检索结果-南通市图书馆

CAGCN:Centrality-Aware Graph Convolution Network for Anomaly Detection in Industrial Control Systems

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2024年第4期39卷 967-983页

作者： Jun Yang Yi-Qiang Sheng Jin-Lin Wang Hong Ni National Network New Media engineering research center Institute of AcousticsChinese Academy of SciencesBeijing 100190China School of Electronic Electrical and Communication EngineeringUniversity of Chinese Academy of SciencesBeijing 100049China

In industrial control systems,the utilization of deep learning based methods achieves improvements for anomaly ***,most current methods ignore the association of inner components in industrial control *** industrial control systems,an anomaly component may affect the neighboring components;therefore,the connective relationship can help us to detect anomalies *** this paper,we propose a centrality-aware graph convolution network(CAGCN)for anomaly detection in industrial control *** the traditional graph convolution network(GCN)model,we utilize the concept of centrality to enhance the ability of graph convolution networks to deal with the inner relationship in industrial control *** experiments show that compared with GCN,our CAGCN has a better ability to utilize this relationship between components in industrial control *** performances of the model are evaluated on the Secure Water Treatment(SWaT)dataset and the Water Distribution(WADI)dataset,the two most common industrial control systems datasets in the field of industrial anomaly *** experimental results show that our CAGCN achieves better results on precision,recall,and F1 score than the state-of-the-art methods.

关键词： graph convolution network(GCN) data mining network centrality anomaly detection industrial control system

Design of Resilient Sensor Networks Balancing Resilience and Efficiency

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Disaster Risk Science 2024年第1期15卷 107-115页

作者： Sergey N.Vecherin Kiril D.Ratmanski Luke Hogewood Igor Linkov Cold Regions research and engineering Laboratory Engineering Research and Development CenterHanoverNH 03755USA Environmental Laboratory Engineering Research and Development CenterVicksburgMS 39180USA

In recent years,the notion of resilience has been developed and applied in many technical areas,becoming exceptionally pertinent to disaster risk *** a disaster situation,accurate sensing information is the key to efficient recovery *** general,resilience aims to minimize the impact of disruptions to systems through the fast recovery of critical functionality,but resilient design may require redundancy and could increase *** this article,we describe a method based on binary linear programming for sensor network design balancing efficiency with *** application of the developed framework is demonstrated for the case of interior building surveillance utilizing infrared sensors in both twoand three-dimensional *** method provides optimal sensor placement,taking into account critical functionality and a desired level of resilience and considering sensor type and *** problem formulation,resilience requirements,and application of the optimization algorithm are described in *** of sensor locations with and without resilience requirements shows that resilient configuration requires redundancy in number of sensors and their intelligent *** tasks are successfully solved by the described method,which can be applied to strengthen the resilience of sensor networks by *** proposed methodology is suitable for large-scale optimization problems with many sensors and extensive coverage areas.

关键词： Binary linear programming Optimal sensor placement Redundant networks Resilience and efciency Resilient sensor networks

Robust textile-based spoof plasmonic frequency scanning antenna for on-body IoT applications

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第8期67卷 269-284页

作者： Zhao-Min CHEN Jun-Lin ZHAN Hao CHEN Ya LI Hongjun HE Wu YANG Zhen-Guo LIU Wei-Bing LU State Key Lab of Millimeter Waves School of Information Science and EngineeringSoutheast University center for Flexible RF Technology Frontiers Science Center for Mobile Information Communication and SecuritySoutheast University Future research Laboratory China Mobile Research Institute Purple Mountain Laboratories

Securing a comfortable, wearable compact frequency beam scanning antenna(FBSA) with robustness to deformation, low specific absorption rate(SAR), and good coverage of the surrounding environment for Internet of Things(IoT) applications, such as on-body navigation and wireless communication is an emerging challenge. In this work, a robust textile-based spoof plasmonic frequency scanning antenna utilizing higher-order modes is presented, which is also robust to deformation caused by the activities of the human body. The innovative design of the element ensures the high-efficiency transmission of the fundamental mode of spoof surface plasmon polaritons(SSPP) structure, providing the potential of being a multifunctional composite device in the compact on-body network. Besides, an artificial magnetic conductor(AMC) is designed underneath the SSPP structure, obtaining a low SAR value(0.113 W/kg), which ensures the safety of users. As a practical realization of this concept, a textile-based spoof plasmonic antenna was fabricated in the microwave regime and the performed experimental results show the proposed antenna has a single-beam radiation characteristic with a 70° beam scanning angle range when the frequency is 4.7–6.0 GHz with a high average realized gain of 13.15 dBi. And it still maintains a steady performance when faced with structure deformation, which proves its robustness. Wireless communication quality experiments are performed to demonstrate the proposed antenna can measure the angles of targets and realize wireless signal transmission to specific targets as the frequency varies, it may find great potential in the field of on-body IoT applications.

