Guoyin Ren, Qidan Guo, Zhijie Yu, Bo Jiang, Gong Li, Dong Li, Xinsong Wang
{"title":"PKDFIN: Prior Knowledge Distillation-Based Face Image Inpainting Network for Missing Regions","authors":"Guoyin Ren, Qidan Guo, Zhijie Yu, Bo Jiang, Gong Li, Dong Li, Xinsong Wang","doi":"10.1155/int/6897997","DOIUrl":"https://doi.org/10.1155/int/6897997","url":null,"abstract":"<p>Existing facial image inpainting methods demonstrate high reliance on the precision of prior knowledge. However, the acquisition of precise prior knowledge remains challenging, and the incorporation of predicted prior knowledge in the restoration process often leads to error propagation and accumulation, thereby compromising the reconstruction quality. To address this limitation, we propose a novel facial image inpainting framework that leverages knowledge distillation, which is specifically designed to mitigate error propagation caused by imprecise prior knowledge. More specifically, we develop a teacher network incorporating accurate facial prior information and establish a knowledge transfer mechanism between the teacher and student networks via knowledge distillation. During the training phase, the student network progressively acquires the prior information encoded in the teacher network, thus improving its restoration capability for missing or corrupted regions. Additionally, we introduce a Coordinate Attention Gated Convolution (CAG) module, which enables effective extraction of both structural and semantic features from intact regions. Experiments conducted on the public facial datasets (CelebA-HQ and FFHQ) show that our method achieves performance improvements over existing approaches in terms of multiple quantitative evaluation metrics, including PSNR, SSIM, MAE, and LPIPS. Thus, the knowledge transfer from teacher to student network via knowledge distillation significantly reduces the dependence on prior knowledge characteristic of existing methods, facilitating more precise and efficient facial image inpainting.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/6897997","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145146935","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":"Deep Learning-Driven Assessment of Student Movement and Performance Using Physiological Data in Physical Education Information Systems: An S-AIoT Solution","authors":"Ping Liu, Elaheh Dastbaravardeh","doi":"10.1155/int/9479311","DOIUrl":"https://doi.org/10.1155/int/9479311","url":null,"abstract":"<p>This study bridges a crucial gap in athletic performance analysis by introducing a novel machine learning (ML) framework that leverages integrated physiological signals (from the DB 2.0 database) towards Sport Artificial Intelligence of Things (S-AIoT). Understanding athletic performance is key to developing effective training programs and enhancing overall physical education. However, traditional methods often fall short in capturing the nuances of human movement. Our primary goal is to develop an innovative method for accurately classifying sports activities using advanced analytical techniques that consider various physiological signals. This study aims to improve classification accuracy and provide real-time analytics for sports performance. To achieve this, we employ spatial and temporal attention mechanisms to dynamically weight critical signals, enabling precise tracking of movement transitions across different sports. The model is trained on comprehensive datasets comprising respiration rate, ECG, and heart rate (HR), providing a multifaceted analysis of athletic performance. Extensive experiments validate the model, which achieves a remarkable accuracy of 90.32%. It is the first model of its kind, outperforming established models like 1D convolutional neural network (CNN), LSTM, BiLSTM, and 1D CNN-BiLSTM. The model demonstrates strong generalization ability on unseen data, proving its effectiveness in diverse scenarios, and exhibits moderate noise resilience, enhancing its practical applicability.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/9479311","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145146934","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":"Time Series Forecasting Based on Multiscale Fusion Transformer in Finance","authors":"Guangxia Xu, Han Hu, Chuang Ma, Jiahui Li","doi":"10.1155/int/3890049","DOIUrl":"https://doi.org/10.1155/int/3890049","url":null,"abstract":"<p>Time series forecasting is significant in market research and decision-making in the financial sector, but the complexity and uncertainty of financial data pose challenges to accurate forecasting. Although deep learning methods, including transformers, have significantly improved the forecasting effect, these methods still have limitations in dealing with the multiscale features of financial time series and their complex serial correlation. They fail to fully utilize the frequency domain’s