Search
107 articles for “neural network architecture”
-
A Dual-Model Deep Learning Framework for Early Alzheimer’s Detection Using Clinical Data and Neuroimaging with Architectural Performance Analysis
Abstract: Alzheimer’s disease (AD) poses a significant global health challenge due to its increasing prevalence and the absence of definitive cures. Early diagnosis is crucial for effective intervention and management. This study presents a dual-model deep learning framework for the early detection and classification of AD using both structured clinical data and neuroimaging datasets. Model 1 utilizes a greedy layer-wise autoencoder approach applied to structured data, achieving optimal binary classification accuracy …
Published in Research and Reviews: A Journal of Neuroscience · Vol. 16, Issue 1, 2026 · pp. 1–12 Read article
-
Comparative Analysis of Data Augmentation Techniques in CNN-based Classification of Atelectasis
Abstract: This research delves into the critical issue of atelectasis, its causes, and potential complications if left untreated. Leveraging deep learning algorithms, particularly convolutional neural networks (CNN), the paper explores their application in medical image analysis, focusing on the detection of atelectasis using the “chestX-ray8” database. The study compares various data augmentation techniques for improved accuracy, showcasing the importance of augmentation in enhancing model generalization. Through meticulous experimentation and evaluation, the …
Published in Journal of Microwave Engineering and Technologies · Vol. 11, Issue 3, 2024 · pp. 1–8 Read article
-
Pneumonia Detection and Classification Using Deep Learning
Abstract: Pneumonia, an infectious lung disease primarily caused by bacteria, often exacerbated by environmental factors, leads to the accumulation of pus in the lung’s alveoli. Accurate diagnosis through chest X-rays, ultrasounds, or lung biopsies is crucial to avoid misdiagnosis and ensure proper treatment, crucial for patients’ quality of life. Diagnostic capacities have been greatly improved by deep learning advances, especially with convolutional neural networks (CNNs). This research presents a robust CNN-based …
Published in Journal of Microwave Engineering and Technologies · Vol. 11, Issue 3, 2024 · pp. 9–19 Read article
-
Power and Area - Aware Recursive Multiplier Architecture Utilizing Polymer Composites for Neural Network Acceleration
Abstract: Approximate computing is widely applied in error - tolerant systems as an effective technique to enhance circuit performance by deliberately allowing occasional inaccuracies instead of strictly ensuring precise results for every computation. Among the fundamental building blocks of digital systems, multipliers play a crucial role in signal processing, control systems, and machine learning applications; however, they demand significant power, silicon area, and timing resources. Leveraging error - tolerant approximate multipliers …
Published in Journal of Polymer & Composites · Vol. 14, Issue 1, 2026 · pp. 1320–1337 Read article
-
Neuromorphic Spiking Neural Networks and Event-Driven Hardware: Architectures, Learning Paradigms, and Experimental Realizations
Abstract: With the current computational boom the research community is seeking for more sustainable energy efficient i.e. biologically inspired models of conventional Artificial Neural Networks (ANNs). Spiking Neural Networks (SNNs) known as the third generation of neural network models, provide a revolutionary approach by mimicking the asynchronized event-driven and temporally accurate signaling of the mammalian brain. Whereas conventional deep learning models operate with real-valued activations and dense matrix multiplications, SNNs use …
Published in Current Trends in Signal Processing · Vol. 16, Issue 2, 2026 Read article
-
Skin Disease prediction and classification from dermoscopy images using Neural Network
Abstract: Skin diseases are among the most common health-related problems affecting people of all age groups, and their occurrence often varies with seasonal and environmental conditions. Delayed or incorrect diagnosis of skin disorders can lead to severe complications, making early and accurate detection extremely important for effective treatment and prevention. In recent years, rapid advancements in deep learning and neural network technologies have significantly contributed to the development of automated medical …
Published in Journal of Computer Technology & Applications · Vol. 17, Issue 1, 2026 Read article
-
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
-
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
-
Cyclist Safety Enhancement: A Multi-Modal Hazard Detection System
Abstract: This study presents a multi-modal hazard detection system to enhance cyclist safety in urban environments. Lever- aging a combination of computer vision, object tracking, and predictive modeling, the system offers a comprehensive approach to identifying and mitigating potential risks. Key contributions include improved depth estimation through object size priors, multi-class tracking utilizing KCF and Brisk, and a novel recurrent neural network architecture for predicting bicycle movement. The system’s collision detection …
Published in International Journal of Machine Systems and Manufacturing Technology · Vol. 1, Issue 2, 2023 · pp. 35–83 Read article
-
AI Hindi Poem Generator
Abstract: The Hindi Poetry Generator project represents a pioneering initiative in the domain of computational creativity, blending machine learning algorithms and natural language processing methodologies to craft poetic expressions in the Hindi language. Rooted in the vast landscape of Hindi literature, this project harnesses the power of deep learning models to generate evocative and culturally significant poetry. At its core, the system relies on neural networks and sophisticated language modeling techniques …
Published in Recent Trends in Programming languages · Vol. 11, Issue 2, 2024 · pp. 10–16 Read article
-
Enhanced Task Automation through IoT and ChatGPT Integration in Personal AI Companions
