检索结果-内蒙古大学图书馆

A Novel Lightweight IoT Intrusion Detection Model Based on Self-knowledge Distillation

IEEE Internet of Things Journal 2025年第11期12卷 16912-16930页

作者： Wang, Zhendong Zhou, Renqiang Yang, Shuxin He, Daojing Chan, Sammy Jiangxi University of Science and Technology School of Information Engineering Ganzhou341000 China Nanchang University Software Engineering Institute Nanchang330047 China Harbin Institute of Technology School of Computer Science and Technology Shenzhen518055 China City University of Hong Kong Department of Electrical Engineering Hong Kong

The Internet of Things (IoT) environment contains many different types of devices, each with different functionalities, communication protocols, and security capabilities, which makes the IoT a complex challenge for security protection. Therefore, network intrusion detection (NID) is needed to detect intrusions in the network to secure the IoT. In recent years, deep learning-based intrusion detection systems have achieved excellent results, but they tend to require high computational resources and storage space, which is not feasible for most IoT devices. In this paper, we propose a lightweight intrusion detection model based on self-knowledge distillation, namely TBCLNN, which improves the detection accuracy while also reducing the number of model parameters and computational cost. Specifically, we use the binary Harris Hawk optimization algorithm for dimensionality reduction of traffic features. We use lightweight convolution, such as Tied Block Convolution (TBC), to design lightweight neural network models with residual and inverse residual structures. Moreover, we propose an improved self-knowledge distillation loss function to solve the sample imbalance problem and compensate for the performance degradation caused by lightweight neural networks. The multiclassification accuracy of our proposed method exceeds 99% on all three publicly available IoT datasets. The experimental results show that our method has a small model size and requires only low computational resources, making it suitable for resource-constrained IoT intrusion detection. © 2014 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

RF-Based Sensing and AI Decision Support for Stroke Patient Monitoring: A Digital Twin Approach

引用

IEEE Access 2025年 13卷 74047-74061页

作者： Khan, Sagheer Anwar, Usman Khan, Aftab Arslan, Tughrul The University of Edinburgh School of Engineering EdinburghEH9 3FF United Kingdom Department of Computer and Software Engineering CoEME Islamabad44000 Pakistan Allama Iqbal Open University Department of Computer Science Islamabad44310 Pakistan

Stroke occurs when the blood flow to a certain region of the brain is disrupted. It is a leading cause of long-term disability and can result in cognitive impairments, speech difficulties, and motor dysfunction. Regular monitoring and timely intervention are critical to minimizing the damage and improving outcomes. This article presents a novel Radio Frequency (RF) sensing and Artificial Intelligence (AI) based Digital Twin (DT) model for effective detection of stroke. Through backscattering RF signals, the proposed Ultra Wide Band (UWB) antenna provides stroke detection. The implementation of Machine Learning (ML) and Deep Learning (DL) technologies for stroke classification provides the necessary decision support to healthcare professionals in DT stroke patient monitoring. The statistical and autonomous (AutoEncoders (AE) and Stacked AutoEncoders (SAE) with structure 32-16-32, 64-32-16-32-64, and 128-64-32-16-32-64-128) feature data is enlarged through Gaussian noise feature data augmentation. The Fine KNN algorithm provides the 93.4% and 92.3% classification accuracies of binary and multi-class classification respectively. Out of the 4 autonomous feature extraction methods, the Fine KNN algorithm with SAE structure 64-32-16-32-64 provided the highest accuracies of 88.2% and 74.8% for binary and multi-class classification. © 2013 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Parkinson’s Disease Detection from Resting State EEG Using Multi-head Graph Structure Learning with Gradient Weighted Graph Attention Explanations 7th

Parkinson’s Disease Detection from Resting State EEG Using...

引用

7th International Workshop on Machine Learning in Clinical Neuroimaging, MLCN 2024, Held in Conjunction with 27th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2024

作者： Neves, Christopher Zeng, Yong Xiao, Yiming Department of Computer Science and Software Engineering Concordia University MontrealQC Canada Concordia Institute for Information Systems Engineering Concordia University MontrealQC Canada

ISBN: (纸本)9783031787607

Parkinson’s disease (PD) is a debilitating neurodegenerative disease that has severe impacts on an individual’s quality of life. Compared with structural and functional MRI-based biomarkers for the disease, electroencephalography (EEG) can provide more accessible alternatives for clinical insights. While deep learning (DL) techniques have provided excellent outcomes, many techniques fail to model spatial information and dynamic brain connectivity, and face challenges in robust feature learning, limited data sizes, and poor explainability. To address these issues, we proposed a novel graph neural network (GNN) technique for explainable PD detection using resting state EEG. Specifically, we employ structured global convolutions with contrastive learning to better model complex features with limited data, a novel multi-head graph structure learner to capture the non-Euclidean structure of EEG data, and a head-wise gradient-weighted graph attention explainer to offer neural connectivity insights. We developed and evaluated our method using the UC San Diego Parkinson’s disease EEG dataset, and achieved 69.40% detection accuracy in subject-wise leave-one-out cross-validation while generating intuitive explanations for the learnt graph topology. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

