检索结果-内蒙古大学图书馆

Intrusion Detection in IoT Networks Using Dynamic Graph modeling and Graph-Based Neural Networks

IEEE ACCESS 2025年 13卷 65356-65375页

作者： Villegas-Ch, William Govea, Jaime Navarro, Alexandra Maldonado Jativa, Pablo Palacios Univ Las Amer Escuela Ingn Cibersegur FICA Quito 170125 Ecuador Univ Las Amer Escuela Postgrad Derecho Quito 170125 Ecuador Univ Diego Portales Escuela Informat & Telecomunicac Santiago 8370191 Chile

The rapid expansion of Internet of Things (IoT) networks has significantly increased security vulnerabilities, exposing critical infrastructures to sophisticated cyberattacks. Traditional Intrusion Detection Systems, based mainly on signature matching and predefined rules, present limitations in identifying emerging threats and distributed attacks due to their inability to analyze complex interactions within IoT networks. To address this problem, this study proposes a graph-based intrusion detection model using Graph Neural Networks (GNNs), leveraging a dynamic representation of IoT network traffic. In this model, devices are represented as nodes and communications as weighted edges, integrating features such as communication frequency, transmitted data volume, and protocol type. The proposed method was evaluated using a customized dataset from a simulated IoT network to reflect real-world attack scenarios, including Denial of Service, Spoofing, and Man-in-the-Middle. Experimental results demonstrate that our GNN-based model significantly outperforms traditional machine learning methods, achieving an F1-Score of 0.95 and an AUC-ROC of 0.98, compared to values between 0.84 and 0.91 for Support Vector Machines and Random Forests. Furthermore, the system reduces the false positive rate by 40% compared to signature-based IDS, improving its applicability in operational environments. The model also proved scalable, maintaining an inference time of 2.5 ms per sample on graphs of up to 10,000 nodes, making it viable for real-time deployment. These findings confirm that graph-based anomaly detection is a promising approach for securing large-scale IoT infrastructures, providing increased precision, adaptability, and robustness against emerging cyber threats.

关键词： Adaptation models Intrusion detection Internet of Things Telecommunication traffic Real-time systems Image edge detection computational modeling Protocols Feature extraction Anomaly detection Graph neural networks (GNNs) intrusion detection in IoT graph-based anomaly detection cybersecurity in IoT networks

来源：评论

学校读者我要写书评

暂无评论

EMIKNet: Expanding Multiple-Instance Inverse Kinematics Network for Multiple End-Effector and Multiple Solutions

引用

IEEE ACCESS 2025年 13卷 25087-25096页

作者： Go, Youn-Jae Moon, Jun Hanyang Univ Dept Artificial Intelligence Seoul 04763 South Korea

Inverse Kinematics (IK) is essential for robot control but suffers from computational complexity as the number of links and end-effectors increases, thereby affecting real-time control accuracy and performance. In this letter, we propose a neural network-based IK approach to efficiently address the IK challenges in complex robotic systems with multiple end-effectors and methods for obtaining multiple solutions. The proposed method is constructed via interconnected Gaussian Mixture Models (GMM), which consist of two main components: (i) a hierarchical computation framework for calculating joint angles while considering joint limits, and (ii) a 'sub-link' concept to reduce the hierarchical computation. The experimental results of 7-Degrees of Freedom (DOF) robot arm manipulator with a single end-effector and 22-DOF robot arm-hand manipulator with multiple end-effectors show that the proposed method reduces both Euclidean Distance and Angular Distance as well as the Run-time, compared with the model-based numerical and earlier neural network methods. We also verify multiple solutions obtained through hierarchical computation of GMM.

关键词： End effectors Robots Robot kinematics computational modeling Numerical models Neural networks Gaussian distribution Accuracy Motion capture Collision avoidance Deep learning methods kinematics motion control

来源：评论

学校读者我要写书评

暂无评论

The Physiome Project and Digital Twins

引用

IEEE REVIEWS IN BIOMEDICAL ENGINEERING 2025年 18卷 300-315页

作者： Hunter, P. de Bono, B. Brooks, D. Christie, R. Hussan, J. Lin, M. Nickerson, D. Univ Auckland Auckland Bioengn Inst Auckland 1010 New Zealand

Interest in the concept of a virtual human model that can encompass human physiology and anatomy on a biophysical (mechanistic) basis, and can assist with the clinical diagnosis and treatment of disease, appears to be growing rapidly around the globe. When such models are personalised and coupled with continual diagnostic measurements, they are called 'digital twins'. We argue here that the most useful form of virtual human model will be one that is constrained by the laws of physics, contains a comprehensive knowledge graph of all human physiology and anatomy, is multiscale in the sense of linking systems physiology down to protein function, and can to some extent be personalized and linked directly with clinical records. We discuss current progress from the IUPS Physiome Project and the requirements for a framework to achieve such a model.