multiscale features and spatial relationships. For this situation, this study proposes a time series forecasting method based on the multiscale fusion transformer for financial data, which aims to extract significant periodic patterns using frequency domain analysis effectively. Besides, the multiscale attention mechanism and graph convolution module are introduced to realize the detailed modeling of the time series simultaneously, effectively capture the spatial relationship, and obtain the correlation between different series on multiple frequency scales. In this study, experimental validation is carried out on several financial time series datasets, and the findings demonstrate that the proposed approach positively impacts predicting accuracy.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/3890049","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145146373","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}
Jinjin Liu, Sa Xue, Xinyu Zhang, Fengyuan Xiang, Yuanyuan Ma
{"title":"Steganography Defense Network Based on Simulation of Steganography Information Distribution","authors":"Jinjin Liu, Sa Xue, Xinyu Zhang, Fengyuan Xiang, Yuanyuan Ma","doi":"10.1155/int/9958912","DOIUrl":"https://doi.org/10.1155/int/9958912","url":null,"abstract":"<p>In order to block the spread of illegal stego-image and reduce the erasing traces of steganography attacks on images, this paper proposes a steganography attack network based on simulation of steganography information distribution. First, a strategy of simulating steganography noise was adopted, and the distribution of steganography noise was learned by convolutional neural network, and a small amount of noise was added to the position of the secret message accurately to complete the attack on the steganography information, while protecting the image content to the maximum extent. In addition, different image recovery modules are designed in the deep network, such as the shallow feature extraction module, progressive attention recovery module, and detail feature reconstruction module, which collectively leverage hierarchical pixel features to mitigate discrepancies between reconstructed and original images while preserving visual fidelity before and after image attacks. Through two kinds of loss functions, the deep network model continuously optimizes the network performance to achieve the minimum degree of damage to the image content and the maximum degree of recovery of the reconstructed image. Experimental results show that the proposed method is superior to other methods in erasing secret message and restoring image quality.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/9958912","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145146302","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":"Cross-Object Transfer Learning-Based Few-Shot Surface Defect Detection of Lithium Batteries","authors":"Zhongsheng Chen, Bo Hu, Wang Zuo","doi":"10.1155/int/4904188","DOIUrl":"https://doi.org/10.1155/int/4904188","url":null,"abstract":"<p>Lithium batteries are one class of key components in new-energy vehicles, and surface defects are easily generated during production, causing serious threats to safety. Most deep learning methods of surface defect detection heavily rely on lots of high-quality labeled samples. Unfortunately, it is very difficult and expensive to prepare defect datasets of lithium batteries in practice. To deal with this issue, this paper presents cross-object transfer learning (COTL)–based few-shot surface defect detection of lithium batteries by resort to massive defect samples of other objects. The COTL model is composed of image preprocessing, feature extraction, feature fusion, and contrastive learning-based defect detection modules. The ResNeXt-101 network is used as the backbone to enhance feature extraction capability. The path aggregation feature pyramid network (PAFPN) is used to realize multiscale feature fusion. The contrastive learning branch is added to improve the discrimination ability among different categories of region proposals under few defect samples and increase the generalization ability. Then, experiments are done to testify the proposed method, where base-class defect dataset from other objects and new-class defect dataset from soft-pack lithium batteries are adopted for training and testing. Furthermore, model comparison and ablation studies are performed. The results show that the recall rate, the AP50, the mAP, and the F1 values of the COTL model are much better than those of other existing models when only using few defect samples. In particular, when there are only 30 new-class defect samples, the above four metrics of the COTL model are already larger than 0.90. The results testify that the proposed COTL model provides a more effective solution for few-shot surface defect detection of lithium batteries.