会议名称:
20th International Workshop on Digital-Forensics and Watermarking (IWDW)
会议时间:
NOV 20-22, 2021
会议地点:
Beijing, PEOPLES R CHINA
会议主办单位:
[Zhang, Le-Bing;Cai, Juan] Huaihua Univ, Huaihua 418000, Peoples R China.^[Peng, Fei] Hunan Univ, Changsha 410082, Peoples R China.^[Long, Min] Changsha Univ Sci & Technol, Changsha 410114, Peoples R China.
会议论文集名称:
Lecture Notes in Computer Science
关键词:
Face morphing detection;Morphing artifacts;Attention convolutional neural network;Multiple scales
摘要:
Face morphing attack is becoming a serious threat to the existing face recognition systems. Some different approaches for morphing attack detection have been put forward. However, there are few methods concentrated on detecting the morphing artifacts, which often appear in morphed facial images. In this work, we propose a multiple scales attention convolutional neural network (MSA-CNN), a novel approach that can effectively detect the morphing artifacts in face morphing attacks. It utilizes the attention mechanism to continuously pay attention to the morphing artifacts in multiple scales and finally realizes face morphing detection. Experimental results and analysis show that it can effectively locate the region of morphing artifacts, and outperforms the existing deep learning-based blind face morphing detection frameworks.
会议论文集名称:
International Conference on Power and Energy Systems
关键词:
demand side;substation bus;flexibility of load;radial basis function neural network
摘要:
At present, due to the extreme weather and the sound of the seasonal peak, there are local and phased tensions in power in many places. In order to solve this problem, the research and analysis of demand side is a very important and critical step. Firstly, the concept of flexible load flexibility is put forward. The flexibility of reducible load, shiftable load and interruptible load is defined and quantified by mathematical model. The definition of flexible load flexibility is extended, the flexibility model of flexible aggregate load of substation bus on demand side is proposed, and several cases that have great influence on substation flexibility are analyzed. Finally, a prediction model of substation flexibility based on radial basis function neural network is proposed. The accuracy of the model is verified by simulation, which provides a key basis for the two-way interaction of demand response and source load.
关键词:
FAST single objective optimization;variable step size search method;objective programming
摘要:
As one of the three major innovations of FAST, the active reflective surface is composed of main components such as the main cable net, reflective panel, pull-down cable, actuator and supporting structure. Its essence is to adjust the reflecting surface in the illumination range to the designated parabolic position in real time according to the position of the observed celestial body, so that the parallel electromagnetic waves emitted by the celestial body will always converge at one point after being reflected by the reflecting surface. Aiming at the problem that the Chinese FAST sky eye reflector panel automatically adjusts the overall shape to the working paraboloid to achieve the best electromagnetic wave reflection effect under the condition of different positions of the measured celestial body, a single target optimization, target planning, single reflector panel and other models have been constructed. With the ideal parabola and actuator adjustment scheme, the reception ratio after adjustment is increased by 5 times. According to the adjustment strategy of the reflective panel obtained by the research, the nodes with a node displacement greater than 0.5m account for 0.14%, and the performance is good.
会议名称:
IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications (IMWS-AMP)
会议时间:
NOV 27-29, 2022
会议地点:
S China Univ Technol, Guangzhou, PEOPLES R CHINA
会议主办单位:
S China Univ Technol
摘要:
In this paper, a 1 bit programmable metasurface is designed, which can control the amplitude and phase by optimizing the encoding method. Firstly, the working principle of metasurface for RCS (Radar Cross Section) reduction is demonstrated, and the designed coding metasurface is simulated and analyzed. Then the amplitude and phase manipulation are simulated by MATLAB and CST respectively. The simulation results show that different coding sequences have a good effect on the reduction of RCS, and can achieve the dual regulation of amplitude and phase. As a result, this kind of coding metasurface is expected to further improve the stealth performance of the target.
