检索结果-内蒙古大学图书馆

Power Electronics, Computer Applications (ICPECA), IEEE International Conference on

作者： Shangqing Cui Dongqin Feng College of Control Science and Engineering Zhejiang University Hangzhou China

With the application of Internet technologies in the industrial field, industrial control systems (ICS) have the possibility of suffering malicious network attacks. Because ICS is widely used in critical infrastructure, designing attack detection algorithms for it can effectively reduce losses. Many papers have built physical models for cyber-attacks against ICS and the corresponding detection algorithms have been proposed. However, the detection performance can be further improved. This paper establishes the simulation attack on the Tennessee Eastman (TE) process and proposes an improved support vector machine (SVM) method to detect integrity attacks. This algorithm uses contribution plots and recursive feature elimination to select features. Compared with the principal component analysis (PCA) feature extraction, the detection accuracy is improved. After adding system dynamics to the algorithm, the time to detect attacks is advanced.

关键词： Support vector machines System dynamics Industrial control Heuristic algorithms Feature extraction detection algorithms Integrated circuit modeling

来源：评论

学校读者我要写书评

暂无评论

Change Point detection with Neural Online Density-Ratio Estimator

Change Point Detection with Neural Online Density-Ratio Esti...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiuheng Wang Ricardo Augusto Borsoi Cédric Richard Jie Chen Université Côte d’Azur CNRS OCA Nice France Université de Lorraine CNRS CRAN Vandoeuvre-lès-Nancy France School of Marine Science and Technology Northwestern Polytechnical University Xi’an China

Detecting change points in streaming time series data is a long standing problem in signal processing. A plethora of methods have been proposed to address it, depending on the hypotheses at hand. Non-parametric approaches are particularly interesting as they do not make any assumption on the distribution of data or on the nature of changes. Nevertheless, leveraging recent advances in deep learning to detect change points in time series data is still challenging. In this paper, we propose a change point detection method using an online approach based on neural networks to directly estimate the density-ratio between current and reference windows of the data stream. A variational continual learning framework is employed to train the neural network in an online manner while retaining information learned from past data. This leads to a statistically-principled fully nonparametric framework to detect change points from streaming data. Experimental results with synthetic and real data illustrate the effectiveness of the proposed approach.

关键词： Deep learning Neural networks Time series analysis Signal processing Acoustics Speech processing detection algorithms

来源：评论

学校读者我要写书评

暂无评论

A Density-based Clustering Approach to detect Colluding SSDF Attackers in Cognitive Radio Networks 37

A Density-based Clustering Approach to detect Colluding SSDF...

引用

37th International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC)

作者： Taggu, Amar Marchang, Ningrinla North Eastern Reg Inst Sci & Technol NERIST Dept Comp Sci & Engn Nirjuli India

ISBN: (数字)9781665485593

ISBN: (纸本)9781665485593

Among the many attacks that Cognitive Radio Networks (CRN) are vulnerable to, Spectrum Sensing Data Falsification (SSDF) attack is one of the most common attacks. The current work focusses on an advanced form of SSDF attacks, called Colluding SSDF attack. The colluding attack is a collaborative well-planned and well-timed attack where a leader instructs the other attackers when and how to attack a CRN during sensing period. Needless to say, Colluding SSDF attacks are harder to detect and thus, they are more harmful. To detect this attack, we have proposed a technique based on Density-Based Spatial Clustering of Applications with Noise (DBSCAN) [1]. The density-based clustering technique separates the high-density clusters (normal SUs) from low-density clusters (attackers). Simulation results demonstrate the effectiveness of the proposed when the percentage of attackers is less than 50%. Additionally, a performance comparison of the proposed method has been done with an existing work, agglomerative clustering detection algorithm (ACD)[2].

关键词： Computers Simulation Collaboration Clustering algorithms Sensors Cognitive radio detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Research on Automatic detection Algorithm for Lumbar Disc Herniation Based on FCOS

Research on Automatic Detection Algorithm for Lumbar Disc He...

引用

Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI), IEEE International Conference on

作者： Tingqiang Guan Ziming Wang Wei Hu School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China Department of Spine and Osteopathy Ward Liuzhou Peoples' Hospital Guilin China

ISBN: (数字)9798350372052

ISBN: (纸本)9798350372069

Lumbar disc herniation is a common spinal disease, and its diagnosis and treatment usually rely on medical imaging technology. Traditional medical image diagnosis methods require high labor and time costs. This article proposes an object detection network based on FCOS to achieve automated detection of lumbar disc herniation. This network introduces the idea of group convolution and incorporates attention mechanisms. In addition, the Soft NMS algorithm was used in the inference stage to avoid the problem of target boxes being violently deleted. The method proposed in this article achieved a mAP of 0.661 on the MRI test set, which has higher accuracy compared to other networks. This method provides a feasible and effective solution for detecting lumbar disc herniation, which is expected to assist doctors in clinical diagnosis.

