range of activities aimed at preserving the functionality and safety of substations, which serve as pivotal nodes in the electrical grid. Effective maintenance strategies encompass routine inspections, preventive measures, and corrective actions to address equipment wear and potential failures. Advances in technology have introduced innovative tools and techniques for substation maintenance, including automated diagnostic systems, predictive analytics, and real-time monitoring (...) solutions. For that an Intelligent chat bot is build, Substation maintenance is a critical aspect of ensuring the reliable operation and longevity of electrical power systems. This process involves a range of activities aimed at preserving the functionality and safety of substations, which serve as pivotal nodes in the electrical grid. Effective maintenance strategies encompass routine inspections, preventive measures, and corrective actions to address equipment wear and potential failures. Advances in technology have introduced innovative tools and techniques for substation maintenance, including automated diagnostic systems, predictive analytics, and realtime monitoring solutions. (shrink)

This project explores the issue of high dropout rates in school education. We utilize a machine learning-driven approach to analyze data on student demographics, academic performance, attendance, and socioeconomic factors. By identifying at-risk students early, we aim to provide targeted interventions that will reduce dropout rates. This document outlines the structure, methodology, and findings of the project, leveraging techniques such as data preprocessing, model training, hyperparameter tuning, and risk stratification.

The primary objective of this research is to enhance the precision and speed of stock handling while minimizing human intervention and error. Our design incorporates state-of-the-art sensors, real-time tracking systems, and autonomous robots programmed with advanced algorithms for object identification, gripping, and movement. We propose a systematic workflow for automating the storage and retrieval process, starting from the identification of the stock to its precise placement and retrieval within the storage facility. The design also addresses potential challenges such as robot (...) mobility, collision avoidance, and space optimization. Performance metrics, including accuracy, time efficiency, and system scalability, are measured using simulation-based experiments in a controlled environment. The results show significant improvements in operational efficiency compared to traditional stock management approaches. This integration paves the way for future advancements in fully automated warehouses, reducing the need for human labor and increasing reliability. Finally, we discuss potential enhancements, including AI-based decision-making algorithms, multi-robot collaboration, and integration with Internet of Things (IoT) for real-time data analysis and continuous system improvement. (shrink)

In an increasingly interconnected world, language barriers continue to hinder effective communication across diverse populations. BharathLingo addresses this challenge by offering a user-friendly text translation platform specifically designed to facilitate translation between English and multiple Indian regional languages such as Hindi, Telugu, Bengali, Tamil, and more. Developed using Flask and powered by machine translation algorithms, BharathLingo allows users to input text manually or upload files for translation, delivering instant and accurate translations. The platform’s seamless interface and commitment to privacy make (...) it an ideal solution for students, professionals, and travellers seeking to bridge linguistic divides. This paper outlines the architecture, design choices, and challenges of developing BharathLingo, including its deployment using the Waitress web server. (shrink)

The diversion of forest land for development requires accurate tree enumeration to assess environmental impact. Traditional methods, like manual counting and sampling, are labor-intensive, time-consuming, and prone to error. This project leverages high-resolution satellite and drone imagery, combined with advanced image processing and machine learning, to automate tree counting. Our system includes analytical tools, and provides authorities with historical environmental data (like rainfall, temperature, humidity) for informed decision-making. With a userfriendly interface and appealing data visualizations, it also integrates Google Maps (...) API for user-generated satellite imagery. This solution aims to enhance accuracy, efficiency, and scalability in tree enumeration, supporting sustainable forest management and regulatory compliance. (shrink)

