Search
218 articles for “deep learning and neural networks”
-
AI, Robotics, and the Future of Waste Management: A Systematic Review of Advanced Collection and Sorting Systems
Abstract: The rapid growth of cities and rise in population have made waste management a major concern that calls for innovative and efficient solutions. Conventional waste collecting techniques are dangerous, time-consuming, and frequently ineffective. The development of automated waste management systems powered by cutting-edge technology like robotics, deep learning, artificial intelligence (AI), and the Internet of Things (IoT) is examined in this study. Vision-based systems, convolutional neural networks (CNN) for garbage …
Published in International Journal of Robotics and Automation in Mechanics · Vol. 3, Issue 1, 2025 · pp. 1–6 Read article
-
A Review on Artificial Intelligence Techniques for Analyzing Deforestation and Illegal Logging Using Satellite Imagery
Abstract: Deforestation and illegal logging remain critical environmental threats, driving biodiversity loss, climate change, and socio-economic disruption. Conventional monitoring techniques frequently do not yield real-time, large-scale insights. Recent developments in Artificial Intelligence (AI), especially in deep learning and computer vision, have revolutionized the ability to analyze high-resolution satellite images for detecting deforestation and monitoring illegal logging. This review synthesizes recent developments in AI-driven approaches, highlighting convolutional neural networks (CNNs), anomaly detection …
Published in International Journal of Satellite Remote Sensing · Vol. 4, Issue 1, 2026 · pp. 1–9 Read article
-
A Physics-Informed Graph Neural Network Framework for Real- Time Thermal-Aware Fault Prediction and Adaptive Power Optimization in Heterogeneous System-on-Chip Architectures
Abstract: Heterogeneous System-on-Chip (SoC) architectures are increasingly adopted in edge computing, artificial intelligence, autonomous systems, and high-performance embedded platforms due to their superior computational efficiency and flexibility. However, increasing integration density and workload diversity introduce severe thermal hotspots, accelerated device degradation, and unexpected hardware faults that adversely affect system reliability and energy efficiency. This study proposes a Physics-Informed Graph Neural Network (PI-GNN) framework for real-time thermal- aware fault prediction and adaptive …
Published in Journal of VLSI Design Tools and Technology · Vol. 16, Issue 2, 2026 Read article
-
Multivariant Disease Detection from Different Plant Leaves and Classification
Abstract: Agricultural growth is significant in Indian GDP which is based on yield of crops, quality of the plants and procedure of the plants taken. To maintain good quality of plant, the plant diseases should be identified and then given proper suggestions to farmers for specific fertilizers and pesticides to be used. The use of specific fertilizers or pesticides makes plant more health with good quality so that farmers can get …
Published in Research and Reviews : Journal of Crop science and Technology · Vol. 15, Issue 2, 2026 · pp. 27–35 Read article
-
Controlling Media Player Through Hand Gesture Recognition System Using CNN and RNN Models
Abstract: Artificial intelligence markup language (AIML) project represents a pioneering endeavor in the realm of media player control through hand gesture recognition, merging advanced technologies like convolutional neural networks (CNN) and recurrent neural networks (RNN). By harnessing the image analysis capabilities of CNN, our system ensures accurate, real-time detection, and interpretation of intricate hand gestures, enabling users to interact with their media content naturally and seamlessly. What sets our project apart …
Published in Journal of Computer Technology & Applications · Vol. 15, Issue 1, 2024 · pp. 29–34 Read article
-
Parkinson’s Disease Detection on Spiral Images Using CNN with Meta-Classifiers
Abstract: In this work, we provide a detailed method for identifying Parkinson’s Disease (PD) by integrating Convolutional Neural Network (CNN) and meta-classifiers. Through the utilization of a varied dataset consisting of handwritten spiral images, our methodology demonstrates commendable accuracy across a range of models. Specifically, our CNN model with meta-classifiers surpasses alternative approaches, achieving an impressive accuracy rate of 95.07%. By utilizing pre-established VGG16 and ResNet50 architectures as bases, the region-based …
Published in Journal of Computer Technology & Applications · Vol. 16, Issue 1, 2025 · pp. 55–66 Read article
-
Brain Tumor Detection Using RestNet50 Architecture
Abstract: This paper presents a novel deep learning model for brain tumor diagnosis from MRI scans on the basis of ResNet50 with some modifications. Optimizing the modified layers and pre-trained ResNet50 for improved diagnostic accuracy and reliability in real-world clinical settings is one of the key contributions of this paper. The model was trained on an extremely well-balanced data of 2,577 MRI scans, which were split equally among the tumor and …