会议论文集名称:
IEEE International Conference on Trust Security and Privacy in Computing and Communications
关键词:
Platoon;False data injection attack;Sequential importance sampling;Intrusion detection,Threshold
摘要:
Intelligent connected vehicle platoon technology can reduce traffic congestion and vehicle fuel. However, attacks on the data transmitted by the platoon are one of the primary challenges encountered by the platoon during its travels. The false data injection (FDI) attack can lead to road congestion and even vehicle collisions, which can impact the platoon. However, the complexity of the cellular - vehicle to everything (C-V2X) environment, the single source of the message and the poor data processing capability of the on board unit (OBU) make the traditional detection methods' success rate and response time poor. This study proposes a platoon state information fusion method using the communication characteristics of the platoon in C-V2X and proposes a novel platoon intrusion detection model based on this fusion method combined with sequential importance sampling (SIS). The SIS is a measured strategy of Monte Carlo integration sampling. Specifically, the method takes the status information of the platoon members as the predicted value input. It uses the leader vehicle status information as the posterior probability of the observed value to the current moment of the platoon members. The posterior probabilities of the platoon members and the weights of the platoon members at the last moment are used as input to update the weights of the platoon members at the current moment and obtain the desired platoon status information at the present moment. Moreover, it compares the status information of the platoon members with the desired status information to detect attacks on the platoon. Finally, the effectiveness of the method is demonstrated by simulation.
会议论文集名称:
IEEE International Symposium on Power Electronics for Distributed Generation Systems
关键词:
Cascaded H-bridge PV system;quadruple active bridges;reduced capacitance;low-frequency voltage ripple;fluctuation ratio;reliability
摘要:
Cascaded H-bridge (CHB) multilevel converters are promising candidates for large-scale grid-connected PV systems thanks to its modularity, scalability and distributed maximum power point tracking (DMPPT). However, CHB converters inherently have low-frequency power ripple in dc links, thus require large dc-link electrolytic capacitors to mitigate the resulting voltage ripple, which will lead in reduction of system reliability. In order to solve the above issues, this paper adopts the system topology architecture composed of CHB multilevel converter and quadruple active bridges (QAB) dc-dc converters, combining with the intercross control structure. This scheme not only can improve the system reliability by decreasing the dc-link capacitance, but also can prevent the low-frequency ripple propagating to the PV ports. Simulation results clearly verify the effectiveness and feasibility of the topology and control strategy.
关键词:
SiC FET;SiC MOSFET;Si IGBT;cascode;hybrid switch
摘要:
Hybrid switches, e.g., configured by parallel connection of Si IGBT and SiC MOSFET, have been approved to be an optimal solution, which can reduce cost and meanwhile increase the efficiency. The latest generation SiC FETs of UnitedSiC are becoming increasingly popular. Apart from the low on-resistance and good switching performances, main benefits of SiC FETs are the gate drive voltage consistent with the traditional Si IGBTs and avoiding the gate oxygen layer reliability trap, which is existed in the SiC MOSFET. Therefore, this paper proposes a SiC FET/Si IGBT hybrid switch. Both the dynamic and static characteristics between the proposed SiC FET/Si IGBT and traditional SiC MOSFET/Si IGBT hybrid switches are compared under the same test conditions. The simulation results clearly show that the proposed SiC FET/Si IGBT hybrid switch has lower forward conduction resistance, smaller switching losses, lower reverse conduction voltage drop and better reverse recovery performances.
摘要:
The decomposition of multi-subject fMRI data using rank-(L,L,1,1) block term decomposition (BTD) can preserve higher-way data structure and is more robust to noise effects by decomposing shared spatial maps (SMs) into a product of two rank-L loading matrices. However, since the number of whole-brain voxels is very large and rank L is larger than 1, the rank-(L,L,1,1) BTD requires high computation and memory. Therefore, we propose an accelerated rank-(L,L,1,1) BTD algorithm based upon the method of alternating least squares (ALS). We speed up updates of loading matrices by reducing fMRI data into subspaces, and add an orthonormality constraint on shared SMs to improve the performance. Moreover, we evaluate the rank-L effect on the proposed method for actual task-related fMRI data. The proposed method shows better performance when L=35. Meanwhile, experimental comparison results verify that the proposed method largely reduced (17.36 times) computation time compared to ALS while also providing satisfying separation performance.
会议主办单位:
[Gui, Qiang;Li, Wei] Huazhong Univ Sci & Technol, Sch Naval Architecture & Ocean Engn, Wuhan, Peoples R China.^[Chai, Yingbin] Wuhan Univ Technol, Sch Naval Architecture Ocean & Energy Power Engn, Wuhan, Peoples R China.^[You, Xiangyu] Changsha Univ Sci & Technol, Sch Hydraul & Environm Engn, Changsha, Peoples R China.
