检索结果-内蒙古大学图书馆

Formal modeling and performance evaluation for hybrid systems: A probabilistic hybrid process algebra-based approach

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Fujun J. Cao, Zining Tan, Lixing Li, Zhen College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Key Laboratory of Safety-Critical Software Nanjing University of Aeronautics and Astronautics Ministry of Industry and Information Technology Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics Nanjing China Science and Technology on Electro-optic Control Laboratory Luoyang China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China

Probabilistic behavior is omnipresent in computer controlled systems, in particular, so-called safety-critical hybrid systems, because of various reasons, like uncertain environments, or fundamental properties of nature. In this paper, we extend existing hybrid process algebra ACPsrths with probability without replacing nondeterministic choice operator. In view of some shortcomings in existing approximate probabilistic bisimulation, we relax the constrains and propose a novel approximate probabilistic bisimulation relation. After that, we present a performance evaluation language CTRML, to reason over probabilistic systems, which extend the results to real number. Along with the specification language, we present a set of algorithms for the evaluation of the language. Additionally, we transfer the hybrid process algebra to probabilistic transition system and show experimental results. Copyright © 2020, The Authors. All rights reserved.

关键词： Hybrid systems

A Preliminary Study on the Functional Coupling between Nerve and Blood Microcirculation for Applications in Rehabilitation Robots

学校读者我要写书评

暂无评论

A Preliminary Study on the Functional Coupling between Nerve...

IEEE International Conference on Robotics and Biomimetics

作者： Qingge Li Yuanzhe Dong Yuxiang Zhang Xin Wang Naifu Jiang Jianping Huang Han Cui Lan Tian Yue Zheng Xiangxin Li Lin Wang Guanglin Li Wenyuan Liang Liang Peng Peng Fang CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen China National Research Center for Rehabilitation Technical Aids Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Rehabilitation robots play an important role in the motor function rehabilitation for stroke survivors with hemiplegia. However, the rehabilitation effect of current robots is still limited partly because a single training of motor function can be strongly affected by the decreased blood supply function of the bedridden patients. This work proposed an approach to study the coupling relationship between the motor and blood supply functions by combining the synchronously recorded EEG and cerebral blood oxygen information, where the cerebrations in different movement paradigms were analyzed from an aspect of "functional coupling". The results show that the information of oxyhemoglobin concentration change (ΔHbO) can effectively indicate the cortex activation, and a stronger blood supply is needed in cortexes to perform body movements. The correlations within motor cortexes are significantly stronger than the ones between motor and prefrontal cortexes, and a higher resistance level of extremity training will cause stronger correlations. Calculation of transfer entropy (TE) shows that there exists a bidirectional information transmission between the electrophysiological and blood supply signals, and more information is transmitted always in the direction from ΔHbO to EEG than in the opposite direction. The information transmission or the coupling relationship can be significantly enhanced by extremity movements, and large TE values are achieved in the Theta, Beta and Gamma frequency bands of EEG that correspond to motor functions. This work has demonstrated the functional coupling between nerve and blood microcirculation, which would provide a technical guidance to improve the rehabilitation effect for current robot systems and have great application potentials.

关键词：

Frequency Perception Network for Camouflaged Object Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cong, Runmin Sun, Mengyao Zhang, Sanyi Zhou, Xiaofei Zhang, Wei Zhao, Yao School of Control Science and Engineering Key Laboratory of Machine Intelligence and System Control Ministry of Education Shandong University Jinan Shandong China School of Automation Hangzhou Dianzi University Zhejiang Hangzhou China Institute of Information Science Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing Jiaotong University Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China

Camouflaged object detection (COD) aims to accurately detect objects hidden in the surrounding environment. However, the existing COD methods mainly locate camouflaged objects in the RGB domain, their performance has not been fully exploited in many challenging scenarios. Considering that the features of the camouflaged object and the background are more discriminative in the frequency domain, we propose a novel learnable and separable frequency perception mechanism driven by the semantic hierarchy in the frequency domain. Our entire network adopts a two-stage model, including a frequency-guided coarse localization stage and a detail-preserving fine localization stage. With the multi-level features extracted by the backbone, we design a flexible frequency perception module based on octave convolution for coarse positioning. Then, we design the correction fusion module to step-by-step integrate the high-level features through the prior-guided correction and cross-layer feature channel association, and finally combine them with the shallow features to achieve the detailed correction of the camouflaged objects. Compared with the currently existing models, our proposed method achieves competitive performance in three popular benchmark datasets both qualitatively and quantitatively. The code will be released at https://***/rmcong/FPNet_ACMMM23. © 2023, CC BY-NC-SA.

关键词： Frequency domain analysis

Redundant-Manipulator Minimal Motion via Different-Precision Discrete-Time Zhang Neural Dynamics Algorithms Especially Ten-Instant One

学校读者我要写书评

暂无评论

Redundant-Manipulator Minimal Motion via Different-Precision...

