检索结果-内蒙古大学图书馆

A Channel-Augmented Multi-Domain Graph Convolutional Network for Fatigue Driving Detection

学校读者我要写书评

暂无评论

A Channel-Augmented Multi-Domain Graph Convolutional Network...

Industrial Automation, Robotics and Control engineering (IARCE), International Conference on

作者： Mingyi Sun Weigang Cui Yang Li Department of Automation Science and Electrical Engineering Beihang University Beijing China School of Engineering Medicine Beihang University Beijing China Department of Automation Science and Electrical Engineering State Key Laboratory of Virtual Reality Technology and Systems The Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

ISBN: (数字)9798350380323

ISBN: (纸本)9798350380330

Electroencephalography (EEG) has emerged as a crucial cornerstone within the realm of brain-computer interface (BCI) applications, with its significance notably pronounced in the field of fatigue detection. However, the inherent limitations of EEG acquisition equipment during real driving scenarios have contributed to the constrained robustness of existing models. Moreover, most of recent methods failed to extract robust multi-domain features, leading to a suboptimal performance. To address these challenges, we propose a novel channel-augmented multi-domain graph convolutional network (CA-MDGCNet). Specifically, the initial EEG signals are enriched by incorporating supplementary virtual EEG channels, distinguished as learnable parameters within the network architecture. Then, differential entropy features are extracted from the augmented EEG signals. Following this, a multi-domain graph convolutional network is designed to encode high-level EEG features by means of convolutions in diverse paths, which is beneficial to integrating the characteristics extracted from multiple domains. Finally, the classification block derives the detection outcome from the refined feature maps. To substantiate the potency of the proposed method, the validation was conducted on the publicly accessible SEED-VIG. The proposed CA-MDGCNet not only demonstrates more promising performance compared to state-of-the-art approaches but also underscores the potential viability of our method for the realm of fatigue driving detection.

关键词： Graph convolutional networks Convolution Service robots Neural activity Feature extraction Fatigue Brain modeling Electroencephalography Entropy Robustness

Active tactile object exploration with Gaussian processes

学校读者我要写书评

暂无评论

Active tactile object exploration with Gaussian processes

IEEE/RSJ International Conference on Intelligent Robots and systems

作者： Zhengkun Yi Roberto Calandra Filipe Veiga Herke van Hoof Tucker Hermans Yilei Zhang Jan Peters Intelligent Autonomous Systems Lab Department of Computer Science Technische Universitat Darmstadt Hochschulstr. 10 64289 Germany School of Mechanical and Aerospace Engineering Nanyang Technological University 50 Nanyang Avenue Singapore 639798 University of Utah Robotics Center School of Computing University of Utah USA

ISBN: (纸本)9781509037636

Accurate object shape knowledge provides important information for performing stable grasping and dexterous manipulation. When modeling an object using tactile sensors, touching the object surface at a fixed grid of points can be sample inefficient. In this paper, we present an active touch strategy to efficiently reduce the surface geometry uncertainty by leveraging a probabilistic representation of object surface. In particular, we model the object surface using a Gaussian process and use the associated uncertainty information to efficiently determine the next point to explore. We validate the resulting method for tactile object surface modeling using a real robot to reconstruct multiple, complex object surfaces.

关键词： Gaussian processes Touch tactile sensors grid point

Uniqueness and uniform structural stability of poiseuille flows in an infinitely long pipe with navier boundary conditions

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Yun Xie, Chunjing School of Mathematical Sciences Center for dynamical systems and differential equations Soochow University Suzhou China School of mathematical Sciences Institute of Natural Sciences Ministry of Education Key Laboratory of Scientific and Engineering Computing IMA-Shanghai Shanghai Jiao Tong University 800 Dongchuan Road Shanghai China

In this paper, uniqueness and uniform structural stability of Poiseuille flows in an infinitely long pipe with Navier boundary conditions are established for axisymmetric solutions of steady Navier-Stokes system. The crucial point is that the estimate is uniform with respect both the flux of flows and slip coefficient which appeared in Navier boundary conditions. With the aid of special structure of Navier-Stokes system and the refined estimate for some quantities such as radial velocity, the uniqueness and existence of steady solutions of Navier-Stokes system can be obtained even when the external forces are large as long as the fluxes of flows are large. The delicate decomposition in the two dimensional plane for slip coefficient and frequency corresponding to Fourier variable in the axial direction plays a key role to achieve these estimates. Copyright © 2021, The Authors. All rights reserved.

