检索结果-内蒙古大学图书馆

Perceptual Hashing With Deep and Texture Features

IEEE MULTIMEDIA 2024年第1期31卷 65-75页

作者： Yu, Mengzhu Tang, Zhenjun Liang, Xiaoping Zhang, Xianquan Zhang, Xinpeng Guangxi Normal Univ Software Engn Guilin 541004 Peoples R China Guangxi Normal Univ Sch Comp Sci & Engn Guilin 541004 Peoples R China Fudan Univ Sch Comp Sci Shanghai 200433 Peoples R China

Image hashing is a useful technique for many multimedia systems, such as image authentication, image copy detection, tampering detection, and image quality assessment (IQA). However, most of the image hashing schemes do not make desirable performance of IQA. To tackle this, a new hashing scheme with deep and texture features is proposed for reduced-reference (RR)-IQA. In the proposed hashing, deep features are calculated from the discrete cosine transform coefficients of the three-order tensor stacked by the feature maps generated by the pretrained ResNet18. Texture features are extracted by the gray-level co-occurrence matrix in the nonsubsampled shearlet transform domain. Hash is determined by combining the quantized versions of the deep and texture features. Extensive experiments performed on open datasets indicate that the proposed perceptual hashing is superior to some baseline schemes in the performances of RR-IQA and classification.

关键词： Feature extraction Discrete cosine transforms Tensors Distortion Robustness Three-dimensional displays Sensitivity Transforms Image quality Multimedia systems Classification algorithms detection algorithms Hash functions

来源：评论

学校读者我要写书评

暂无评论

Compressive Sensing-Based Joint Activity and Data detection for Grant-Free Massive IoT Access

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2022年第3期21卷 1851-1869页

作者： Mei, Yikun Gao, Zhen Wu, Yongpeng Chen, Wei Zhang, Jun Ng, Derrick Wing Kwan Di Renzo, Marco Beijing Inst Technol Sch Informat & Elect Adv Res Inst Multidisciplinary Sci Beijing 100081 Peoples R China Beijing Inst Technol Adv Res Inst Multidisciplinary Sci Beijing 100081 Peoples R China Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing 100044 Peoples R China Shanghai Jiao Tong Univ Dept Elect Engn Shanghai 200240 Peoples R China Univ New South Wales Sch Elect Engn & Telecommun Sydney NSW 2025 Australia Univ Paris Saclay Lab Signaux & Syst CNRS Cent SupelecUniv Paris Sud F-91192 Paris France

Massive machine-type communications (mMTC) are poised to provide ubiquitous connectivity for billions of Internet-of-Things (IoT) devices. However, the required low-latency massive access necessitates a paradigm shift in the design of random access schemes, which invokes a need of efficient joint activity and data detection (JADD) algorithms. By exploiting the feature of sporadic traffic in massive access, a beacon-aided slotted grant-free massive access solution is proposed. Specifically, we spread the uplink access signals in multiple subcarriers with pre-equalization processing and formulate the JADD as a multiple measurement vectors (MMV) compressive sensing problem. Moreover, to leverage the structured sparsity of uplink massive access signals among multiple time slots, we develop two computationally efficient detection algorithms, which are termed as orthogonal approximate message passing (OAMP)-MMV algorithm with simplified structure learning (SSL) and accurate structure learning (ASL). To achieve accurate detection, the expectation maximization algorithm is exploited for learning the sparsity ratio and the noise variance. To further improve the detection performance, channel coding is applied and successive interference cancellation (SIC)-based OAMP-MMV-SSL and OAMP-MMV-ASL algorithms are developed, where the likelihood ratio obtained in the soft-decision can be exploited for refining the activity identification. Finally, the state evolution of the proposed OAMP-MMV-SSL and OAMP-MMV-ASL algorithms is derived to predict the performance theoretically. Simulation results verify that the proposed solutions outperform various state-of-the-art baseline schemes, enabling low-latency random access and high-reliable massive IoT connectivity with overloading.

关键词： Inference algorithms Approximation algorithms Uplink OFDM Performance evaluation Wireless communication detection algorithms Compressive sensing grant-free massive access orthogonal approximate message passing multiple measurement vectors successive interference cancellation

来源：评论

学校读者我要写书评

暂无评论

CENSor: Detecting Illicit Bitcoin Operation via GCN-Based Hyperedge Classification

引用

IEEE ACCESS 2024年 12卷 152330-152346页

作者： Lee, Suyeol Kim, Jaehan Seo, Minjae Ho Na, Seung Shin, Seungwon Kim, Jinwoo FuriosaAI Seoul 06036 South Korea Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon 34141 South Korea ETRI Daejeon 34129 South Korea Kwangwoon Univ Sch Software Seoul 01897 South Korea

