Search
370 articles for “Network analysis”
-
CNN-Based Wound Segmentation: A Review of Models and Performance Evaluation
Abstract: Deep learning, particularly convolutional neural networks (CNNs), has altered medical image processing by automating and precisely segmenting complex medical pictures. Wound segmentation, a critical application in automated wound assessment, is essential for wound size estimation, classification, and healing progress monitoring. This study presents a comprehensive review of CNN-based wound segmentation models, focusing on their architectures, methodologies, and performance on diverse datasets. Four deep learning models, including two U-Net variants (5-layer …
Published in Current Trends in Signal Processing · Vol. 15, Issue 1, 2025 · pp. 33–46 Read article
-
Deep Learning-Based Alzheimer’s Disease Detection: A CNN Approach
Abstract: Alzheimer’s disease (AD) is a neurological condition that worsens with time and impairs a patient’s quality of life by causing cognitive loss. For prompt intervention and management of AD, early identification is essential. In this work, we propose a deep learning-based method for automatically classifying Alzheimer’s disease from medical imaging data using convolutional neural networks (CNNs). Our algorithm is intended to evaluate brain MRI images and detect anatomical variations suggestive …
Published in Research and Reviews: A Journal of Neuroscience · Vol. 15, Issue 3, 2025 Read article
-
Study of Social Trends Prediction Using AI
Abstract: AI (Artificial Intelligence) has fundamentally changed the ability to analyze social trends by using large datasets to develop predictions about human behavior, public sentiment, and global events. Using methodologies such as Natural Language Processing (NLP), Time-Series Forecasting, and Graph-Based Social Network Analysis, AI is able to find hidden correlations in a variety of available datasets, from social media to economic indicators to public records, and fundamentally changes decision-making based on …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 12, Issue 3, 2025 · pp. 19–29 Read article
-
Comparison and Analysis of Facial Emotion Detection Using Various Deep Learning Neural Networks
Abstract: Facial emotion recognition employs Convolutional Neural Networks (CNNs), Residual Networks (ResNet), Long Short-Term Memory (LSTM) networks, and Deep Neural Networks (DNNs) to automatically identify various emotions, including disgust, anger, fear, happiness, sadness, surprise, and neutrality. This study utilizes transfer learning along with data preprocessing techniques such as rotation, flipping, brightness adjustment, and enhancement methods. Traditional machine learning models achieve an accuracy range of 45 to 50%. In contrast, our proposed …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 12, Issue 2, 2025 · pp. 37–42 Read article
-
Fake Cryptocurrency Detection Using Python
Abstract: This study investigates the use of Python-based techniques for detecting fraudulent cryptocurrencies, addressing a growing concern in the digital financial ecosystem. The research methodology integrates various data science approaches, including web scraping, API integration, and advanced data analysis using Pandas and NLTK. Machine learning models, particularly classification algorithms such as Random Forest, are employed to analyze key features extracted from cryptocurrency whitepapers, social media discussions, and transactional data. By training …
Published in Recent Trends in Programming languages · Vol. 12, Issue 1, 2025 · pp. 1–7 Read article
-
Contextualising health-disaster risk reduction pillars for under-resourced rural secondary schools in Limpopo Province, South Africa
Abstract: School communities in under-resourced rural settings face a disproportionate burden of health-related disasters, including outbreaks, water and sanitation failures, food insecurity and compound events that disrupt learning and wellbeing. Yet school based disaster risk reduction (DRR) evidence in Southern Africa is uneven with limited empirically guidance tailored to the organisational and infrastructural realities of disadvantaged schools. Drawing on the Comprehensive School Safety Framework and the World Health Organization's Health Emergency …
Published in International Journal of Education Sciences · Vol. 3, Issue 1, 2026 · pp. 124–135 Read article
-
Spatiotemporal Analysis of Mean-Field Coupled Lorenz Oscillators for Applications in Electronic Network Design and Chaotic Synchronization
Abstract: This study investigates the spatiotemporal behavior of a network of 100 coupled Lorenz oscillators interacting through mean-field coupling with coupling strength κ = 0.1 and explores its relevance to electronic system design and nonlinear network architectures. While each oscillator follows classical Lorenz dynamics, the coupling mechanism enables collective behavior that resembles synchronization phenomena observed in distributed electronic and communication systems. Numerical simulations reveal rich dynamical characteristics including partial synchronization, emergent …
