International Journal of Cognitive Computing in Engineering最新文献

{"title":"ECG-based transfer learning for cardiovascular disease: A scoping review","authors":"Sharifah Noor Masidayu Sayed Ismail ,&nbsp;Siti Fatimah Abdul Razak ,&nbsp;Nor Azlina Ab Aziz","doi":"10.1016/j.ijcce.2025.01.007","DOIUrl":"10.1016/j.ijcce.2025.01.007","url":null,"abstract":"<div><div>An electrocardiogram (ECG) measures the electrical activity of the heart. It is valuable for the early detection of cardiovascular disease (CVD). Advancements in medical diagnosis using artificial intelligence have popularised transfer learning among researchers in machine learning and deep learning. This scoping review focuses on the application of ECG-based transfer learning for CVD identification, examining the most common types of CVD studied, the input formats used, frequently referenced databases, and the extent of transfer learning's application in diagnosing CVD through ECG analysis. We also conducted a bibliographic analysis to provide an overview of the current situation in the CVD research field. Our analysis of over 70 studies published in the last six years indicates that arrhythmias are the most extensively studied CVD, with the MIT-BIH arrhythmia dataset being the most commonly used in previous research. Pre-trained models such as ResNet, AlexNet, and VGG, which are trained on ImageNet, are often used with two-dimensional (2D) ECG data as network input, achieving accuracy rates exceeding 90 %. The bibliographic analysis indicates that China and India are the highest contributors in this field. Our study also identifies several issues requiring further investigation and recommends areas for future research, including hyperparameter tuning to enhance model performance.</div></div>","PeriodicalId":100694,"journal":{"name":"International Journal of Cognitive Computing in Engineering","volume":"6 ","pages":"Pages 280-297"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143139488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel region based neighbors searching classification algorithm for big data","authors":"Rajib Kumar Halder,&nbsp;Mohammed Nasir Uddin,&nbsp;Md Ashraf Uddin","doi":"10.1016/j.ijcce.2025.05.002","DOIUrl":"10.1016/j.ijcce.2025.05.002","url":null,"abstract":"<div><div>The K-Nearest Neighbors (KNN) algorithm remains a cornerstone of machine learning due to its intuitive design and effectiveness in classification tasks. However, its performance often suffers from critical limitations, such as sensitivity to the choice of the parameter K and an inability to effectively capture complex relationships among neighboring instances. To overcome these challenges, we propose the <strong>Region-Based Neighbors Searching Classification Algorithm (RNSCA)</strong>—a novel, adaptive framework that significantly enhances the scalability, flexibility, and accuracy of traditional KNN, especially in high-dimensional and large-scale datasets. RNSCA leverages dynamic, region-based partitioning for more focused and efficient neighbor searches and incorporates a weighted activation function to prioritize the most relevant data points during classification. Additionally, ensemble learning techniques are integrated to strengthen model robustness and improve generalization. The proposed algorithm is extensively validated on benchmark datasets including Iris, Crop Recommendation, Breast Cancer, Diabetes, and Chronic Kidney Disease (CKD). Experimental results consistently demonstrate RNSCA’s superior performance in modeling nuanced local structures and mitigating the core limitations of conventional KNN. This research presents a compelling advancement in classification algorithms, with practical implications across domains such as healthcare, agriculture, and environmental intelligence.</div></div>","PeriodicalId":100694,"journal":{"name":"International Journal of Cognitive Computing in Engineering","volume":"6 ","pages":"Pages 516-536"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143932195","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Yoga practices effect on VCSS-based classification of patients with chronic venous insufficiency based on hybrid machine learning algorithms","authors":"Changhong Pan ,&nbsp;Lu Qi ,&nbsp;Lili Zhao ,&nbsp;Yijun Wei","doi":"10.1016/j.ijcce.2025.01.003","DOIUrl":"10.1016/j.ijcce.2025.01.003","url":null,"abstract":"<div><div>Advancements in technology have increased work demands, neglecting individual well-being and causing mental pressure and decreased fitness. The COVID-19 pandemic has worsened this, leading to a surge in psychological stress. Non-pharmacological approaches like yoga are gaining popularity for stress management, showing positive effects on the autonomic nervous system and offering benefits such as improved cardio-respiratory health and metabolic efficiency, as well as positive effects on conditions like Type-2 diabetes, Chronic Venous Disease (CVD), and obesity. This investigation aims to introduce proficiently functioning machine learning classifiers, such as single and hybrid forms of Decision Trees (DT), into the domain of studies within this particular category. The study utilized 2 optimization algorithms, namely the Honey Badger Algorithm (HBA) and the Arithmetic Optimization Algorithm (AOA), to develop hybrid models. Venous Clinical Severity Score (VCSS) levels prior to and one month following yoga sessions were among the variables in the questionnaire that were considered as inputs: effective influences on CVD. The developed prediction models were trained, and their operational capability was tested. The extracted results classified the samples into 4 classes: Absent, Mild, Moderate, and Severe Chronic Venous Insufficiency (CVI). Comparative analysis revealed that DTHB (Decision Tree optimized with Honey Badger Algorithm) with maximum Accuracy and Precision of higher than 90 % was the optimal model, especially for classifying patients with Moderate and Severe levels of CVI needing emergency medical action.