Computational Intelligence最新文献

{"title":"Speech2Dementia: A Novel Deep Learning Framework Integrating Enhanced CNN and Large Language Models for Automatic Detection of Alzheimer's Dementia","authors":"Bandaru A. Chakravarthi,&nbsp;Gandla Shivakanth","doi":"10.1111/coin.70051","DOIUrl":"https://doi.org/10.1111/coin.70051","url":null,"abstract":"<div>\u0000 \u0000 <p>Early diagnosis of Alzheimer's disease (AD) is important for early intervention, but current diagnostic tools tend to use unimodal methods, processing either speech or text separately. Although models such as the ComParE Baseline for audio and BERT-based text classifiers have been successful, they do not take advantage of the complementary strengths of both modalities, which restricts their diagnostic power. To overcome this, we suggest SPID-AD (Speech-Based Intelligent Detection of Alzheimer's Dementia), a multimodal deep-learning approach that combines linguistic and acoustic features for the automated detection of Alzheimer's. Our approach uses a BERT-based architecture to mine semantic patterns from transcripts and an augmented Convolutional Neural Network (CNN) to process Mel-spectrogram representations of speech. By combining these features in dense layers, the model retains language-related as well as auditory biomarkers of cognitive impairment. Assessed on the DementiaBank Pitt Corpus, SPID-AD has 95.6% classification accuracy, surpassing state-of-the-art models in precision, recall, and F1-score. The findings demonstrate the strength of multimodal analysis in detecting dementia speech patterns, providing a non-invasive, AI-based diagnostic tool that may assist clinicians in the early detection of Alzheimer's.</p>\u0000 </div>","PeriodicalId":55228,"journal":{"name":"Computational Intelligence","volume":"41 2","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143809489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Semantic Communication System for Standard Knowledge in Power Iot Networks","authors":"Zhengping Lin,&nbsp;Yanrong Yang,&nbsp;Xin Wang,&nbsp;Yuan La,&nbsp;Jie Lin","doi":"10.1111/coin.70045","DOIUrl":"https://doi.org/10.1111/coin.70045","url":null,"abstract":"<div>\u0000 \u0000 <p>The growing complexity of power Internet of Things (IoT) networks necessitates efficient and reliable communication capable of handling the continuous stream of data generated by distributed sensors, smart meters, and control systems. To handle this system, this paper proposes a semantic communication system for transmitting standard knowledge in power IoT networks, leveraging deep joint source-channel coding (Deep JSCC) to enhance communication efficiency and resilience. Unlike traditional communication approaches that prioritize bit-level accuracy, semantic communication focuses on conveying the meaning and relevance of information, ensuring that critical control signals and operational data are transmitted accurately, even under noisy channel conditions. The integration of Deep JSCC unifies data compression and error correction into a single neural network, enabling the system to dynamically balance the trade-off between compression efficiency and robustness to interference. The proposed semantic communication system also incorporates reinforcement learning (RL) to optimize network resource allocation on the bandwidth and transmission power, based on the semantic relevance of the transmitted knowledge. Experimental results demonstrate the effectiveness of the system in maintaining high reliability and low latency, even in resource-constrained environments, ensuring seamless grid operation and real-time decision-making. This research offers a novel framework for intelligent communication in power IoT networks, paving the way for sustainable energy management through efficient data handling, adaptive resource optimization, and improved communication reliability.</p>\u0000 </div>","PeriodicalId":55228,"journal":{"name":"Computational Intelligence","volume":"41 2","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143770099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Facilitating Air Transportation of Agricultural Systems via Intelligent Runway Detection","authors":"Zhaozi Zu,&nbsp;Hongjie Lei,&nbsp;Zhongjun Qu,&nbsp;Zhiyi Huang,&nbsp;Wenbo Suo","doi":"10.1111/coin.70046","DOIUrl":"https://doi.org/10.1111/coin.70046","url":null,"abstract":"<div>\u0000 \u0000 <p>Intelligent runway detection technology is crucial for the development of low-carbon, smart agricultural systems pertaining to the air transportation of agricultural products. Accurate detection of the location and orientation of the runway can effectively assist in safe