Published in Journal of Electronic Design Technology · Vol. 17, Issue 2, 2026 Read article
-
Thevenin Impedance Networks for Spice Simulation Using Analog Behavioural Modelling
Abstract: PSPICE/OrCAD software analog behavioral modeling (FREQ) option is used to obtain equivalent circuits for Thevenin equivalent resistance to be used for three types of applications for different circuits (other different networks with these Thevenin models at DC), and Spice files are described to simulation circuits with AC analyses. Three different applications are useful in linear integrated circuits using DC Thevenin resistance of two networks are considered. Firstly, the DC Thevenin …
Published in Journal of VLSI Design Tools and Technology · Vol. 14, Issue 3, 2024 · pp. 39–46 Read article
-
Optimization of Lightweight Polymer Composites Using Finite Element Analysis Machine Learning and Topology Optimization Techniques for Aerospace Applications
Abstract: The advancement of aerospace engineering depends on lightweight polymer matrix composites (PMCs) because they help decrease weight while improving fuel efficiency and payload capacity together with increased structural integrity. Research developed a computer program comprising FEA with ANN and TO optimize high-performance PMCs through integrated design approaches. The combination of Python-controlled LS-DYNA simulations measured hybrid composite laminate resistance to impact while an ANN model obtained data from simulations to forecast …
Published in Journal of Polymer & Composites · Vol. 13, Issue 6, 2025 · pp. 693–709 Read article
-
Advanced Deep Learning Techniques for Sickle Cell Anaemia Detection
Abstract: Sickle Cell Anemia (SCA) is a prevalent genetic blood disorder characterized by the presence of abnormal hemoglobin, resulting in the distinctive sickle shape of red blood cells. Timely and accurate identification of Sickle Cell Anemia (SCA) is essential for effective management and treatment. This study presents a new method that utilizes Convolutional Neural Networks (CNNs), a deep learning model particularly effective for image analysis. The process involves using microscopic images …
Published in Research and Reviews: A Journal of Medicine · Vol. 14, Issue 3, 2024 · pp. 9–15 Read article
-
Intuitionistic Fuzzy Hypergraph Laplacians and Dominating Transversals for Resilient Discrete Network Design
Abstract: This manuscript develops a discrete mathematical framework for resilience analysis on networks whose interactions are polyadic, uncertain, and partially conflicting. Classical graphs compress multi-way coordination into pairwise edges, while ordinary fuzzy graphs often ignore the non-membership information that becomes critical in emergency logistics, infrastructure interdependence, and cyberphysical coordination. We therefore formulate an intuitionistic fuzzy hypergraph in which each vertex hyperedge incidence carries membership, non-membership, and hesitation, and we construct a …
Published in Research & Reviews: Discrete Mathematical Structures · Vol. 13, Issue 2, 2026 · pp. 15–21 Read article
-
Plant Disease Detection Using Machine Learning
Abstract: Plant diseases significantly threaten global crop yields and affect both nutritional safety and farmer income. Accurate and early detection of plant diseases is essential for effective intervention and treatment. In this study, we used the CNN model (convolutional neural network) to explore a deep learning-based approach for plant disease classification. The model was trained and evaluated on a large dataset encompassing 38 different classes of plant disease, including healthy leaves. …
Published in Journal of Multimedia Technology & Recent Advancements · Vol. 12, Issue 2, 2025 · pp. 07–19 Read article
-
Leveraging Standards and Deep Learning Approaches to Secure Internet of Things (IoT) Devices from Cyber Attack
Abstract: The widespread adoption of Internet of Things (IoT) devices between 2019 and 2024 has significantly grows in various sectors in Japan, including healthcare, manufacturing, and the development of smart cities. Although this growth offers many advantages, it also makes these devices more vulnerable to cyber threats. High-profile security breaches in Japan have sparked discussions about the requirement for enhanced security measures to protect the rapidly evolving IoT technologies. This study …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 13, Issue 1, 2025 Read article
-
Deep Learning Based Detection and Classification of Brain Tumors Using MRI Images
