检索结果-内蒙古大学图书馆

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Ashirbad Pradhan Jiayuan He Ning Jiang Department of Systems Design Engineering Engineering Bionics Lab Faculty of Engineering University of Waterloo Waterloo Canada National Clinical Research Center for Geriatrics West China Hospital Sichuan University China Manufacturing Sichuan University Chengdu China

Recently, surface electromyography (sEMG) has emerged as a novel biometric trait for personal identification, potentially providing a superior spoof-resistant solution over existing traits. The sEMG possesses a unique dual-mode security: they differ between individuals (biometric-mode), and different gestures have different sEMG characteristics (knowledge-mode). To leverage the knowledge-mode facet of the dual-mode security, the previous studies have utilized a multicode framework involving the fusion of codes (gestures), however, the analysis involved data recorded on a single day and from a small subject-pool. In this study, wrist EMG data collected from 43 participants over three different days while performing static hand/wrist gestures was utilized in two cross-day analyses, where the training and testing data were from different days. Three levels of fusion, score, rank, and decision were investigated to determine the optimal fusion scheme. The results showed that the score-level fusion scheme resulted in a median rank-1 accuracy of 77.9% and rank-5 accuracy of 99.6%, all significantly higher (p<0.001) than the respective single-code gesture. Our results showed that the multicode sEMG biometric framework provides superior identification performance in a more realistic cross-day scenario.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Computationally efficient multiscale estimation of large-scale dynamic systems

引用

IEEE International Conference on Image Processing

作者： T.T. Ho P.W. Fieguth A.S. Willsky Lab. for Inf. & Decision Syst. MIT Cambridge MA USA Department of Systems Design Engineering University of Waterloo Canada

ISBN: (纸本)0818688211

Statistical estimation of large-scale dynamic systems governed by stochastic partial differential equations is important in a wide range of scientific applications. However, the realization of computationally efficient algorithms for statistical estimation of such dynamic systems is very difficult. Conventional linear least squares methods are impractical for both computational and storage reasons. A previously-developed multiscale estimation methodology has been successfully applied to a number of large-scale static estimation problems. In this paper we apply the multiscale approach to the more challenging dynamic estimation problems, introducing a recursive procedure that efficiently propagates multiscale models for the estimation errors in a manner analogous to, but more efficient than, the Kalman filter's propagation of the error covariances. We illustrate our research in the context of 1-D and 2-D diffusive processes.

关键词： Large-scale systems Estimation error Sea measurements Stochastic systems Partial differential equations Recursive estimation Kalman filters Optical filters Optical computing Oceans

来源：评论

学校读者我要写书评

暂无评论

Self-Reproduction and Evolution in Cellular Automata: 25 Years after Evoloops

arXiv

引用

arXiv 2024年

作者： Sayama, Hiroki Nehaniv, Chrystopher L. Binghamton Center of Complex Systems Binghamton University State University of New York BinghamtonNY United States Waseda Innovation Lab Waseda University Tokyo Japan Waterloo Institute for Complexity and Innovation Departments of Systems Design Engineering of Electrical & Computer Engineering and of Applied Mathematics University of Waterloo WaterlooON Canada

The year of 2024 marks the 25th anniversary of the publication of evoloops, an evolutionary variant of Chris Langton’s self-reproducing loops which proved constructively that Darwinian evolution of self-reproducing organisms by variation and natural selection is possible within deterministic cellular automata. Over the last few decades, this line of Artificial Life research has since undergone several important developments. Although it experienced a relative dormancy of activities for a while, the recent rise of interest in open-ended evolution and the success of continuous cellular automata models have brought researchers’ attention back to how to make spatio-temporal patterns self-reproduce and evolve within spatially distributed computational media. This article provides a review of the relevant literature on this topic over the past 25 years and highlights the major accomplishments made so far, the challenges being faced, and promising future research directions. Copyright © 2024, The Authors. All rights reserved.

关键词： Cellular automata

来源：评论

学校读者我要写书评

暂无评论

Vehicle Group Identification and Evolutionary Analysis Using Vehicle Trajectory Data

SSRN

引用

SSRN 2023年

作者： Lei, Cailin Shangguan, Qiangqiang Ji, Yuxiong Du, Yuchuan Samuel, Siby Key Laboratory of Road and Traffic Engineering Ministry of Education Tongji University Shanghai201804 China Department of Systems Design Engineering University of Waterloo 200 University Avenue West WaterlooONN2L 3G1 Canada Department of Civil and Environmental Engineering University of Waterloo WaterlooONN2L 3G1 Canada User Performance Lab Department of Systems Design Engineering University of Waterloo 200 University Avenue West WaterlooONN2L 3G1 Canada

