作者:
Zhai, ChaoFan, PengyangZhang, Hai -TaoChina Univ Geosci
Sch Automat Hubei Key Lab Adv Control & Intelligent Automat Co Wuhan 430074 Peoples R China China Univ Geosci
Engn Res Ctr Intelligent Technol Geoexplorat Minist Educ Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol
Engn Res Ctr Autonomous Intelligent Unmanned Syst Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol
State Key Lab Digital Mfg Equipments & Technol Wuhan 430074 Peoples R China
It has long been a challenging task for multi-agent systems (MASs) to inexpensively service probable events in non-convex environments. Coverage control provides an efficient framework to address MAS deployment proble...
详细信息
It has long been a challenging task for multi-agent systems (MASs) to inexpensively service probable events in non-convex environments. Coverage control provides an efficient framework to address MAS deployment problem for optimizing the cost of tackling unknown events. By means of the divideand-conquer methodology, this paper proposes a sectorial coverage formulation to configure MASs in non-convex hollow environments while ensuring load balancing among subregions. Thereby, a distributed controller is designed to drive each agent towards a desirable configuration that minimizes the coverage cost by simultaneously adopting sectorial partition mechanism. Theoretical analysis is conducted to ensure the asymptotic stability of closed-loop MASs with exponential convergence of equitable partition. In addition, a circular search algorithm is proposed to identify desirable solutions to such a sectorial coverage problem, which guarantees approximating the optimal deployment of MASs with arbitrarily small tolerance. Finally, both numerical simulations and multi-robot experiments are conducted to substantiate the efficiency of the present sectorial coverage approach.& COPY;2023 Elsevier Ltd. All rights reserved.
The widespread installation of advanced metering infrastructure (AMI) brings convenience to applications including but not limited to load management and demand response. However, AMI is also at risk of electricity th...
详细信息
The widespread installation of advanced metering infrastructure (AMI) brings convenience to applications including but not limited to load management and demand response. However, AMI is also at risk of electricity theft and non-technical loss. Using the smart meter data provided by AMI to dig out user electricity consumption behavior is an effective way to construct electricity theft detectors. In this paper, a new intermittent electricity theft attack behavior is presented which switches between committing electricity theft and honestly consuming electricity alternately to skillfully evade the existing detectors. Based on the assumption that the labels of intermittent adversaries are unavailable, a new machine learning-based detection framework is proposed to detect this attack. Initially electricity features are constructed based on time intervals divided by a numerical iteration method. Then light gradient boosting method (LightGBM) is used to classify the normal users and adversaries. Further, the disperse degree of users is designed for capturing the differences between the intermittent adversaries and others. A new 2D label set is then constructed by combining the predicted labels of LightGBM and the disperse degree. Finally, a variational Bayesian Gaussian mixture model is employed based on the 2D label set to sort the users into the normal users and adversaries visually. Results of the case studies show that the presented attack can evade state-of-the-art detectors but still gain high profits. In addition, the proposed machine learning-based detector outperforms state-of-the-art detectors on both persistent attacks and intermittent attacks.
A brain-computer interface (BCI) enables direct communication between the brain and an external device. Electroencephalogram (EEG) is a common input signal for BCIs, due to its convenience and low cost. Most research ...
详细信息
A brain-computer interface (BCI) enables direct communication between the brain and an external device. Electroencephalogram (EEG) is a common input signal for BCIs, due to its convenience and low cost. Most research on EEG-based BCIs focuses on the accurate decoding of EEG signals, while ignoring their security. Recent studies have shown that machine learning models in BCIs are vulnerable to adversarial attacks. This paper proposes adversarial filtering based evasion and backdoor attacks to EEG-based BCIs, which are very easy to implement. Experiments on three datasets from different BCI paradigms demonstrated the effectiveness of our proposed attack approaches. To our knowledge, this is the first study on adversarial filtering for EEG-based BCIs, raising a new security concern and calling for more attention on the security of BCIs.