Abstract: Brain tumor detection using magnetic resonance imaging (MRI) is a critical task in the early detection and treatment of brain tumors. Manual analysis of brain tumor detection using MRI is a tedious task that requires expertise in the field. Therefore, this study proposes a deep learning-based approach for brain tumor detection and classification using Convolutional Neural Networks (CNN). The proposed approach preprocesses the MRI image using normalization, resizing, and noise …
Published in International Journal of Brain Sciences · Vol. 3, Issue 2, 2026 Read article
-
Advancing EEG Technology for Affordable and Effective Epilepsy Detection
Abstract: For a proper diagnosis and prompt treatment, epilepsy, a neurological condition marked by recurring seizures, needs to be continuously monitored. Manual interpretation is frequently used in traditional approaches for identifying epileptic seizures from electroencephalogram (EEG) signals, which can be laborious and error-prone. In this research, a novel method for automatically detecting epilepsy from EEG data using deep learning algorithms is presented. According to centers for disease control and prevention (CDC) …
Published in Trends in Opto-electro & Optical Communication · Vol. 14, Issue 3, 2024 · pp. 11–18 Read article
-
A Review of Blocking Side-Channel Threats in Parallel Cloud Systems
Abstract: Side-channel attacks (SCAs) pose a critical security threat to parallel computing systems, particularly in shared cloud environments where multi-tenancy and resource contention create exploitable vulnerabilities. This study presents a comprehensive review of SCAs in parallel architectures, analyzing attack vectors such as cache-based exploits (e.g., Prime + Probe, Flush + Reload), timing attacks, power analysis, and network-based covert channels. We examine real-world cases including Spectre and Meltdown vulnerabilities that exposed fundamental …
Published in Recent Trends in Parallel Computing · Vol. 12, Issue 2, 2025 · pp. 15–25 Read article
-
Machine Learning Assisted Timing Violation Prediction in Sub-7nm VLSI Physical Design
Abstract: The continuous scaling of semiconductor technology into the sub-7nm regime has introduced significant challenges in timing closure due to process variability, interconnect delay, power density, and manufacturing uncertainties. Conventional static timing analysis techniques often require extensive computational resources and iterative optimization cycles, resulting in increased design complexity and longer turnaround time. This research proposes a Machine Learning Assisted Timing Violation Prediction framework for sub-7nm VLSI physical design to improve early-stage …
Published in International Journal of VLSI Circuit Design & Technology · Vol. 4, Issue 1, 2026 Read article
-
Sentimental Analysis in Twitter Using Python
Abstract: Social media websites are a great source of information because they have a lot of data. For instance, Twitter generates millions of packets of text. These statistics may be employed for commercial or charitable purposes. One of the hottest new buzzwords for many business strategies is the analysis of data from these social networking websites. Sentimental analysis can be used to manage election campaigns, global health problems, technical concepts, inventions, …
Published in International Journal of Computer Science Languages · Vol. 1, Issue 1, 2023 · pp. 28–32 Read article
-
AI-Driven Psychological Profiling on Social Media: Mechanisms, Ethical Breaches, and Regulatory Challenges in Data Inference
Abstract: This literature review examines AI-driven psychological profiling on social media, analyzing 21 academic studies that focus on machine learning techniques such as supervised learning, deep neural networks, sentiment analysis, and natural language processing. These methodologies infer mental health indicators—such as depression, anxiety, and stress—from users' digital footprints, encompassing linguistic patterns, engagement metrics, and temporal behaviors. While these tools offer potential for early detection of psychological distress, they also raise significant …
Published in Recent Trends in Social Studies · Vol. 2, Issue 1, 2025 · pp. 1–7 Read article
-
Application of Convolutional Neural Networks in Design of Efficient Pipe Flow System
Abstract: Convolutional Neural Networks exhibit remarkable capabilities in flow pattern recognition, pressure drop prediction, leak detection, and system optimization through their ability to process complex spatial and temporal data patterns. The study examines CNN architectures specifically adapted for fluid dynamics applications, including data preprocessing techniques, feature extraction methods, and performance optimization strategies. Key applications include real-time flow monitoring, predictive maintenance, design parameter optimization, and anomaly detection in pipe networks. Comparative analysis …
Published in Recent Trends in Fluid Mechanics · Vol. 12, Issue 3, 2025 · pp. 1–9 Read article