"Genius AI" is an innovative SaaS platform poised to revolutionize the landscape of artificial intelligence tools. This dynamic platform integrates a diverse array of AI functionalities, including conversation generation, code generation, music generation, and video generation, all in one centralized hub. At its core, Smart AI harnesses cutting-edge machine learning algorithms and neural networks to empower users with unparalleled capabilities. The conversation generation feature enables seamless interaction with users through natural language processing, facilitating engaging and lifelike conversations. At its core, (...) Smart AI harnesses cutting-edge machine learning algorithms and neural networks to empower users with unparalleled capabilities. The conversation generation feature enables seamless interaction with users through natural language processing, facilitating engaging and lifelike conversations. At its core, Smart AI harnesses cutting-edge machine learning algorithms and neural networks to empower users with unparalleled capabilities. The conversation generation feature enables seamless interaction with users through natural language processing, facilitating engaging and lifelike conversations. For developers and coders, Smart AI offers a ground breaking code generation tool, streamlining the process of software development by automatically generating code snippets tailored to specific requirements and programming languages. Moreover, music aficionados can leverage Smart AI's advanced algorithms to compose original melodies, harmonies, and rhythms, personalized to suit any style or genre. Meanwhile, the video generation functionality empowers content creators with the ability to effortlessly produce high-quality videos, complete with customizable elements and visual effects. With its user-friendly interface and scalable architecture, Smart AI caters to a broad spectrum of industries and applications, from e-commerce and marketing to entertainment and education. Whether enhancing customer engagement, accelerating software development, or fostering artistic expression, Smart AI unlocks endless possibilities for innovation and creativity. Join the forefront of AI-driven transformation with Smart AI and redefine the way we interact with technology. (shrink)

Underwater Wireless Sensor Networks (UWSNs) are pivotal for various applications, including oceanographic data collection, environmental monitoring, and naval operations. However, the harsh underwater environment poses challenges in designing efficient routing protocols, especially concerning energy consumption and data transmission reliability. This paper proposes an optimized depth-based routing protocol for energy-aware data transmission in UWSNs, focusing on minimizing energy usage while ensuring robust data delivery. The protocol dynamically adjusts transmission power based on node depth and residual energy, reducing communication overhead and prolonging (...) network lifetime. (shrink)

The AWSAR Job Portal is developed to provide job seekers with a platform to register, log in, and apply for jobs with ease. The purpose of this project was to create a full-stack web application, ensuring smooth user experience and addressing common challenges such as responsiveness and compatibility across browsers. The project used technologies like React.js, Tailwind CSS for frontend development, and Node.js with Express.js for backend management. MongoDB was implemented for database storage. The key challenge faced was the unresponsiveness (...) of the 'Apply to a job' button post-login, which was successfully resolved through code optimization. This manuscript discusses the system's architecture, methodology, issues encountered, and future enhancements. (shrink)

Given the great significance of institutions in the journey towards sustainability, most of them lack the ability to measure and improve their ESG activities. Based on this argument, this work presents the development of a web-based application called ESGConnect, intended to assist institutions in the evaluation process pertaining to their sustainability practices through an interactive structured submission and feedback mechanism. In ESGConnect, institutions provide ESG-related documents, which administrators verify and score with recommendations on how to enhance the documents based on (...) the Environmental, Social, and Governance criteria. User-specific dashboards are present on the tool: administrators monitor submissions, whereas users see scores and comments associated with the submissions. In addition to these items, ESGConnect also supports collaboration because students and various stakeholders are allowed to have a dedicated online community for discussion and sharing information on sustainability practices. The architecture of the platform relies on Java Servlets, JSP, and database integration for easy handling of user management and data. Preliminary testing does indeed suggest that ESGConnect might be able to facilitate better communications and actionable insights for institutions interested in improving their sustainability efforts. Expansion of the platform features and improvement in scalability to service a much larger number of educational institutions are part of the future work. (shrink)

Pneumonia is a serious respiratory infection that poses significant health risks, particularly if not diagnosed and treated promptly. Traditional methods of pneumonia diagnosis rely on the manual interpretation of chest X-ray images by radiologists, a process that can be time-consuming, subjective, and error-prone, especially in regions with limited access to experienced medical professionals. To address these challenges, this study explores the development of an automated deep learning-based system for pneumonia detection using chest X-ray images. The results demonstrate that the deep (...) learning model can achieve high levels of accuracy, sensitivity, and specificity, making it a valuable tool for assisting radiologists in diagnosing pneumonia more quickly and reliably. Moreover, the system's scalability and ease of deployment make it particularly beneficial in resource-limited settings, where timely and accurate diagnosis is crucial. This research highlights the potential of deep learning to revolutionize medical diagnostics, improving patient outcomes through enhanced diagnostic accuracy and efficiency. (shrink)

