Search
416 articles for “neural network method”
-
Renewable Solar Energy Prediction in India : 2025-2030
Abstract: As India endeavors to realize its objective of achieving 500 GW of renewable energy capacity by the year 2030, the precise forecasting of solar power generation is rendered increasingly essential. This scholarly article conducts a comprehensive review of the utilization of machine learning (ML) methodologies in the prediction of solar energy across diverse Indian states, underscoring their potential to address the complexities associated with the variability of solar irradiance. Conventional …
Published in Journal of Power Electronics and Power Systems · Vol. 14, Issue 3, 2024 · pp. 41–46 Read article
-
Convolutional Neural Network Based Ripeness Detection of Fruits
Abstract: The accurate and efficient assessment of fruit ripeness plays a crucial role in ensuring the quality of fruits and optimizing supply chain management. This paper presents a novel approach for the automated detection of apple and banana ripeness using Convolutional Neural Networks (CNNs). The suggested method supports the capability of CNNs to learn hierarchical features from images, variations in color and shape associated with different ripeness stages. The online dataset …
Published in Research & Reviews : Journal of Agricultural Science and Technology · Vol. 13, Issue 2, 2024 · pp. 30–36 Read article
-
Robustness of Deepfake Detection Systems Against Adversarial Attacks
Abstract: This paper explores a deep learning system to detect deepfake videos, a common type of fake media. With the use of sophisticated methods such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs), our system can reliably discern between authentic and altered videos. It analyzes both the images and the audio in videos to find signs of deepfake manipulation. We process video frames and audio, extract features with CNNs …
Published in Journal of Instrumentation Technology & Innovations · Vol. 14, Issue 2, 2024 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
-
AI-Assisted Optimization of Supersonic Airfoil Shapes Using CFD Coupling
Abstract: This paper presents a novel framework for optimizing supersonic airfoil geometries through integrated artificial intelligence and computational fluid dynamics coupling. Traditional gradient-based optimization methods for high-speed aerodynamic shapes suffer from computational expense and convergence difficulties in non-convex design spaces. The proposed methodology employs a deep neural network surrogate model trained on high-fidelity Reynolds-Averaged Navier-Stokes solutions to approximate aerodynamic performance metrics across the design space. A hybrid particle swarm-genetic algorithm searches …
Published in Journal of Aerospace Engineering & Technology · Vol. 16, Issue 1, 2026 · pp. 8–17 Read article
-
Performance Comparison of IRT Method with NNMPC Method
Abstract: The continuous stirred tank reactor (CSTR) system was used for experimentation and the improved relay tuning (IRT) method was applied for design of optimum PID settings. The closed loop response was obtained using these optimum PID settings and compared with that of neural network model predictive control (NNMPC) method. The integral absolute error (IAE) criterion for the performance evaluation was used and it was found that the integral error has …
Published in Journal of Control & Instrumentation · Vol. 7, Issue 2, 2016 · pp. 1–4 Read article
-
Pair of Retina Recognition System Using Hopfield Neural Network Algorithm
Abstract: process of pair of retina recognition system using feature fusion method has been proposed in this paper. Left and right retinal images of human have been used for the inputs of this retinal recognition system. Wavelet based retinal image pre-processing technique has been applied to process the retina images. After extracting the features from the left and right retinal images, features are concatenated using feature fusion technique. Principal Component Analysis …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 2, Issue 2, 2015 · pp. 41–45 Read article
-
Artificial Neural Network-Based Multifocus Image Fusion
Abstract: Fusion of multiple images is needed for combining information contained in images obtained using different imaging devices or different camera settings. Due to the physics of optical lenses present in these devices, it is difficult to capture an image that has all the relevant objects well in focus. Thus, artificial neural network (ANN)-based multifocus image fusion method in YCbCr color space is proposed. Input images are first mapped from RGB …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 5, Issue 3, 2018 · pp. 16–23 Read article
-
Artificial Neural Network Model for Stock Market Forecasting
Abstract: AbstractIn recent years, many attempts have been made to predict the behavior of bonds, currencies, stocks or stock markets. Neural networks, as an intelligent data mining method, have been used in many different challenging pattern recognition problems such as stock market prediction. The aim of this paper is to predict stock market using artificial neural networks (ANNs). The authors used feed forward neural network trained by back-propagation algorithm to make …
Published in Journal of Computer Technology & Applications · Vol. 5, Issue 1, 2014 · pp. 7–12 Read article
-
Bearing Fault Diagnosis Using ANN and SVM with the Help of Wavelet Transform Based Features
Abstract: Many researchers use vibration signals as fault characteristics of any rotating bearing for fault detection and use various optimization techniques available for fault of bearing classification. The method of fault classification uses few neural network (NN) geometry and parameters necessary for the formulation. There is no derived formulation which can be used to select the optimal values for the network parameters. The parameters which are required to be calculated, impacts …
Published in Recent Trends in Electronics Communication Systems · Vol. 4, Issue 2, 2017 · pp. 26–34 Read article
-
Prediction of Excitation Current of Synchronous Machines Based on Neural Network Model
