Search
7 articles for “CNN-LSTM Model”
-
Deep Learning-Based Thermal Prediction Models for Solid-State Electronic Devices
Abstract: The rapid advancement of solid-state electronic devices in high-performance computing, communication systems, automotive electronics, and renewable energy applications has significantly increased concerns related to thermal management and device reliability. Excessive heat generation in semiconductor devices adversely affects operational efficiency, switching performance, lifespan, and overall system stability. Traditional thermal prediction methods often require complex numerical computations and extensive simulation time, making them less suitable for real-time monitoring and adaptive control applications. …
Published in International Journal of Solid State Innovations & Research · Vol. 4, Issue 1, 2026 Read article
-
Optimized Machine Learning Framework for Battery State Prediction in Smart Charging Systems
Abstract: Good estimation of battery states, including State-of-Charge (SoC), State-of-Health (SoH), and Remaining Useful Life (RUL), are important in managing energy wisely and controlling the adaptive charging. This work introduces a streamlined machine learning model based on the ability to use multi-dimensional sensor measurements in terms of voltage, current, temperature, and cycle number to forecast battery conditions with high accuracy. Decent preprocessing, such as noise elimination, feature scaling, and calculated features, …
Published in International Journal of Energy and Thermal Applications · Vol. 4, Issue 1, 2026 · pp. 11–23 Read article
-
Advanced Lithium-Ion Battery Prognostics: A Comprehensive Review of Machine Learning Approaches for Remaining Useful Life Prediction
Abstract: The lithium-ion battery (LIB), as one of the main sources for portable power systems, has been increasingly popular owing to its widespread applications in electric vehicles, consumer electronics, aerospace and renewable energy. Despite their advantages in high energy density and long cycle life, LIBs suffer from degradation over time of aging and cycling, resulting in loss of performance, safety issues, and economic bottlenecks. Predicting their Remaining Useful Life (RUL) is …
Published in International Journal of Mechanical Dynamics and Systems Analysis · Vol. 3, Issue 2, 2025 · pp. 12–27 Read article
-
Automated Suspicious Activity Detection in Video Surveillance Using Deep Learning: A Review
Abstract: In the current era of advanced security systems, video surveillance plays an essential role in ensuring safety by detecting suspicious activities. With the increase in real-time data, manual monitoring has become impractical, paving the way for automated surveillance systems utilizing machine learning (ML) and artificial intelligence (AI) technologies. This paper explores the integration of ML and AI models, specifically convolutional neural networks (CNNs) and long short-term memory (LSTM) networks, for …
Published in International Journal of Optical Innovations & Research · Vol. 3, Issue 1, 2025 · pp. 20–27 Read article
-
Multimodal Data Fusion with Hybrid Machine Learning for Enhanced Prediction of Li-Ion Battery Remaining Useful Life and State of Charge
Abstract: Lithium-ion battery materials used in modern energy storage systems are required to exhibit high reliability, safety, and long lifecycle performance under varying operational and environmental conditions. Accurate prediction of Remaining Useful Life (RUL) and State of Charge (SoC) is therefore essential for understanding material degradation behavior, improving manufacturing quality, and enabling effective lifecycle management. However, nonlinear electrochemical aging, load variability, and thermal uncertainty significantly complicate accurate estimation of these parameters. …
Published in International Journal of Electro-Mechanics and Material Behaviour · Vol. 4, Issue 1, 2026 · pp. 1–5 Read article
-
Violent Event Recognition and Monitoring Using Deep Learning for Surveillance Videos
Abstract: The significance of real-time capabilities in human detection and tracking is discussed in the abstract of the paper. We talk about tracking, eye detection, and face detection. A thorough motion detection program for use in video monitoring and other applications is suggested by the study. The goal of the study is to further human tracking technology. Optical flow features and appearance-invariant features from a Darknet CNN model are integrated. Acquiring …
Published in International Journal of Advanced Robotics and Automation Technology · Vol. 1, Issue 2, 2023 · pp. 39–44 Read article
-
AI Driven IoT Based Decision Making System for Brain wave study: KSK approach for Brain wave study
Abstract: The rapid convergence of Internet of Things (IoT) architectures and deep learning has unlocked unprecedented potential for real-time neuro-diagnostic monitoring. This paper presents a novel framework for an AI-driven IoT ecosystem designed to capture, transmit, and interpret human electroencephalography (EEG) signals with minimal latency. Traditional brain-computer interface (BCI) studies are often constrained by localized computing power and the high dimensionality of neural data. Our proposed architecture integrates low-power EEG sensors …
Published in International Journal of Brain Sciences · Vol. 3, Issue 2, 2026 Read article