This project aims to develop a machine learning-based predictive model for diagnosing CKD at an early stage. By utilizing a range of clinical features such as age, blood pressure, blood sugar, and other relevant biomarkers, we employ machine learning algorithms, including Decision Trees, Random Forests, and Support Vector Machines (SVM), to predict the likelihood of a patient developing CKD. The dataset used in this study includes medical records of patients with various kidney conditions, and preprocessing techniques such as normalization and (...) missing data handling are applied to ensure the model’s robustness. The performance of the model is evaluated using metrics such as accuracy, precision, recall, and F1-score to ensure reliable predictions. (shrink)

Cloud storage's scalability, accessibility, and affordability have made it essential in the digital age. Data security and privacy remain a major issue due to the large volume of sensitive data kept on cloud services. Traditional encryption is safe but slows data recovery, especially for keyword searches. Secure, fine-grained access control and quick keyword searches over encrypted data are possible using attribute-based keyword search (ABKS). This study examines how ABKS might optimize search efficiency and data security in cloud storage systems. We (...) examine index compression, query processing improvement, and encryption optimization to decrease computational cost and preserve security. After a thorough investigation, the article shows how these methods may boost cloud storage system performance, security, and usability. Tests show that improved ABKS speeds up search searches and lowers storage costs, making it a viable cloud storage alternative. Exploring sophisticated machine learning algorithms for predictive search improvements and strengthening ABKS against emerging security vulnerabilities are future research priorities. (shrink)

The study outlines the technical challenges encountered during migration, including data compatibility issues, schema conversion, and security compliance, as well as strategies to mitigate these obstacles. Testing and validation techniques are applied throughout the migration, highlighting essential checkpoints to confirm data accuracy and optimal performance in the Snowflake environment. Postmigration performance metrics are evaluated to illustrate improvements in query execution, scalability, and overall system efficiency compared to the legacy system. The results underscore the advantages of Snowflake’s architecture in handling high-volume, (...) concurrent queries without compromising speed or accuracy. (shrink)

The accuracy levels of VGG19 and 3D CNN are compared using the performance metrics. This comparison helps in identifying which model performs better in the task of facial reconstruction from distorted images. Visualizing the results in the form of a graph provides a clear and concise way to understand the comparative performance of the algorithms. The ultimate goal of this project is to develop a system that can accurately reconstruct distorted faces, which can be invaluable in identifying accident victims or (...) assisting in medical treatments. By providing a reliable method for facial reconstruction, this technology can potentially save lives and improve outcomes for individuals involved in accidents. (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 rapid advancement of artificial intelligence (AI) technologies has revolutionized various industries, including the realm of education and career guidance. This project endeavors to harness the power of AI to develop a sophisticated career guidance application that offers personalized and effective recommendations to students and job seekers. The primary objective of this project is to address the limitations of traditional career guidance methods, which often lack customization and fail to adapt to individual preferences, skills, and aspirations. Through the integration of (...) AI algorithms, NLP techniques, and ML models, our application aims to provide accurate interest assessments, skill matching, and tailored educational pathways. The scope of the project encompasses the design, development, and implementation of AI-driven functionalities such as interest assessment, skill analysis, resume building, and personalized recommendations. T. (shrink)

The rapid evolution of phishing techniques necessitates more sophisticated detection and classification methods. In this paper, we propose a novel approach to phishing content classification using a Genetic Ranking Optimization Algorithm (GROA), combined with dynamic weighting, to improve the accuracy and ranking of phishing versus legitimate content. Our method leverages features such as URL structure, email content analysis, and user behavior patterns to enhance the detection system's decision-making process. The Genetic Ranking Optimization Algorithm (GROA) is used to rank phishing content (...) based on multiple features by optimizing the ranking system through iterative selection and weighting. Dynamic weighting further enhances the process by adjusting the weights of features based on their importance in real-time. This hybrid approach enables the model to learn from the data, improving classification over time. (shrink)

Cloud computing has transformed data management and storage by providing unmatched scalability, flexibility, and cost-effectiveness. However, rising cloud storage use has raised data security and privacy issues. As sensitive data being outsourced to third-party cloud providers, security is crucial. Traditional encryption methods secure data but make data recovery difficult. Specifically, efficiently searching encrypted data without compromising security is difficult.