关键词： frequency beam scanning antenna (FBSA) Internet of Things (IoT) on-body communication spoof surface plasmon polaritons (SSPP) textile-based antenna

Graph Signal Reconstruction from Low-Resolution Multi-Bit Observations

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第1期33卷 153-160页

作者： Zhaoting LIU Chen YU Yafeng WANG Shuchen LIU School of communication engineering Hangzhou Dianzi University

Low hardware cost and power consumption in information transmission, processing and storage is an urgent demand for many big data problems, in which the high-dimensional data often be modelled as graph *** paper considers the problem of recovering a smooth graph signal by using its low-resolution multi-bit quantized observations. The underlying problem is formulated as a regularized maximum-likelihood optimization and is solved via an expectation maximization scheme. With this scheme, the multi-bit graph signal recovery(MB-GSR) is efficiently implemented by using the quantized observations collected from random subsets of graph nodes. The simulation results show that increasing the sampling resolution to 2 or 3 bits per sample leads to a considerable performance improvement, while the energy consumption and implementation costs remain much lower compared to the implementation of high resolution sampling.

关键词： Quantization (signal) Costs Power demand Simulation Energy resolution Signal sampling Signal reconstruction

Robust zero-watermarking algorithm based on discrete wavelet transform and daisy descriptors for encrypted medical image

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第1期9卷 40-53页

作者： Yiyi Yuan Jingbing Li Jing Liu Uzair Aslam Bhatti Zilong Liu Yen-wei Chen School of Information and communication engineering Hainan UniversityHaikouChina research center for Healthcare Data Science Zhejiang LabHangzhouChina Graduate School of Information Science and engineering Ritsumeikan University ShigaJapan

In the intricate network environment,the secure transmission of medical images faces challenges such as information leakage and malicious tampering,significantly impacting the accuracy of disease diagnoses by medical *** address this problem,the authors propose a robust feature watermarking algorithm for encrypted medical images based on multi-stage discrete wavelet transform(DWT),Daisy descriptor,and discrete cosine transform(DCT).The algorithm initially encrypts the original medical image through DWT-DCT and Logistic ***,a 3-stage DWT transformation is applied to the encrypted medical image,with the centre point of the LL3 sub-band within its low-frequency component serving as the sampling *** Daisy descriptor matrix for this point is then ***,a DCT transformation is performed on the Daisy descriptor matrix,and the low-frequency portion is processed using the perceptual hashing algorithm to generate a 32-bit binary feature vector for the medical *** scheme utilises cryptographic knowledge and zero-watermarking technique to embed watermarks without modifying medical images and can extract the watermark from test images without the original image,which meets the basic re-quirements of medical image *** embedding and extraction of water-marks are accomplished in a mere 0.160 and 0.411s,respectively,with minimal computational *** results demonstrate the robustness of the algorithm against both conventional attacks and geometric attacks,with a notable performance in resisting rotation attacks.

关键词： daisy descriptor DCT DWT encryption domain medical image zero-watermarking

Self-dispersed molybdenum disulfide quantum dot/graphene crumpled ball as efficient high temperature lubricant additive

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Friction 2024年第8期12卷 1771-1784页

作者： Guiru DU Yujuan ZHANG Shuguang FAN Ningning SONG Shengmao ZHANG Pingyu ZHANG engineering research center for Nanomaterials Henan UniversityKaifeng 475004China

Inorganic nanoparticles have been proved as powerful lubricant additives at elevated ***,the tribological properties are inevitably impaired due to poor dispersion and insufficient high temperature resistance of organic matter modified ***,we prepare a self-dispersed molybdenum disulfide quantum dot/graphene crumpled ball(MGCB)comprising molybdenum disulfide quantum dot uniformly interspersed on the wrinkled graphene *** crumpled ball composite possesses excellent dispersity in polyalkylene glycol base oil without depending on surface *** with the conventional phosphate esters lubricant,our results indicate MGCB could vastly improve the lubrication performance of polyalkylene glycol with an extremely low concentration(0.05 wt%)at elevated temperature(150°C),showing a friction reduction of 47%and a wear reduction of 30%compared with the conventional phosphate esters lubricant(tricresyl phosphate,TCP).This is because crumpled ball potentiates synergistic lubrication effect within the boundary ***,we envision our designed self-dispersed MGCB has significant potential in tribological application at elevated temperature.

