Search
13 articles for “F1 score”
-
A Study on CNN-Based Image Mosaicing
Abstract: The intricate tapestry of image mosaicing, while a cornerstone of computer vision, has long been constrained by the rigidity of classical, geometry-driven pipelines. Hand-crafted feature detectors and homography estimators, while effective in controlled environments, prove brittle when confronted with the challenges of real-world scenes: significant parallax, dynamic moving objects, repetitive textures, and illumination variance. This work introduces a fundamental paradigm shift, proposing a deep convolutional neural network (CNN) architecture designed …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 12, Issue 1, 2026 · pp. 1–7 Read article
-
CyberSentinel: A Proposed Hybrid AI Framework for Real-Time Cyber Threat Intelligence
Abstract: Modern cyberattacks have grown far more sophisticated, frequent, and fast-moving than the signature-based intrusion detection systems many organizations still rely on. This paper proposes CyberSentinel, a hybrid artificial intelligence framework for real-time cyber threat intelligence (CTI) that combines three complementary techniques into a single detection pipeline: a Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) module for network traffic anomaly detection, a Random Forest ensemble for structured log classification, and a transformer-based …
Published in International Journal of Telecommunications & Emerging Technologies · Vol. 12, Issue 2, 2026 Read article
-
Cost-Constrained Sensor Reduction for Deployment AwareIoT-Based Multiclass Water Quality Monitoring
Abstract: Large-scale Internet of Things deployment for water quality monitoring systems is bounded by the capital and several other costs associated with the multi-dimensional sensor. While prior research demonstrates strong predictive performance using multi- parameter physicochemical sensing, limited attention has been given to explicit sensing cost constraints and deployment feasibility. This work formulates multiclass water quality classification as a cost-constrained learning problem in which sensing dimensionality is minimized subject to bounded …
Published in International Journal of Digital Communication and Analog Signals · Vol. 12, Issue 2, 2026 Read article
-
Detailed survey on detection of Dirtiness of PV panels using different approaches
Abstract: The accumulation of dust, dirt, bird droppings, pollen, and other environmental contaminants on photovoltaic (PV) panels significantly reduces their power generation efficiency and increases operational and maintenance costs. Therefore, timely and accurate detection of the cleanliness condition of solar panels is essential for maintaining optimal energy production, improving system reliability, and extending the operational lifespan of PV installations. In recent years, considerable research interest has been directed toward automated soiling …
Published in International Journal of Electrical Power System and Technology · Vol. 12, Issue 2, 2026 Read article
-
Classification of power quality disturbances using advanced deep learning algorithms for Accurate and efficient electrical signal analysis
Abstract: Power systems today have to deal with more and more power quality issues (PQDs) like voltage drops, rises, harmonics, and transients because more people are using renewable energy sources and electronic devices. These problems can hurt equipment, stop services, and lower the overall reliability of power. In real-time settings, traditional detection methods often don't work as quickly or accurately as they should. This paper looks at how deep learning models, …
Published in International Journal of Power Electronics Controllers and Converters · Vol. 12, Issue 2, 2026 Read article
-
Speech Emotion Recognition using Multi- Kernel CNN for Features extraction and Random Forest Classifier
Abstract: Identifying human emotional states from speech signals is the main goal of Speech Emotion Recognition (SER), which has grown to be a significant area of study in affective computing. However, class imbalance and efficient feature extraction from speech data pose problems for many of the current methods. This study suggests a hybrid framework that combines a Random Forest (RF) classifier with a multi-kernel Convolutional Neural Network (CNN) to address these …
Published in International Journal of Digital Communication and Analog Signals · Vol. 12, Issue 2, 2026 Read article
-
Predicting Traffic Congestion in Mumbai Using Artificial Intelligence