Cryptocurrencies have increasingly been used as a medium for illicit financial activities by criminals. Annually, billions of dollars' worth of Bitcoin penetrate cryptocurrency exchanges. Despite the critical need for advanced Bitcoin financial forensics to investigate these criminal activities, no novel methods have been developed to detect illicit Bitcoin operations. Existing approaches to identifying illegal Bitcoin activity are limited due to their inadequate consideration of graph data. To address these limitations, we present a novel approach, Hyperedge Classification, to detect illegal transactions with greater precision. This approach introduces a novel cluster-based Hyperedge-Node Switching technique, which enables effective hyperedge classification and visualization of hyperedge relationships. Additionally, we propose a framework named CENSor (Cluster-based Edge Node Switching Detector), which offers more powerful and robust detection capabilities compared to traditional techniques for both illegal entity detection and illegal transaction detection. Our cluster-based Hyperedge-Node Switching technique demonstrates its effectiveness with an F1-score of 0.867, outperforming comparative baselines. Moreover, CENSor visualizes the Bitcoin cluster graph and the Hyperedge-Node switched graph, highlighting the importance of utilizing appropriate graph information in Bitcoin analysis. Finally, we demonstrate that CENSor is resilient to an adversarial attack aimed at evading detection.

关键词： Bitcoin Switches Image edge detection Forensics Feature extraction Visualization Scalability Cryptocurrency detection algorithms illicit entity detection hypergraph graph neural network

来源：评论

学校读者我要写书评

暂无评论

Automatic welding imperfections detection in a smart factory via 2-D laser scanner

引用

JOURNAL OF MANUFACTURING PROCESSES 2022年 73卷 948-960页

作者： Bologna, Francesco Tannous, Michael Romano, Donato Stefanini, Cesare Scuola Super Sant Anna BioRobot Inst Viale R Piaggio 34 I-56025 Pontedera PI Italy Scuola Super Sant Anna Dept Excellence Robot & Artificial Intelligence I-56025 Pisa Italy Baker Hughes Co Nuovo Pignone Tecnol Srl Via Felice Matteucci 2 I-50127 Florence FI Italy Khalifa Univ Healthcare Engn Innovat Ctr Abu Dhabi U Arab Emirates

Welding defect detection is crucial to determine welding quality and assure correct mechanical performance of the welded joint during operation. Most of common detection techniques are performed offline, are time consuming, and strongly dependent on the operator skill. In the present work, two novel automatic online welding imperfections detection approaches are presented for classifying qualified and defective profiles acquired with a 2-D laser scanner on square grooves in a multi-pass Gas Tungsten Arc Welding process. In particular, a Heuristic Algorithm has been developed to analyze different geometrical characteristics of the profile for its classification. The Heuristic Algorithm has been validated on five welded coupons, created in Baker Hughes welding laboratory in Massa, Italy. Coupons have been scanned and resulting profiles have been manually labeled. The Heuristic Algorithm showed good performance, with a F1 score of 94.8%. Additionally, a multi-layer feed forward Neural Network has been trained and tested on the profiles acquired from the five welded coupons, with an overall F1 score of 91.0%. The promising results of the two proposed approaches will lead to a wider test campaign, before implementing a mixed solution in a multi-pass robotic Gas Tungsten Arc Welding industrial process.

关键词： Artificial intelligence Automation detection algorithms Industry 4 0 Welding

来源：评论

学校读者我要写书评

暂无评论

Ellipse Encoding for Arbitrary-Oriented SAR Ship detection Based on Dynamic Key Points

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2022年 60卷

作者： Gao, Fei Huo, Yiyang Sun, Jinping Yu, Tao Hussain, Amir Zhou, Huiyu Beihang Univ Sch Elect & Informat Engn Beijing 100191 Peoples R China Taiyuan Satellite Launch Ctr Xinzhou 36300 Peoples R China Edinburgh Napier Univ Cyber & Big Data Res Lab Edinburgh EH11 4BN Midlothian Scotland Univ Leicester Sch Comp & Math Sci Leicester LE1 7RH Leics England