aircraft landings and avoid potential risks. However, existing runway detection methods struggle in foggy conditions due to light scattering, causing blurry images and obscuring runway details, resulting in poor detection performance. Towards this issue, this paper proposes an adaptive image-based runway boundary detection method by combining image processing and filter prediction to enhance images automatically. It leverages runway symmetry to enhance feature maps and global-local information fusion. A shape loss function based on the runway's parallel boundaries is also introduced. These developments finally endow the proposed method with robustness towards foggy conditions. Experimental results demonstrate the method's effectiveness, achieving an average IoU of 73.58<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mo>%</mo>\u0000 </mrow>\u0000 <annotation>$$ % $$</annotation>\u0000 </semantics></math> on internal datasets, surpassing other advanced methods.</p>\u0000 </div>","PeriodicalId":55228,"journal":{"name":"Computational Intelligence","volume":"41 2","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143741033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Superpixel-Based Hyperspectral Image Denoising via Local-Global Low-Rank Approximation","authors":"Ya-Ru Fan,&nbsp;Daihui Li","doi":"10.1111/coin.70047","DOIUrl":"https://doi.org/10.1111/coin.70047","url":null,"abstract":"<div>\u0000 \u0000 <p>Recently, superpixel segmentation-based hyperspectral image (HSI) denoising methods have attracted increasing attention, since they could obtain the size-adaptive superpixel fiber rather than a cube with fixed spatial size. The superpixel fiber flexibly exploits the local similarity at different scales and leads to significant low-rankness. In this paper, we propose the parallel HSI denoising models which simultaneously consider the local and global low-rankness of the HSI based on superpixel segmentation. In the proposed models, the non-convex but smooth log-determination function is adopted to better characterize the low-rankness of the HSI. We also propose an adaptive weighted strategy to optimize the restored HSI. An efficient iterative algorithm is developed to solve the parallel models. Several experiments verify the superior performance of the proposed approach over other competing methods.</p>\u0000 </div>","PeriodicalId":55228,"journal":{"name":"Computational Intelligence","volume":"41 2","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reinforcement Learning Driven Cross-Trained Worker Assignment Approach Based on Big Models: A Study for A Hybrid Seru Production System Considering Learning Effect","authors":"Taixin Li,&nbsp;Chenxi Ye,&nbsp;Lang Wu,&nbsp;Feng Liu,&nbsp;Chengxiao Yu","doi":"10.1111/coin.70048","DOIUrl":"https://doi.org/10.1111/coin.70048","url":null,"abstract":"<div>\u0000 \u0000 <p>As manufacturing faces evolving customer demands, the integration of Industrial Internet of Things (IIoT) networks is crucial for enhancing production flexibility. In this context, the Seru Production System (SPS) has emerged as a highly adaptable production mode and emphasizes the strategic assignment of cross-trained workers, particularly in hybrid configurations combining divisional and rotating serus. This paper proposes a novel bi-objective mathematical model incorporating learning effects to minimize makespan and balance workloads among workers. With the development of Artificial Intelligence Generated Content (AIGC) empowered big models, new breakthroughs have emerged in industrial manufacturing decision-making. These models utilize deep learning for foundational content processing and leverage reinforcement learning to optimize strategies. This process provides robust support for achieving efficient decision optimization. Building on the concepts of AIGC big models training, this study employs reinforcement learning to refine the results of multi-objective genetic algorithms, thereby improving the solution capability of the bi-objective model. Experimental results demonstrate that the proposed algorithm effectively provides optimal strategies for tuning crossover and mutation operations. Additionally, numerical experiments offer insights into the formation of hybrid SPS configurations.