检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

作者： R.A. Dara M. Kamel Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Waterloo ONT Canada

The availability of large and complex data sets has shifted the focus of pattern recognition toward developing techniques that can efficiently handle these types of data sets. Multiple classifier systems have the promise of reducing the error and complexity by partitioning the data space and combining classifier predictions. However, difficulties arise in ways of generating these various partitions and using them effectively. In this paper, several methods of partitioning is studied and compared, by examining implicit and explicit sharing of the training patterns among multiple classifiers. We implemented several partitioning techniques using random and a more intelligent approach, clustering, to obtain more insight into the effect of shared and disjoint data representation across the training subsets. Improved classification accuracy suggests that implicit sharing of training patterns is always beneficial, while explicit sharing is useful for small size training data.

关键词： Training data Boosting Diversity reception Voting pattern analysis machine intelligence Laboratories Availability pattern recognition Diversity methods

来源：评论

学校读者我要写书评

暂无评论

A reinforcement learning framework for parameter control in computer vision applications

A reinforcement learning framework for parameter control in ...

引用

Canadian Conference on Computer and Robot Vision, CRV

作者： G.W. Taylor Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Waterloo ONT Canada

We propose a framework for solving the parameter selection problem for computer vision applications using reinforcement learning agents. Connectionist-based function approximation is employed to reduce the state space. Automatic determination of fuzzy membership functions is stated as a specific case of the parameter selection problem. Entropy of a fuzzy event is used as a reinforcement. We have carried out experiments to generate brightness membership functions for several images. The results show that the reinforcement learning approach is superior to an existing simulated annealing-based approach.

关键词： Learning Computer vision Application software State-space methods Simulated annealing Filters pattern analysis machine intelligence Laboratories Function approximation

来源：评论

学校读者我要写书评

暂无评论

Comparing viewpoint evaluation functions for model-based inspectional coverage

Comparing viewpoint evaluation functions for model-based ins...

引用

Canadian Conference on Computer and Robot Vision, CRV

作者： C. Wong M. Kamel Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Waterloo ONT Canada

Though based on rigorously developed ideas from imaging geometry, viewpoint evaluation in the active area of camera placement planning research still relies on the intuition and creativity of researchers for the formulation of objective measures. In this paper, a comparative study of five different viewpoint evaluation functions is presented. All five functions are based on a similar set of imaging requirements and considerations but each is unique in its formulation, and in some cases, in its objective. Functional behaviour and performance for the vision task of model-based inspectional coverage are studied quantitatively and qualitatively.

关键词： Inspection Cameras machine vision Layout Image analysis Sensor systems Surveillance Solid modeling pattern analysis machine intelligence

来源：评论

学校读者我要写书评

暂无评论

Solving Multitrip Pickup and Delivery Problem With Time Windows and Manpower Planning Using Multiobjective Algorithms

引用

IEEE/CAA Journal of Automatica Sinica 2020年第4期7卷 1134-1153页

作者： Jiahai Wang Yuyan Sun Zizhen Zhang Shangce Gao the Department of Computer Science and also with the Key Laboratory of Machine Intelligence and Advanced ComputingMinistry of Educationand also with the Guangdong Key Laboratory of Big Data Analysis and ProcessingSun Yat-sen UniversityGuangzhou 510275China the Department of Computer Science Sun Yat-sen UniversityGuangzhou 510275China the Faculty of Engineering University of ToyamaToyama-shi 930-8555Japan

The multitrip pickup and delivery problem with time windows and manpower planning(MTPDPTW-MP)determines a set of ambulance routes and finds staff assignment for a hospital. It involves different stakeholders with diverse interests and objectives. This study firstly introduces a multiobjective MTPDPTW-MP(MO-MTPDPTWMP) with three objectives to better describe the real-world scenario. A multiobjective iterated local search algorithm with adaptive neighborhood selection(MOILS-ANS) is proposed to solve the problem. MOILS-ANS can generate a diverse set of alternative solutions for decision makers to meet their requirements. To better explore the search space, problem-specific neighborhood structures and an adaptive neighborhood selection strategy are carefully designed in MOILS-ANS. Experimental results show that the proposed MOILS-ANS significantly outperforms the other two multiobjective algorithms. Besides, the nature of objective functions and the properties of the problem are analyzed. Finally, the proposed MOILS-ANS is compared with the previous single-objective algorithm and the benefits of multiobjective optimization are discussed.

关键词： Adaptive neighborhood selection manpower planning multiobjective optimization multitrip pickup and delivery problem with time windows

来源：评论

学校读者我要写书评

暂无评论

Multi-label learning with pairwise relevance ordering 21

Multi-label learning with pairwise relevance ordering

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Ming-Kun Xie Sheng-Jun Huang College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing 211106

ISBN: (纸本)9781713845393

Precisely annotating objects with multiple labels is costly and has become a critical bottleneck in real-world multi-label classification tasks. Instead, deciding the relative order of label pairs is obviously less laborious than collecting exact labels. However, the supervised information of pairwise relevance ordering is less informative than exact labels. It is thus an important challenge to effectively learn with such weak supervision. In this paper, we formalize this problem as a novel learning framework, called multi-label learning with pairwise relevance ordering (PRO). We show that the unbiased estimator of classification risk can be derived with a cost-sensitive loss only from PRO examples. Theoretically, we provide the estimation error bound for the proposed estimator and further prove that it is consistent with respect to the commonly used ranking loss. Empirical studies on multiple datasets and metrics validate the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Opposition-Based Q(λ) Algorithm

Opposition-Based Q(λ) Algorithm

引用

International Joint Conference on Neural Networks (IJCNN)

作者： M. Shokri H.R. Tizhoosh M. Kamel Pattern Analysis and Machine Intelligence Laboratory Department of Systems Design Engineering University of Waterloo ONT Canada Pattern Analysis and Machine Intelligence Laboratory Department of Electrical and Computer Engineering University of Waterloo ONT Canada

The problem of delayed reward in reinforcement learning is usually tackled by implementing the mechanism of eligibility traces. In this paper we introduce an extension of eligibility traces to solve one of the challenging problems in reinforcement learning. The concept of opposition traces is proposed in this work to deal with large state space problems in reinforcement learning applications. We combine the idea of opposition and eligibility traces to construct the opposition-based Q(lambda). The results are compared with the conventional Watkins' Q(lambda) and reflect a remarkable performance increase.

