Search
35 articles for “Deep Learning on Graphs”
-
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 · pp. 19–28 Read article
-
Music Recommendation System and Mood Tweak Using Facial Emotion Recognition
Abstract: A user’s emotions can be detected through their facial expressions, these characteristics can be parsed, and the information can be used to improve the user’s experience. With the computing capabilities of on-board graphic processing, there is a new trend of functionality being considered in the field of emotion detection. The use of Convolutional and Recurring Neural Networks (CNN & RNN) to conduct a comparison on which deep learning can be …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 9, Issue 1, 2022 · pp. 43–49 Read article
-
Enhanced Deep Learning Techniques for Defect Detection in Steel-Fiber-Reinforced Composites: A Comparative Study of KerasTuner, CNN–PSO, and CNN–GWO
Abstract: The identification of microstructural defects in steel-fibre-reinforced composites is useful for the material integrity, mechanical reliability and longevity. Classic material inspection techniques face difficulties in recognizing the complex and visually similar defects because of heterogeneous material morphology, changing imaging conditions, and limits of manual feature extraction. To tackle those problems, this study presents a comparative deep-learning framework that integrates Convolutional Neural Networks (CNNs) with three hyperparameter optimization techniques namely KerasTuner, …
Published in Journal of Polymer & Composites · Vol. 14, Issue 5, 2026 · pp. 377–403 Read article
-
Real-Time Object Detection and Tracking in Traffic Surveillance: Implementing Algorithms That Can Process Video Streams for Immediate Traffic Monitoring
Abstract: The rapid growth in urban development and traffic congestion calls for adopting high standards of traffic surveillance systems for monitoring. This paper reviews the current advancement and future trends of real-time object detection and tracking technology and its implications for traffic surveillance. Conventional approaches to traffic monitoring can provide more or less accurate data, but they are not easily scalable and cannot cope with rapidly changing conditions typical within urban …
Published in International Journal of Algorithms Design and Analysis Review · Vol. 3, Issue 1, 2025 · pp. 18–39 Read article
-
Image-Based Crack Morphology Characterisation for Electrical Failure Analysis in Conductive Polymer Composites
Abstract: Electrical performance in conductive polymer composites is strongly governed by crack-network evolution, yet failure analysis typically relies on qualitative image inspection or electrical anomaly detection in isolation. This work proposes an end-to-end framework that converts optical/SEM crack imagery into a standardised crack morphology signature and quantitatively links it to electrical degradation indicators. A two-stage learning strategy is adopted: crack-representation pretraining using the public Concrete Crack Images for Classification dataset, followed …
Published in Journal of Polymer & Composites · Vol. 14, Issue 2, 2026 · pp. 1375-1386 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
-
Retinal Disease Detection Using Deep CNN
Abstract: Age-related macular degeneration, glaucoma, and diabetic retinopathy are the three main causes of blindness in the globe. To avoid visual loss, early identification and treatment of these disorders are essential. The goal of this research is to create an automated method for detecting retinal diseases by analyzing retinal fundus pictures with machine learning techniques. Python and the Tkinter package for the graphical user interface are used in the construction of …
Published in Research and Reviews : A Journal of Medical Science and Technology · Vol. 13, Issue 2, 2024 · pp. 46–50 Read article
-
Advancements in Data Structures: Bridging the Gap Between Theory and Real-world Applications
Abstract: In the rapidly advancing landscape of computer science, this study unfolds a comprehensive exploration of Data Structures, spanning from foundational principles to cutting-edge innovations. Data structures form the backbone of computational processes, and this study aims to dissect and illuminate their pivotal role. Beginning with fundamental concepts such as Arrays, Linked Lists, Stacks, and Queues, the narrative progresses to intricate structures like Trees, Graphs, and Hash Tables. Practical applications in …
Published in International Journal of Data Structure Studies · Vol. 2, Issue 1, 2024 · pp. 14–20 Read article
-
A Review Paper on The Mathematical Foundations of Artificial Intelligence