CLS-3D: Content-Wise LiDAR-Camera Fusion and Slot Reweighting Transformer for 3D Object Detection in Autonomous Vehicles

引用

IEEE Access 2025年 13卷 69840-69856页

作者： Mushtaq, Husnain Latif, Sohaib Saad Bin Ilyas, Muhammad Mohsin, Syed Muhammad Ali, Mohammed Central South University School of Computer Science and Engineering Changsha410083 China Grand Asian University Department of Computer Science and Software Engineering Sialkot51040 Pakistan The University of Chenab Department of Computer Science Gujranwala50700 Pakistan COMSATS University Islamabad Department of Computer Science Islamabad45550 Pakistan Virtual University of Pakistan Standard College of Modern Sciences Lahore55150 Pakistan King Khalid University Department of Computer Science Abha61421 Saudi Arabia Abha61421 Saudi Arabia

Accurate 3D object detection is vital in autonomous driving. Single-modal detectors, using either camera or LiDAR, struggle with issues like limited depth perception or difficulty in distinguishing semantically similar objects. While multimodal approaches aim to address these limitations by combining LiDAR and camera data, they often face complexities in integrating sparse and uneven point cloud distributions, resulting in inefficient feature fusion. To tackle these challenges, we propose CLS-3D (Content-wise LiDAR-Camera Fusion and Slot Reweighting Transformer for 3D Object Detection). This novel framework fuses LiDAR and camera features using a single multi-modal backbone and augments them with the semantic probabilities obtained from the image stream. Our method captures local and global spatial relationships through a slot reweighting mechanism and incorporates I3C-IoU loss for precise box regression. The semantically augmented features, via a single multi-modal backbone, are embedded using a content-based transformer and processed through a slot-wise auto-encoder structure with channel-wise positional embeddings and a feed-forward MLP network. Our model improves temporal consistency and detection accuracy by dynamically adjusting feature relevance through slot-wise reweighting. We further define a I3C-IoU metric, considering centre, overlap, and scale for enhanced box regression accuracy. This mechanism allows the model to focus on significant temporal information, enhancing its ability to learn complex sequences and improving the overall performance of 3D object detection, especially in challenging scenarios such as occlusion and long-range detection. Extensive experiments on the KITTI and nuScenes benchmark demonstrate that CLS-3D achieves state-of-the-art performance, with 89.52% 3D mAP and 94.08% BEV mAP, outperforming existing methods. © 2013 IEEE.

关键词： Depth perception

来源：评论

学校读者我要写书评

暂无评论

Early Diabetic Retinopathy Cyber-Physical Detection System Using Attention-Guided Deep CNN Fusion

引用

IEEE Transactions on Network Science and engineering 2025年第3期12卷 1898-1910页

作者： Hossain, M. Shamim Shorfuzzaman, Mohammad King Saud University Research Chair of Pervasive and Mobile Computing Department of Software Engineering College of Computer and Information Sciences Riyadh12372 Saudi Arabia Taif University Department of Computer Science College of Computers and Information Technology Taif21944 Saudi Arabia

Diabetic retinopathy is the most common and severe eye complication of diabetes, and it can cause vision loss or even blindness due to retina damage. Automatic and faster detection of various DR stages is crucial and can benefit both patients and ophthalmologists. With the ubiquity of measurement devices and growing processing power, cyber-physical characterization is becoming an enabler technology in many disciplines. This paper proposes a cyber-physical system (CPS) framework that will aid clinicians in establishing an early diagnosis of DR. Particularly;we present a component-based CPS architecture to use a deep learning-based predictive model deployed on the cloud for effective DR diagnosis and incorporate medical devices. To this end, a deep learning-based explainable CNN fusion model has been introduced in the proposed framework for automatic screening and interpretation of DR stages using digital fundus images. We extract salient features using various fine-tuned CNN models in conjunction with an attention network, and we use a locally connected layer to calculate the weighted contribution of these networks. We measure the performance of our approach using a public dataset comprising fundus images of five different categories. Experimental results demonstrate the proposed approach's effectiveness for faster and more accurate detection of various DR stages. © 2013 IEEE.