</p>\u0000 </div>","PeriodicalId":55228,"journal":{"name":"Computational Intelligence","volume":"41 2","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Motor Imagery Classification Using fNIRS Brain Signals: A Method Based on Synthetic Data Augmentation and Cosine-Modulated Attention","authors":"Cheng Peng,&nbsp;Baojiang Li,&nbsp;Haiyan Wang,&nbsp;Xinbing Shi,&nbsp;Yuxing Qin","doi":"10.1111/coin.70044","DOIUrl":"https://doi.org/10.1111/coin.70044","url":null,"abstract":"<div>\u0000 \u0000 <p>Functional near-infrared spectroscopy (fNIRS), renowned for its high spatial resolution, shows substantial promise in brain-computer interface (BCI) applications. However, challenges such as lengthy data acquisition processes and susceptibility to noise can limit data availability and reduce classification accuracy. To overcome these limitations, we introduce the CosineGAN-transformer network (CGTNet), which integrates a dual discriminator GAN for generating high-quality synthetic data with a Transformer-based classification network. Equipped with a multi-head self-attention mechanism, this network excels at capturing the intricate spatiotemporal relationships inherent in high-resolution fNIRS signals. The dual discriminator framework ensures that both the temporal and spatial aspects of the synthetic data closely resemble the original signals, thereby enhancing data diversity and fidelity. Experimental results on a publicly available fNIRS dataset, comprising 30 participants performing motor imagery tasks (right-hand tapping, left-hand tapping, and foot tapping), demonstrate that CGTNet achieves an accuracy of 82.67%, outperforming existing methods. Key contributions of this work include the use of multi-head self-attention for refined feature extraction and a dual discriminator Generative Adversarial Networks (GAN) framework that maintains data quality and consistency. These advancements significantly improve the robustness and accuracy of BCI systems, offering promising applications in neurorehabilitation and assistive technologies.</p>\u0000 </div>","PeriodicalId":55228,"journal":{"name":"Computational Intelligence","volume":"41 2","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"RETRACTION","authors":"","doi":"10.1111/coin.70040","DOIUrl":"https://doi.org/10.1111/coin.70040","url":null,"abstract":"<p>\u0000 <b>RETRACTION</b>: <span>J. Mao</span>, <span>Q. Sun</span>, <span>X. Wang</span>, <span>B. Muthu</span>, <span>S. Krishnamoorthy</span>, “ <span>The Importance of Public Support in the Implementation of Green Transportation in the Smart Cities</span>,” <i>Computational Intelligence</i> <span>40</span> no. <span>1</span> (<span>2024</span>): e12326, https://doi.org/10.1111/coin.12326.</p><p>The above article, published online on 26 April 2020 in Wiley Online Library (wileyonlinelibrary.com) has been retracted by agreement between the journal Editor-in-Chief, Diana Inkpen; and Wiley Periodicals LLC. The article was published as part of a guest-edited issue. Following an investigation by the publisher, all parties have concluded that this article was accepted solely on the basis of a compromised peer review process. The editors have therefore decided to retract the article.</p><p>The authors disagree with the retraction.</p>","PeriodicalId":55228,"journal":{"name":"Computational Intelligence","volume":"41 2","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/coin.70040","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"RETRACTION","authors":"","doi":"10.1111/coin.70039","DOIUrl":"https://doi.org/10.1111/coin.70039","url":null,"abstract":"<p>\u0000 <b>RETRACTION:</b> <span>H. Yuan</span>, <span>H. Zhang</span>, <span>X. Liu</span>, <span>X. Jiao</span>, “ <span>Traffic Wave Model Based on Vehicle-Infrastructure Cooperative and Vehicle Communication Data</span>,” <i>Computational Intelligence</i> <span>36</span> no. <span>4</span> (<span>2020</span>): 1755-1772, \u0000https://doi.org/10.1111/coin.12346.</p><p>The above article, published online on 27 May 2020 in Wiley Online Library (\u0000wileyonlinelibrary.com) has been retracted by agreement between the journal Editor-in-Chief, Diana Inkpen; and Wiley Periodicals LLC. The article was published as part of a guest-edited issue. Following an investigation by the publisher, all parties have concluded that this article was accepted solely on the basis of a compromised peer review process. The editors have therefore decided to retract the article.