检索结果-内蒙古大学图书馆

IEEE International Symposium on Intelligent Control (ISIC)

作者： S.Y.T. Lang A.K.C. Wong Autonomous Systems Laboratory Institute of In formation Technology National Research Council Canada Ottawa ONT Canada Pattern Analysis and Machine Intelligence Laboratory Department of Systems Design Engineering University of Waterloo Waterloo ONT Canada

A method for mobile robot localization using natural environmental features is presented. An attributed graph boundary representation of free space is used. A local sensor model is registered with a global model by a subgraph isomorphism technique. Geometric and structural knowledge is used to search for mappings. The set of possible mappings is incrementally determined. Simultaneously, the associated coordinate transformation between the global and local models is refined. The model registration technique is implemented in software, and two examples are shown.< >

关键词： Mobile robots Sensor phenomena and characterization Dead reckoning Sonar navigation Councils Wires Laboratories Information technology Space technology Calibration

来源：评论

学校读者我要写书评

暂无评论

Optimization of a Neural Dynamics Based Controller for a Nonholonomic Mobile Robot Using Genetic Algorithms

Optimization of a Neural Dynamics Based Controller for a Non...

引用

International Conference on Control and Automation (ICCA)

作者： Hao Li S.X. Yang F. Karray Pattern Analysis and Machine Intelligence (PAMI) Lab Systems Design Engineering University of Waterloo Waterloo ONT Canada Advanced Robotics and Intelligent Systems (ARIS) Laboratory School of Engineering University of Guelph Guelph ONT Canada

In this paper, a neural dynamics based controller for a nonholonomic mobile robot is proposed. The turn angle of the robot in the proposed model is characterized by a biologically inspired shunting equation derived from Hodgkin and Huxley’s membrane equation. This model is capable of generating smooth steering velocity command that drives the robot to track desired paths. Some parameters in the proposed neural dynamics based controller need to be selected. A genetic algorithm is designed to optimize the model parameters that can guarantee the convergence of tracking error of the mobile robot. Simulation studies of a fourdegree-of-freedom mobile robot are conducted, which demonstrate the effectiveness of the proposed motion controller.

关键词： Mobile robots Genetic algorithms Biological system modeling Equations Biomembranes Algorithm design and analysis design optimization Convergence Motion control

来源：评论

学校读者我要写书评

暂无评论

Search Difficulty of Two-Connected Ring-based Topological Network designs

Search Difficulty of Two-Connected Ring-based Topological Ne...

引用

IEEE Symposium on Foundations of Computational intelligence, FOCI

作者： Beatrice Ombuki-Berman Mario Ventresca Computer Science Department Brock University Saint Catharines ONT Canada Pattern Analysis and Machine Intelligence (PAMI) laboratory in the Systems Design Engineering Department University of Waterloo Waterloo ONT Canada

Ring-based network design problems have many important applications, especially in the fields of logistics and telecommunications. This paper focuses on the recently proposed two-connected network with bounded rings problem. We investigate the search difficulty of both the Euclidean edge and unit edge length ring size bounds flavors of this problem by performing an information-theoretic fitness landscape analysis for several instances of the problem. Our results further confirm the hypothesis that the unit edge length version of the problem is indeed more difficult. The investigation also further reveals that smaller sized ring bounds lead to harder problems for Euclidean edge lengths. However, for unit edge lengths we did not establish such a relationship

关键词： Logistics Performance analysis Telecommunication network topology Costs Telecommunication traffic Computational intelligence Information analysis Helium Abstracts design optimization

来源：评论

学校读者我要写书评

暂无评论

Modular neural network architectures for classification

Modular neural network architectures for classification

引用

International Conference on Neural Networks

作者： G. Auda M. Kamel H. Raafat Pattern Analysis And Machine Intelligence Laboratory Systems Design Eneering Department University of Waterloo Canada University of Waterloo Waterloo ON CA Department of Mathematics and Computer Science Kuwait University Kuwait

One of the major drawbacks of the current neural network generation is the inability to cope with the increase of size/complexity of classification tasks. Modular neural network classifiers attempt to solve this problem through a "divide and conquer" approach. However. The performance of the modular neural network classifiers is sensitive to efficiency of the "task decomposition" technique and the "multi-module decision-making" strategy. After a brief review of previous work with emphasis on five published modular classifiers-decoupled nets, ART-BP, hierarchical network, multiple experts, and multiple identical networks (majority vote and average output decisions)-this paper introduces the cooperative modular neural network (CMNN). The CMNN classifier outperforms the surveyed nets due to its novel task decomposition and multi-module decision-making techniques.