This paper has been designed to develop the user-friendly server log management and monitoring system for the educational portal in an endeavor to enhance its capabilities. Server log management assumes a primary role in the current digital world in the maintenance of the health of the system, in the diagnosis of problems, and in ensuring that accountability is maintained. Current practice in log management is usually disjointed and does not have advanced mechanisms capable of handling the complexities of modern systems. (...) Our approach consolidates log information collection from the source thus coming through operating systems, applications, services, and devices on the network using Logstash to collect much easier log data. All log data collected will be structured in Elasticsearch with compression and archiving, which allows for long-term storage and minimizes the costs to the consumer. This means that users will be able to make more precise queries and filter log entries for analyzing the same in terms of time, log level, source, and keywords. In order to improve responsiveness to issues of critical concern, Kibana will be configured to send alerts based on predefined rules and provide insights through the use of charts and dashboards. All of these capabilities will allow them to determine trends, build reports, and support auditing and compliance. A high priority for the project was accessibility. We shall have an intuitive system: easy to implement, easy to use, for the target user groups intended here with minimum technical knowledge on their part, well supported by documentation. Deliverables expected would include a server log management system tuned for the Educational portal framework, which would improve system performance and security monitoring, real- time incident response, and operational efficiency through automating log classification. Finally, the project will implement Educational portal with an all-around effective tool for log management that can aid in efficient governance and security along with compliance to regulatory standards. Of course, our system will use the ELK stack to make it scalable and flexible enough to be ready for the unique demands of Educational based applications. (shrink)

The proposed system combines predictive analytics and historical data to flag potential emergencies before they occur. The visual analytics platform provides comprehensive reports to healthcare providers, enabling them to monitor trends, identify risk factors, and make informed decisions. This approach significantly enhances patient care by minimizing delays in response and improving overall health outcomes. The system's architecture, based on big data frameworks, supports scalable and efficient data processing. The study demonstrates how the integration of predictive models and data visualization tools (...) can revolutionize health alert systems, making them more responsive and adaptive to individual patient needs. Future enhancements will focus on incorporating machine learning models for more personalized predictions and extending the system's capabilities to remote patient care. (shrink)

News Rakshak is an advanced web application that monitors, analyzes, and verifies news related to government schemes in regional media across multiple platforms, including 200+ websites, e-papers, and YouTube channels. The application leverages Natural Language Processing (NLP) for sentiment analysis and integrates Artificial Intelligence (AI) to identify and flag fake news and videos. Sentiments are classified as positive, neutral, or negative, rated on a scale from 0 to 5, providing Public Information Bureau (PIB) officers with actionable insights. The system uses (...) Optical Character Recognition (OCR) for extracting text from image-based news formats and delivers real-time alerts to officials via multiple channels. The user-friendly interface, equipped with filtering options, enables effective trend visualization. News Rakshak serves as a comprehensive tool for tracking and verifying government-related news sentiment and authenticity, ensuring accurate feedback from regional media. (shrink)

The integration of robotics and stock management systems has revolutionized warehouse operations, offering greater efficiency, accuracy, and flexibility. This paper presents an optimal design for integrating robotic systems with stock management for pick-and-place operations in warehousing environments. The primary objective of this research is to enhance the precision and speed of stock handling while minimizing human intervention and error. Our design incorporates state-of-the-art sensors, real-time tracking systems, and autonomous robots programmed with advanced algorithms for object identification, gripping, and movement.

The establishment of a centralized Nasha Mukti (drug deaddiction) database is a vital initiative aimed at consolidating information from various sources to effectively combat substance abuse. By unifying data from deaddiction centers, healthcare providers, and law enforcement, this database will enhance coordination, improve intervention strategies, and support research and policy formulation. Ultimately, it seeks to create an integrated system to address substance abuse on both community and national levels.

.Terrain recognition is critical in various applications, including autonomous navigation, disaster response, and remote sensing. Traditional methods rely heavily on convolutional neural networks (CNNs), which require significant computational resources for high accuracy. Vision transformers (ViTs) have recently emerged as a novel approach to image processing, offering superior capability in processing long-range dependencies in visual data. This paper proposes a terrain recognition model based on Vision Transformers, aiming to improve classification accuracy and processing efficiency on complex terrain datasets. Key steps include (...) pre-processing satellite imagery, feature extraction through transformer architecture, and performance evaluation. Our results demonstrate that ViTs significantly enhance recognition accuracy, making them a promising alternative to CNNs in terrain analysis tasks. (shrink)