关键词： Computer science Costs Convolution Magnetic resonance imaging Object detection Inference algorithms detection algorithms

来源：评论

学校读者我要写书评

暂无评论

YOLO-LF: An Ultra-Lightweight and Fast Forest Fire detection Algorithm for Edge Devices

YOLO-LF: An Ultra-Lightweight and Fast Forest Fire Detection...

引用

Networking Systems of AI (INSAI), International Conference on

作者： Zhuoyue Ding Run Ye Xiaojia Zhuo Qilin Li Lei Huang Bin Yan School of Automation Engineering University of Electronic Science and Technology of China Chengdu China Metering Center State Grid Sichuan Electric Power Company Chengdu China School of Resources and Environment University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350344660

ISBN: (纸本)9798350344677

In recent years, there has been signification progress in deep learning-based forest fire detection techniques for natural environment monitoring. However, existing object detection algorithms designed for forest fire scenarios often suffer from computational intensity and storage space consumption, rendering them unsuitable for deployment on edge devices. Moreover, forest fire scenarios have high real-time performance, but current edge device deployments of object detection algorithms result in substantial latency and often miss critical rescue opportunities. To address these challenges, this paper proposes a novel lightweight forest fire detection algorithm, YOLO-LF (LF means both light and fast), which leverages a ShuffleNetv2 backbone network, Group Shuffle Convolutions (GSConv) as the base feature extraction block, and lightweight C3_Faster modules as the feature fusion module, and the lightweight operator Content-Aware ReAssembly of Features (CARAFE) as the up-sampling method. The algorithm ensures real-time detection by edge devices while being able to guarantee the accuracy of forest fires. Ultimately, the results on the forest fire dataset show that YOLO-LF mAP@ 0.5 (average accuracy) and FPS (frames per second) reach 71.2% and 110f/s on the PC side, respectively. On the Raspberry Pi 4B platform, the FPS of YOLO-LF is 5.88 times higher than that of the YOLOv5s, which achieves a high accuracy real-time detection with 20+FPS. The model is not only applicable to forest fires, but also a generalized lightweight detection model that can meet most of the requirements for real-time detection deployed on edge devices, and thus has great theoretical significance and application value.

关键词： YOLO Accuracy Image edge detection Computational modeling Forestry Feature extraction Rendering (computer graphics) Real-time systems Complexity theory detection algorithms

来源：评论

学校读者我要写书评

暂无评论

SLAM Loop Closure detection Algorithm Based on 3D Bag-of-Words Model

SLAM Loop Closure Detection Algorithm Based on 3D Bag-of-Wor...

引用

Computer, Internet of Things and Smart City (CIoTSC), International Conference on

作者： Wu Liangdong Zou Yaping Wang Dong Chen Ling School of Computer Engineering and Design Hunan Normal University Changsha China

ISBN: (数字)9798350306569

ISBN: (纸本)9798350306576

In outdoor environments, the loop closure detection in laser-based SLAM faces challenges such as complex lighting variations, low-texture regions, occlusions, and dynamic objects, which limit the accuracy and efficiency of loop closure detection. To address this issue, a novel laser-based SLAM loop closure detection algorithm is proposed, specifically designed for outdoor environments, based on three-dimensional global descriptor features. The algorithm utilizes a BoWЗD model constructed from the three-dimensional laser features for precise point-to-point matching and loop closure detection. The proposed algorithm is integrated into the LeGO-LOAM system and evaluated on the publicly available KITTI dataset. Experimental results demonstrate a 64% improvement in absolute trajectory accuracy and reduced computational time compared to the baseline algorithm.

关键词： Solid modeling Simultaneous localization and mapping Accuracy Three-dimensional displays Smart cities Feature extraction Laser modes Approximation algorithms Trajectory detection algorithms

来源：评论

学校读者我要写书评

暂无评论

A DDoS attack detection algorithm based on improved grid search to optimize SVM in SDN environment

A DDoS attack detection algorithm based on improved grid sea...

引用

Electrical Engineering, Big Data and algorithms (EEBDA), IEEE International Conference on

作者： Meigen Huang Boqi Zhao Chongqing University of Posts and Telecommunications Chongqing China

Software defined network has proposed a new architecture idea, but the controller is vulnerable to distributed denial of service attacks, resulting in a single point of failure. This paper proposes a DDoS attack detection algorithm based on improved grid search optimization SVM in SDN environment. Firstly, according to the characteristics of DDoS attacks and information of flow table items, the most relevant six-dimensional features are selected, then use the improved grid search algorithm to calculate the optimal penalty coefficient and kernel function parameters of SVM model, finally use SVM algorithm to detect DDoS attacks and improve the performance of intrusion detection algorithm. The experimental results in the same scene show that the improved SVM has higher detection rate and recall rate than the SVM algorithm.