会议论文集名称:
OCEANS-IEEE
关键词:
overlapping finite element method;acoustic propagation;harmonic trigonometric functions;linear dependence
摘要:
The classic finite element method (FEM) is an effective numerical tool for the study of underwater acoustic propagation which is of great importance for the utilization of marine resources. However, the numerical solutions obtained by the FEM for the acoustic problems are unreliable at relatively high computational wavenumbers. In this work the overlapping finite element method (OFEM) is introduced to the time-harmonic acoustic propagation and an enriched scheme (EOFEM) augmented by the harmonic trigonometric functions is proposed to improve the performance of the original scheme. The performance of the proposed EOFEM is studied by a singular eigenmode of the Helmholtz problem in an L-shaped domain. The numerical experiment reveals that the EOFEM can achieve more accurate solutions at relatively high computational wavenumber than the original OFEM and the classic FEM, and is more reliable in handling the distorted mesh.
会议论文集名称:
International Conference on Power and Energy Systems
关键词:
aggregation of induction motors;component-based approach;load model;aggregation of static loads
摘要:
With the continuous development of power system, the accuracy of load modeling is required to be higher and higher. Aggregated modeling of motors is very important for integrated load modeling. Due to the deficiency in traditional aggregation method that static loads and induction motors are assumed to be connected to the same bus, an aggregation method of load considering distribution network is presented. In this method, according to nodal voltage equation of distribution network, connection nodes were removed, while load nodes were retained. Then, according to the principle that active and reactive power losses were equivalent before and after aggregation, equivalent distribution network impedance was calculated with the retained nodes voltages and admittances of the reduced distribution network. Moreover, voltage of the fictitious bus was obtained with the voltage and injecting current of the power supply point and the equivalent distribution network. Furthermore, static loads and induction motors were displaced to the fictitious bus. Finally, according to the electromagnetic model, induction motors displaced to the fictitious bus were aggregated into a single one, and static loads were aggregated to a composite one. Because the distribution net-work impedance is considered, the aggregation model well preserves the characteristic of composite load model of distribution network. The active and reactive fitting errors are small. A case is also taken to validate that the pro-posed method can improve the simulation precision.
期刊:
Annual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks workshops,2022年2022-September:425-433 ISSN:2473-0440
作者机构:
[Ding, Xiangling] Hunan Univ Sci & Technol, Sch Comp Sci & Engn, Xiangtan, Peoples R China.;[Ding, Xiangling] Guangdong Key Lab Intelligent Informat Proc, Shenzhen, Peoples R China.;[Ding, Xiangling] Shenzhen Key Lab Media Secur, Shenzhen, Peoples R China.;[Ding, Xiangling] Chinese Acad Sci, Inst Informat Engn, State Key Lab Informat Secur, Beijing, Peoples R China.;[Ding, Xiangling] Zhengzhou Xinda Inst Adv Technol, Zhengzhou, Peoples R China.
会议名称:
19th Annual IEEE International Conference on Sensing, Communication, and Networking (IEEE SECON)
会议时间:
SEP 20-23, 2022
会议地点:
ELECTR NETWORK
会议主办单位:
[Ding, Xiangling] Hunan Univ Sci & Technol, Sch Comp Sci & Engn, Xiangtan, Peoples R China.^[Ding, Xiangling] Guangdong Key Lab Intelligent Informat Proc, Shenzhen, Peoples R China.^[Ding, Xiangling] Shenzhen Key Lab Media Secur, Shenzhen, Peoples R China.^[Ding, Xiangling] Chinese Acad Sci, Inst Informat Engn, State Key Lab Informat Secur, Beijing, Peoples R China.^[Ding, Xiangling] Zhengzhou Xinda Inst Adv Technol, Zhengzhou, Peoples R China.^[Ding, Xiangling] Hunan Key Lab Serv Comp & Novel Software Technol, Xiangtan, Peoples R China.^[Ding, Xiangling] Guangdong Key Lab Informat Secur Technol, Guangzhou, Peoples R China.^[Zhu, Wenjie;Zhang, Dengyong] Changsha Univ Sci & Techno, Sch Comp & Commun Engn, Changsha, Peoples R China.