There have been increasing interests in studying multiplex dynamical networks *** paper focuses on topology identiflcation of two-layer multiplex networks with peer-to-peer interlayer *** a two-layer network model in ...
详细信息
There have been increasing interests in studying multiplex dynamical networks *** paper focuses on topology identiflcation of two-layer multiplex networks with peer-to-peer interlayer *** a two-layer network model in which different layers have different coupling patterns,we propose novel methods to recover unknown topological structure of one layer,using the information of the other layer known as a *** proposed methods make full use of the measured evolutional states of the multiplex network itself,and treat the layer with a known structure as an auxiliary layer which is designed to identify the unknown topological *** with the traditional synchronization-based identiflcation method,the proposed methods are in no need of constructing an additional auxiliary network to identify the unknown topological layer,and thus greatly reduce the cost of topology ***,numerical simulations validate the effectiveness of the proposed methods.
Recent human matting methods typically suffer from two drawbacks: 1) high computation overhead caused by multiple stages, and 2) limited practical application due to the need for auxiliary guidance (e.g., trimap, mask...
详细信息
ISBN:
(纸本)9789819788576;9789819788583
Recent human matting methods typically suffer from two drawbacks: 1) high computation overhead caused by multiple stages, and 2) limited practical application due to the need for auxiliary guidance (e.g., trimap, mask, or background). To address these issues, we propose EfficientMatting, a real-time human matting method using only a single image as input. Specifically, EfficientMatting incorporates a bilateral network composed of two complementary branches: a transformer-based context information branch and a CNN-based spatial information branch. Furthermore, we introduce three novel techniques to enhance model performance while maintaining high inference efficiency. Firstly, we design a Semantic Guided Fusion Module (SGFM), which empowers the model to dynamically acquire valuable features with the assistance of context information. Secondly, we design a lightweight Detail Preservation Module (DPM) to achieve detail preservation and mitigate image artifacts during the upsampling process. Thirdly, we introduce the Supervised-Enhanced Training Strategy (SETS) to explicitly provide supervision on hidden features. Extensive experiments on P3M-10k, Human-2K, and PPM-100 datasets show that EfficientMatting outperforms state-of-the-art real-time human matting methods in terms of both model performance and inference speed.
As environmental pollution becomes increasingly serious and industrial energy consumption continuously rises, an intelligent and efficient industrial energy management policy is urgently needed to reduce costs and max...
详细信息
As environmental pollution becomes increasingly serious and industrial energy consumption continuously rises, an intelligent and efficient industrial energy management policy is urgently needed to reduce costs and maximize the benefits of industrial energy systems. However, modern industrial energy systems are characterized by hybrid industrial equipment actions, diverse objectives, and highly intermittent and stochastically distributed renewable energy sources. Therefore, efficient operation and control are difficult. This article presents a novel, model-free energy management policy using a hybrid action deep reinforcement learning algorithm for energy scheduling of industrial equipments operating in various modes. Specifically, the interaction process between the industrial energy management center and each equipment is modeled as a Markov decision process that minimizes the daily operating cost of the energy system and maximizes the revenue of the production equipment. Then, a double parameterized deep Q-networks that does not require an explicit environmental model is developed to learn the hybrid action signals using actor and critic networks, in which the double Q value mechanism avoids value overestimation and improves the algorithm efficiency. In addition, the policy gradient of the proposed algorithm is derived and its convergence proof is discussed. Finally, numerical studies are conducted using real-world data to evaluate algorithm performance and verify its effectiveness.
Multimodal emotion recognition in conversation (ERC) has garnered growing attention fromresearch communities in various fields. In this paper, we propose a Cross-modal Fusion Network with Emotion-Shift Awareness (CFN-...