关键词： Physiology Biological system modeling computational modeling Biological systems Standards Proteins Digital twins Predictive models Mathematical models Kidney Bioengineering bond graphs digital twins finite element scaffolds multiscale modeling physiome virtual human

来源：评论

学校读者我要写书评

暂无评论

Research on Parameter-Efficient Knowledge Graph Completion Methods and Their Performance in the Cybersecurity Field

引用

IEEE ACCESS 2025年 13卷 22998-23012页

作者： Chen, Bin Li, Hongyi Shi, Ze Beihang Univ Sch Cyber Sci & Technol Beijing 100191 Peoples R China Chongqing Technol & Business Univ Sch Artificial Intelligence Chongqing 400067 Peoples R China

As an advanced knowledge management and reasoning tool, knowledge graph technology can significantly enhance the efficiency of managing and analyzing cyberthreat intelligence, providing strong technical support for cybersecurity threat identification and situational awareness. This paper proposes a multi-level graph clustering-based model for completing cyberthreat intelligence knowledge graphs (GCCKG). The model utilizes a multi-level graph clustering approach to divide the knowledge graph into communities and selects a portion of high-degree entities within each community as the reserved entities. Additionally, we propose a path-enhanced cosine similarity measurement method to measure the similarity between entities, and a graph attention network is employed to iteratively update the embeddings of entities and relations, capturing key information in the graph-structured data. Experimental results demonstrate that the proposed GCCKG model significantly improves evaluation values such as MRR and Hits@K in knowledge graph completion tasks on several general domain knowledge graphs, including FB15K, WN18, FB15K-237, as well as the cyberthreat intelligence knowledge graph CS13K, while also significantly reducing the model's parameter size. This provides a novel solution for knowledge graph completion in the field of cyberthreat intelligence.

关键词： Knowledge graphs Computer security Cognition Semantics computational modeling Accuracy Ontologies Data models Vectors Tail cybersecurity cyberthreat intelligence knowledge graph completion

来源：评论

学校读者我要写书评

暂无评论

Parameter Interpolation Adversarial Training for Robust Image Classification

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2025年 20卷 1613-1623页

作者： Liu, Xin Yang, Yichen He, Kun Hopcroft, John E. Huazhong Univ Sci & Technol Sch Comp Sci & Technol Wuhan 430074 Peoples R China Cornell Univ Comp Sci Dept Ithaca NY 14853 USA

Though deep neural networks exhibit superior performance on various tasks, they are still plagued by adversarial examples. Adversarial training has been demonstrated to be the most effective method to defend against adversarial attacks. However, existing adversarial training methods show that the model robustness has apparent oscillations and overfitting issues in the training process, degrading the defense efficacy. To address these issues, we propose a novel framework called Parameter Interpolation Adversarial Training (PIAT). PIAT tunes the model parameters between each epoch by interpolating the parameters of the previous and current epochs. It makes the decision boundary of model change more moderate and alleviates the overfitting issue, helping the model converge better and achieving higher model robustness. In addition, we suggest using the Normalized Mean Square Error (NMSE) to further improve the robustness by aligning the relative magnitude of logits between clean and adversarial examples rather than the absolute magnitude. Extensive experiments conducted on several benchmark datasets demonstrate that our framework could prominently improve the robustness of both Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs).

关键词： Training Robustness Overfitting computational modeling Oscillators Interpolation Accuracy Perturbation methods Mean square error methods Optimization Adversarial examples adversarial training parameter interpolation normalized mean square error

来源：评论

学校读者我要写书评

暂无评论

Binarized Neural Networks for Resource-Efficient Spike Sorting

引用

IEEE ACCESS 2025年 13卷 60258-60269页

作者： Meyer, Luca M. Zamani, Majid Demosthenous, Andreas Univ Southampton Sch Elect & Comp Sci Southampton SO17 1BJ England UCL Dept Elect & Elect Engn London WC1E 7JE England