</p>","PeriodicalId":55228,"journal":{"name":"Computational Intelligence","volume":"41 2","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/coin.70039","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Modified U-Shaped Transfer Function: Applied to Classify Parkinson'S Disease","authors":"Suvita Rani Sharma,&nbsp;Birmohan Singh,&nbsp;Manpreet Kaur","doi":"10.1111/coin.70036","DOIUrl":"https://doi.org/10.1111/coin.70036","url":null,"abstract":"<div>\u0000 \u0000 <p>Transfer functions have a very important role in metaheuristic optimization-based feature selection algorithms as these functions map the continuous search space into binary space. The U-shaped transfer function (UTF) is one of the transfer functions used to solve the problem of feature selection. However, the UTF requires the selection of parametric values, which can vary for different types of data. To address this issue, an approach to select the parameters of the UTF has been proposed based on a time-varying adaption method, resulting in the modified U-shaped transfer function (MUTF). Furthermore, a methodology has been proposed to enhance feature selection and classification for Parkinson's disease by utilizing z-score normalization in conjunction with a modified U-shaped transfer function and the binary self-adaptive bald eagle search (MUTF-SABES) optimization algorithm. The z-score normalization has been used to mitigate issues caused by outliers. Also, the performance of the k nearest neighbor classifier is improved by selecting an optimal parameter value using the proposed MUTF-SABES algorithm. The effectiveness of the proposed methodology is validated on seven different Parkinson's disease datasets and compared with five state-of-the-art optimization algorithms: Salp Swarm algorithm, Harris Hawks optimization, equilibrium optimizer, aquilla optimizer, and Honey Badger algorithm, to evaluate its performance superiority. The results achieved using the proposed approach have been superior or analogous to the erstwhile algorithms for performance comparability. Friedman's mean rank test is used to check the statistical significance of the propounded approach. The lowest Friedman's mean rank value obtained using the proposed approach indicates that the proposed approach has the potential to become an alternative to other well-known strategies.</p>\u0000 </div>","PeriodicalId":55228,"journal":{"name":"Computational Intelligence","volume":"41 2","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"One Unsupervised Feature Selection Method for the Classical Linear Classifier in Land Coverage Classification With PolSAR Imagery","authors":"Kun Tian,&nbsp;Xichao Liu,&nbsp;Dapeng Tao,&nbsp;Jun Ni","doi":"10.1111/coin.70025","DOIUrl":"https://doi.org/10.1111/coin.70025","url":null,"abstract":"<div>\u0000 \u0000 <p>Land coverage mapping and classification is one of the critical information-based tools for sustainable agricultural development, enabling relevant departments to carry out agricultural resource adjustments, yield predictions, and other tasks in advance. As a vital means of acquiring land cover and usage information, SAR sensors have become an important research direction due to their all-weather and all-day working capabilities. Nevertheless, traditional classification methods in PolSAR image classification often input a combination of various scattering features, i.e., high-dimensional feature combination, into classifiers, leading to mutual interference among different features and consequently degrading classification performance, especially for linear classifiers such as NRS and SVM. To mitigate this interference, this paper proposed an unsupervised feature selection based on spectral clustering (FSSC) that constructs a targeted approach by leveraging the linear expression capabilities of high-dimensional features. In this method, the linear relationships between different features are first analyzed, and the linear similarity between features can be quantitatively expressed using Pearson correlation coefficients, forming a feature similarity matrix. Subsequently, the similarity matrix undergoes unsupervised similarity partitioning through spectral clustering, dividing the features into distinct combinations. Features within clustering subsets can be considered as combinations with high linear similarity. Therefore, KL divergence is applied to select the most representative features within each cluster, and the resulting representative feature combinations from different clustering subsets are combined to form an optimal feature set, achieving the purpose of feature selection. This method maps high-dimensional feature combinations into low-dimensional ones while preserving the essential attributes of the original data, thereby retaining the valuable feature information and enhancing classification performance. Experimental outcomes conclusively show that the proposed method enhances the overall accuracy (OA) of SVM by 4.51% and the OA of NRS by 2.34% in the Flevoland Dataset, underscoring its efficacy in PolSAR image classification, especially for linear classifiers.</p>\u0000 </div>","PeriodicalId":55228,"journal":{"name":"Computational Intelligence","volume":"41 2","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}