International Journal of Intelligent Systems最新文献

{"title":"Development and Validation of Explainable Artificial Intelligence System for Automatic Diagnosis of Cervical Lymphadenopathy From Ultrasound Images","authors":"Ming Xu,&nbsp;Yubiao Yue,&nbsp;Zhenzhang Li,&nbsp;Yinhong Li,&nbsp;Guoying Li,&nbsp;Haihua Liang,&nbsp;Di Liu,&nbsp;Xiaohong Xu","doi":"10.1155/int/5432766","DOIUrl":"https://doi.org/10.1155/int/5432766","url":null,"abstract":"<div>\u0000 <p>Clinical diagnosis of cervical lymphadenopathy (CLA) using ultrasound images is a time-consuming and laborious process that heavily relies on expert experience. This study aimed to develop an intelligent computer-aided diagnosis (CAD) system using deep learning models (DLMs) to enhance the efficiency of ultrasound screening and diagnostic accuracy of CLA. We retrospectively collected 4089 ultrasound images of cervical lymph nodes across four categories from two hospitals: normal, benign CLA, primary malignant CLA, and metastatic malignant CLA. We employed transfer learning, data augmentation, and five-fold cross-validation to evaluate the diagnostic performance of DLMs with different architectures. To boost the application potential of DLMs, we investigated the potential impact of various optimizers and machine learning classifiers on their diagnostic performance. Our findings revealed that EfficientNet-B1 with transfer learning and root-mean-square-propagation optimizer achieved state-of-the-art performance, with overall accuracies of 97.0% and 90.8% on the internal and external test sets, respectively. Additionally, human–machine comparison experiments and the implementation of explainable artificial intelligence technology further enhance the reliability and safety of DLMs and help clinicians easily understand the DLM results. Finally, we developed an application that can be implemented in systems running Microsoft Windows. However, additional prospective studies are required to validate the clinical utility of the developed application. All pretrained DLMs, codes, and application are available at https://github.com/YubiaoYue/DeepUS-CLN.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/5432766","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143564807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"An Improved A ∗ Algorithm Based on Simulated Annealing and Multidistance Heuristic Function","authors":"Yuandong Chen,&nbsp;Jinhao Pang,&nbsp;Zeyang Huang,&nbsp;Yuchen Gou,&nbsp;Zhen Jiang,&nbsp;Dewang Chen","doi":"10.1155/int/5979509","DOIUrl":"https://doi.org/10.1155/int/5979509","url":null,"abstract":"<div>\u0000 <p>The traditional A ^∗ algorithm has problems such as low search speed and huge expansion nodes, resulting in low algorithm efficiency. This article proposes a circular arc distance calculation method in the heuristic function, which combines the Euclidean distance and the Manhattan distance as radius, uses a deviation distance as the correction, and assignes dynamic weights to the combined distance to make the overall heuristic function cost close to reality. Furthermore, the repulsive potential field function and turning cost are introduced into the heuristic function, to consider the relative position of obstacles while minimizing turns in the path. In order to reduce the comparison of nodes with similar cost values, the bounded suboptimal method is used, and the idea of simulated annealing is introduced to overcome the local optima trapped by node expansion. Simulation experiments show that the average running time of the improved algorithm has decreased by about 70%, the number of extended nodes has decreased by 92%, and the path has also been shortened, proving the effectiveness of the algorithm improvement.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/5979509","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143554985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Gradient Reconstruction Protection Based on Sparse Learning and Gradient Perturbation in IoV","authors":"Jia Zhao,&nbsp;Xinyu Rao,&nbsp;Bokai Yang,&nbsp;Yanchun Wang,&nbsp;Jiaqi He,&nbsp;Hongliang Ma,&nbsp;Wenjia Niu,&nbsp;Wei Wang","doi":"10.1155/int/9253392","DOIUrl":"https://doi.org/10.1155/int/9253392","url":null,"abstract":"<div>\u0000 <p>Existing research indicates that original federated learning is not absolutely secure; attackers can infer the original training data based on reconstructed gradient information. Therefore, we will further investigate methods to protect data privacy and prevent adversaries from reconstructing sensitive training samples from shared gradients. To achieve this, we propose a defense strategy called SLGD, which enhances model robustness by combining sparse learning and gradient perturbation techniques. The core idea of this approach consists of two parts. First, before processing training data at the RSU, we preprocess the data using sparse techniques to reduce data transmission and compress data size. Second, the strategy extracts feature representations from the model and performs gradient filtering based on the <i>l</i>₂ norm of this layer. Selected gradient values are then perturbed using Von Mises–Fisher (VMF) distribution to obfuscate gradient information, thereby defending against gradient reconstruction attacks and ensuring model security. Finally, we validate the effectiveness and superiority of the proposed method across different datasets and attack scenarios.