</div></div>","PeriodicalId":100694,"journal":{"name":"International Journal of Cognitive Computing in Engineering","volume":"6 ","pages":"Pages 255-266"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143139930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An improved quantum-inspired particle swarm optimisation approach to reduce energy consumption in IoT networks","authors":"Yousra Mahmoudi ,&nbsp;Nadjet Zioui ,&nbsp;Hacène Belbachir","doi":"10.1016/j.ijcce.2025.01.010","DOIUrl":"10.1016/j.ijcce.2025.01.010","url":null,"abstract":"<div><div>The Internet of Things (IoT) plays a pivotal role in modern society, connecting everyday objects to the internet and enabling smart functionalities that enhance efficiency, convenience, and sustainability across multiple sectors. As IoT networks have expanded in scale and complexity, optimising energy consumption has become critical to ensuring their long-term sustainability and cost-effectiveness. This paper introduces quantum-inspired particle swarm optimisation clustering (QIPSOC), an innovative metaheuristic that relies on a novel mathematical formulation (MPMC) and integrates principles from quantum computing and particle swarm optimisation to achieve energy-efficient clustering, balancing network performance constraints and energy consumption. By encoding particles as <span><math><mi>n</mi></math></span>-qubit systems and employing quantum-inspired motion through qubit rotations along with an inertial damping factor, QIPSOC enhances solution diversity, mitigates premature convergence to local optima, and guides the exploration of the solution space to achieve significant energy savings, ranging from 17.99 % to over 91 %, depending on the network configuration. These results underscore QIPSOC's superiority over state-of-the-art methods in optimising energy efficiency and performance in IoT networks, making it well-suited for real-world deployment scenarios requiring rapid decision-making.</div></div>","PeriodicalId":100694,"journal":{"name":"International Journal of Cognitive Computing in Engineering","volume":"6 ","pages":"Pages 313-322"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143139931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The application of improved SURF optical flow algorithm in seismic support safety monitoring system","authors":"Jiahui Wang","doi":"10.1016/j.ijcce.2024.11.006","DOIUrl":"10.1016/j.ijcce.2024.11.006","url":null,"abstract":"<div><div>Frequent earthquakes pose a major threat to the safety of building structures. As a critical component of earthquake-resistant systems, dynamic health monitoring of seismic isolation bearings is essential. However, existing monitoring methods are limited by high cost and poor environmental adaptability, and it is difficult to meet real-time requirements under complex conditions. Therefore, this study combines the stable acceleration feature point matching with the optical flow algorithm, and uses the proportional purification method and the bidirectional purification method to effectively match and purify the feature points. By optimizing the feature point matching and dynamic tracking accuracy, a seismic bearing safety monitoring system based on the improved feature optical flow algorithm is designed. The experimental results show that the improved model achieves a feature recognition rate of &gt;90 %, and the number of feature tracking losses is &lt;70. At the same time, the displacement time history curve of the seismic isolation bearing and the laser displacement sensor has the highest degree of fit, the error of the horizontal displacement peak is 2.13 %, and the absolute error is &lt;0 .3mm. Compared with traditional methods, this system achieves high-precision real-time monitoring at a low cost, providing reliable technical support for the health management of seismic isolation bearings, and also opens up a new direction in the field of structural health monitoring.</div></div>","PeriodicalId":100694,"journal":{"name":"International Journal of Cognitive Computing in Engineering","volume":"6 ","pages":"Pages 109-119"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143139923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dynamic Agricultural Pest Classification Using Enhanced SAO-CNN and Swarm Intelligence Optimization for UAVs","authors":"Shiwei Chu,&nbsp;Wenxia Bao","doi":"10.1016/j.ijcce.2025.04.002","DOIUrl":"10.1016/j.ijcce.2025.04.002","url":null,"abstract":"<div><div>The rapid advancement of agricultural modernization demands urgent solutions for accurate and real-time pest monitoring to enhance crop productivity. Traditional manual methods lack efficiency and fail to capture dynamic pest behaviors, while existing deep learning models struggle with robustness in complex environments. To address these challenges, this study proposes a novel Dynamic Agricultural Pest Classification System that integrates an enhanced Self-Activation Optimization Convolutional