关键词： Biomedical equipment

来源：评论

学校读者我要写书评

暂无评论

SLwF: A Split Learning Without Forgetting Framework for Internet of Things

引用

IEEE Internet of Things Journal 2025年第9期12卷 12008-12020页

作者： Feng, Xingyu Jia, Renqi Luo, Chengwen Leung, Victor C. M. Xu, Weitao School of Information Engineering Beijing100190 China City University of Hong Kong Shenzhen Research Institute Hong Kong Hong Kong City University of Hong Kong Department of Computer Science Hong Kong Hong Kong Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

Split learning (SL) is widely regarded as a promising distributed machine learning framework with superior privacy-preserving properties, lower communication and computation costs. However, in real Internet of Things (IoT) scenarios, existing SL may not perform well because the local data of IoT devices often do not follow the same distribution. This leads to the model continuously adapting to the current data distribution in each training epoch, resulting in a catastrophic forgetting phenomenon. Existing methods typically attempt to add raw or generated data from previous devices in the current training epoch to review knowledge, but direct access to the local data of other devices carries serious privacy risks. Data augmentation techniques based on generative networks often have poor robustness and increase the computation cost on the device side. To address these challenges, we propose a new SL framework called SL without Forgetting (SLwF). To mitigate catastrophic forgetting without accessing any previous data, we propose a contrastive learning-based training method that leverages current training data to review previous knowledge, and learn new knowledge better. Furthermore, we adopt an exponential moving average (EMA)-based model update strategy to preserve lost knowledge, further alleviating the forgetting problem. We implement the SLwF framework in real IoT scenarios and extensively evaluated its performance using four publicly available datasets. Compared to other related research (e.g., IoTSL), SLwF performs better in terms of final accuracy and robustness while avoiding excessive device energy consumption. © 2014 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Evaluating machine learning and statistical learning techniques for cancer classification and diagnosis

引用

Iran Journal of computer Science 2025年 1-20页

作者： Alwazy, Asmaa Salim Hussaien Buyrukoğlu, Gonca Buyrukoğlu, Selim Baker, Mohammed Rashad Department of Electronics and Computer Engineering Çankırı Karatekin University Çankırı 18100 Türkiye Department of Statistics Çankırı Karatekin University Çankırı 18100 Türkiye Department of Computer Engineering Çankırı Karatekin University Çankırı 18100 Türkiye Department of Software Engineering University of Kirkuk Kirkuk Iraq

Accurate cancer diagnosis is critical for effective treatment and positive patient outcomes. This study investigates the robustness of machine learning (ML) and statistical learning (SL) algorithms in classifying and diagnosing lung, prostate, breast, and heart disease. We evaluated and compared the performance of several algorithms, including support vector classifier (SVC), random forest (RF), XGBoost, decision tree (DT), elastic net, Lasso, and ridge, using four medical data sets. Multiple metrics, such as accuracy, precision, recall, F1-score, and area under the curve (AUC), are used to assess the performance. Hyperparameter tuning is conducted using GridSearchCV. The results demonstrated that RF and SVC achieved near-perfect accuracy (up to 98%) and AUC scores (1.00) in distinguishing between benign and malignant lung and breast cancer samples. SL algorithms exhibited robust and consistent performance for prostate cancer, achieving accuracy, precision, recall, and F1-scores of approximately 90%, making them suitable for data sets with smaller sample sizes. However, SVC-based ML algorithms outperformed SL methods in overall accuracy for prostate cancer, although SL methods provided a stable baseline. For heart disease, SVC achieved the highest accuracy (82%), while regularized SL models such as Elastic Net and Lasso performed similarly, with an accuracy of 80%. This study highlights the importance of selecting algorithms tailored to the data set’s characteristics and the specific diagnostic requirements. It also underscores the complementary strengths of ML and SL approaches, suggesting that an integrated strategy may offer the most effective solution. The findings contribute to the growing evidence supporting integrating computational methods into clinical practice to enhance diagnostic accuracy and improve patient care. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Cancer classification Data mining Diagnosis Machine learning algorithms Statistical learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Fingerprint Matching for Noisy and Distorted Patterns using a Siamese Network with ResNet50 and Multihead Attention

引用

IEEE Access 2025年 13卷 88047-88064页

作者： Sawhney, Tinny Sharma, Ashu Abrol, Pawanesh Lehana, Parveen Kumar Chaahat Yadav, Vaishali Scherer, Rafal Kulakov, Oleksii AlZubi, Ahmad Ali University of Jammu DSP Lab Department of Electronics India University of Jammu Department of Computer Science and IT India Chitkara University Institute of Engineering and Technology Chitkara University Department of Computer Science and Engineering Punjab India Manipal University Jaipur Jaipur India Czestochowa University of Technology Department of Artificial Intelligence Częstochowa Poland National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute" Faculty of Informatics and Software Engineering Kyiv Ukraine King Saud University Community College Department of Computer Science Riyadh Saudi Arabia