会议论文集名称:
IEEE International Conference on Sensing Communication and Networking
关键词:
video forensics;deepfake videos;phase-level stream;temporality-level stream
作者:
Tang, Qiang;Li, LinJiang;Wang, Jin;Kim, Gwang-Jun;Tang, Bin
作者机构:
[Li, LinJiang; Wang, Jin; Tang, Qiang; Tang, Bin] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Hunan Prov Key Lab Intelligent Proc Big Data Tran, Changsha 410114, Hunan, Peoples R China.;[Kim, Gwang-Jun] Chonnam Natl Univ, Dept Comp Engn, Gwangju 61186, South Korea.
会议名称:
8th International Conference on Artificial Intelligence and Security (ICAIS)
会议时间:
JUL 15-20, 2022
会议地点:
Qinghai, PEOPLES R CHINA
会议主办单位:
[Tang, Qiang;Li, LinJiang;Wang, Jin;Tang, Bin] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Hunan Prov Key Lab Intelligent Proc Big Data Tran, Changsha 410114, Hunan, Peoples R China.^[Kim, Gwang-Jun] Chonnam Natl Univ, Dept Comp Engn, Gwangju 61186, South Korea.
会议论文集名称:
Lecture Notes in Computer Science
关键词:
Mobile edge computing;Electric vehicles;UAV trajectory
摘要:
The research on the Internet of Things (IoT) and edge computing, especially Unmanned Aerial Vehicles assisted Mobile Edge Computing (UAV assisted MEC) attracted more and more interests of researchers. Nowadays, Electric Vehicles (EV) was introduced into the UAV assisted MEC system to improve system suitability and robustness. In this paper, an UAV and EV assisted MEC system was proposed and a paralled processing was involved with the goal of the edge side energy efficiency maximization, by jointly optimizing the communication scheduling, computing frequency and the trajectory of the UAV. The problem was formulated as a Mixed Integer Non-Liner Programming (MINLP), which was hard to solve. Therefore, the MINLP was divided into three sub-problems by applying the Block Coordinate Descent (BCD) method and solved by using Exhaustive Method (EM) and Successive Convex Optimization (SCO). In addition, a heuristic algorithm was put forward to get the optimization solution. The simulation results showed that our strategy has better performance compared with other benchmarks.
摘要:
Estimating accurate torque and speed is critical to control the operation of permanent magnet synchronous motors (PMSM). But the temperature factors are usually neglected in existing studies, which degrades estimation accuracy. In this paper, a thermal-aware digital twin model is proposed for PMSM to estimate motor torque and speed with the motor temperature and d-q axis current and voltage. Firstly, the motor parameters related to torque and speed are extracted by the Spearman correlation coefficients. Moreover, the stator winding temperature is selected as the input feature. Secondly, a digital model based on BP neural networks (BPNN) is established to estimate torque and speed. Thirdly, the parameters of the BPNN model are optimized by the whale optimization algorithm to accelerate the convergence speed and avoid local optima. Finally, experimental results show that the mean square error (MSE) of the BPNN model considering the temperature factors is reduced by 8.3%, which verifies that there is an effect of temperature on the torque and speed estimation. The MSE of the proposed method is reduced by 11.7% on average, which confirmed the higher accuracy of the proposed method compared with the classical BPNN model.
会议论文集名称:
International Conference on Control and Robots
关键词:
Neural-network;tremor;surgical robots
摘要:
As a representation of teleoperated robots, surgical robots based on teleoperation are widely applied in the medical field. Generally, it can greatly guarantee the performance of microsurgery in terms of control and postoperative recovery by using a surgical robot in comparison with traditional surgical operation. However, the performance of surgical robots is greatly disturbed by the physiological tremor of surgeon in the process of operation. In order to cancel the impacts of tremor signal, a neural-network-based (NN-based) algorithm is developed in this paper. For the proposed NN-based approach, we develop a hybrid wavelet basis function to deal with the variable tremor signal. Additionally, the proposed method can cancel the tremor signals based on the excellent ability of nonlinear mapping and generalization and does not rely on a priori structural parameters. In order to evaluate the performance of the proposed method, comparative experiments of five different kinds of NN-based tremor filter are performed by using tremor signals with different frequencies and amplitudes. Experimental results validated that the proposed algorithm can achieve the performance of suppressing the tremor signal of the processing error. It is can be noted that the surgical robots can ensure the control performance of the surgical robots by using the developed NN-based filter. The developed method can also be applied as a filter for suppressing vibrations of processing operations in the future, such as chatter in micro-milling.