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/4904188","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145146277","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":"Reliability Analysis Based on Aleatory and Epistemic Uncertainty Using Binary Decision Diagrams","authors":"Elena Zaitseva, Vitaly Levashenko","doi":"10.1155/int/6471577","DOIUrl":"https://doi.org/10.1155/int/6471577","url":null,"abstract":"<p>The development of a mathematical model is an important step in reliability analysis. However, initial data are often not clearly defined, and some necessary information about the system’s behavior may be missing. Most mathematical models in reliability analysis primarily address aleatory uncertainty. However, recently, many problems in reliability analysis increasingly need to take into consideration epistemic uncertainty. Therefore, methods for developing mathematical models based on uncertain initial data should be refined to account for both aleatory and epistemic uncertainties. This is particularly true for models that represent a system using binary decision diagrams (BDDs). This paper proposes a new method for constructing a system’s mathematical model in the form of a BDD based on incomplete and uncertain data. Machine learning approaches and principles are employed in this method to account for the epistemic uncertainty of the initial data. A fuzzy classifier, specifically a fuzzy decision tree (FDT), is used to build a BDD from epistemically uncertain data. The use of a tree-based classifier allows simplifying the transformation between FDT and BDD.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/6471577","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145146276","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":"Deepfake Detection in Image Sequences: A Temporal Approach for Anomaly Detection","authors":"Rongju Yao, Zhiqing Bai, Jing Tong, Khosro Rezaee","doi":"10.1155/int/8566328","DOIUrl":"https://doi.org/10.1155/int/8566328","url":null,"abstract":"<p>The rapid development of deepfake technology has led to the generation of a large amount of tampered video and image content, posing a major challenge to content authenticity verification. In particular, detecting deepfakes in image sequences (e.g., agricultural product packaging) is particularly difficult because the anomalies introduced by the tampering techniques are often subtle and temporally continuous. In this paper, we propose a new deepfake detection method based on time series, combining independent component analysis (FastICA) with anomaly detection techniques. We first apply FastICA to extract independent components from image sequences to identify anomalous visual patterns that are unique to deepfake tampering. In addition, we use an efficient anomaly detection algorithm, LSHiforest, to achieve scalable and accurate identification of suspicious sequences. Experimental results show that the proposed method can still detect deepfake content with high accuracy in challenging scenarios with complex temporal dynamics. Our work provides a promising solution for real-time and large-scale detection of deepfake content in dynamic media.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/8566328","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145111397","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":"IoT Intrusion Detection: Implementing a Dual-Layered Security Approach","authors":"Erdal Özdoğan, Onur Ceran, Mevlüt Uysal, Mutlu Tahsin Üstündağ","doi":"10.1155/int/8884584","DOIUrl":"https://doi.org/10.1155/int/8884584","url":null,"abstract":"<p>The proliferation of Internet of Things (IoT) devices has significantly increased the attack surface, making IoT security a critical concern. Traditional intrusion detection systems often fall short in addressing the complex and staged nature of IoT attacks. In this study, we propose a dual-layered intrusion detection system to enhance IoT security. The first layer employs the extreme gradient boosting algorithm to detect reconnaissance attacks, which are typically the initial stage of a multistage cyberattack. In the second layer, an artificial neural network is utilized to classify various IoT-specific attacks. Our model is evaluated using three benchmark datasets: UNSW-NB15, BoT-IoT, and IoT-ID20. The proposed model demonstrates a first-stage accuracy of 99.98%, sensitivity of 99.14%, and specificity of 94.47%. In the second stage, we achieved accuracy rates of 96.97%, 99.99%, and 98.70% across the datasets. This two-stage approach not only improves detection accuracy but also ensures early intervention by identifying reconnaissance attacks, thereby reducing the potential impact of subsequent attack stages. The primary objective of this model is to efficiently detect reconnaissance attacks with minimal resource consumption, thereby reducing the workload of the ANN model. Our findings underscore the importance of a staged defense mechanism in IoT networks, leveraging the strengths of different machine learning algorithms to provide robust security.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/8884584","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145111413","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}
