Search
238 articles for “Classification accuracy”
-
Baggage Detection and Recognition Using Local Tri-Directional Pattern
Abstract: Nowadays, pattern-based image retrieval algorithms are gaining popularity just because of their uniqueness. There are several issues in the previously proposed systems. The proposed system resolves issues highlighted in the literature. Our proposed system is tested on two image datasets ILIDS and PETS 2006. LTDP provides good results as compared to LBP in baggage detection on two classes that either bag is present or not in an image because LTDP …
Published in International Journal of Mobile Computing Technology · Vol. 1, Issue 1, 2023 · pp. 8–17 Read article
-
Intelligent Aquaculture System for Fish Disease Detection Using Machine Learning
Abstract: Aquaculture is one of the key factors for global food security, but fish diseases bring about heavy economic losses and jeopardize sustainability. One of the most important aspects of global food security is aquaculture, but fish infections endanger sustainability and cause significant financial losses. Early diagnosis is not possible since traditional disease detection techniques are laborious and necessitate expert intervention. To effectively detect fish infections, this study suggests an Intelligent …
Published in Journal of Telecommunication, Switching Systems and Networks · Vol. 12, Issue 2, 2025 · pp. 30–37 Read article
-
Identification of Papaya Fruit Ripening Process Using AI
Abstract: Identifying the ripening process of papaya fruit using artificial intelligence involves employing machine learning algorithms to analyze various features such as color changes, texture alterations and chemical compositions. This model is capable of analyzing visual cues to determine the stage of ripeness. The dataset compares images of papaya at various ripening stages, and our AI model demonstrated high accuracy in classifying these stages. Employing machine learning algorithms and image processing …
Published in Research & Reviews : Journal of Food Science & Technology · Vol. 13, Issue 2, 2024 · pp. 23–30 Read article
-
Enhancing Customer Engagement with AI-Driven Movie Recommenders: Integrating Neural Collaborative Filtering, Sentiment Analysis, and Conversational Agents
Abstract: In today’s competitive digital landscape, user engagement is a critical factor for the success of entertainment platforms, especially those offering movie recommendations. This study introduces a comprehensive AI-driven framework designed to enhance customer interaction, satisfaction, and loyalty through the intelligent integration of multiple deep learning models. The system combines three core components: Neural Collaborative Filtering (NCF) for generating personalized movie recommendations based on user behavior and preferences, Long Short-Term Memory …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 12, Issue 3, 2025 · pp. 45–54 Read article
-
GreenDiagnosis: Intelligent Crop Disease Detection Using Deep Learning Algorithm
Abstract: Agriculture in parts of India relies on labour-intensive traditions, maintaining disease-free crops is crucial. Manual methods can be inaccurate, driving farmers towards AI-based solutions. AI offers a proactive approach to address real-time farming challenges. Among these is the invasion of pests, which diminishes crop quality. Combating pest-related diseases poses a challenge, prompting innovation. Effective surveillance and early detection of crop diseases play a pivotal role in ensuring global food security …
Published in Research & Reviews : Journal of Agricultural Science and Technology · Vol. 14, Issue 2, 2025 · pp. 8–18 Read article
-
Comparison of K-nearest Neighbor and Artificial Neural Network Classifiers for the Detection of Breast Cancer
Abstract: Breast cancer is the most common type of cancer seen in women in the present day, which is also considered a life-threatening disease. If this cancer can be detected in its early stage it can be a lifesaver for many people around the world. Machine Learning techniques have become one of the hotspots for predicting the early diagnosis of breast cancer. This research work experiments with the two most popularly …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 11, Issue 1, 2024 · pp. 78–83 Read article
-
An Effective Convolutional Neural Network for Identifying Cancer Blood Disorder Cells Using Microscopic Images