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/9253392","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143533450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Orientation-Aware Reversible Data Hiding With Brainstorming Optimization for UAV Aerial Images","authors":"Xiaodan Tai,&nbsp;Yannan Ren,&nbsp;Jing Li,&nbsp;Jiande Sun,&nbsp;Kai Zhang,&nbsp;Wenbo Wan","doi":"10.1155/int/2796189","DOIUrl":"https://doi.org/10.1155/int/2796189","url":null,"abstract":"<div>\u0000 <p>In recent years, with the rapid development of unmanned aerial vehicle (UAV), aerial images have extended across various industries such as intelligent building, agriculture, transportation, and Industry 4.0. Notably, the security of UAV-assisted data acquisition during transmission has become a critical concern. The reversible data hiding (RDH) method can hide data in aerial images for transmission and ensure secure communication. In general, an aerial image may exhibit substantially different orientation regularity from a natural scene image. This casts major challenges to the RDH method, for which existing approaches lack effective mechanisms to capture such content type variations, and thus are difficult to generalize from one type to another. In this paper, the orientation-aware selectivity mechanism is introduced to achieve an accurate orientation-aware prediction along different directions in local regions with different structure regularity. Furthermore, we propose a progressive brainstorming optimization algorithm (BSO)-guided optimal PSNR value strategy, which can obtain a superior perceptual performance and the corresponding thresholds by further exploring the pixel correlations within the UAV aerial images. Experimental results on the USC-SIPI Miscellaneous dataset and two challenging aerial datasets, including the USC-SIPI High Altitude Aerial Imagery dataset and the Kaggle dataset, demonstrate that the proposed framework enhances the imperceptibility powerfully in marked UAV aerial images and ensures sufficient embedding capacity effectively. The average PSNR of the marked image obtained by the proposed method is 63.85 dB when embedded with 30,000 bits of data, which is an improvement of 0.59 dB compared to the current state-of-the-art RDH methods.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/2796189","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143513502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"GANSCCS: Synergizing Generative Adversarial Networks and Spectral Clustering for Enhanced MRI Resolution in the Diagnosis of Cervical Spondylosis","authors":"Robin Kumar,&nbsp;Dalwinder Singh,&nbsp;Rahul Malik,&nbsp;Isha Batra,&nbsp;Mamoona Humayun,&nbsp;Javed Ali Khan","doi":"10.1155/int/6674913","DOIUrl":"https://doi.org/10.1155/int/6674913","url":null,"abstract":"<div>\u0000 <p>The expeditious improvement in medical imaging technology has been crucial in diagnosing various conditions like cervical spondylosis. However, there is a need for improvement in terms of accuracy and efficiency in the existing models to obtain optimal diagnostic results. This limitation of existing models particularly hampers the resolution and clarity of MRI where there is a need for finer details for the accurate diagnoses of the problem. To limit this gap, our research represents a pioneering approach that merges GAN and spectral clustering. Our research shows the innovative amalgamation of two technologies. The GAN model is enhanced by the sturdy segmentation abilities of spectral clustering, resulting in the significant betterment in diagnosis of problems. This GAN is specifically designed for medical imaging; it consists of a deep convolutional network based on U-Net architecture. GAN consists of a generator that generates the MRI image through a series of convolutional and deconvolutional layers, and a discriminator checks whether the MRI image is real or generated. This approach not only improves the quality of the image but also leads to a more brisk and accurate diagnosis of cervical spine deformities. The methodology was meticulously tested on diverse datasets, including Medscape, RSNA 2022, and CTSpine1k. The results were remarkable, showing an 8.3% increase in accuracy, 5.5% improvement in precision, 8.5% higher recall, 3.5% greater AUC, 4.9% increased specificity, and a 1.9% reduction in delay compared to the existing classification methods. The influence of this work is profound, providing a consideration spike in the capability of diagnosing problems of cervical spondylosis. By providing improved image resolution and highly precise diagnostic tools, this advancement helps clinicians to make more accurate decisions as well as provides various innovations that help in medical imaging in the future.