检索结果-内蒙古大学图书馆

16th Genetic and Evolutionary Computation Conference Companion, GECCO 2014 Companion

作者： Zhang, Guang-Wei Zhan, Zhi-Hui Du, Ke-Jing Chen, Wei-Neng Department of Computer Science Sun Yat-sen University Guangzhou 510275 China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Engineering Research Center of Supercomputing Engineering Software Ministry of Education China Department of Management Science City University of Hong Kong Kowloon Hong Kong

ISBN: (纸本)9781450328814

This paper proposes a novel normalization group strategy (NGS) to extend brain storm optimization (BSO) for power electronic circuit (PEC) design and optimization. As different variables in different dimensions of the PEC represent different circuit components such as resistor, capacitor, or inductor, they have different physical significances and various search space that are even not in comparable range. Therefore, the traditional group method used in BSO, which is based on the solution position information, is not suitable when solving PEC. In order to overcome this issue, the NGS proposed in this paper normalizes different dimensions of the solution to the same comparable range. This way, the grouping operator of BSO can work when using BSO to solve PEC. The NGS based BSO (NGBSO) approach has been implemented to optimize the design of a buck regulator in PEC. The results are compared with those obtained by using genetic algorithm (GA) and particle swarm optimization (PSO). Results show that the NGBSO algorithm outperforms GA and PSO in our PEC design and optimization study. Moreover, the NGS can be regarded as an efficient method to extend BSO to real-world application problems whose dimensions are with different physical significances and search ranges.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Psychological stress detection from cross-media microblog data using Deep Sparse Neural Network

Psychological stress detection from cross-media microblog da...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Huijie Lin Jia Jia Quan Guo Yuanyuan Xue Jie Huang Lianhong Cai Ling Feng TNList and Key Laboratory of Pervasive Computing Ministry of Education Department of Computer Science and Technology Tsinghua University Beiiing China Machine Intelligence Laboratory Sichuan University Chengdu China

Long-term stress may lead to many severe physical and mental problems. Traditional psychological stress detection usually relies on the active individual participation, which makes the detection labor-consuming, time-costing and hysteretic. With the rapid development of social networks, people become more and more willing to share moods via microblog platforms. In this paper, we propose an automatic stress detection method from cross-media microblog data. We construct a three-level framework to formulate the problem. We first obtain a set of low-level features from the tweets. Then we define and extract middle-level representations based on psychological and art theories: linguistic attributes from tweets' texts, visual attributes from tweets' images, and social attributes from tweets' comments, retweets and favorites. Finally, a Deep Sparse Neural Network is designed to learn the stress categories incorporating the cross-media attributes. Experiment results show that the proposed method is effective and efficient on detecting psychological stress from microblog data.

关键词： Stress Psychology Feature extraction Image color analysis Pragmatics Brightness Joints

来源：评论

学校读者我要写书评

暂无评论

A pso approach for software project planning 14

A pso approach for software project planning

引用

16th Genetic and Evolutionary Computation Conference Companion, GECCO 2014 Companion

作者： Jia, Ya-Hui Chen, Wei-Neng Hu, Xiao-Min Department of Computer Science Sun Yat-sen University China School of Advanced Computing Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Engineering Research Center of Supercomputing Engineering Software Ministry of Education China School of Public Health Sun Yat-sen University China

ISBN: (纸本)9781450328814

Search-based software project management is a hot research point in software engineering. Based on the event-based scheduler (EBS) we have proposed in previous work [1], this paper intends to further propose a two-phase particle swarm optimization approach which uses a set-based representation for task scheduling and an integer representation for workload assignment scheduling to improve planning performance. Experimental results on 83 instances demonstrate the effectiveness of the proposed approach.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Neural network based bilingual language model growing for statistical machine translation

Neural network based bilingual language model growing for st...

引用

2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014

作者： Wang, Rui Zhao, Hai Lu, Bao-Liang Utiyama, Masao Sumita, Eiichro Department of Computer Science and Engineering Center for Brain-Like Computing and Machine Intelligence Shanghai Jiao Tong University Shanghai200240 China Multilingual Translation Laboratory MASTAR Project National Institute of Information and Communications Technology 3-5 Hikaridai Keihanna Science City Kyoto619-0289 Japan Key Laboratory Shanghai Education Commission Intelligent Interaction Cognitive Engineering Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9781937284961

Since larger n-gram Language Model (LM) usually performs better in Statistical machine Translation (SMT), how to construct efficient large LM is an important topic in SMT. However, most of the existing LM growing methods need an extra monolingual corpus, where additional LM adaption technology is necessary. In this paper, we propose a novel neural network based bilingual LM growing method, only using the bilingual parallel corpus in SMT. The results show that our method can improve both the perplexity score for LM evaluation and BLEU score for SMT, and significantly outperforms the existing LM growing methods without extra corpus. © 2014 Association for Computational Linguistics.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning hierarchical translation spans

Learning hierarchical translation spans

引用

2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014

作者： Zhang, Jingyi Utiyama, Masao Sumita, Eiichro Zhao, Hai Department of Computer Science and Engineering Center for Brain-Like Computing and Machine Intelligence Shanghai Jiao Tong Unviersity Shanghai200240 China Key Laboratory Shanghai Education Commission Intelligent Interaction Cognitive Engineering Shanghai Jiao Tong Unviersity Shanghai200240 China National Institute of Information and Communications Technology 3-5Hikaridai Keihanna Science City Kyoto619-0289 Japan