Neural Network (SAO-CNN) with bio-inspired swarm intelligence for UAVs. The SAO-CNN innovatively combines adaptive convolutional layers, self-supervised learning, and ConvLSTM to optimize spatial-temporal feature extraction, while swarm algorithms (ACO and PSO) enhance UAV path planning and task allocation. Key contributions include: (1) A hybrid SAO-CNN architecture that dynamically adjusts convolution kernels and leverages unlabeled data through self-supervised learning, improving adaptability to lighting and background variations. (2) A UAV swarm intelligence framework optimized via bio-inspired algorithms, reducing flight time by 29.2% and energy consumption by 32% compared to non-optimized systems. (3) Superior performance with 91.2% classification accuracy, 0.89 recall, and 32 FPS processing speed, outperforming state-of-the-art models (e.g., YOLO variants, ResNet, and ConvLSTM) in both static and dynamic scenarios. This work provides a robust solution for real-time pest monitoring, significantly advancing precision agriculture and sustainable crop management.</div></div>","PeriodicalId":100694,"journal":{"name":"International Journal of Cognitive Computing in Engineering","volume":"6 ","pages":"Pages 588-602"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144290809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence-inspired comprehensive framework for desertification prediction","authors":"Shtwai Alsubai ,&nbsp;Mogeeb A.A. Mosleh ,&nbsp;Suheer A. Al-Hadhrami ,&nbsp;Munish Bhatia","doi":"10.1016/j.ijcce.2025.02.007","DOIUrl":"10.1016/j.ijcce.2025.02.007","url":null,"abstract":"<div><div>Desertification greatly affects land deterioration, farming efficiency, economic growth, and health, especially in Gulf nations. Climate change has worsened desertification, making developmental issues in the area even more difficult. This research presents an enhanced framework utilizing the Internet of Things (IoT) for ongoing monitoring, data gathering, and analysis to evaluate desertification patterns. The framework utilizes Bayesian Belief Networks (BBN) to categorize IoT data, while a low-latency processing method on edge computing platforms enables effective detection of desertification trends. The classified data is subsequently analyzed using an Artificial Neural Network (ANN) optimized with a Genetic Algorithm (GA) for forecasting decisions. Using cloud computing infrastructure, the ANN-GA model examines intricate data connections to forecast desertification risk elements. Moreover, the Autoregressive Integrated Moving Average (ARIMA) model is employed to predict desertification over varied time intervals.</div><div>Experimental simulations illustrate the effectiveness of the suggested framework, attaining enhanced performance in essential metrics: Temporal Delay (103.68 s), Classification Efficacy—Sensitivity (96.44 %), Precision (95.56 %), Specificity (96.97 %), and F-Measure (96.69 %)—Predictive Efficiency—Accuracy (97.76 %) and Root Mean Square Error (RMSE) (1.95 %)—along with Reliability (93.73 %) and Stability (75 %). The results of classification effectiveness and prediction performance emphasize the framework's ability to detect high-risk zones and predict the severity of desertification.</div><div>This innovative method improves the comprehension of desertification processes and encourages sustainable land management practices, reducing the socio-economic impacts of desertification and bolstering at-risk ecosystems. The results of the study hold considerable importance for enhancing regional efforts in combating desertification, ensuring food security, and formulating environmental sustainability policies.</div></div>","PeriodicalId":100694,"journal":{"name":"International Journal of Cognitive Computing in Engineering","volume":"6 ","pages":"Pages 462-476"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143815342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cognitive AI and implicit pseudo-spline wavelets for enhanced seismic prediction","authors":"Mutaz Mohammad","doi":"10.1016/j.ijcce.2025.02.003","DOIUrl":"10.1016/j.ijcce.2025.02.003","url":null,"abstract":"<div><div>Using data from 1900 to 2024, this study developed an innovative artificial intelligence (AI)-powered framework for predicting earthquakes in Japan. By incorporating state-of-the-art cognitive computing techniques with expert seismic assessments, the proposed algorithm addresses some of the complex challenges in earthquake prediction. The model fuses AI systems with numerical methods such as the Finite Element Method (FEM) and pseudo-spline collocation techniques to simulate seismic wave propagation in a stratified spherical Earth. This study employed cognitive computing mechanisms to categorize and analyze seismic activities using a vector-based structure that compares past seismic events with predefined classifications. Moreover, the framework integrates expert knowledge of the stress distribution in the Earth’s crust to establish a comprehensive model for seismic forecasting. This AI-driven methodology provides deeper insight into seismic wave behavior and introduces a self-improving data-centric system that could support decision-making for reducing earthquake risk.