The framework leverages a hybrid cloud architecture, combining the scalability of public clouds with the security of private clouds. By employing a combination of client-side hashing, metadata indexing, and machine learning-based duplicate detection, the framework achieves significant storage savings without compromising data integrity. Real-time testing on a hybrid cloud setup demonstrated a 65% reduction in storage needs and a 40% improvement in data retrieval times. Additionally, the system employs blockchain for immutable logging of deduplication activities, enhancing transparency and traceability. This (...) study concludes with an evaluation of the deduplication framework's impact on cost efficiency, system performance, and potential scalability. Future enhancements aim to integrate multi-cloud interoperability and advanced compression algorithms to further refine storage management. (shrink)

The predictive capacity of the model is evaluated using evaluation measures, such as accuracy, precision, recall, F1-score, and the area under the ROC curve (AUC-ROC). Our findings show that improved machine learning models perform better than conventional methods, offering trustworthy forecasts that can help medical practitioners with early diagnosis and individualized treatment planning. In order to achieve even higher predicted accuracy, the study's conclusion discusses the significance of its findings for clinical practice as well as future improvements that might be (...) made, like adding wearable device data in real-time or investigating deep learning techniques. (shrink)

A wide variety of two-wheelers of all category light- weighted, medium – weighted and heavy weighted vehicles have been introduced in the market. The objective of the study is to know the preference and satisfaction of women consumers over two-wheelers and the various aspects, which determines the purchase or buying behavior and to know the expectations of women consumers over two-wheelers. The sample size of the study was conducted in Tiruchirappalli city with 75 respondents through Non-Probability Random Sampling Method. The (...) tools and techniques used were simple percentage, chi-square and ANOVA. (shrink)

The dataset is preprocessed to remove noise and augmented to address the issue of class imbalance. The CNN model is then trained, validated, and tested on this dataset. The results indicate that the deep learning model achieves a classification accuracy of over 95% for most plant diseases. Additionally, the system is designed to provide real-time feedback to farmers, helping them take immediate corrective action. This automated approach eliminates the need for expert human intervention and can be deployed on mobile devices (...) for ease of use in rural areas. The potential future applications of this system include integration with precision agriculture techniques and expansion to a wider range of crops. (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)

The model is trained on a large dataset containing images of various food items along with their nutritional information. After preprocessing the input image, the model classifies the food and estimates the calorie count by leveraging its learned features. The estimated calorie value is then displayed to the user in real-time. This project leverages key technologies, including image recognition, deep learning, and nutrition analysis. It is designed to be integrated into mobile applications or web platforms, allowing users to track their (...) daily caloric intake efficiently. The system's accuracy is continuously improved through training on a diverse dataset, ensuring reliable calorie estimation across different food items. (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.

his project aims to provide an automated system for accurately estimating the calorie content of food and beverages using advanced deep learning algorithms. With the increasing demand for health-conscious individuals, there is a need for a reliable, efficient, and easy-to-use tool that can help users make informed dietary choices. The project utilizes image processing techniques and deep learning models, such as Convolutional Neural Networks (CNN), to analyze food images and predict the corresponding calorie content. The system works by first capturing (...) an image of the food or beverage, which is then processed and passed through a pre-trained deep learning model. (shrink)

The Internet of Things (IoT) wireless LAN in healthcare has moved away from traditional methods that include hospital visits and continuous monitoring. The Internet of Things allows the use of certain means, including the detection, processing and transmission of physical and biomedical parameters. With powerful algorithms and intelligent systems, it will be available to provide unprecedented levels of critical data for real-time life that are collected and analyzed to guide people in research, management and emergency care. This chapter provides a (...) quick overview of IoT features and how they relate to wireless discovery and technology to deploy the medical applications you need. In the world, the revolution in any industry is to connect your products and devices to the Internet and make them independent and remotely connected, so that anyone can use and view them from anywhere and anytime. The Internet of Things provides us with a home automation system that uses smart devices to overcome this obstacle, allowing us to easily manage our appliances. A smart city is a vision to integrate a variety of information and communication solutions for residents with essential services, such as smart parking on all streets. The main motivation for using the Internet for parking objects is simply collecting data to get free parking. The IoT-based RTSSPS architecture is divided into three parts: a WSN-based smart street parking module, an IoT-based smart street parking module, and an IoT-based smart street parking module. IoT-based cloud with street parking algorithm, rating and future directions. (shrink)