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/6674913","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143513822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Consistency Regularization Semisupervised Learning for PolSAR Image Classification","authors":"Yu Wang,&nbsp;Shan Jiang,&nbsp;Weijie Li","doi":"10.1155/int/7261699","DOIUrl":"https://doi.org/10.1155/int/7261699","url":null,"abstract":"<div>\u0000 <p>Polarimetric Synthetic Aperture Radar (PolSAR) images have emerged as an important data source for land cover classification research due to their all-weather, all-day monitoring capabilities. Deep learning-based classification methods have recently gained significant attention in PolSAR image classification since they have demonstrated excellent performance in the computer vision field. However, the main issue with deep learning-based methods is that they require large amounts of training data. Additionally, the scarcity of labeled data is a significant challenge in the PolSAR image field. Therefore, in this article, we proposed an advanced semisupervised deep self-training algorithm for PolSAR image classification, which utilized both labeled and unlabeled data in a semisupervised way. Then, a training optimization method and a high-confidence sample selection strategy are proposed by integrating consistency regularization. In addition, to achieve stronger feature extraction capabilities, we designed a deep learning-based classifier that combines residual blocks with an efficient multiscale attention module. We have conducted experiments on three popular real PolSAR datasets: 1989 Flevoland, 1991 Flevoland, and Oberpfaffenhofen. The classification results on these datasets demonstrated that the proposed method outperforms several other comparison algorithms, with overall accuracy up to 99.3%, 99.15%, and 94.12%, respectively. These results demonstrated the effectiveness of the proposed method for PolSAR image classification.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/7261699","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143481637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Exploring Batch Normalization’s Impact on Dense Layers of Multiclass and Multilabel Classifiers","authors":"Misganaw Aguate Widneh,&nbsp;Amlakie Aschale Alemu,&nbsp;Dereje Derib Getie","doi":"10.1155/int/1466655","DOIUrl":"https://doi.org/10.1155/int/1466655","url":null,"abstract":"<div>\u0000 <p>Leveraging batch normalization (BN) is crucial for deep learning for quick and precise identification of objects. It is a commonly used approach to reduce the variation of input distribution using BN. However, the complex parameters computed at the classifier layer of convolutional neural network (CNN) are the reason for model overfitting and consumption of long training time. This study is proposed to make a comparative analysis of models’ performances on multiclass and multilabel classifiers with and without BN at dense layers of CNN. Consequently, for both classifications, BN layers are incorporated at the fully connected layer of CNN. To build a model, we used datasets of medical plant leaves, potato leaves, and fashion images. The pretrained models such as Mobile Net, VGG16, and Inception Net are customized (tuned) using the transfer learning technique. We made adjustments to training and model hyperparameters, including batch size, number of layers, learning rate, number of epochs, and optimizers. After several experiments on the three models, we observed that the best way to improve the model’s accuracy is by applying BN at the CNN’s dense layer. BN improved the performances of the models on both multiclass and multilabel classifications. This improvement has more significant change in the multilabel classification. Hence, using medicinal plant dataset, the model achieved accuracy of 93% and 83% for multilabel with and without BN, respectively, while achieving 99.2% and 99% for multiclass classification. The experiment also proved that the effectiveness of BN is affected on type datasets, depth of CNN, and batch sizes.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/1466655","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143475758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Strategies to Mitigate Model Drift of a Machine Learning Prediction Model for Acute Kidney Injury in General Hospitalization","authors":"Jie Xu,&nbsp;Heng Liu,&nbsp;Guisen Li,&nbsp;Wenjun Mi,&nbsp;Martin Gallagher,&nbsp;Yunlin Feng","doi":"10.1155/int/2240862","DOIUrl":"https://doi.org/10.1155/int/2240862","url":null,"abstract":"<div>\u0000 <p><b>Background:</b> Model drift is a major challenge for applications of clinical prediction models. We aimed to investigate the effect of two strategies to mitigate model drift based on a previously reported prediction model for acute kidney injury (AKI).