Yuheng Li, Tinghao Wang, Ning Luo, Lijuan Zhou, Qian Chen
{"title":"CGMamba: Intelligent Identification of Counterfeit Goods Based on State Space Models","authors":"Yuheng Li, Tinghao Wang, Ning Luo, Lijuan Zhou, Qian Chen","doi":"10.1155/int/9939880","DOIUrl":"https://doi.org/10.1155/int/9939880","url":null,"abstract":"<p>The global economy and society are seriously threatened by the pervasive spread of counterfeit goods. Their high level of simulation makes real and fake goods extremely similar in appearance and difficult to distinguish. The existing identification techniques mostly use CNNs and transformer architectures. However, CNNs have limitations in modeling long-range dependencies, leading to their limited classification performance, while vision transformers (ViTs), although excellent in modeling long-range dependencies, the quadratic computational complexity of their self-attention mechanism makes it difficult to be widely used in real-world scenarios with limited computational resources. According to recent research, long-range relationships can be accurately modeled using the state space model (SSM), which is represented by Mamba, while preserving linear computational complexity. Motivated by this, we proposed CGMamba, a SSM-based intelligent recognition model for counterfeit goods. Specifically, we constructed a novel hybrid basic block called global-local feature aggregation (GLFA). This block greatly enhances the feature extraction capability for counterfeit goods by deeply integrating the local feature extraction capability of the CNN and the global modeling capability of SSM. It is composed of three components: a local feature extractor, a global feature extractor, and an adaptive feature aggregation module (AFAM). In addition, to address the problem of lack of counterfeit goods image data, we constructed a large counterfeit goods dataset containing 101,480 images covering 104 categories for model training and evaluation. The experimental results showed that CGMamba achieved 90.99% Top 1 accuracy on the self-constructed dataset and 79.5% on the public dataset CNFOOD-241, which significantly outperforms the existing methods. The source code is available at https://github.com/wth1998/CGMamba.git.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/9939880","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145101093","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}
Hua Wang, Yongjie Cui, Lianhua Wang, Yuhong Sun, Chuyan Wang
{"title":"A Blockchain-Based Certificateless Anonymous Cross-Domain Authentication Scheme for IoV","authors":"Hua Wang, Yongjie Cui, Lianhua Wang, Yuhong Sun, Chuyan Wang","doi":"10.1155/int/1782136","DOIUrl":"https://doi.org/10.1155/int/1782136","url":null,"abstract":"<p>As an essential component of the internet of things, the internet of vehicles (IoV) holds broad application prospects in areas such as safe driving, intelligent transportation, and service reservations. Due to the security and privacy requirements, anonymous authentication schemes are widely used in IoV. However, traditional certificate-based anonymous authentication schemes suffer from several drawbacks such as poor scalability and high management costs of certificates. Furthermore, centralized authentication architectures are susceptible to a single point of failure. To this end, we propose a blockchain-based certificateless anonymous cross-domain authentication (BCACA) scheme for IoV. In this scheme, we adapt a network model with multiple domain managers (DMs) based on blockchain, in which DMs establish distributed trust within the network and act as miners to upload vehicle registration and authentication transactions to the blockchain, assisting in cross-domain authentication. Based on this framework, a certificateless signature scheme is designed, which supports authentication across different domains without the need for complex certificate exchange mechanisms. In addition, this scheme provides an identity revocation mechanism encompassing both intradomain and cross-domain scenarios to ensure the security and reliability of the IoV. Security proofs demonstrate that the scheme is provably secure under the random oracle model and exhibits strong resistance against known attacks. Performance analysis indicates that the proposed scheme has lower computational overhead and transmission delay compared to other relevant schemes.</p>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":3.7,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/1782136","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145058090","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}