关键词： Stability

Attention Is Not the Only Choice: Counterfactual Reasoning for Path-Based Explainable Recommendation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Yicong Sun, Xiangguo Chen, Hongxu Zhang, Sixiao Yang, Yu Xu, Guandong Data Science and Machine Intelligence Lab Faculty of Engineering and Information Technology University of Technology Sydney SydneyNSW2007 Australia Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong999077 Hong Kong School of Information Technology and Electrical Engineering The University of Queensland BrisbaneQLD4072 Australia Department of Systems Engineering and Engineering Management Nanyang Technological University Singapore999077 Singapore Department of Computing The Hong Kong Polytechnic University Hong Kong999077 Hong Kong

Compared with only pursuing recommendation accuracy, the explainability of a recommendation model has drawn more attention in recent years. Many graph-based recommendations resort to informative paths with the attention mechanism for the explanation. Unfortunately, these attention weights are intentionally designed for model accuracy but not explainability. Recently, some researchers have started to question attention-based explainability because the attention weights are unstable for different reproductions, and they may not always align with human intuition. Inspired by the counterfactual reasoning from causality learning theory, we propose a novel explainable framework targeting path-based recommendations, wherein the explainable weights of paths are learned to replace attention weights. Specifically, we design two counterfactual reasoning algorithms from both path representation and path topological structure perspectives. Moreover, unlike traditional case studies, we also propose a package of explainability evaluation solutions with both qualitative and quantitative methods. We conduct extensive experiments on four real-world datasets, the results of which further demonstrate the effectiveness and reliability of our method. Copyright © 2024, The Authors. All rights reserved.

关键词： Graphic methods

Lessons Learnt from Designing a Smart Clothing Telehealth System for Hospital Use 20

学校读者我要写书评

暂无评论

Lessons Learnt from Designing a Smart Clothing Telehealth Sy...

Proceedings of the 32nd Australian Conference on Human-Computer Interaction

作者： Deepti Aggarwal Thuong Hoang Bernd Ploderer Frank Vetere Rohit Ashok Khot Mark Bradford HAFP Research Lab RMIT University Australia School of Information Technology Deakin University Australia School of Electrical Engineering and Computer Science Queensland University of Technology Australia Interaction Design Lab School of Computing and Information Systems The University of Melbourne Australia Dept. of Anaesthesia and Pain Management Royal Children's Hospital Australia

ISBN: (纸本)9781450389754

In this paper, we describe the design journey of a smart clothing system, SoPhy from the research laboratory to finally being evaluated in the hospital setting. SoPhy is a smart socks-based system, designed to make physiotherapy video consultations effective for assessing lower limb issues. SoPhy is the result of a 3-year journey of development, study and refinement of a research prototype done in collaboration with a physiotherapist. Drawing on this journey, we present seven lessons that emphasize on the importance of fostering strong collaborations with clinicians to move beyond laboratory studies and reach the target health setting. We provide contextual narratives on how we designed a comfortable smart clothing for patients; how we created an intuitive mapping of sensor data for clinicians; how we integrated hospital practice in the system design, and how we managed the ethics clearance for the field evaluation. We hope that these lessons are useful for HCI and health researchers who aim to innovate the field of health but feel restricted with the little knowledge of design and electronics.

关键词： Telehealth Physiotherapy Video Consultations Smart Clothing Digital health

Cryptanalyzing an image encryption algorithm based on autoblocking and electrocardiography

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Li, Chengqing Lin, Dongdong Lü, Jinhu Hao, Feng School of Computer Science and Electronic Engineering Hunan University Hunan410082 China Academy of Mathematics and Systems Sciences Chinese Academy of Sciences Beijing100190 China School of Computing Science Newcastle University Newcastle Upon TyneNE1 7RU United Kingdom

This paper analyzes the security of an image encryption algorithm proposed by Ye and Huang [IEEE MultiMedia, vol. 23, pp. 64-71, 2016]. The Ye-Huang algorithm uses electrocardiography (ECG) signals to generate the initial key for a chaotic system and applies an autoblocking method to divide a plain image into blocks of certain sizes suitable for subsequent encryption. The designers claimed that the proposed algorithm is "strong and flexible enough for practical applications". In this paper, we perform a thorough analysis of their algorithm from the view point of modern cryptography. We find it is vulnerable to the known plaintext attack: based on one pair of a known plain-image and its corresponding cipher-image, an adversary is able to derive a mask image, which can be used as an equivalent secret key to successfully decrypt other cipherimages encrypted under the same key with a non-negligible probability of 1/256. Using this as a typical counterexample, we summarize security defects in the design of the Ye-Huang algorithm. The lessons are generally applicable to many other image encryption *** Codes 94A60 Copyright © 2017, The Authors. All rights reserved.