In recent years, there has been growing interest in developing oriented bounding box (OBB)-based deep learning approaches to detect arbitrary-oriented ship targets in synthetic aperture radar (SAR) images. However, most existing OBB-based detection methods suffer from boundary discontinuity problems for bounding box angle prediction and key point regression challenges. In this article, we present a novel OBB-based detection algorithm that utilizes ellipse encoding to effectively exploit the geometric and scattering properties of ship targets. Specifically, the ship contour is fit by an OBB inscribed ellipse that is encoded as a set of distances between dynamic key points on the bow and target center. By combining the bow angle interval and the decoding process, the negative impact of the boundary discontinuity problem is avoided. In addition, we propose an elliptical Gaussian distribution heatmap and a pooling strategy termed double-peak max-pooling (DPM) to deal with the challenge of separating densely distributed ships in inshore scenes. The former can enhance the heatmap's ship-side score gap between neighboring ship targets, while the latter can solve the problem of target center responses being suppressed after max-pooling. Simulation experiments conducted on the benchmark Rotating SAR Ship detection Dataset (RSSDD) and Rotated Ship detection Dataset in SAR Images (RSDD-SAR) demonstrate the superior performance of our method for ship target detection compared to several state-of-the-art OBB-based algorithms. Ablation experiments show that elliptical Gaussian distribution heatmap and DPM can further improve the inshore detection performance.

关键词： Marine vehicles Feature extraction detection algorithms Synthetic aperture radar Radar polarimetry Heating systems Scattering Arbitrary-oriented boundary discontinuity ellipse encoding ship detection synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

A Multidimensional Hardware Trojan Design Platform to Enhance Hardware Security

引用

IEEE EMBEDDED SYSTEMS LETTERS 2025年第1期17卷 46-49页

作者： Das, Nilanjana Hasler, Mattis Pauls, Friedrich Haas, Sebastian Barkhausen Inst Scalable Comp Hardware Dept D-01067 Dresden Germany

This letter proposes a novel kind of HT design named multidimensional HTs (MDHTs) and develops a method to generate configurable MDHT benchmark platform. The proposed MDHT circuits include multiple net(s) as trigger signals from each of the rarely activated, highly activated, and partially activated categories to increase MDHT's adverse effects. The generated MDHT-infected circuits are tested by an unsupervised machine learning-based HT detection technique-controllability and observability for HT detection (COTD). Experimentation on ISCAS benchmarks ensures that the detection method is unable to detect the developed MDHT circuits as the nets belong to higher and partial activities are creating at least 50% and at most 80% false negative rate which validates the MDHT insertion framework in addition to the available HT benchmarks.

关键词： Benchmark testing detection algorithms Trojan horses Observability Switches Logic gates Controllability Benchmark controllability k-means clustering multidimensional hardware Trojan (MDHT) observability transition probability (TP)

来源：评论

学校读者我要写书评

暂无评论

A Fast Community detection Algorithm Based on Reconstructing Signed Networks

引用

IEEE SYSTEMS JOURNAL 2022年第1期16卷 614-625页

作者： Xia, Chengyi Luo, Yongping Wang, Li Li, Hui-Jia Tianjin Univ Technol Tianjin Key Lab Intelligence Comp & Novel Softwar Engn Res Ctr Learning Based Intelligent Syst Minist Educ Tianjin 300384 Peoples R China Beijing Univ Posts & Telecommun Sch Sci Beijing 100876 Peoples R China

Signed networks depict the individual cooperative or hostile relationship in a population, which can help to deeply mine the characteristics of complex networks and predict the potential collaboration between individuals by analyzing their interaction within different groups or communities. In this article, first of all, an improved modularity function for signed networks is proposed on the basis of the existing modularity function. Then, a new community detection algorithm for signed networks has also been devised, and time complexity analysis shows that the time required for the algorithm has a linear relationship with the number of nodes in the sparse networks. Meanwhile, the affinity index that can be used to convert directed signed networks into the corresponding undirected signed networks is come up with. Finally, the current algorithm has been applied into several illustrative and realistic networks. The experimental results indicate that the number of communities given by the proposed algorithm is consistent with that of actual communities, and thus, it can be further conducive to identifying the community structure hidden within the real-world systems.

关键词： Indexes Partitioning algorithms Image edge detection Clustering algorithms Oscillators Heuristic algorithms detection algorithms Affinity index community detection community structure modularity network reconstruction signed network

来源：评论

学校读者我要写书评

暂无评论

A Snowfall detection Algorithm for ATMS Over Ocean, Sea Ice, and Coast

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2022年 15卷 1411-1420页

作者： You, Yalei Meng, Huan Dong, Jun Fan, Yongzhen Ferraro, Ralph R. Gu, Guojun Wang, Likun Univ Maryland Cooperat Inst Satellite Faith Syst Studies CISESS Earth Syst Sci Interdisciplinary Ctr ESSIC College Pk MD 20740 USA NOAA NESDIS STAR College Pk MD 20740 USA Univ Maryland Earth Syst Sci Interdisciplinary Ctr ESSIC College Pk MD 20740 USA