Published in Current Trends in Signal Processing · Vol. 15, Issue 2, 2025 · pp. 1–13 Read article
-
Enhancing Customer Engagement with AI-Driven Movie Recommenders: Integrating Neural Collaborative Filtering, Sentiment Analysis, and Conversational Agents
Abstract: In today’s competitive digital landscape, user engagement is a critical factor for the success of entertainment platforms, especially those offering movie recommendations. This study introduces a comprehensive AI-driven framework designed to enhance customer interaction, satisfaction, and loyalty through the intelligent integration of multiple deep learning models. The system combines three core components: Neural Collaborative Filtering (NCF) for generating personalized movie recommendations based on user behavior and preferences, Long Short-Term Memory …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 12, Issue 3, 2025 · pp. 45–54 Read article
-
Lip Reading: Transforming Speech to Text
Abstract: Lip reading, the ability to interpret spoken language by observing lip movements, is a valuable skill that can aid in various applications, particularly in enhancing speech recognition systems. This project explores the implementation of a deep learning-based lip-reading model to improve the accuracy and robustness of speech recognition in challenging environments, such as noisy or audio-limited settings. The proposed lip-reading system leverages Convolutional Neural Networks (CNNs) and Recurrent Neural Networks …
Published in Current Trends in Signal Processing · Vol. 14, Issue 1, 2024 · pp. 23–33 Read article
-
Advancements in AI-Driven Sound Spectrogram Analysis: From Deep Learning to Quantum and Neuromorphic Processing
Abstract: The rapid advancement of artificial intelligence (AI) has significantly reshaped the field of audio signal processing, with sound spectrogram analysis emerging as a central research focus. Spectrograms provide a rich time–frequency representation of audio signals, making them particularly suitable for data-driven learning approaches. This paper presents an in-depth and original review of modern AI-based techniques applied to spectrogram analysis, highlighting their growing impact across critical application areas such as healthcare …
Published in Journal of Multimedia Technology & Recent Advancements · Vol. 13, Issue 1, 2026 · pp. 01–06 Read article
-
A Survey On Leveraging Machine Learning for Phishing Attack Prediction and Detection
Abstract: Phishing is one of the biggest cybersecurity threats that exploits user trust by masquerading as a legitimate site or email to steal personal and sensitive information. A state- of-the-art-phishing detection systems survey, this review showcases the evolution from traditional list-based techniques, including blacklisting and whitelisting to machine learning and deep learning models. While list-based systems cannot evolve to detect new and zero-day attacks, the ML algorithms of Decision Tree, Random …
Published in Journal of Microelectronics and Solid State Devices · Vol. 12, Issue 3, 2025 · pp. 1–10 Read article
-
Automatic Car Controller Based on Sign Board using Deep Learning and IOT
Abstract: The rapid growth of intelligent transportation systems has increased the demand for safer and more efficient driving solutions. Conventional vehicles often rely heavily on human intervention, which can lead to accidents due to negligence, fatigue, or poor visibility of traffic signs. This project proposes an automated car control system that utilizes deep learning and Internet of Things (IoT) technologies to recognize traffic signboards and respond accordingly. The primary objective is …
Published in Journal of Control & Instrumentation · Vol. 17, Issue 2, 2026 Read article
-
Malicious Network Traffic Detection Using Hybrid Feature Selection with Ensemble Neural Network
Abstract: The detection of malicious network traffic is a critical aspect of cybersecurity, aiming to protect sensitive data and maintain the integrity of network systems. This study introduces a novel approach that combines hybrid feature selection with ensemble neural networks to enhance the accuracy and efficiency of malicious network traffic detection. The dataset used in this study was obtained from Kaggle and offers a wide-ranging and varied collection of network traffic …
Published in Nano Trends – A Journal of Nano Technology & Its Applications · Vol. 27, Issue 3, 2025 Read article
-
AI-Assisted Defect Detection in Polymer Composite Insulators Using an Optimised Ensemble Deep Learning Framework for Structural Health Monitoring