Chinese Automation Congress (CAC)

作者： Zanyu Tang Jinjin Guo Jianrong Chen Yunong Zhang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Jishou University Jishou China Guangdong Key Laboratory of Modern Control Technology Guangzhou China School of Public Health and Management Youjiang Medical University for Nationalities Baise China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Guangzhou China

ISBN: (纸本)9781665426480

As a significant and basic robotic sub-topic, the problem of optimal MPC (motion planning & control) of ordinarily redundant manipulator widely exists in many fields, such as industry and daily-life applications. Following previous work, the aim of this paper is at solving the problem of velocity-level minimal joint motion planning & control (VLMJMPC) in a way of discrete time. Firstly, the VLMJMPC problem is introduced and analyzed using Zhang neural dynamics (ZND) method, and the motion scheme is then given. Secondly, by using ZND and Lagrange-multiplier methods, a continuous-time (CT) model for real-time solving the problem is established. In order to realize on digital computers, we use a ten-instant Zhang time discretization (abbreviated as ZTD) general formula with the fifth-order precision to discretize the model, and a special algorithm with high precision is derived, developed and analyzed. Finally, five discrete-time ZND (DTZND) algorithms are further acquired by adopting this ten-instant ZTD formula and other ZTD formulas, and the corresponding theoretical analyses are given. Computer experiment results numerically verify the online effectiveness and correctness of the developed five DTZND algorithms.

关键词： Industries Digital computers Service robots Heuristic algorithms Computational modeling Dynamics Real-time systems

Intelligent vision-Assisted Obstacle Avoidance and Unknown Seasonal Products Navigation in Farmer's Market for the Visually Impaired

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Liu, Mei Chen, Yunhua Djoulde, Aristide He, Mengfan Rao, Jinjun Giernacki, Wojciech Wang, Zhiming Chen, Jinbo Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China Institute of Robotics and Machine Intelligence Faculty of Control Robotics and Electrical Engineering Poznan University of Technology Piotrowo 3a Poznan60-965 Poland

Abstract: Shopping at a farmer's market is a considerable daily challenge for the visually impaired. General indoor obstacle avoidance and navigation algorithms are not fully applicable to the crowded and dynamic shopping environment of farmer's market. To overcome these challenges and provide precise assistance to visually impaired, this paper proposes an intelligent vision-assisted (IVA) algorithm for navigating narrow and crowded farmer's market aisles. The algorithm employs a pedestrian detection camera based on deep learning as the hardware to intelligently detect the type and number of pedestrians in front, and guides a navigation robot to adopt corresponding obstacle avoidance strategies in time according to the detection results. Different from general obstacle avoidance methods, IVA doesn't have issues of guiding robot to make frequent turns and change routes when avoiding obstacles in a crowded and narrow environment, making it more suitable for the visually impaired. Additionally, this paper proposes an unknown seasonal product navigation (USPN) algorithm for robots to automatically search for navigation information that has changed. When used in conjunction with a camera driven by deep learning, USPN successfully guided a navigation robot to identify the names and coordinates of newly listed products. Compared with general navigation algorithms, USPN can guide robots to update product information timely and intelligently. Experimental tests conducted in a farmer's market demonstrated that IVA is more intelligent and efficient than the dynamic window approach (DWA) in obstacle avoidance performance, and it is more suitable for guiding the visually impaired;furthermore, USPN successfully guides the robot to automatically acquire products information that changes with the seasons, and the acquired product categories and locations are precise. Particularly, IVA and USPN can be used as references when designing guide robots for use in public spaces like super

关键词： Navigation

Transfer Learning for EEG-Based Brain-Computer Interfaces: A Review of Progress Made Since 2016

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wu, Dongrui Xu, Yifan Lu, Bao-Liang The Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Brain Science and Technology Research Center Qing Yuan Research Institute Shanghai Jiao Tong University 800 Dong Chuan Road Shanghai200240 China

A brain-computer interface (BCI) enables a user to communicate with a computer directly using brain signals. The most common non-invasive BCI modality, electroencephalogram (EEG), is sensitive to noise/artifact and suffers between-subject/within-subject non-stationarity. Therefore, it is difficult to build a generic pattern recognition model in an EEG-based BCI system that is optimal for different subjects, during different sessions, for different devices and tasks. Usually, a calibration session is needed to collect some training data for a new subject, which is time-consuming and user unfriendly. Transfer learning (TL), which utilizes data or knowledge from similar or relevant subjects/sessions/devices/tasks to facilitate learning for a new subject/session/device/task, is frequently used to reduce the amount of calibration effort. This paper reviews journal publications on TL approaches in EEG-based BCIs in the last few years, i.e., since 2016. Six paradigms and applications - motor imagery, event-related potentials, steady-state visual evoked potentials, affective BCIs, regression problems, and adversarial attacks - are considered. For each paradigm/application, we group the TL approaches into cross-subject/session, cross-device, and cross-task settings and review them separately. Observations and conclusions are made at the end of the paper, which may point to future research directions. Copyright © 2020, The Authors. All rights reserved.