关键词： Support vector machines Electrical engineering Intrusion detection Denial-of-service attack Feature extraction detection algorithms Software defined networking

来源：评论

学校读者我要写书评

暂无评论

Spatially-Coupled Faster-than-Nyquist Signaling 33

Spatially-Coupled Faster-than-Nyquist Signaling

引用

33rd IEEE Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

作者： Lu, Qingya Li, Shuangyang Bai, Baoming Yuan, Jinhong Xidian Univ State Key Lab ISN Xian Peoples R China Univ New South Wales Sch Elect Engn & Telecommun Sydney NSW Australia

ISBN: (数字)9781665480536

ISBN: (纸本)9781665480536

A spatially-coupled faster-than-Nyquist (SC-FTN) signaling is proposed in this paper. The signal of SC-FTN signaling is generated continuously by interleaving and repeating the coded FTN signals and a graph-based iterative sliding-window detector can be applied for signal detection. Both bounding and extrinsic information transfer chart analysis are provided to study the error performance of SC-FTN signaling, where performances of both error floor and convergence are considered. Those analyses unveil the intrinsic relationship between error floor, decoding threshold, and detection/decoding complexity, which provides guidelines for the designs of practical systems. Numerical results show that the promising error performance can be achieved with a simple FTN detection, where the bit error rate of coded SC-FTN signaling outperforms both state-of-art coded FTN systems and the BPSK capacity of Nyquist signaling.

关键词： Simulation Interference Detectors Iterative algorithms detection algorithms Iterative decoding Floors

来源：评论

学校读者我要写书评

暂无评论

Exploiting Internet of Things Protocols for Malicious Data Exfiltration Activities

引用

IEEE ACCESS 2021年 9卷 104261-104280页

作者： Vaccari, Ivan Narteni, Sara Aiello, Maurizio Mongelli, Maurizio Cambiaso, Enrico IEIIT Inst Consiglio Nazl Ric CNR I-16149 Genoa Italy Univ Genoa Dept Informat Bioengn Robot & Syst Engn DIBRIS I-16145 Genoa Italy

Internet of Things is a widely adopted and pervasive technology, but also one of the most relevant in cyber-security, given the volume and sensitivity of shared data and the availability of affordable but insecure products. In this paper, we propose a novel cyber-threat exploiting the Message Queue Telemetry Transport (MQTT) protocol to implement a tunneling attack. In IoT networks, sensitive and critical information are exchanged between devices or external systems to perform data analysis. For this reason, a tunneling threat could be adopted by a malicious user to steal information. In this context, a tunneling system based on MQTT can be considered since this communication protocol could be allowed to pass through enterprise firewalls because it is widely adopted in this IoT world. An attacker can exploit the MQTT protocol for various purposes such as steal information or access to not-allowed websites/servers. In particular in this work, we contribute in two main points: initially we demonstrate how the proposed threat is able to encapsulate messages through the MQTT protocol, by also comparing it with other tunneling systems exploiting different communication protocols. Obtained results show that exploiting MQTT for tunneling purposes is a good choice, compared to other communication protocols, especially for payloads up to 3000 bytes. Then, we propose and validate an initial machine learning based approach able to detect the proposed MQTT tunnel, by comparing different detection algorithms tested with and without a hyperparameter optimization, in terms of accuracy, F1 score and Receiver Operating Characteristic (ROC) curve. In this case, obtained results show that some algorithms are able to identify the attack, with an accuracy exceeding 95%, while others lack of such capability.

关键词： Protocols Tunneling Internet of Things Security Authentication Support vector machines Performance evaluation Cyber-security network security IoT MQTT tunneling systems machine learning detection algorithms data exfiltration

来源：评论

学校读者我要写书评

暂无评论

A Temporal Network Community detection Method Based on Steady Labels and Label Propagation SteadyProp (A Temporal Network Community detection Algorithm with Steady Labels and Label Propagation)

A Temporal Network Community Detection Method Based on Stead...

引用

Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI), IEEE International Conference on

作者： Zhixaing Yang Yuxia Zheng Zhihao Gong Taolue Long Yuan Jiang Nanchang Hangkong University Nanchang China

ISBN: (数字)9798350372052

ISBN: (纸本)9798350372069

Accurate community detection is crucial for timely comprehension of network structures, understanding evolutionary patterns, and predicting future network behaviors. It greatly enhances applications in social network analysis, disease prediction, and treatment, among others. In temporal community detection algorithms, inert nodes within communities tend to persist within the same community across multiple time slices. In this paper, these nodes are assigned steady-state labels. Identifying and applying steady-state labeled nodes accelerates and smoothens the process of community detection. Thus, this paper introduces a rapid temporal network community detection approach based on steazdy-state labels and label propagation. By leveraging the propagation of steady-state labels at each time step, this method achieves faster temporal community partitioning, effectively enhancing the accuracy and smoothness of such partitions.

关键词： Computer science Social networking (online) Steady-state detection algorithms Intelligent control Diseases

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：