Dermatoglyphics, the study of unique ridge patterns on fingertips, plays a crucial role in fingerprint-based identification. However, skin conditions such as psoriasis, eczema, and verruca vulgaris can distort these patterns. This distortion creates challenges for fingerprint matching systems in forensic science and biometric authentication. This paper proposes a Siamese network with a modified ResNet50 architecture and multihead attention mechanisms to improve fingerprint matching under such distortions. The Siamese network enables the system to compare fingerprint pairs effectively, even under distortions. The modified ResNet50 architecture captures intricate ridge patterns, while the multihead attention mechanisms focus on critical fingerprint regions. Overall, the proposed approach enhances the system’s ability to learn discriminative features. As a result, it can effectively differentiate between matched and unmatched fingerprint pairs, even in the presence of moderate to extreme noise. The proposed system was trained on the Sokoto coventry fingerprint dataset (SOCOFing) and a custom dataset. Experimental results demonstrate high accuracy, with the system achieving 99.47% accuracy under low noise conditions and 90% under moderate noise. However, performance declined to 55.56% under extreme distortions. A comparative analysis highlighted the superiority of the proposed system over widely used minutiae-based methods. The latter exhibited a significant drop in matching scores, falling below 15% for highly distorted fingerprints. These findings underscore the limitations of traditional fingerprint recognition techniques and highlight the effectiveness of proposed approach in handling dermatoglyphic distortions. © 2013 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Deep domain adaptation by joint distribution neural matching

引用

Neural Computing and Applications 2025年 1-21页

作者： Hong, Zijie Chen, Sentao Wen, Lisheng Yang, Xiaowei School of Software Engineering South China University of Technology Panyu District Guangdong Guangzhou510006 China Department of Computer Science Shantou University Daxue Road Guangdong Shantou515063 China

Domain adaptation aims to learn a prediction model that performs well in a target domain with unlabeled data by harnessing the distributionally different labeled data from a source domain. In this paper, we design a simple yet powerful neural network approach named joint distribution neural matching (JOINT) to address the challenge of joint distribution difference/mismatch in domain adaptation. Our JOINT approach matches the source joint distribution and the target one in the activation space of a neural network by minimizing an estimate of the Jensen–Shannon (JS) divergence between the two joint distributions. The estimated JS divergence is derived in an explicit form, which frees our approach from solving a minimax adversarial problem when matching the distributions. Experiments on four representative large-scale visual recognition datasets show that our JOINT approach outperforms the state-of-the-art under both unsupervised and semi-supervised domain adaptation settings. Our code will be available at https://***/TitanRisen/JOINT-CODE. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of text mining and clustering techniques for assessing functional dependency between manual test cases

引用

software Quality Journal 2025年第2期33卷 1-36页

作者： Tahvili, Sahar Hatvani, Leo Felderer, Michael de Oliveira Neto, Francisco Gomes Afzal, Wasif Feldt, Robert Compute Platforms Engineering Unit Ericsson AB Stockholm Sweden Department of Industrial AI Systems Mälardalen University Västerås Sweden Institute of Software Technology German Aerospace Center Cologne Germany Department of Mathematics and Computer Science University of Cologne Cologne Germany Department of Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden Department of Computer Science and Engineering Blekinge Institute of Technology Karlskrona Sweden Department of Computer Science and Engineering University of Gothenburg Gothenburg Sweden

Text mining techniques, particularly those leveraging machine learning for natural language processing, have gained significant attention for qualitative data analysis in software testing. However, their complexity and lack of transparency can pose challenges, especially in safety-critical domains where simpler, interpretable solutions are often preferred unless accuracy is heavily compromised. This study investigates the trade-offs between complexity, effort, accuracy, and utility in text mining and clustering techniques, focusing on their application for detecting functional dependencies among manual integration test cases in safety-critical systems. Using empirical data from an industrial testing project at ALSTOM Sweden, we evaluate various string distance methods, NCD compressors, and machine learning approaches. The results highlight the impact of preprocessing techniques, such as tokenization, and intrinsic factors, such as text length, on algorithm performance. Findings demonstrate how text mining and clustering can be optimized for safety-critical contexts, offering actionable insights for researchers and practitioners aiming to balance simplicity and effectiveness in their testing workflows. © The Author(s) 2025.

关键词： Artificial intelligence Clustering Natural language processing software testing Text mining

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：