Abstract: Abstract — Mumbai's ongoing traffic problems are brought on by the city's fast urbanization, population expansion, and growing reliance on private automobiles. The majority of traffic management technologies in use today are reactive, frequently reacting only after congestion has already arisen. Using information from a variety of sources, such as commuter surveys, weather reports, and traffic incident logs, this study explores the application of artificial intelligence (AI) and machine learning …
Published in International Journal of Transportation Engineering and Traffic System · Vol. 12, Issue 2, 2026 Read article
-
An approach for Intelligent detection of dirty PV panels using image processing with YOLOv8
Abstract: The efficiency of solar photovoltaic (PV) systems is greatly affected by the condition of panel surfaces, as dust buildup and other impurities can noticeably reduce power output. Traditional maintenance methods rely largely on manual inspection, which can be subjective, inconsistent, and impractical for large-scale installations. To address these challenges, this work investigates a deep learning-based computer vision approach for the automatic assessment of solar panel cleanliness. In this work, a …
Published in International Journal of Renewable Energy and its Commercialization · Vol. 12, Issue 2, 2026 Read article
-
Enhancing Facial Expression Analysis Using CNNs: Insights from ML and Deep Learning Comparisons
Abstract: Emotion recognition from facial manifestations increases the interaction between humans and computers by enabling the interaction between humans and computers to effectively explain human feelings. This study presents a comparative analysis of three approaches to the emotional recognition of faces: a custom Convolutional Neural Network (CNN) model, Traditional Machine Learning (ML) methods, and other deep learning architectures such as VGG, ResNet, and Hybrid CNN–RNN models. The proposed CNN-based system, developed …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 12, Issue 1, 2026 · pp. 23–31 Read article
-
Comparison Analysis of Lumpy Skin Disease Detection System Using X-Ray Images of Animals with the Help of Deep Learning
Abstract: Lumpy Skin Disease (LSD), caused by the Capripoxvirus, is a highly contagious viral infection impacting cattle and other livestock, resulting in significant economic losses due to decreased productivity and mortality. Early detection is critical to mitigate its spread and reduce its impact on agriculture and dairy sectors. This study investigates the efficacy of deep learning methodologies for detecting LSD through X-ray images, offering a non-invasive diagnostic approach to identify internal …
Published in International Journal of Animal Biotechnology and Applications · Vol. 11, Issue 2, 2025 · pp. 1–5 Read article
-
Evaluation of Machine Learning and Deep Learning Models for Classification Tasks on Crime Data: A Comparative Study
Abstract: The classification of crime data has grown more and more important for public safety and law enforcement due to the increasing demand for precise and effective predictive models. To classify crime data, this study assesses and contrasts the effectiveness of several machine learning (ML) and deep learning (DL) models, such as decision trees, support vector machines, neural networks, and convolutional neural networks. The study evaluates the models' accuracy, efficiency, and …
Published in International Journal of Digital Communication and Analog Signals · Vol. 11, Issue 1, 2025 · pp. 1–15 Read article
-
Advanced Diabetic Retinopathy Detection Using Deep Learning Classifiers
Abstract: Diabetic Retinopathy (DR) is an eye condition that arises from diabetes-related complications, making early detection essential for effective treatment. As diabetes advances, an individual’s vision may deteriorate, potentially resulting in diabetic retinopathy. This condition is divided into two primary types: Non-Proliferative Diabetic Retinopathy (NPDR) and Proliferative Diabetic Retinopathy (PDR). Early treatment to maintain a strategic distance from a change less visual impedance is basic as it may save diabetic retinopathy …
Published in International Journal of Image Processing and Pattern Recognition · Vol. 11, Issue 1, 2025 · pp. 26–33 Read article
-
Brain Tumor Detection using Machine Learning Methods-KNN, SVM, DT, RF
Abstract: Brain tumor is a major contributor to illness and death worldwide, and timely diagnosis is essential for successful treatment and improved outcomes Recent research has looked into the possibility of machine learning algorithms for detecting and classifying brain tumours in medical pictures. In this study, four commonly used machine learning algorithms (K-Nearest Neighbours, Decision Trees, Support Vector Machines, and Random Forests) were evaluated for their effectiveness in brain tumor detection. …
Published in International Journal of Chemical Engineering and Processing · Vol. 9, Issue 2, 2023 · pp. 48–59 Read article