Journal of Big Data Technology and Business Analytics

Transforming Manufacturing with AI: Advanced Predictive Maintenance Solutions

Mekala R, Mohanraj E, Abirami A, Lakshmanaprakash S, Rukumanikhandan C — Fri, 13 Sep 2024 00:00:00 +0000

This paper examines the use of data analytics and Artificial Intelligence (AI) in predictive maintenance in the industrial sector, emphasizing the importance of these technologies in raising operational effectiveness and decreasing downtime. It addresses integrating Artificial Intelligence (AI) techniques with data analytics to anticipate equipment breakdowns and improve maintenance schedules. These approaches include machine learning algorithms and deep learning models like Long Short Term Memory (LSTM). The chapter also includes a case study on the NASA Turbofan Engine Degradation. The simulation uses LSTM models to predict the remaining lifespan of turbine engines using artificial intelligence data from sensors. Evaluation metrics are used to evaluate the models' prediction ability and pinpoint areas that require more improvement. These metrics include the Mean Square Error (MSE), Mean Absolute Error (MAE), and R-squared score.

A Comprehensive Review of Machine Learning Approaches in Livestock Health Monitoring

Shiva Sumanth Reddy, Manjunath D R, Jahnavi S, Nandini C — Wed, 25 Sep 2024 00:00:00 +0000

Livestock health monitoring has emerged as a crucial area in agricultural technology, where Machine Learning (ML) approaches offer promising solutions for disease detection, heat stress management, and behavioral anomaly identification. This review explores the latest advancements in applying machine learning models to livestock health monitoring, focusing on methods such as deep learning, IoT integration, and multimodal frameworks. Techniques like Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and hybrid models have significantly improved early detection of communicable and non-communicable diseases. Additionally, AI-based systems monitoring heat stress and behavioral changes have enhanced overall livestock management, reducing economic losses and improving animal welfare. This review synthesizes current trends and challenges in deploying ML models in real-world farming environments, particularly integrating IoT devices to collect and analyze health data. Moreover, it highlights future directions in improving the accuracy and scalability of ML models, including optimizing data collection and leveraging real-time analytics. This review aims to guide future developments in AI-driven livestock health monitoring systems by providing a comprehensive overview of current research.

SpeakSmart: Empowering Public Speakers, Elevating Every Speech

Thu, 17 Oct 2024 00:00:00 +0000

Public speaking is one of the most essential skills in many professional fields, but it often comes with challenges due to limited experience or fear. We propose developing advanced public speaking software to tackle these issues and improve users' presentation skills. Using the latest technologies like deep learning and natural language processing, the software will offer real-time recording and analysis of presentations, providing suitable feedback on aspects such as speaking rate, emotional tone, body language, and content delivery. With features for speech analysis, facial emotion detection, and body language evaluation, the software aims to give users detailed insights to enhance their public speaking skills. This project is designed to help users overcome public speaking fear and become more confident and influential speakers.
Along with these core features, the software also includes interactive training modules that allow users to practice in a real-time environment to gain confidence over time. The software will guide speakers toward overcoming public speaking anxiety through personalized feedback and adaptive learning paths. The system also supports multilingual analysis, making it accessible to a broader audience. Furthermore, the software can provide customized advice on improving audience connection by using sentiment analysis. This project is designed to help individuals become more confident and compelling speakers and to bridge the gap between theoretical knowledge and real-world practice.

Multiclass Date Fruit Prediction Using SVM and Logistic Regression with OVO and OVR

G. Ravi Kumar, G. Thippanna, Maninti Venkateswarlu — Wed, 13 Nov 2024 00:00:00 +0000

Multiclass classification plays a crucial role in various AI applications requiring simultaneous recognition of multiple classes. This research investigates the application of multiclass classification techniques to predict the species of date fruits using Support Vector Machine (SVM) and Logistic Regression (LR) algorithms with One-Versus-One (OVO) and One-Versus-Rest (OVR) strategies. The dataset comprises 898 samples with 35 elements and 7 distinct labels. The experimental results demonstrate the superiority of SVM over LR, achieving the highest accuracy of 93.68% with the OVR strategy. Moreover, OVR outperformed OVO in both algorithms, showcasing its efficacy for multiclass problems. These findings offer valuable insights for date fruit prediction and further advance the state of multiclass classification techniques in AI applications.