Abstract: Blood, bone marrow, and lymphatic systems are all impacted by hematological cancer is known as a cancer blood disorder. Blood malignancies and various blood disorders pose significant health challenges across all age groups. Early disease detection is essential for effective cancer blood disorder treatment and management. If a blood cancer is not identified in time, it may be hazardous. It results in abnormal white blood cell production by the bone …
Published in Research and Reviews: Journal of Oncology and Hematology · Vol. 13, Issue 2, 2024 · pp. 29–35 Read article
-
Interpretable Skin Cancer Detection via Optimized CNN Models for Smart Healthcare Solutions
Abstract: Skin cancer is a common and potentially life-threatening condition, highlighting the importance of reliable and efficient diagnostic techniques. Recently, convolutional neural networks (CNNs) have demonstrated significant potential in automating the classification of skin cancer using thermoscopic images. Despite these advancements, the lack of interpretability in these models poses a barrier to their widespread use in clinical settings. In this study, we propose an interpretable CNN architecture optimized for skin cancer …
Published in Research & Reviews: A Journal of Bioinformatics · Vol. 12, Issue 1, 2025 · pp. 41–45 Read article
-
Eye Disease Classification Using K-means Clustering Algorithm and Ensemble Classification Approach
Abstract: In this study, we present a comprehensive approach for the classification of eye diseases, specifically targeting normal, cataract, glaucoma, and diabetic retinopathy conditions. This research uses a dataset from Kaggle, which provides a wide and varied collection of retinal images to ensure good representation. The methodology encompasses advanced image processing and machine learning techniques to ensure accurate diagnosis and prediction. The preprocessing phase involves a series of image enhancement techniques …
Published in International Journal of Bioinformatics and Computational Biology · Vol. 3, Issue 2, 2025 · pp. 15–27 Read article
-
Deep Learning models for real time detection of crop diseases in the Maharashtra/Mumbai district
Abstract: This research project addresses the critical agricultural challenge of crop disease management in the Maharashtra region of India by leveraging modern deep learning techniques. The primary objective is to identify, implement, and compare the efficacy of various deep learning architectures—including Convolutional Neural Networks (CNNs), MobileNet, and EfficientNet—for the real-time classification of diseases in key crops such as cotton, soybean, and sugarcane. A custom dataset of agricultural images specific to Maharashtra's …
Published in Research and Reviews : Journal of Crop science and Technology · Vol. 15, Issue 2, 2026 · pp. 36–48 Read article
-
Gradient Boosted Regression Tree Approach to Predicting Toxic Interactions on X and YouTube
Abstract: In the digital age, social media platforms play a vital role in facilitating user engagement, encompassing both positive interactions and avenues for negative, often harmful behaviors. Recognizing and addressing toxic exchanges is paramount to nurturing healthy online communities and preserving users’ well-being. This study introduces a novel method for identifying toxic interactions by utilizing Gradient Boosting Regression Trees (GBRT) algorithm, a machine learning approach renowned for its exceptional accuracy and …
Published in Trends in Opto-electro & Optical Communication · Vol. 15, Issue 3, 2025 · pp. 7–14 Read article
-
Breast Cancer Detection Using Machine Learning: A Comparative Analysis of Supervised Learning Algorithms
Abstract: Globally, breast cancer remains a predominant cause of mortality among women, highlighting the urgent need for timely and precise diagnostic approaches. This research explores the application of machine learning algorithms—including Logistic Regression, SVM, Naïve Bayes, KNN, and Random Forest—on the Wisconsin Breast Cancer Dataset for effective tumor classification. Key pre-processing steps such as missing value handling, feature scaling, and dimensionality reduction were employed to improve model performance. The study evaluated …
Published in Research & Reviews: A Journal of Bioinformatics · Vol. 12, Issue 3, 2025 · pp. 46–52 Read article
-
Performance of Artificial Neural Network for Tree Species Identification using Sentinel-2 Data
Abstract: Accurate land cover mapping, especially concerning vegetation, is crucial for effective land use policy planning and sustainable forest management. Hence, achieving accuracy in mapping requires a deep understanding of composition changes, vegetation conditions, and the spatial distribution of tree species. In the spatial context of tree species, it holds significant potential for applications including invasive species monitoring, delineating contaminated areas, and biodiversity conservation. However, traditional methods for tree species identification …