关键词： Cryptography

When crowdsensing meets federated learning: Privacy-preserving mobile crowdsensing system

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhao, Bowen Liu, Ximeng Chen, Weineng the School of Computing and Information Systems Singapore Management University Singapore Singapore the College of Mathematics and Computer Science Fuzhou University Fujian China Cyberspace Security Research Center Peng Cheng Laboratory Shenzhen China the School of Computer Science and Engineering South China University of Technology Guangzhou China

Mobile crowdsensing (MCS) is an emerging sensing data collection pattern with scalability, low deployment cost, and distributed characteristics. Traditional MCS systems suffer from privacy concerns and fair reward distribution. Moreover, existing privacy-preserving MCS solutions usually focus on the privacy protection of data collection rather than that of data processing. To tackle faced problems of MCS, in this paper, we integrate federated learning (FL) into MCS and propose a privacy-preserving MCS system, called CROWDFL. Specifically, in order to protect privacy, participants locally process sensing data via federated learning and only upload encrypted training models. Particularly, a privacy-preserving federated averaging algorithm is proposed to average encrypted training models. To reduce computation and communication overhead of restraining dropped participants, discard and retransmission strategies are designed. Besides, a privacy-preserving posted pricing incentive mechanism is designed, which tries to break the dilemma of privacy protection and data evaluation. Theoretical analysis and experimental evaluation on a practical MCS application demonstrate the proposed CROWDFL can effectively protect participants privacy and is feasible and efficient. © 2021, CC BY.

关键词： Data acquisition

Non-invasive neuroimaging: Generalized Linear Models for interpreting functional Near Infrared Spectroscopy signals

学校读者我要写书评

暂无评论

Non-invasive neuroimaging: Generalized Linear Models for int...

International IEEE/EMBS Conference on Neural engineering, CNE

作者： Michele Butti Matteo Caffini Anna C. Merzagora Anna M. Bianchi Giuseppe Baselli Banu Onaral Piercesare Secchi Sergio Cerutti Department of Biomedical Engineering Polytechnic University of Milan Italy Department of Physics Polytechnic University of Milan Italy School of Biomedical Engineering Science and Health Systems Drexel University Philadelphia PA USA Modeling and Scientific Computing Center (MOX) Department of Mathematics Polytechnic University of Milano Milan USA

Cognitive activity is related to important changes in the local blood flow level and in the oxygenation of the blood. These two effects lead to a modification of the optical properties of the cerebral cortex. With the aid of the functional near infrared spectroscopy (fNIRS) technique it is possible, through optical measures, to achieve information about the hemodynamic features of the brain activation. The aim of this study was to find a method to identify and to map the cerebral areas activated during a sustained attention task (Conner's continuous performance test - CPT) in a group of healthy subjects. This information will be of fundamental interest for a following study on a group of patients that will be administered the same examination. We propose a new analysis method based on the theory of generalized linear model (GLM) in order to obtain intuitive cerebral activation maps during the performing of cognitive tasks

关键词： Neuroimaging Infrared spectra Biomedical engineering Testing Blood flow Biomedical optical imaging Brain Optical signal processing Biomedical measurements Hemodynamics

Symmetrized two-scale finite element discretizations for partial differential equations with symmetric solutions

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hou, Pengyu Liu, Fang Zhou, Aihui School of Mathematical Sciences Beijing Normal University Beijing100875 China School of Statistics and Mathematics Central University of Finance and Economics Beijing102206 China LSEC Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

In this paper, a symmetrized two-scale finite element method is proposed for a class of partial differential equations with symmetric solutions. With this method, the finite element approximation on a fine tensor product grid is reduced to the finite element approximations on a much coarse grid and a univariant fine grid. It is shown by both theory and numerics including electronic structure calculations that the resulting approximation still maintains an asymptotically optimal accuracy. Consequently the symmetrized two-scale finite element method reduces computational cost *** Codes 65N15, 65N25, 65N30, 65N50 Copyright © 2022, The Authors. All rights reserved.

关键词： Partial differential equations