Vehicles often move forward in groups on the highways, especially when speed and density are high simultaneously. Abnormal maneuvers of a vehicle in a group influence multiple vehicles surrounding it, potentially leading to traffic accidents. We propose an approach to identify vehicle groups and analyse the factors influencing their evolutions using vehicle trajectory data. The proposed approach quantifies the interactions between neighboring vehicles based on the potential energy field, represents the interactive relationships among multiple vehicles using a multi-vehicle interaction network, and adopts the process of sub-network segmentation to identify vehicle groups. A random-parameter logistic regression (RPLG) model is developed to examine the influence of vehicle group features on vehicle group split. The effectiveness of the proposed approach is demonstrated in a case study using a real-world dataset. The case study reveals that: (1) the interaction strengths between vehicles tend to increase with increasing speed, (2) the interaction strength between a vehicle and its preceding vehicle is the largest, while the interaction strengths between a vehicle and its vehicles on its sides are the lowest, and (3) higher longitudinal and lateral speeds, larger fluctuations in longitudinal speeds and accelerations, larger group size, larger distances between vehicles, more lanes occupied by a vehicle group, and higher vehicle interactions significantly increase the probability of vehicle group split. The findings of this study can potentially support the traffic management and development of autonomous driving technology in connected vehicle environments. © 2023, The Authors. All rights reserved.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Vision-based speaker detection using Bayesian networks

Vision-based speaker detection using Bayesian networks

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： J.M. Rehg K.P. Murphy P.W. Fieguth Cambridge Research Lab Compaq Computer Corporation Cambridge MA USA Department of Computer Science University of California Berkeley CA USA Department of Systems Design Engineering University of Waterloo Waterloo ONT Canada

The development of user interfaces based on vision and speech requires the solution of a challenging statistical inference problem: The intentions and actions of multiple individuals must be inferred from noisy and ambiguous data. We argue that Bayesian network models are an attractive statistical framework for cue fusion in these applications. Bayes nets combine a natural mechanism for expressing contextual information with efficient algorithms for learning and inference. We illustrate these points through the development of a Bayes net model for detecting when a user is speaking. The model combines four simple vision sensors: face detection, skin color, skin texture, and mouth motion. We present some promising experimental results.

关键词： Bayesian methods Face detection Application software Speech Inference algorithms Skin Computer networks Testing Training data Computer vision

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning for parameter control of text detection in images from video sequences

Reinforcement learning for parameter control of text detecti...

引用

Proceedings - 2004 International Conference on Information and Communication Technologies: From Theory to Applications, ICTTA 2004

作者： Taylor, Graham W. Wolf, Christian PAMI Lab. Dept. of Systems Design Engineering University of Waterloo 200 University Avenue W. Waterloo Ont. N2L 3G1 Canada Lab. d'Info. en Images/Syst. d'Info. INSA de Lyon Bât. J. Verne 20 rue Albert Einstein 69621 Villeurbanne Cedex France

ISBN: (纸本)0780384822

A general framework for reinforcement learning (RL) to the parameter selection problem in multi-step image and vision-based tasks is discussed. RL is described as a computational approach to learning through interacting with the environment. The utility of the framework has been demonstrated by optimizing a set of parameters for an algorithm to detect text images taken from video sequences. It is suggested that introducing image features in the state space will allow for optimization on a per-image, rather than per-set basis.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

SAMSON: Spectral Absorption-fluorescence Microscopy System for ON-site-imaging of algae

arXiv

引用

arXiv 2018年

作者： Deglint, Jason L. Tang, Lyndon Wang, Yitian Jin, Chao Wong, Alexander Vision and Image Processing Lab Systems Design Engineering University of Waterloo Ontario Canada School of Environmental Science and Engineering Yat-sen University Guangzhou510275 China

This paper presents SAMSON, a Spectral Absorption-fluorescence Microscopy System for ON-site-imaging of algae within a water sample. designed to be portable and low-cost for on-site use, the optical sub-system of SAMSON consists of a mixture of low-cost optics and electronics, designed specifically to capture both fluorescent and absorption responses from a water sample. The graphical user interface (GUI) sub-system of SAMSON was designed to enable flexible visualisation of algae in the water sample in real-time, with the ability to perform fine-grained exposure control and illumination wavelength selection. We demonstrate SAMSON’s capabilities by equipping the system with two fluorescent illumination sources and seven absorption illumination sources to enable the capture of multispectral data from six different algae species (three from the Cyanophyta phylum (blue-green algae) and three from the Chlorophyta phylum (green algae)). The key benefit of SAMSON is the ability to perform rapid acquisition of fluorescence and absorption data at different wavelengths and magnification levels, thus opening the door for machine learning methods to automatically identify and enumerate different algae in water samples using this rich wealth of data. Copyright © 2018, The Authors. All rights reserved.