</div></div>","PeriodicalId":100694,"journal":{"name":"International Journal of Cognitive Computing in Engineering","volume":"6 ","pages":"Pages 401-411"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid Models for Forecasting Allocative Localization Error in Wireless Sensor Networks","authors":"Guo Li ,&nbsp;Hongyu Sheng","doi":"10.1016/j.ijcce.2025.01.008","DOIUrl":"10.1016/j.ijcce.2025.01.008","url":null,"abstract":"<div><div>This study presents a machine learning-based approach to forecast Allocative Localization Error (ALE) in Wireless Sensor Networks (WSNs), addressing challenges such as dynamic network topologies and resource constraints. The approach utilizes Radial Basis Function (RBF) models enhanced with advanced optimization algorithms, including Coot Optimization Algorithm (COA), Smell Agent Optimization (SAO), and Northern Goshawk Optimization (NGO) to improve ALE prediction accuracy. Hybrid models (RBCO, RBSO, and RFNG) are developed by integrating these optimization techniques, which refine critical RBF parameters, such as spread and center selection, through iterative optimization. Furthermore, an ensemble framework (RSNC) combines all three optimizers with RBF to achieve superior performance. The proposed methods are validated using R² and RMSE metrics, demonstrating their ability to minimize ALE, optimize resource allocation, and extend network lifespans. The study highlights the practical applicability of these models in real-world scenarios, such as environmental monitoring and industrial automation, offering enhanced efficiency and economic benefits. The RFNG model, in particular, achieved the lowest Mean Absolute Relative Error (MARE) of 0.049, demonstrating superior performance compared to other approaches in the test section. Moreover, RBNG obtained 0.069 and 0.978 values for the RMSE and R², respectively, which were the most suitable values compared to other models, namely RBGO, RBSO, RSNC, and RBF. The results indicate that the proposed hybrid models significantly improve the prediction of ALE, leading to more efficient node deployment and better network management. This research provides valuable insights into leveraging machine learning for WSN optimization, benefiting researchers, network engineers, and industries relying on sensor networks for applications such as environmental monitoring, smart cities, and asset tracking.</div></div>","PeriodicalId":100694,"journal":{"name":"International Journal of Cognitive Computing in Engineering","volume":"6 ","pages":"Pages 333-350"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143139944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A class imbalance aware hybrid model for accurate rice variety classification","authors":"Hanumesh Vaidya ,&nbsp;K.V. Prasad ,&nbsp;C. Rajashekhar ,&nbsp;D Tripathi ,&nbsp;Renuka S ,&nbsp;Jyoti Shetty ,&nbsp;Kumar Swamy ,&nbsp;Shobha Y","doi":"10.1016/j.ijcce.2024.12.004","DOIUrl":"10.1016/j.ijcce.2024.12.004","url":null,"abstract":"<div><div>Rice classification plays a critical role in global agriculture, impacting the food security of over 3.5 billion people worldwide. As the complexity of this task has grown, advanced Machine Learning (ML) and Deep Learning (DL) models have emerged as powerful tools for accurate variety identification. These sophisticated algorithms excel in processing extensive datasets, leveraging key characteristics such as grain size, color, and texture to make precise predictions. However, a persistent challenge in this field is a class imbalance, where certain rice varieties are significantly underrepresented in datasets. This imbalance can severely impact model performance, particularly for minority classes, leading to biased predictions that favor more abundant varieties. Many existing models struggle to effectively address this issue, often prioritizing majority classes at the expense of overall generalization across all rice types. To tackle this critical gap in rice classification, we introduce a novel hybrid model: the XGBoost Multi-Layer 33Perceptron (XGB-MLP). This innovative approach is specifically designed to handle class imbalance, ensuring fair and accurate classification across all rice varieties, regardless of their representation in the dataset. Our model demonstrates remarkable versatility, effectively accommodating binary and multi-class scenarios while maintaining robust performance in the face of imbalanced data. As part of our contribution, we have also developed a new dataset intentionally incorporating class imbalance. This dataset serves as a rigorous benchmark for evaluating our model's performance against existing works in the field. The results of our comprehensive evaluation are compelling, with the XGB-MLP model achieving outstanding accuracy across various classification tasks: 99.86 % for binary class, 99.95 % for multi-class, and 98.46 % for a challenging multi-class scenario using a merged dataset. These impressive results not only surpass the performance of existing systems but also firmly establish the XGB-MLP model's efficacy in diverse rice classification tasks. By effectively addressing the longstanding challenge of class imbalance, our approach represents a significant advancement in the field, offering a more reliable and equitable solution for rice variety identification. This breakthrough has far-reaching implications for agricultural management, food security, and the broader application of machine learning in crop science.</div></div>","PeriodicalId":100694,"journal":{"name":"International Journal of Cognitive Computing in Engineering","volume":"6 ","pages":"Pages 170-182"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143139986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}