Published in Journal of Remote Sensing & GIS · Vol. 15, Issue 2, 2024 · pp. 12–21 Read article
-
Optimizing Sentiment Analysis with Naïve Bayes and Random Forest Techniques: A Result-based Approach
Abstract: In the increased digitalization, the sentiment analysis and classification have evolved as an eminent area to determine the polarity of positive, negative, and neutral reviews of the customers and users on products. It is an integral application field that employs supervised learning, Machine Learning, and Natural Language Processing concepts. The proposed Semantic Analysis and Classification using Naive Bayes and Random Forest system accomplishes the sentiment polarity by classifying the user …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 12, Issue 2, 2025 · pp. 46–57 Read article
-
ML Model Comparison for Sentiment Analysis Across Diverse Datasets
Abstract: Analyzing sentiment is crucial for understanding public opinion on various issues in marketing, politics, and social sciences. This study compares the performance of seven different machine learning algorithms for sentiment classification, focusing on their effectiveness, accuracy, and complexity. The research is conducted on a pre-processed dataset with balanced text samples, utilizing feature extraction methods such as Term Frequency-Inverse Document Frequency (TF-IDF). The performance assessment criteria consist of accuracy, precision, recall, …
Published in Journal of Operating Systems Development & Trends · Vol. 12, Issue 2, 2025 · pp. 26–33 Read article
-
State of the Art: A Pandemic Big HealthCare Analytics Solution: Image Data Classification Using Quantum MAML
Abstract: The modern age is facing many pandemic healthcare problems, e.g., covid 19, infections, inflammations, and many more, leading to critical, deadly situations. Survival rate can be increased with proper diagnosis of such data. We have proposed one of the implementations based on a medical image dataset for classification using deep reinforcement learning (RL) with quantum computing. Deep RL is the combination of DL (deep learning), generative adversarial network (GAN), and …
Published in Research and Reviews : A Journal of Medical Science and Technology · Vol. 14, Issue 2, 2024 · pp. 1–9 Read article
-
Accelerating Unsupervised Feature Learning: Parallelized Training of Denoising Autoencoders
Abstract: Unsupervised representation learning has become a cornerstone of contemporary machine learning, enabling algorithms to extract informative features from un-labelled, high-dimensional data. This work investigates the efficacy of stacked denoising autoencoders (SDAEs) trained via parallelized stochastic gradient descent (SGD) as a scalable approach to feature extraction. By strategically leveraging multi-threaded computation, our study systematically examines the trade-offs between increased parallelism, training efficiency, and the preservation of model accuracy. Experiments on the …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 12, Issue 3, 2025 · pp. 56–64 Read article
-
Advanced Polymer Nanocomposite EEG Electrodes for Enhanced Epileptic Seizure Detection: A Comparative Analysis
Abstract: Electroencephalography (EEG) has been very important in the detection of epileptic seizures so as to enable successful diagnosis, surveillance and therapy of epilepsy. Nevertheless, EEG electrodes based on traditional metals may be limited due to high or high contact impedance, lack of biocompatibility, discomfort to patients and prone to motion artifacts, which interfere with signal quality and diagnostic adequacy. The recent progress in material science has resulted in coming up …
Published in Journal of Polymer & Composites · Vol. 14, Issue 1, 2026 Read article
-
Network Intrusion Detection System Using Decision Tree
Abstract: This paper presents a novel approach to network intrusion detection systems (NIDS) using advanced decision tree algorithms to address critical limitations in existing IDS solutions. Traditional IDSs often struggle with high false positive and negative rates, lack of scalability, and poor interpretability. Our proposed IDS leverages decision trees to enhance detection accuracy, interpretability, and scalability, thereby improving network security. Decision trees are chosen for their adaptive learning capabilities, transparent decision-making …
Published in Journal Of Network security · Vol. 12, Issue 2, 2024 · pp. 22–33 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