Abstract: There are several difficulties found to estimate the excitation current & and optimum input parameters of synchronous motors. Heuristic methods are frequently used to weightt the problem's parameters or optimum coefficients. As a result, a neural network model is modified in this study to explore the best parameters and estimate the excitation current of a synchronous motor with minimal prediction errors for both the testing dataset and cross validation. Excitation …
Published in Recent Trends in Electronics Communication Systems · Vol. 10, Issue 1, 2023 · pp. 28–33 Read article
-
Attendance System Based on Facial Recognition
Abstract: Attendance management is a fundamental aspect of educational institutions and workplaces, ensuring accountability, discipline, and operational efficiency. Traditional methods, such as manual roll calls, RFID cards, and fingerprint scanners, are often time-consuming, error-prone, and susceptible to fraud. This research presents an automated attendance management system utilizing face recognition technology to address these challenges effectively. The proposed system employs OpenCV for real-time image processing, the face recognition library for accurate facial …
Published in International Journal of Electronics Automation · Vol. 3, Issue 1, 2025 · pp. 28–34 Read article
-
Recent Advances in Content-based Image Retrieval: Techniques and Applications
Abstract: Content-based image retrieval (CBIR) plays a vital role in computer vision, driven by the increasing need for fast and accurate image retrieval across fields like healthcare, e-commerce, and digital libraries. This study offers a detailed review of CBIR methodologies, charting their progression from traditional feature extraction techniques, such as Local Binary Patterns (LBP), to contemporary deep learning-driven methods. The transformative impact of convolution neural networks (CNNs) is highlighted, emphasizing their …
Published in Journal of Computer Technology & Applications · Vol. 16, Issue 1, 2025 · pp. 67–71 Read article
-
Physics-Informed Neural Networks for Multiphysics Analysis of Biomedical Polymer Composite Systems
Abstract: Physics-Informed Neural Networks (PINNs) offer an effective model of solving coupled multiphysics equations in biomedical polymer composite systems, which are data-driven. In the given work, the PINN method is presented where equations of elasticity, mass diffusion, and heat transfer are integrated to model the complex processes that take place in composite biomaterials. The neural network loss is specified to include the governing partial different equations which enables both the system …
Published in Journal of Polymer & Composites · Vol. 14, Issue 4, 2026 Read article
-
Traffic Sign Detection and Recognition Using Deep learning based- Convolutional Neural Network Algorithm
Abstract: The concept of Deep Convolutional Neural Organizations (CNNs) is a quickly arising new zone for Automatic traffic sign detection and recognition among the few master frameworks, such as independent driving and driver assistance. Here, in this paper, for traffic sign detection, we have utilized another methodology that uses a newly developed identification calculation and an RGB-based tone thresholding procedure. Results of the proposed identification and acknowledgement approaches are assessed on …
Published in Recent Trends in Electronics Communication Systems · Vol. 8, Issue 1, 2021 · pp. 24–29 Read article
-
Designing of Low Pass Finite Impulse Response Filter using Radial Basis Function Neural Network
Abstract: The present paper investigates an approach to design and analysis of a low pass finite impulse response (FIR) filter using artificial neural network. The main aim of design is to find out the filter coefficients that define the filter transfer functions. A datasheet of 40 different values of h (n), i.e., coefficient of digital low pass FIR filter are used for filter designing. In this paper Radial Basis Function method …
Published in Journal of Control & Instrumentation · Vol. 5, Issue 2, 2014 · pp. 21–24 Read article
-
Health Risk and Evaluation of Atmospheric Pollutants in Owerri Metropolis and Sub-Urban Areas of Imo State, Nigeria Using Chemometric Models
Abstract: Concern about health risk from atmospheric pollutants; Particulate Matter (PM10), Sulphur dioxide (SO2), Nitrogen dioxide (NO2) and Carbon Monoxide (CO) prompted atmospheric monitoring and inhalation health risk assessment for residents of Owerri Metropolis and its Sub-urban areas. Field measurements were carried out in 35 select locations within Imo State. Monitoring was carried out using Chemometric methods as Matrix Laboratory (MATLAB) and Artificial Neural Network (ANN). According to the experiment results, …
Published in Research & Reviews : Journal of Statistics · Vol. 13, Issue 1, 2024 · pp. 47–79 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
-
Survey Paper on Multilingual Live Call Translation Using Deep Learning
Abstract: This research work surveys cutting-edge language translation technologies, including multi-lingual, real-time translation, voice recognition, speech-to-text conversion, and transcription in the hearing process. The study explores the complex mechanisms behind voice call language translation, focusing on sophisticated machine learning models integrated with cloud-based or local applications to facilitate seamless communication across language barriers. Furthermore, conducting research in live communication analyzes the complexity of text and voice techniques to deliver translated content …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 11, Issue 2, 2024 · pp. 13–21 Read article
-
Fake Currency Detection Using Convolutional Neural Networks
Abstract: In today’s world, due to increasing technology like scanning, color printing, and duplicating, the identification of bogus notes by the human eye is almost getting impossible. Knowingly or unknowingly, due to the usage of bogus currency notes, the Indian economy is also being impacted badly. Hence, the identification of bogus currency notes is really important. This paper deals with regard to identifying whether the given sample of the currency note …
Published in Journal of Electronic Design Technology · Vol. 14, Issue 2, 2023 · pp. 9–17 Read article