作者:
Zhang, J. I. N.;Luo, Meng;Sun, Cheng;Qu, Peiqi
作者机构:
[Qu, Peiqi; Zhang, J. I. N.] Hunan Normal Univ, Coll Informat Sci & Engn, Changsha, Peoples R China.;[Luo, Meng; Sun, Cheng] Hunan Normal Univ, Coll Math & Stat, Changsha, Peoples R China.;[Zhang, J. I. N.] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha, Peoples R China.
会议名称:
21st International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP)
会议时间:
DEC 03-05, 2021
会议地点:
ELECTR NETWORK
会议主办单位:
[Zhang, J. I. N.;Qu, Peiqi] Hunan Normal Univ, Coll Informat Sci & Engn, Changsha, Peoples R China.^[Luo, Meng;Sun, Cheng] Hunan Normal Univ, Coll Math & Stat, Changsha, Peoples R China.^[Zhang, J. I. N.] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha, Peoples R China.
摘要:
Vehicle detection in aerial images has been applied in many fields and attracted more and more scholars' attention. In the task, the objects are multidirectional and arranged densely, the background information is complex, and the scale of the object is different. To achieve better detection performance, an improved detection model BFR-RetinaNet is proposed, which is based on the single-stage object detection model RetinaNet. BFR-RetinaNet optimizes vehicle positioning by adding a directional anchor box regression branch. Simultaneously, the model introduces a balanced feature pyramid structure to enhance the extraction of features and reduce the interference of complex backgrounds. The experimental results on the aerial dataset show that the precision, recall, and average precision of the proposed model have been improved to varying degrees. It achieves 86.2% Precision, 98.4% Recall, and 90.8% Average Precision (AP), which is 7.96, 0.45, and 0.58 points higher than R-RetinaNet.
摘要:
The cases of complex multi-form vehicle crash with vulnerable road users are serious crimes committed. However, there is a lack of practical and repeatable verification method for relevant cases now. This study surveying the data of vehicle-crash scenes, the crash sequences were decoupled into crash patterns among multiple units, and a simulation analysis method of full sequence dynamics modeling, simulation analysis, crash scene reconstruction and trace verification was constructed. The validity and calculation reliability of the method were verified by scientific research on actual crash cases. The decoupling simulation method constructed in this paper is suitable for solving the crash coupling of multi-vehicle/multi-person/multi-times sequence, which provides a new identification method for complex form crash analysis.
摘要:
In this paper, we propose a novel key-point detector with only one-level feature with the stride of 8, which is 75.0% less than methods with the stride of 4. Due to the reduction of the feature layers, firstly we adopt a new key-point labeling method, which can make full use of the detection points on the feature map. Secondly, we propose a U-shaped feature fusion module with group residual dense blocks, which works together with grouped convolutional and re-parameterization methods to bring significant improvements while reducing parameters. Thirdly, we use a soft non-key-point branch to re-weight the classification score. Using NVIDIA GeForce 3060 GPU and based on the VOC dataset, the proposed model with RepVGG-A0 runs about 51.4% faster than CenterNet with ResNet-18, runs 261.3% faster, and achieves higher accuracy than CenterNet with ResNet-101 under the resolution of 512 x 512.
摘要:
Conflict analysis is commonly based on a conflict situation involving agents and their ratings or attitudes toward a set of issues. Analyzing the relationships between agents is one of the essential topics in conflict analysis. Alliance, conflict, and neutrality are three typical relations. The majority of existing research adopts an auxiliary function that uses +1, -1, and 0 to denote these three relations concerning a single issue. An auxiliary function is aggregated for a group of issues, which is primarily limited to taking the average in the existing works. Moreover, computing the values of an auxiliary function is also associated with potential semantics issues. This paper proposes a probabilistic approach to analyzing agent relations, which is very different from the current approaches. Bayesian confirmation is adopted to explore how a rating confirms or disconfirms the alliance/conflict relation between two agents. Accordingly, we construct three regions of confirmatory, disconfirmatory, and neutral ratings. Three types of confirmation rules are induced from these regions and used to devise appropriate strategies in maintaining and developing relations with agents.