关键词： Learning Delay Acceleration Neural networks pattern analysis machine intelligence Laboratories System analysis and design Design engineering Systems engineering and theory

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Recognition using Gaussian Mixture Vector Autoregressive Models

Speech Emotion Recognition using Gaussian Mixture Vector Aut...

引用

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

作者： Moataz M. H. El Ayadi Mohamed S. Kamel Fakhri Karray Electrical and Computer Engineering Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Canada

It is believed that modeling temporal structure of the speech data may be useful for the problem of speech emotion recognition (T. Nwe et al., 2003). In this paper, Gaussian mixture vector autoregressive model is proposed as a statistical classifier for this task. The main motivation behind using such a model is its ability to model the dependency among extracted speech feature vectors as well as the multi-modality in their distribution. When applied to the Berlin emotional speech database, the proposed technique provides a classification accuracy of 76% versus 71% for the hidden Markov model, 67% for the k-nearest neighbors, 55% for feed-forward neural networks. The model gives also better discrimination between high-arousal, low arousal, and neutral emotions than the HMM.

关键词： Emotion recognition Hidden Markov models Speech analysis Reactive power Feature extraction Neural networks Speech synthesis pattern analysis machine intelligence Spatial databases

来源：评论

学校读者我要写书评

暂无评论

A testbed platform for assessing human-robot verbal interaction

A testbed platform for assessing human-robot verbal interact...

引用

International Conference on Autonomous and Intelligent Systems (AIS)

作者： Hassene Bouraoui Alaa Khamis Fakhri Krray Pattern Analysis and Machine Intelligence (PAMI) Laboratory University of Waterloo Waterloo ONT Canada

Verbal interaction provides a natural and social-style interaction mode by which robots can communicate with general public who is likely unknowledgeable in robotics. This interaction mechanism is also very important for a broad range of users such as hands/eyes-busy users, motor-impaired users, users with vision impairment and users working in hostile environments. This paper presents a testbed that can be used to study human-robot verbal interaction. The proposed testbed encompasses a Java-based user interfaces and a user-independent automatic speech recognizer with a modified grammar module in the context of human-robot interaction. The performance of the proposed testbed has been evaluated quantitatively using a set of evaluation metrics such as word correct rate, recognition Time and success and false action rates. The conducted experiments show the promising features of the system.

关键词： Robots Speech recognition Speech Grammar Noise measurement Natural languages Humans

来源：评论

学校读者我要写书评

暂无评论

Fuzzy reinforcement learning for embedded soccer agents in a multi-agent context

Fuzzy reinforcement learning for embedded soccer agents in a...

引用

作者： Tehrani, A.M. Kamel, M.S. Khamis, A.M. Pattern Analysis and Machine Intelligence Lab. Electrical and Computer Engineering Department University of Waterloo Waterloo Ont. N2L 3G1 Canada Mechanical Engineering Department University of Waterloo Canada Department of Cooperative Intelligent Systems Canada Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Canada Department of Systems Engineering and Automation Carlos III University of Madrid Spain

The work presented in this paper aims at combining fuzzy function approximation and reinforcement learning in order to create robotic soccer agents that are able to coordinate their behaviours locally and socially while learning from experience. This simultaneous coordination and learning ability can play a crucial role in improving the behaviour usage of robotic soccer agents. To achieve this goal, a fuzzy reinforcement learning technique for a single agent is first examined and then this technique is applied to multiple agents. The conducted experiments through a soccer simulation system show that the performance of robot scoring speed is improved using the proposed approach.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning

arXiv

引用

arXiv 2023年

作者： Liu, Jiexi Chen, Songcan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence

Learning universal time series representations applicable to various types of downstream tasks is challenging but valuable in real applications. Recently, researchers have attempted to leverage the success of self-supervised contrastive learning (SSCL) in Computer Vision(CV) and Natural Language Processing(NLP) to tackle time series representation. Nevertheless, due to the special temporal characteristics, relying solely on empirical guidance from other domains may be ineffective for time series and difficult to adapt to multiple downstream tasks. To this end, we review three parts involved in SSCL including 1) designing augmentation methods for positive pairs, 2) constructing (hard) negative pairs, and 3) designing SSCL loss. For 1) and 2), we find that unsuitable positive and negative pair construction may introduce inappropriate inductive biases, which neither preserve temporal properties nor provide sufficient discriminative features. For 3), just exploring segment- or instance-level semantics information is not enough for learning universal representation. To remedy the above issues, we propose a novel self-supervised framework named TimesURL. Specifically, we first introduce a frequency-temporal-based augmentation to keep the temporal property unchanged. And then, we construct double Universums as a special kind of hard negative to guide better contrastive learning. Additionally, we introduce time reconstruction as a joint optimization objective with contrastive learning to capture both segment-level and instance-level information. As a result, TimesURL can learn high-quality universal representations and achieve state-of-the-art performance in 6 different downstream tasks, including short- and long-term forecasting, imputation, classification, anomaly detection and transfer learning. Copyright © 2023, The Authors. All rights reserved.

关键词： Time series

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：