关键词： self-dispersed crumpled ball graphene molybdenum disulfide quantum dot high temperature tribological properties

Synthesis of boron nitride nanorod and its performance as a metalfree catalyst for oxidative desulfurization of diesel fuel

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Chemical engineering 2024年第4期68卷 120-132页

作者： Tanaz Ghanadi Gholamreza Moradi Alimorad Rashidi Catalyst research center Faculty of Chemical and Petroleum EngineeringRazi UniversityKermanshahIran Nanotechnology research center Research Institute of Petroleum Industry(RIPI)TehranIran

In order to reduce the sulfur compounds in diesel fuel,boron nitride(BN)has been used as a novel metal-free catalyst in the present *** nanocatalyst was synthesized via template-free approach followed by heating treatment at 900℃ in nitrogen atmosphere that the characteristics of the sample were identified by the X-ray diffraction,Fourier-transform infrared spectroscopy,Raman spectroscopy,field emission scanning electron microscopy,transmission electron microscopy,atomic force microscopy,and N2 adsorption-desorption *** results of structural and morphological analysis represented that BN has been successfully *** efficacy of the main operating parameters on the process was studied by using response surface methodology based on the Box-Behnken design *** prepared catalyst showed high efficiency in oxidative desulfurization of diesel fuel with initial sulfur content of 8040 mg·kg^(-1)*** statistical analysis,a significant quadratic model was obtained to predict the sulfur removal as a function of efficient *** maximum efficiency of 72.4%was achieved under optimized conditions at oxidant/sulfur molar ratio of 10.2,temperature of 71℃,reaction time of 113 min,and catalyst dosage of 0.36 ***,the reusability of the BN was studied,and the result showed little reduction in activity of the catalyst after 10 times ***,a plausible mechanism was proposed for oxidation of sulfur compounds on the surface of the *** present study shows that BN materials can be selected as promising metal-free catalysts for desulfurization process.

关键词： Desulfurization Boron nitride(BN)nanostructure Experimental design BoxeBehnken

High adsorption selectivity of activated carbon and carbon molecular sieve boosting CO_(2)/N_(2) and CH_(4)/N_(2) separation

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Chemical engineering 2024年第3期67卷 282-297页

作者： Siang Chen Wenling Wu Zhaoyang Niu Deqi Kong Wenbin Li Zhongli Tang Donghui Zhang The research center of Chemical engineering School of Chemical Engineering and TechnologyTianjin UniversityTianjin 300072China

Flue gas and coal bed methane are two important sources of greenhouse *** swing adsorption process has a wide range of application in the field of gas separation,and the selection of adsorbent is *** this regard,in order to assess the better adsorbent for separating CO_(2) from flue gas and CH_(4) from coal bed methane,adsorption isotherms of CO_(2),CH_(4) and N_(2) on activated carbon and carbon molecular sieve are measured at 303.15,318.15 and 333.15 K,and up to 250 *** experimental data fit better with Langmuir 2 compared to Langmuir 3 and Langmuir-Freundlich models,and Clausius-Clapeyron equation was used to calculate the isosteric *** the order of the adsorbed amount and the adsorption heat on the two adsorbents are CO_(2)>CH_(4)>N_(2).The adsorption kinetics are calculated by the pseudo-first kinetic model,and the order of adsorption rates on activated carbon is N_(2)-CH_(4)>CO_(2),while on carbon molecular sieve,it is CO_(2)-N_(2)>CH_(4).It is shown that relative molecular mass and adsorption heat are the primary effect on kinetics for activated carbon,while kinetic diameter is the main resistance factor for carbon molecular ***,the adsorption selectivity of CH_(4)/N_(2) and CO_(2)/N_(2) were estimated with the ideal adsorption solution theory,and carbon molecular sieve performed best at 318.15 K for both CO_(2) and CH_(4) *** study suggested that activated carbon is a better choice for separating flue gas and carbon molecular sieve can be a strong candidate for separating coal bed methane.

关键词： Activated carbon Carbon molecular sieve Adsorbent evaluation Adsorption equilibrium and kinetics Heat of adsorption Selectivity

research on Sarcasm Detection Technology Based on Image-Text Fusion

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第6期79卷 5225-5242页

作者： Xiaofang Jin Yuying Yang YinanWu Ying Xu School of Information and communication engineering Communication University of ChinaBeijing100024China Cable Television Technology research Institute Academy of Broadcasting ScienceBeijing100053China

The emergence of new media in various fields has continuously strengthened the social aspect of social *** tend to express emotions in social interactions,and many people even use satire,metaphors,and other techniques to express some negative emotions,it is necessary to detect sarcasm in social comment *** sarcasm,the more reference data modalities used,the better the experimental *** paper conducts research on sarcasm detection technology based on image-text fusion *** effectively utilize the features of each modality,a feature reconstruction output algorithm is *** algorithm is based on the attention mechanism,learns the low-rank features of another modality through cross-modality,the eigenvectors are reconstructed for the corresponding modality through weighted *** only the image modality in the dataset is used,the preprocessed data has outstanding performance in reconstructing the output model,with an accuracy rate of 87.6%.When using only the text modality data in the dataset,the reconstructed output model is optimal,with an accuracy rate of 85.2%.To improve feature fusion between modalities for effective classification,a weight adaptive learning algorithm is *** algorithm uses a neural network combined with an attention mechanism to calculate the attention weight of each modality to achieve weight adaptive learning purposes,with an accuracy rate of 87.9%.Extensive experiments on a benchmark dataset demonstrate the superiority of our proposed model.

关键词： Sentiment analysis sarcasm detection feature fusion feature reconstruction