Deep learning is fastly gaining ground in neuroscience. In the field of implantable brain computer interfaces, a fundamental application of deep learning is to sort action potentials (known as spikes), measured with extracellular electrodes, according to their origin neurons. This enables the generation of precise modulatory patterns of neuronal circuits. Deep learning-based spike sorting algorithms are based on power-intensive dot products, which poses challenges for on-chip processing with resource-constrained devices. In contrast, binarized neural networks offer great potential for on-chip sorting, mainly relying on bitwise operations and accumulations. However, recently published binarized models perform significantly worse than deep full-precision networks and fail on challenging neural data. This work presents a binarized neural network for spike sorting that narrows the performance gap between recently developed binarized models and more accurate full-precision models. The novelty of this work resides in the developed network architecture. In comparison to previous research, this work presents a deep binarized neural network featuring two hidden layers, each containing 256 units to effectively capture the spike characteristics of complex neural data. Before training, spikes were pre-sorted in an unsupervised way to generate pseudo-labels. Subsequently, the deep binarized model and an equally sized full-precision model were trained and evaluated using experimentally obtained and synthetic spike waveforms. The proposed binarized model could achieve results close to more advanced network types, such as convolutional and long short-term memory networks, which is remarkable considering that the binarized model was primarily designed to maintain a balance between resource consumption and accuracy. The equally sized full-precision model could even outperform the aforementioned models, despite its much lighter architecture.

关键词： Sorting Recording Data models Neurons Accuracy System-on-chip computational modeling Biological neural networks Deep learning Feature extraction Binarized neural network deep learning implantable brain computer interfaces neural spike classification signal processing spike sorting

来源：评论

学校读者我要写书评

暂无评论

COST CA20120 INTERACT Framework of Artificial Intelligence-Based Channel modeling

引用

IEEE WIRELESS COMMUNICATIONS 2025年

作者： He, Ruisi Cicco, Nicola D. Ai, Bo Yang, Mi Miao, Yang Boban, Mate Beijing Jiaotong Univ Beijing Peoples R China Politecn Milan Milan Italy Univ Twente Enschede Netherlands Huawei Technol Duesseldorf GmbH Dusseldorf Germany

Accurate channel models are the prerequisite for communication-theoretic investigations as well as system design. Channel modeling generally relies on statistical and deterministic approaches. However, there are still significant limits for the traditional modeling methods in terms of accuracy, generalization ability, and computational complexity. The fundamental reason is that establishing a quantified and accurate mapping between the physical environment and channel characteristics becomes increasingly challenging for modern communication systems. Here, in the context of COST CA20120 Action, we evaluate and discuss the feasibility and implementation of using artificial intelligence (AI) for channel modeling, and explore where the future of this field lies. Firstly, we present a framework of AI-based channel modeling to characterize complex wireless channels. Then, we highlight in detail some major challenges and present the possible solutions: estimating the uncertainty of AI-based channel predictions;integrating prior knowledge of propagation to improve generalization capabilities;and interpretable AI for channel modeling. We present and discuss numerical results to showcase the capabilities of AI-based channel modeling.

关键词： Predictive models Artificial intelligence Data models computational modeling Accuracy Uncertainty Costs Channel models Atmospheric modeling Numerical models

来源：评论

学校读者我要写书评

暂无评论

DOA Estimation by Feature Extraction Based on Parallel Deep Neural Networks and MRMR Feature Selection Algorithm

引用

IEEE ACCESS 2025年 13卷 40480-40502页

作者： Al-Tameemi, Ashwaq Neaman Hassan Feghhi, Mahmood Mohassel Tazehkand, Behzad Mozaffari Univ Tabriz Fac Elect & Comp Engn Tabriz *** Iran

An active research topic in the array signal processing field is the direction of arrival (DOA) estimation, where establishing an efficient estimation of radio waves received from an antenna array is of great interest. Recent studies mostly focus on deep neural network (DNN) algorithms to improve the performance of DOA estimation in mmWave communication systems. These studies did not give importance to the diversity of features extracted from the data and the relationship between them, which affects the efficiency of DOA estimation. To improve the performance, we propose a new model for DOA estimation based on a parallel deep neural network (PDNN). It efficiently extracts spatial and temporal features, then fuses them and selects the distinct ones while removing the redundant ones. In parallel, the proposed model extracts spatial and temporal features using a convolution neural network (CNN) and long short-term memory (LSTM). Combining spatial and temporal features increases efficiency due to feature diversity. Then, a minimum redundancy and maximum relevance (MRMR) algorithm is proposed to select the distinct features. The performance of the proposed model is evaluated by conducting a wide range of experiments on uncorrelated narrowband data with different scenarios and based on the root mean square error (RMSE) coefficient. The results by computer simulations on a uniform linear array show that the proposed structure significantly increases the accuracy of DOA estimation and is more robust to changes in input parameters than traditional algorithms, such as estimation of signal parameters via invariant rotation (ESPRIT), classification of multiple signals (MUSIC), and DNN method. These results demonstrate the superiority of the proposed PDNN model over other techniques, especially in terms of accuracy.