This study developed a snowfall detection algorithm over ocean, sea ice, and coast for the advanced technology microwave sounder (ATMS) onboard both NPP and NOAA-20 satellites. The detection algorithm was trained from collocated observations between ATMS-NPP and CloudSat cloud profiling radar (CPR) snowfall product. Both brightness temperature (TB) variables and global forecast system (GFS) output variables are evaluated for snowfall detection in this algorithm. Results show that combining TB variables and GFS variables provide the optimal snowfall detection performance. The Heidke skill score (HSS) values are about 0.56 over all three surface types, and the probability of detection (POD) values are 0.76, 0.70, and 0.72 over ocean, sea ice, and coast, respectively. The importance of the GFS variables differs greatly among these three surface types. The detection algorithm primarily depends on TB variables over ocean and HSS only increased by 0.05 by adding GFS variables. In contrast, GFS variables are critically important to snowfall detection over sea ice and coastal regions. Without GFS variables, the HSS values over both sea ice and coastal regions decrease sharply from about 0.56 to about 0.40. Over ocean, we also developed a regional snowfall detection model in each 10 degrees grid box, which greatly outperform the global detection model over certain regions (e.g., sea of Okhotsk and Labrador Sea). Case studies and validation against NOAA-20 observations showed that the snowfall detection algorithm performs well, which will benefit coastal communities by providing information on snowstorms offshore before they transition to land.

关键词： Ocean temperature Oceans Sea surface Microwave radiometry Microwave integrated circuits Microwave FET integrated circuits detection algorithms Microwave radiometry satellite applications snow

来源：评论

学校读者我要写书评

暂无评论

A Signature Recognition Technique With a Powerful Verification Mechanism Based on CNN and PCA

引用

IEEE ACCESS 2024年 12卷 40634-40656页

作者： Abosamra, Gibrael Oqaibi, Hadi King Abdulaziz Univ Fac Comp & Informat Technol Dept Comp Informat Syst Jeddah 21589 Saudi Arabia

In this paper, we embed a signature verification mechanism in a previously introduced architecture for signature recognition to detect in-distribution and out-of-distribution random forgeries. In the previous architecture, a CNN was trained on the genuine user training dataset and then used as a feature extraction module. A k-NN algorithm with cosine distance was then used to classify the unknown signatures based on the nearest cosine distance neighbor. This architecture led to higher than 99% accuracy, but without verification, because any unknown signature will converge to one of the identities of the training dataset's users. To add a verification mechanism that differentiates between genuine and random forgeries, we use PCA to select the most discriminating features used in calculating the cosine distance between the training and testing signatures. A fixed parameter thresholding technique based on the training distances is introduced that best differentiates between the genuine and random-user signatures. Moreover, enhancement of the technique is carried out by combining the output of the Softmax layer and the last convolution layer of the ResNet18 model to get a highly discriminative representation of the handwritten signatures. Accordingly, the introduced verification mechanism resulted in very low false positive and negative rates for test signatures from inside and outside the main dataset, with an insignificant decrease in the high identification accuracy. The complete architecture has been tested on three publicly available datasets, showing superior results.

关键词： Training Principal component analysis Feature extraction Forgery Vectors Convolutional neural networks Data models Nearest neighbor methods detection algorithms Handwriting recognition cosine distance false negative rate false positive rate k-Nearest neighbor algorithm out-of-distribution detection signature identification signature verification

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of the Machine Learning algorithms in IoT IDS Systems

引用

IEEE ACCESS 2024年 12卷 46785-46811页

作者： Ozdogan, Erdal Gazi Univ IT Dept TR-06560 Ankara Turkiye

In this study, machine learning algorithms in IoT IDS (Internet of Things Intrusion detection System) systems are comprehensively compared from various aspects. Accuracy, precision, and training time are evaluated. The effects of data preprocessing techniques including normalization, outlier removal, standardization, and regularization on the datasets are examined. Furthermore, the impact of dataset balancing, considering both balanced and imbalanced scenarios, on machine learning performance is investigated. The contribution of feature selection on the four different datasets is also analyzed. Based on findings, it is observed that certain preprocessing operations provide significant advantages in various ML algorithms, whereas others have very low impact, and their performance varies depending on the dataset and feature selection. The aim of this study is to facilitate the complexity and lengthiness of machine learning processes and algorithm selection, providing insights for future academic research. By addressing this objective, an effort is made to shed light on simplifying the utilization of machine learning algorithms. The challenges arising from the complexity of machine learning processes in IoT IDS systems are addressed by this study. This contribution can greatly benefit researchers in their academic endeavors. This multifaceted approach proves beneficial when comparing the methods under consideration, fostering a scientific discourse on their efficacy within contexts.

关键词： detection algorithms IoT attack detection IoT IDS ML algorithm comparison machine learning preprocessing machine learning in IoT IDS

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：