详细信息
Multimodal emotion recognition in conversation (ERC) has garnered growing attention fromresearch communities in various fields. In this paper, we propose a Cross-modal Fusion Network with Emotion-Shift Awareness (CFN-ESA) for ERC. Extant approaches employ each modality equally without distinguishing the amount of emotional information in these modalities, rendering it hard to adequately extract complementary information from multimodal data. To cope with this problem, in CFN-ESA, we treat textual modality as the primary source of emotional information, while visual and acoustic modalities are taken as the secondary sources. Besides, most multimodal ERC models ignore emotion-shift information and overfocus on contextual information, leading to the failure of emotion recognition under emotion-shift scenario. We elaborate an emotion-shift module to address this challenge. CFN-ESA mainly consists of unimodal encoder (RUME), cross-modal encoder (ACME), and emotion-shift module (LESM). RUME is applied to extract conversation-level contextual emotional cues while pulling together data distributions between modalities;ACME is utilized to perform multimodal interaction centered on textual modality;LESM is used to model emotion shift and capture emotion-shift information, thereby guiding the learning of the main task. Experimental results demonstrate that CFN-ESA can effectively promote performance for ERC and remarkably outperform state-of-the-art models.
Direct torque control (DTC) is increasingly attracted for high performance control of surface permanent magnet synchronous motors (SPMSMs) due to its easy implementation and fast dynamic response. However, the convent...
详细信息
Direct torque control (DTC) is increasingly attracted for high performance control of surface permanent magnet synchronous motors (SPMSMs) due to its easy implementation and fast dynamic response. However, the conventional switching-table-based method inevitably produces large torque and stator flux ripples because the selection of inverter's active-voltage vector is depending on the sign of torque and flux errors through hysteresis comparators regardless of their amplitude errors. To resolve these problems, a novel DTC strategy based on flux-torque decoupling is proposed in this paper. With the proposed method, two desired voltage vectors are firstly constructed to achieve the decoupling control of stator flux and torque by analyzing the relationships between applied voltage and torque and stator flux derivative. Afterwards, by applying vector synthesis to analyze the generation of two desired voltage vectors, the corresponding inverter's active-voltage vectors and their duty ratios are determined, so as to achieve the precise regulation of stator flux and torque with little ripples. Furthermore, in order to minimize the influence of machine parameters variations, a simple and real-time identification method for the ratio between permanent magnet flux linkage and stator inductance is presented. Finally, the experimental results indicate the effectiveness and feasibility of the proposed strategy.
This article presents a closed-form analytical solution to the harmonic spectrum of output voltage of a single-phase H-bridge inverter, and gives the precise harmonic spectrum considering the effects of dead time and ...
详细信息
This article presents a closed-form analytical solution to the harmonic spectrum of output voltage of a single-phase H-bridge inverter, and gives the precise harmonic spectrum considering the effects of dead time and dc bus voltage ripple in a digitally controlled system. Since the H-bridge is the basic block in converters, this solution and spectrum can be extended and applied to a variety of pulsewidth-modulation-based topologies. The interaction between modulation waveform and triangular during the modulation process is fully analyzed from a mathematical perspective so that the combined effects of digital sampling, dead time, and dc bus voltage ripple on the output voltage are summarized in time and frequency domains. Furthermore, the presented harmonic spectra do not need to judge the current polarity in calculation, which means that the exact amplitude and phase of each output harmonic can be obtained accurately, providing the important theoretical basis for system parameter design and specific harmonic compensation or elimination. The presented analysis results are verified by simulations and experiments.
Dead time is generally used to avoid the short circuit of the dc source, which causes harmonics in the output voltage and current of the voltage source inverters (VSIs). Based on an accurate harmonics calculation mode...
详细信息
Dead time is generally used to avoid the short circuit of the dc source, which causes harmonics in the output voltage and current of the voltage source inverters (VSIs). Based on an accurate harmonics calculation model of digital sinusoidal pulsewidth modulation, harmonics caused by dead time can be analyzed and calculated accurately. The proposed method obtains the compensation waveforms by the derived calculation module and detailed operation steps and then injects these into the sinusoidal reference voltage to eliminate the corresponding frequency harmonics caused by the dead time effect. The phase delay of the fundamental voltage caused by dead time is also considered. Moreover, this method avoids detecting the current polarity, affecting the compensation effect. Simulation and experimental results of the proposed method are presented to validate the effectiveness.
暂无评论