关键词： Direction-of-arrival estimation Estimation Feature extraction Artificial neural networks Accuracy Antenna arrays Arrays Long short term memory Data models computational modeling Signal processing parallel deep neural network uniform linear array CNN LSTM MRMR mmWave

来源：评论

学校读者我要写书评

暂无评论

Clip-Driven Universal Model for Multi-Material Decomposition in Dual-Energy CT

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING

引用

IEEE TRANSACTIONS ON computational IMAGING 2025年 11卷 349-361页

作者： Wang, Xianghong Xiang, Jiajun Mao, Aihua Xie, Jiayi Jin, Peng Ding, Mingchao Yuan, Yixuan Lu, Yanye Yu, Lequan Cai, Hongmin Lei, Baiying Niu, Tianye Shenzhen Bay Lab Shenzhen 518067 Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510641 Peoples R China Peking Univ Third Hosp Beijing Key Lab Magnet Resonance Imaging Devices & Beijing 510641 Peoples R China Peking Univ Aerosp Ctr Hosp Aerosp Sch Clin Med Dept Myxomatol Beijing 100049 Peoples R China Chinese Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China Peking Univ Hlth Sci Ctr Inst Med Technol Beijing 100191 Peoples R China Peking Univ Shenzhen Grad Sch Inst Biomed Engn Shenzhen 518055 Peoples R China Univ Hong Kong Dept Stat & Actuarial Sci Hong Kong Peoples R China Shenzhen Univ Sch Biomed Engn Guangdong Key Lab Biomed Measurements & Ultrasound Shenzhen 518060 Peoples R China Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230026 Peoples R China

Dual-energy computed tomography (DECT) offers quantitative insights and facilitates material decomposition, aiding in precise diagnosis and treatment planning. However, existing methods for material decomposition, often tailored to specific material types, need more generalizability and increase computational load with each additional material. We propose a CLIP-Driven Universal Model for adaptive Multi-Material Decomposition (MMD) to tackle this challenge. This model utilizes the semantic capabilities of text embeddings from Contrastive Language-Image Pre-training (CLIP), allowing a single network to manage structured feature embedding for multiple materials. A novel Siamese encoder and differential map fusion technique have also been integrated to enhance the decomposition accuracy while maintaining robustness across various conditions. Experiments on the simulated and physical patient studies have evidenced our model's superiority over traditional methods. Notably, it has significantly improved the Dice Similarity Coefficient-4.1%. These results underscore the potential of our network in clinical MMD applications, suggesting a promising avenue for enhancing DECT imaging analysis.

关键词： Computed tomography Imaging Semantics Decoding Adaptation models Feature extraction Computer architecture Image reconstruction Data models computational modeling Dual-energy multi-material decomposition image-domain CLIP-driven siamese encoder

来源：评论

学校读者我要写书评

暂无评论

Score Predictor-Assisted Evolutionary Neural Architecture Search

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN computational INTELLIGENCE 2025年

作者： Jiang, Pengcheng Xue, Yu Neri, Ferrante Nanjing Univ Informat Sci & Technol Sch Software Nanjing 210044 Jiangsu Peoples R China Univ Surrey Sch Comp Sci & Elect Engn NICE Grp Guildford GU2 7XH England

Evolutionary neural architecture search (ENAS) treats neural network design as an optimisation problem and addresses it via evolutionary computation. Despite being flexible and enabling automated design, ENAS typically suffers from high computational costs due to the need to train a network at each fitness evaluation. Surrogate-assisted ENAS methods mitigate the severity of this challenge by replacing the computationally expensive fitness function with an approximate computationally cheap fitness function for some fitness evaluations of the run. Currently, a major research challenge in the field is the smooth integration of such surrogate models (and, often, data collection mechanisms) within ENAS frameworks. This paper puts forth a simple yet effective way to address this challenge. During the initial stage of the optimisation, the proposed algorithm, score predictor-assisted ENAS (SPNAS), evolves a small population of candidate architectures using ground truth fitness, i.e., the testing error rate of the network following its training. The data collected in this stage are then used to train a multi-layer perceptron network that builds an alternative fitness function. Unlike algorithms in previous studies, this novel alternative fitness does not approximate the error rate but is designed to preserve its order relation over populations of candidate architectures. Thus, this approach naturally allows for a computationally cheap population ranking. Most of the evolution is then carried out with the surrogate (i.e., alternative) fitness on a large population without retraining the surrogate model or calculating the ground truth fitness. Experiments conducted on the EvoXBench platform show that on its seven search spaces, SPNAS achieves excellent results in terms of error rate despite the modest use of ground-truth fitness calls.

关键词： Computer architecture Training Encoding Predictive models Neural architecture search Microprocessors computational modeling Accuracy Prediction algorithms Graphics processing units Evolutionary neural architecture search surrogate model genetic algorithm score prediction

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：