关键词： Neural networks Decision making Multi-layer neural network Computer architecture pattern analysis machine intelligence System analysis and design Mathematics Computer science Voting

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Framework for Medical Image Segmentation

A Reinforcement Learning Framework for Medical Image Segment...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： F. Sahba H.R. Tizhoosh M.M.A. Salama Pattern Analysis and Machine Intelligence Laboratory Department of System Design Engineering University of Waterloo Waterloo ONT Canada Department of Electrical and Computer Engineering University of Waterloo Waterloo ONT Canada

This paper introduces a new method to medical image segmentation using a reinforcement learning scheme. We use this novel idea as an effective way to optimally find the appropriate local thresholding and structuring element values and segment the prostate in ultrasound images. Reinforcement learning agent uses an ultrasound image and its manually segmented version and takes some actions (i.e., different thresholding and structuring element values) to change the environment (the quality of segmented image). The agent is provided with a scalar reinforcement signal determined objectively. The agent uses these objective reward/punishment to explore/exploit the solution space. The values obtained using this way can be used as valuable knowledge to fill a Q-matrix. The reinforcement learning agent can use this knowledge for similar ultrasound images as well. The results demonstrate high potential for applying reinforcement learning in the field of medical image segmentation.

关键词： Learning Biomedical imaging Image segmentation Ultrasonic imaging Medical diagnostic imaging pattern analysis machine intelligence Laboratories System analysis and design design engineering

来源：评论

学校读者我要写书评

暂无评论

Digital compressor structure in neural network implementation using complex complementary pass-transistor logic (C/sup 2/PL)

Digital compressor structure in neural network implementatio...

引用

Midwest Symposium on Circuits and systems (MWSCAS)

作者： D. Zhang M. Kamel M.I. Elmasry VLSI Research Group Department of Electrical & Computer Engineering University of Waterloo Waterloo ONT Canada Pattern Analysis & Machine Intelligence Systems Design Engineering University of Waterloo Waterloo ONT Canada

In this paper, a compressor structure based on complex complementary pass-transistor logic (C/sup 2/PL) is presented. Some types of 3-2 compressors in C/sup 2/PL are achieved and a number of experiments are conducted to optimize their performance. Two typical compressor building blocks, the 4-2 compressor and 7-3 compressor, are built and their digital neural network (DNN) applications are discussed. Compared with the complementary pass-transistor logic (CDL) designs, our simulations show that the C/sup 2/PL compressor has the best performances in power, delay and number of transistors.

关键词： Intelligent networks Neural networks CMOS logic circuits Logic design Switches Semiconductor device modeling design engineering Neurons CMOS technology Voltage

来源：评论

学校读者我要写书评

暂无评论

analysis and optimization of a non-time based motion controller for a nonholonomic mobile robot

Analysis and optimization of a non-time based motion control...

引用

IEEE International Symposium on Computational intelligence in Robotics and Automation (CIRA)

作者： Hao Li S.X. Yang F. Karray Advanced Robotics and Intelligent Systems (AFUS) Laboratory School of Engineering University of Guelph Canada Pattem Analysis and Machine Intelligence (PAMI) Laboratory Department of Systems Design Engineering University of Waterloo Canada

In this paper, a non-time based tracking controller of a nonholonomic mobile robot is first analyzed. Non-time based motion controllers have been successfully applied to many areas such as robot motion control, multi-robot coordination, force control, robotic teleoperation and manufacturing automation. However, by the traditional non-time based motion controller many suffer from oscillations in both the linear and angular velocities when there is a large initial tracking error. In this paper, a traditional non-time based tracking controller is optimized using a genetic algorithm, which is used to generate the model parameters that could guarantee the system stability and convergence of tracking error. Simulations using a nonholonomic mobile robot model with a four degree of freedom are conducted to investigate the performance of the proposed controller. The results using the proposed model is compared to those of the conventional model. Generally the proposed model performs better than the conventional model because the genetic algorithm can provide better parameters to minimize tracking error and the oscillation.