关键词： Algae

来源：评论

学校读者我要写书评

暂无评论

Robust Simultaneous and Proportional Myoelectric Control Scheme for Individuals with Transradial Amputations

Robust Simultaneous and Proportional Myoelectric Control Sch...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： A. Pradhan U. Kuruganti W. Hill N. Jiang V. Chester eBionics Lab Systems Design Engineering University of Waterloo Waterloo Canada Andrew and Marjorie McCain Human Performance Laboratory Faculty of Kinesiology University of New Brunswick Fredericton Canada Institute of Biomedical Engineering University of New Brunswick Fredericton Canada

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119915

Commercial myoelectric prostheses need to be accurate and clinically viable to be successful. This study proposed a simultaneous and proportional control scheme with frequency division technique (SPEC-FDT) to address limitations in current myoelectric prosthesis control, specifically to address non-stationaries such as contraction level variations and unintended activations. Twenty able-bodied participants (14 males and 6 females, age 23.4 ± 3.0) and four individuals with transradial amputations performed wrist movements (flexion/extension, rotations and combined movements) in two degrees-of freedom virtual tasks. The SPEC-FDT had a completion rate (CR)>90% for both control and clinical participants which was significantly higher than the conventional technique (CR=68%). Our results showed that SPEC-FDT is highly accurate for both able-bodied and clinical participants and provides a robust myoelectric control scheme allowing for increased prosthetic hand functions.

关键词： Task analysis Prosthetics Robustness Training Electromyography Testing Wrist

来源：评论

学校读者我要写书评

暂无评论

Palmprint authentication system for civil applications

Palmprint authentication system for civil applications

引用

8th European Conference on Computer Vision, ECCV 2004 and International Workshop on Biometric Authentication, BioAW 2004

作者： Zhang, David Lu, Guangming Kong, Adams Wai-Kin Wong, Michael Biometrics Research Centre Department of Computing The Hong Kong Polytechnic University Kowloon Hong Kong Biocomputing Research Lab School of Computer Science and Engineering Harbin Institute of Technology Harbin China Department of Systems Design Engineering University of Waterloo OntarioN2L 3G1 Canada

ISBN: (纸本)3540224998

In this paper, we present a novel biometric authentication system to identify a person’s identity by his/her palmprint. In contrast to existing palmprint systems for criminal applications, the proposed system targets at the civil applications, which require identifying a person in a large database with high confidence in real-time. The system is constituted by four major components: User interface Module, Acquisition Module, Recognition Module and External Module. More than 7,000 palmprint images have been collected to test the performance of the system. The system can identify 400 palms with a low false acceptance rate, 0.02%, and a high genuine acceptance rate, 98.83%. For verification, the system can operate at a false acceptance rate, 0.017% and a false rejection rate, 0.86%. The execution time for the whole process including image collection, preprocessing, feature extraction and matching is less than 1 second. © Springer-Verlag Berlin Heidelberg 2004.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Binary Codes for Tagging X-Ray Images via Deep De-Noising Autoencoders

Binary Codes for Tagging X-Ray Images via Deep De-Noising Au...

引用

International Joint Conference on Neural Networks

作者： Antonio Sze-To H. R. Tizhoosh Andrew K. C. Wong Systems Design Engineering University of Waterloo Ontario Canada N2L 3G1 KIMIA Lab University of Waterloo Ontario Canada N2L 3G1

ISBN: (纸本)9781509006212

A Content-Based Image Retrieval (CBIR) system which identifies similar medical images based on a query image can assist clinicians for more accurate diagnosis. The recent CBIR research trend favors the construction and use of binary codes to represent images. Deep architectures could learn the non-linear relationship among image pixels adaptively, allowing the automatic learning of high-level features from raw pixels. However, most of them require class labels, which are expensive to obtain, particularly for medical images. The methods which do not need class labels utilize a deep autoencoder for binary hashing, but the code construction involves a specific training algorithm and an ad-hoc regularization technique. In this study, we explored using a deep de-noising autoencoder (DDA), with a new unsupervised training scheme using only backpropagation and dropout, to hash images into binary codes. We conducted experiments on more than 14,000 x-ray images. By using class labels only for evaluating the retrieval results, we constructed a 16-bit DDA and a 512-bit DDA independently. Comparing to other unsupervised methods, we succeeded to obtain the lowest total error by using the 512-bit codes for retrieval via exhaustive search, and speed up 9.27 times with the use of the 16-bit codes while keeping a comparable total error. We found that our new training scheme could reduce the total retrieval error significantly by 21.9%. To further boost the image retrieval performance, we developed Radon Autoencoder Barcode (RABC) which are learned from the Radon projections of images using a de-noising autoencoder. Experimental results demonstrated its superior performance in retrieval when it was combined with DDA binary codes.

关键词： Binary codes Training Noise reduction X-ray imaging Image retrieval Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：