</p>\u0000 <p><b>Methods:</b> Deidentified electronic medical data of inpatients in Sichuan Provincial People’s Hospital from January 1, 2019, to December 31, 2022, were collected. AKI was defined by the KDIGO criteria. The top 50 laboratory variables, alongside with sex, age, and the top 20 prescribed medicines were included as predictive variables. In model optimization, the convolution neural network module was replaced by a self-attention module. Periodical refitting with accumulative data was also conducted before temporally external validations. The performance of the innovated model (ATRN) was compared with the previous model (ATCN) and other four models.</p>\u0000 <p><b>Results:</b> A total of 150,373 admissions were identified. The annual incidences of AKI varied between 5.57% and 5.8%. The performance of the models which had used temporal features profoundly declined over time. The ATRN model with module more suitable to capture short-term time dependencies outperformed the other five models both in C-statistics and recall rates perspectives. Periodic refitting the prediction model with accumulative data also helped to effectively mitigate the model drift, especially in models with time series data.</p>\u0000 <p><b>Conclusions:</b> Enhancing the model’s ability to capture short-term time dependencies in time series data and periodic refitting with accumulative data were both capable of mitigating the model drift. The best improvement of model performance was observed in the combination of these two strategies.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/2240862","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143475537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Intelligent Sensing and Identification of Spectrum Anomalies With Alpha-Stable Noise","authors":"Mingqian Liu,&nbsp;Zhaoxi Wen,&nbsp;Yunfei Chen,&nbsp;Junlin Zhang,&nbsp;Huigui Cheng,&nbsp;Nan Zhao","doi":"10.1155/int/5010973","DOIUrl":"https://doi.org/10.1155/int/5010973","url":null,"abstract":"<div>\u0000 <p>As the electromagnetic environment becomes more complex, a significant number of interferences and malfunctions of authorized equipment can result in anomalies in spectrum usage. Utilizing intelligent spectrum technology to sense and identify anomalies in the electromagnetic space is of great significance for the efficient use of the electromagnetic space. In this paper, a method for intelligent sensing and identification of anomalies in spectrum with alpha-stable noise is proposed. First, we use a delayed feedback network (DFN) to suppress alpha-stable noise. Then, we use a long short-term memory (LSTM) autoencoder-based attention mechanism to sense anomaly. Finally, we use the deep forest model to identify abnormal spectrum. Simulation results demonstrate that the proposed method effectively suppresses alpha-stable noise, and it outperforms existing methods in abnormal spectrum sensing and identification.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/5010973","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143447035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Modeling and Recognition of Retinal Blood Vessels Tortuosity in ROP Plus Disease: A Hybrid Segmentation–Classification Scheme","authors":"Alice Varysova,&nbsp;Jan Kubicek,&nbsp;Marek Penhaker,&nbsp;Martin Augustynek,&nbsp;David Oczka,&nbsp;Kristyna Marsolkova,&nbsp;Juraj Timkovic","doi":"10.1155/int/6688133","DOIUrl":"https://doi.org/10.1155/int/6688133","url":null,"abstract":"<div>\u0000 <p>Retinopathy of prematurity (ROP) remains a significant cause of childhood blindness despite advancements in neonatal care. Identifying the plus form of ROP, characterized by dilated and tortuous blood vessels, is crucial for timely intervention. This study introduces an intelligent segmentation–classification system for the autonomous detection of retinal blood vessels and the classification of ROP plus form. Utilizing Clarity RetCam 3 images, our system employs morphological image processing and convolutional neural networks (CNNs) for segmentation and classification, respectively. Testing on a dataset of premature infants’ retinal images demonstrates high segmentation accuracy (median = 0.974) and superior classification performance (accuracy = 0.975, sensitivity = 0.950, and specificity = 1). In addition, the system exhibits versatility, with successful segmentation in adult retinal images from public databases. These findings highlight the system’s potential for clinical use in retinal vessel identification, feature extraction, and ROP plus form classification. The proposed system is capable of effectively identifying retinal blood vessels from both alternatives including adult and premature born retinal images with a high accuracy in contrast to related studies. Thus, this system has the potential to be used in clinical practice for retinal blood vessels’ identification, retinal blood vessels’ feature extraction, and ROP plus form classification.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/6688133","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143447034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}