关键词： Motion analysis Motion control Mobile robots Automatic control Force control Error correction Genetic algorithms Robot motion Robot control Robot kinematics

来源：评论

学校读者我要写书评

暂无评论

A segmentation criterion for digital image compression

A segmentation criterion for digital image compression

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： M.R. El-Sakka M.S. Kamel Pattern Analysis and Machine Intelligence Laboratory Systems Design Engineering Department University of Waterloo Waterloo ONT Canada University of Waterloo Waterloo ON CA Dept. of Syst. Design Eng. Waterloo Univ. Ont. Canada

This paper is concerned with segmenting light intensity images for the sake of compressing them using lossy compression techniques. Among the most commonly used techniques for image segmentation is quad-tree partitioning. In this technique, block variance based criteria are usually used to measure the smoothness of the segmented blocks and to consequently classify them. Block variance, however, does not consider the pixel value distribution within the block. Instead of using the block variance as a segmentation and classification measure, we propose using the mean squared deviation from the neighboring pixels mean. The proposed measure is capable of differentiating between blocks not only according to block pixel values but also according to their distribution within the block. This leads to a much better image segmentation and consequently to higher image compression ratios with lower image degradation. The results show the superiority of the proposed measure over the block variance measure.

关键词： Image segmentation Digital images Image coding Degradation

来源：评论

学校读者我要写书评

暂无评论

Improving Generalization of Deep Neural Networks by Optimum Shifting

arXiv

引用

arXiv 2024年

作者： Zhou, Yuyan Li, Ye Feng, Lei Huang, Sheng-Jun MIIT Key Laboratory of Pattern Analysis and Machine Intelligence College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore

Recent studies showed that the generalization of neural networks is correlated with the sharpness of the loss landscape, and flat minima suggests a better generalization ability than sharp minima. In this paper, we propose a novel method called optimum shifting, which changes the parameters of a neural network from a sharp minimum to a flatter one while maintaining the same training loss value. Our method is based on the observation that when the input and output of a neural network are fixed, the matrix multiplications within the network can be treated as systems of under-determined linear equations, enabling adjustment of parameters in the solution space, which can be simply accomplished by solving a constrained optimization problem. Furthermore, we introduce a practical stochastic optimum shifting technique utilizing the Neural Collapse theory to reduce computational costs and provide more degrees of freedom for optimum shifting. Extensive experiments (including classification and detection) with various deep neural network architectures on benchmark datasets demonstrate the effectiveness of our method. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Distributed nonlinear model predictive control and metric learning for heterogeneous vehicle platooning with cut-in/cut-out maneuvers

arXiv

引用

arXiv 2020年

作者： Basiri, Mohammad Hossein Ghojogh, Benyamin Azad, Nasser L. Fischmeister, Sebastian Karray, Fakhri Crowley, Mark The Department of Systems Design Engineering University of Waterloo ON Canada The Department of Electrical and Computer Engineering University of Waterloo ON Canada The Smart Hybrid and Electric Vehicles Systems Lab The Real-Time Embedded Software Lab The Machine Learning Lab The Centre for Pattern Analysis and Machine Intelligence

Vehicle platooning has been shown to be quite fruitful in the transportation industry to enhance fuel economy, road throughput, and driving comfort. Model Predictive Control (MPC) is widely used in literature for platoon control to achieve certain objectives, such as safely reducing the distance among consecutive vehicles while following the leader vehicle. In this paper, we propose a Distributed Nonlinear MPC (DNMPC), based upon an existing approach, to control a heterogeneous dynamic platoon with unidirectional topologies, handling possible cut-in/cut-out maneuvers. The introduced method addresses a collision-free driving experience while tracking the desired speed profile and maintaining a safe desired gap among the vehicles. The time of convergence in the dynamic platooning is derived based on the time of cut-in and/or cut-out maneuvers. In addition, we analyze the improvement level of driving comfort, fuel economy, and absolute and relative convergence of the method by using distributed metric learning and distributed optimization with Alternating Direction Method of Multipliers (ADMM). Simulation results on a dynamic platoon with cut-in and cut-out maneuvers and with different unidirectional topologies show the effectiveness of the introduced method. Copyright © 2020, The Authors. All rights reserved.

关键词： Topology

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：