Abstract: Artificial Intelligence (AI) is deeply rooted in various branches of mathematics, which provide the theoretical foundation and practical tools for developing intelligent systems. This paper explores the crucial role of mathematics in AI, focusing on key areas such as Linear Algebra, Probability and Statistics, Optimization Techniques, Calculus, Graph Theory, and Fourier and Wavelet Transforms. Linear Algebra is fundamental for representing and manipulating data, with applications in dimensionality reduction and neural …
Published in Research & Reviews: Discrete Mathematical Structures · Vol. 12, Issue 3, 2025 · pp. 7–14 Read article
-
Feature Engineering in Modern Predictive Modeling: Techniques, Automation Frameworks and Emerging Trends
Abstract: Feature engineering plays a crucial role in developing reliable and high-performing predictive models. It involves transforming raw and unprocessed data into meaningful features that help machine learning algorithms achieve better accuracy and overall performance. Feature engineering is helpful in identifying hidden patterns, removing noise, and increasing the signal-to-noise ratio in data sets. Machine learning techniques have progressed remarkably over the years, and the effectiveness of these models largely depends on …
Published in Journal of Computer Technology & Applications · Vol. 17, Issue 2, 2026 · pp. 32–40 Read article
-
Analysis of Various Diabetes Prediction Techniques Based on Machine Learning
Abstract: AbstractData mining is a method of mine from the underdone data for maintains useful information. In organize to obtain fundamental knowledge it is important to remove bulky quantity of data. This method is consist of many important components like data cleaning, data selection, data integrity, pattern evaluation with data mining engine and database with graphical user interface. Diabetes is a chronic disease that is also known as Non‐Insulin Dependent Diabetes …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 8, Issue 1, 2021 · pp. 17–22 Read article
-
Critical Review on Multifunctional Polymer Composites for Weight Reduction and AI Based Battery Thermal Management in Electric Vehicles
Abstract: The rapid growth of electric vehicles (EVs) has intensified the need for advanced materials and intelligent control systems capable of improving energy efficiency, driving range, thermal safety, and overall vehicle sustainability. This paper presents a critical review of multifunctional polymer composites and artificial intelligence-based battery thermal management systems (AI-BTMS) for next-generation EV applications. Polymer composites reinforced with carbon fibers, graphene, boron nitride, nanoclays, and carbon nanotubes offer significant advantages over …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 603–619 Read article
-
Development of Neuromorphic Polymer Composites Using IoT Sensing and Brain-Inspired Learning Algorithms
Abstract: This research aims to develop neuromorphic polymer composites by combining conductive sensing materials, IoT-based sensing data collection and brain-inspired learning models for adaptive response. Hybrid conductive polymer composites were developed by adding carbon nanofibers and graphene Nano platelets to a thermoplastic polymer. IoT sensors (strain, temperature) were employed to collect real-time sensing data that was combined with environmental data. A material-aware neuromorphic learning algorithm was created with event-driven spike coding …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 755–784 Read article
-
A Study on Machine Learning and Cryptographic based Intrusion Detection System in Blockchain and Data Science Environment
Abstract: The recent speedy development of Internet of Things, vehicular networks and cloud computing has greatly boosted the need of effective and safe intrusion detection systems. The shortcomings of the traditional IDS-based approaches are centralized architecture, issue of scalability, and inability to analyze the encrypted and distributed data. To address these issues, the recent studies have paid attention to the incorporation of the latest technologies such as machine learning, deep learning, …
Published in International Journal of Wireless Network Security · Vol. 4, Issue 2, 2026 Read article
-
Information-Seeking Behaviour of B.Ed. Students in Indore Region College Libraries: An Empirical Study
Abstract: The study titled “Information Seeking Behaviour of Users in Bachelor of Education (B.Ed.) College Libraries of the Indore Region: A Study” examines how students, faculty members, and research scholars locate, access, and utilize information resources within B.Ed. college libraries. Using a mixed-method research design, data was collected from 535 respondents through standardized questionnaires—distributed in both physical and digital formats—and supported by informal interviews and personal observations for deeper qualitative insight. …
Published in OmniScience: A Multi-disciplinary Journal · Vol. 16, Issue 1, 2026 · pp. 43–55 Read article