Abstract: A new breed of clever, likable, and natural-sounding personal AI companions could be produced by integrating ChatGPT with IoT gadgets. The Internet of Things (IoT) and artificial intelligence (AI) are developing at a rapid pace, which has created exciting new opportunities for the creation of intelligent and personalized companions. The goal of this suggested system is to improve user experiences by offering a flexible AI-driven assistant. It does this by …
Published in Recent Trends in Sensor Research & Technology · Vol. 11, Issue 2, 2024 · pp. 19–24 Read article
-
Learning Data Structures: Key to Good Programming
Abstract: Data structures are the most crucial feature of good programming and are needed to solve hard computational problems. This model makes use of two different recurrent neural network architectures, specifically long short-term memory (LSTM), and gated recurrent unit (GRU) networks. It explains how selecting and using the correct data structures may speed up computations, optimize memory, and scale code. How data structures and algorithms relate and how to think about …
Published in International Journal of Data Structure Studies · Vol. 4, Issue 1, 2026 · pp. 29–39 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
-
Deep Learning -Based Dental Issue Detection
Abstract: Dentistry is vital for preserving oral health, a key component of overall wellness. Early identification of dental issues is crucial for effective treatment and avoiding further complications. Conventional approaches to diagnosing dental problems typically depend on physical examinations and visual assessments by skilled professionals, which can be both time-intensive and influenced by individual judgment.In recent years, the application of deep learning algorithms has demonstrated significant potential in automating and enhancing …
Published in Research and Reviews: A Journal of Dentistry · Vol. 16, Issue 1, 2025 · pp. 18–23 Read article
-
Performance Analysis of Deep CNN Architectures
Abstract: A Convolutional Neural Network (CNN) is an artificial neural network renowned for its remarkable ability to handle large image datasets effectively, particularly excelling in tasks such as image recognition and classification. The fundamental structure of a CNN relies on mathematical convolution operations, comprising essential components such as convolutional layers, activation functions, pooling layers, and fully connected layers. These components work synergistically to extract and learn hierarchical features from input data, …
Published in Journal of Communication Engineering & Systems · Vol. 14, Issue 2, 2024 · pp. 1–8 Read article
-
Animal Species Prediction Using Deep Learning
Abstract: In the face of escalating biodiversity loss, effective monitoring of animal species is critical for conservation efforts. This study presents a deep learning approach for species detection and a multimodal feature identification technique for animals vulnerable to poaching. The suggested prediction system recognizes objects automatically by the application of deep learning techniques to detect objects and then recognize them by using computer vision techniques, and it is triggered when an …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 13, Issue 1, 2026 · pp. 14–22 Read article
-
Hybrid Quantum–Machine Learning Framework for Nonlinear Rheological Modeling of Polymer and Composite Materials
Abstract: In polymer and composite materials, a major challenge lies in predicting their nonlinear rheological response, owing to complex multiscale interactions that are not captured by traditional constitutive laws or conventional machine learning approaches. In this study, a hybrid Quantum Machine Learning (QML) model comprising Quantum Support Vector Machine (QSVM) and Quantum Neural Network (QNN) architectures is proposed for viscosity prediction without requiring any specific rheological equation. To train and test …
Published in Journal of Polymer & Composites · Vol. 14, Issue 5, 2026 Read article
-
Machine Learning-Based Channel Estimation in 5G, Beyond-5G, and 6G Networks: Recent Advances and Future Directions
Abstract: Accurate channel estimation is one of the most fundamental challenges in modern wireless communication systems. In fifth- generation (5G) New Radio (NR) and emerging sixth-generation (6G) networks, precise knowledge of the wireless channel is essential for achieving reliable data transmission, high spectral efficiency, and low Bit Error Rate (BER). Conventional estimation techniques such as Least Squares (LS) and Minimum Mean Square Error (MMSE) rely on mathematical channel models and predefined …
Published in Journal of Telecommunication, Switching Systems and Networks · Vol. 13, Issue 2, 2026 Read article
-
An Automation Detection for Sign Language Using AI
Abstract: Sign language recognition has attracted considerable interest because of its ability to facilitate communication between the deaf community and the public, thereby bridging communication divides. Traditional approaches to sign language recognition often face challenges in accurately interpreting the complex and nuanced gestures inherent in sign languages. However, recent advancements in deep learning techniques have shown promising results in improving the accuracy and robustness of sign language recognition systems. This study …
Published in Recent Trends in Programming languages · Vol. 11, Issue 1, 2024 · pp. 1–14 Read article
-
ML-Driven Defect Detection in Additive Manufacturing of Polymer Composites Using Thermal Imaging
Abstract: Polymer-based flexible biosensors have emerged as a pivotal technology in continuous health monitoring, yet their deployment in real-world settings is often hindered by undetected micro-defects and signal distortion caused during fabrication or usage. Existing diagnostic frameworks typically rely on post-hoc processing or bulky instrumentation, failing to offer scalable, real-time detection during additive manufacturing workflows. This study introduces an end-to-end, thermographic imaging-integrated framework for in-situ defect identification during the additive manufacturing …
Published in Journal of Polymer & Composites · Vol. 13, Issue 6, 2025 · pp. 201–215 Read article