关键词： Brain computer interface

Weld defect detection of power battery pack based on image segmentation

学校读者我要写书评

暂无评论

International Journal of Wireless and Mobile Computing 2022年第2期23卷 139-145页

作者： Tao, Bo He, Fuqiang Tang, Quan Guo, Zhinan Long, Hansen Li, Shidong Cao, Yongcheng Ruan, Guijian Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan430081 China Precision Manufacturing Institute Wuhan University of Science and Technology Wuhan430081 China OPT Machine Vision Tech Co. Ltd Dongguan523852 China Jingmen Wusan Mechanism Equipment Manufacture Co. Ltd Jingmen431821 China Jiangsu Ruihong Photoelectric Technology Co. Ltd. Suqian321300 China

The safety and production efficiency are an important part of the power batteries production process and need to be considered seriously. Aiming at the welding quality of a power battery, a three-dimensional detection method based on the line laser sensor was proposed. Firstly, the depth data of the weld surface of the battery top cover is obtained by using a line laser sensor, and the defect area is segmented by using a multi thresholds segmentation method based on contour lines. Through the connected domain algorithm, the centres of defective areas are located. And the defect type is determined according to distance between the centres of the defect areas. Experimental results show that the detection rate reaches 97%, which indicates that the scheme has high detection accuracy and strong stability, and verifies the effectiveness of the method. Copyright © 2022 Inderscience Enterprises Ltd.

关键词： Welds

MLP: Motion Label Prior for Temporal Sentence Localization in Untrimmed 3D Human Motions

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yan, Sheng Liu, Mengyuan Wang, Yong Liu, Yang Chen, Chen Liu, Hong School of Artificial Intelligence Chongqing University of Technology Chongqing401120 China Key Laboratory of Machine Perception Shenzhen Graduate School Peking University Shenzhen518055 China College of Computer Science Sichuan University Chengdu610065 China Center for Research in Computer Vision University of Central Florida FL32826 United States

In this paper, we address the unexplored question of temporal sentence localization in human motions (TSLM), aiming to locate a target moment from a 3D human motion that semantically corresponds to a text query. Considering that 3D human motions are captured using specialized motion capture devices, motions with only a few joints lack complex scene information like objects and lighting. Due to this character, motion data has low contextual richness and semantic ambiguity between frames, which limits the accuracy of predictions made by current video localization frameworks extended to TSLM to only a rough level. To refine this, we devise two novel label-prior-assisted training schemes: one embed prior knowledge of foreground and background to highlight the localization chances of target moments, and the other forces the originally rough predictions to overlap with the more accurate predictions obtained from the flipped start/end prior label sequences during recovery training. We show that injecting label-prior knowledge into the model is crucial for improving performance at high IoU. In our constructed TSLM benchmark, our model termed MLP achieves a recall of 44.13 at IoU@0.7 on the BABEL dataset and 71.17 on HumanML3D (Restore), outperforming prior works. Finally, we showcase the potential of our approach in corpus-level moment retrieval. Our source code is openly accessible at https://***/eanson023/mlp. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

Copy and Paste GAN: Face Hallucination From Shaded Thumbnails

学校读者我要写书评

暂无评论

Copy and Paste GAN: Face Hallucination From Shaded Thumbnail...

Conference on Computer vision and Pattern Recognition (CVPR)

作者： Yang Zhang Ivor W. Tsang Yawei Luo Chang-Hui Hu Xiaobo Lu Xin Yu School of Automation Southeast University China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University China Centre for Artificial Intelligence University of Technology Sydney Australia School of Computer Science and Technology Huazhong University of Science and Technology China Southeast University Nanjing China Australian Centre for Robotic Vision Australian National University Australia

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Existing face hallucination methods based on convolutional neural networks (CNN) have achieved impressive performance on low-resolution (LR) faces in a normal illumination condition. However, their performance degrades dramatically when LR faces are captured in low or non-uniform illumination conditions. This paper proposes a Copy and Paste Generative Adversarial Network (CPGAN) to recover authentic high-resolution (HR) face images while compensating for low and non-uniform illumination. To this end, we develop two key components in our CPGAN: internal and external Copy and Paste nets (CPnets). Specifically, our internal CPnet exploits facial information residing in the input image to enhance facial details; while our external CPnet leverages an external HR face for illumination compensation. A new illumination compensation loss is thus developed to capture illumination from the external guided face image effectively. Furthermore, our method offsets illumination and upsamples facial details alternatively in a coarse-to-fine fashion, thus alleviating the correspondence ambiguity between LR inputs and external HR inputs. Extensive experiments demonstrate that our method manifests authentic HR face images in a uniform illumination condition and outperforms state-of-the-art methods qualitatively and quantitatively.

关键词： Face Lighting Gallium nitride Image resolution Feature extraction Generative adversarial networks Automation