Abstract: Polymer composite insulators, particularly those made from silicone rubber and epoxy resins, are increasingly adopted in high-voltage transmission systems due to their superior electrical insulation, lightweight design, hydrophobicity, and environmental durability. Despite their advantages, these materials are susceptible to surface degradation, mechanical cracking, and flashover under prolonged exposure to environmental pollutants, thermal stress, and electrical aging. Accurate, real-time condition assessment of these composite insulators is critical for ensuring operational safety, …
Published in Journal of Polymer & Composites · Vol. 13, Issue 6, 2025 · pp. 253–261 Read article
-
A study in Leveraging Deep Learning and IoT Arrays for Dynamic, Hyper-Local Atmospheric Intelligence
Abstract: The critical demand for high-resolution, actionable atmospheric data is challenged by the high cost and sparse coverage of traditional regulatory monitoring stations. This paper explores the synergistic paradigm shift enabled by integrating low-cost, dense Internet of Things (IoT) sensor arrays with advanced Artificial Intelligence (AI) methodologies, specifically Deep Learning (DL) models. We address the primary limitations of low-cost sensors—inherent bias, sensitivity to environmental drift (temperature/humidity), and calibration inconsistency—by utilizing AI …
Published in International Journal of Atmosphere · Vol. 2, Issue 2, 2025 · pp. 50–62 Read article
-
Real-Time Air Quality Prediction Using IoT-Integrated Polymer Sensors and Recurrent Neural Networks
Abstract: Real-time air quality monitoring remains a critical challenge in urban environments, where traditional sensor infrastructures often suffer from limited responsiveness, poor scalability, and high deployment costs. The increasing prevalence of NO₂ pollution, a key contributor to respiratory and cardiovascular ailments, demands advanced sensing platforms capable of both accurate detection and predictive inference. Existing methods either rely on rigid electronic sensors lacking adaptability or on statistical forecasting models that fail to …
Published in Journal of Polymer & Composites · Vol. 13, Issue 6, 2025 · pp. 332–347 Read article
-
A Machine Learning-based Analysis of Climate Change
Abstract: Climatic variations are a pressing global challenge that demands immediate and comprehensive attention. A wealth of articles has been published on climate change mitigation and adaptation, yet there remains a need for innovative methods to explore the complexities of climatic variations and to devise more efficient and effective strategies for adjustment and alleviation. With technological advancements, machine learning (ML) and deep learning (DL) approaches have derived significant popularity across various …
Published in Research & Reviews : Journal of Space Science & Technology · Vol. 13, Issue 2, 2024 · pp. 1–10 Read article
-
A Machine Learning-Based Non-Invasive System for Blood Group Prediction Using Fingerprint Biometrics
Abstract: The research is targeted at the creation of innovative solution "Fingerprint Based Blood Group Prediction" for instant, non-invasive blood group determination from analysis of finger impressions, a breakthrough possibility in emergency health care. Sophisticated machine learning can be employed to map fingerprint patterns to corresponding blood group information and overcome the current lack of a direct connection between the two. Integration of various technologies: employed React for frontend development, Flask …
Published in Research & Reviews: A Journal of Bioinformatics · Vol. 12, Issue 3, 2025 · pp. 9–18 Read article
-
Routing Protocols in FANETs with Future Enhancements
Abstract: Flying Ad Hoc Networks (FANETs), which are swarms of Unmanned Aerial Vehicles (UAVs), are an emerging solution which revolutionized the area of mission-critical and infrastructure-less communication systems. These networks provide real-time data transfer for use cases such as disaster relief, battlefield observation, environmental monitoring, and 6G-based smart cities. However, the dynamic profile of FANETs, which is defined by high 3D mobility, limited energy resources, unstable wireless links, and constant topology …
Published in Journal of Aerospace Engineering & Technology · Vol. 15, Issue 3, 2025 · pp. 8–13 Read article
-
Environmental Impact Assessment of Ocean Energy Converters Using Quantum Machine Learning
Abstract: The accelerating deployment of ocean energy converters (OECs) across tidal, wave, osmotic, and thermal domains necessitates rigorous, data-intensive environmental impact assessment (EIA) frameworks capable of modelling multi-stressor marine ecosystems in real time. Classical machine learning approaches, while operationally mature, encounter scalability bottlenecks and feature correlation limitations when applied to the high-dimensional, non-linear datasets characteristic of offshore monitoring networks. This paper presents a comprehensive quantum machine learning (QML) framework for the …
Published in Journal of Energy, Environment & Carbon Credits · Vol. 16, Issue 1, 2026 · pp. 22–31 Read article