ISBN: (纸本)9781937284961

We propose a simple and effective approach to learn translation spans for the hierarchical phrase-based translation model. Our model evaluates if a source span should be covered by translation rules during decoding, which is integrated into the translation system as soft constraints. Compared to syntactic constraints, our model is directly acquired from an aligned parallel corpus and does not require parsers. Rich source side contextual features and advanced machine learning methods were utilized for this learning task. The proposed approach was evaluated on NTCIR-9 Chinese-English and Japanese-English translation tasks and showed significant improvement over the baseline system. © 2014 Association for Computational Linguistics.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Acoustics, content and geo-information based sentiment prediction from large-scale networked voice data

Acoustics, content and geo-information based sentiment predi...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zhu Ren Jia Jia Quan Guo Kuo Zhang Lianhong Cai TNList and Key Laboratory of Pervasive Computing Ministry of Education Department of Computer Science and Technology Tsinghua University Beijing China Machine Intelligence Laboratory Sichuan University Chengdu China Sogou Corporation Beijing China

Sentiment analysis from large-scale networked data attracts increasing attention in recent years. Most previous works on sentiment prediction mainly focus on text or image data. However, voice is the most natural and direct way to express people's sentiments in real-time. With the rapid development of smart phone voice dialogue applications (e.g., Siri and Sogou Voice Assistant), the large-scale networked voice data can help us better quantitatively understand the sentimental world we live in. In this paper, we study the problem of sentiment prediction from large-scale networked voice data. In particular, we first investigate the data observations and underlying sentiment patterns in human-mobile voice communication. Then we propose a deep sparse neural network (DSNN) model to incorporate acoustic features, content information and geo-information to automatically predict sentiments. The effectiveness of the proposed model is verified by the experiments on a real dataset from Sogou Voice Assistant application.

关键词： Correlation Cities and towns Feature extraction Acoustics Artificial neural networks Neurons Predictive models

来源：评论

学校读者我要写书评

暂无评论

Research Advance in Swarm Robotics

引用

Defence Technology（防务技术） 2013年第1期9卷 31-63页

作者： TAN Ying ZHENG Zhongyang Key Laboratory of Machine Perception and Intelligence Ministry of Education Department of Machine Intelligence School of Electronics Engineering and Computer Science Peking University

The research progress of swarm robotics is reviewed in details. The swarm robotics inspired from nature is a combination of swarm intelligence and robotics, which shows a great potential in several aspects. First of all, the cooperation of nature swarm and swarm intelligence are briefly introduced, and the special features of the swarm robotics are summarized compared to a single robot and other multi-individual systems. Then the modeling methods for swarm robotics are described by a list of several widely used swarm robotics entity projects and simulation platforms. Finally, as a main part of this paper, the current research on the swarm robotic algorithms are presented in detail, including cooperative control mechanisms in swarm robotics for flocking, navigating and searching applications.

关键词： artificial intelligence swarm robotics cooperative control modeling simulation swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

A novel pheromone-based evolutionary algorithm for solving degree-constrained minimum spanning tree problem

A novel pheromone-based evolutionary algorithm for solving d...

引用

15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013

作者： Huang, Xiao-Ma Gong, Yue-Jiao Zhang, Jun Department of Computer Science Key Laboratory of Machine Intelligence and Sensor Networks Sun Yat-sen University China

ISBN: (纸本)9781450319645

The degree-constrained minimum spanning tree problem (dc- MSTP) is crucial in the design of networks and it is proved to be NP-hard. The recently developed evolutionary algorithm utilizing node-depth-degree representation (EANDD) has successfully enabled the dc-MSTP solvable by generating new spanning trees in average time complexity O(√ n) , which is the fastest in the literature. However, as the generic operation of EANDD is to change two edges that are randomly selected from the entire tree, the efficiency of EANDD still has potential to be further improved. In this paper, we propose a novel pheromone-based tree modification method (PTMM) to improve the efficiency of EANDD. For each edge, a pheromone value is defined based on the historical contribution of the edge to the fitness of the spanning tree. Then, PTMM considers the pheromone value on each edge as a desirability measure for selecting the edge to construct the spanning tree. In this way, the more promising edge is more likely to be selected and therefore the efficiency of the tree modification operation in EANDD can be improved. The effectiveness and effieciency of PTMM is demonstrated on a set of benchmark instances in comparison with the original EANDD.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Space-based initialization strategy for particle swarm optimization

Space-based initialization strategy for particle swarm optim...

引用

15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013

作者： Yin, Liang Hu, Xiao-Min Zhang, Jun Department of Computer Science Key Laboratory of Machine Intelligence and Sensor Networks Sun Yat-sen University China

ISBN: (纸本)9781450319645

Particle Swarm Optimization (PSO) is a population-based stochastic optimization algorithm that has been applied to various scientific and engineering problems. Despite its fast convergence speed, the original PSO is easy to fall into local optima when solving multi-modal functions. To address this problem, we present a novel initialization strategy, namely Space-based Initialization Strategy (SIS), to help PSO avoid local optima. We embed SIS into the standard PSO and form a novel PSO variant named SIS-PSO. The performance of SIS-PSO is validated by 13 benchmark functions and the experimental results demonstrate that the SIS enables PSO to achieve faster convergence speed and higher solution accuracy especially in multi-modal problems.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A set-based locally informed discrete particle swarm optimization

A set-based locally informed discrete particle swarm optimiz...

引用

15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013

作者： Ma, Yun-Yang Gong, Yue-Jiao Chen, Wei-Neng Zhang, Jun Department of Computer Science Key Laboratory of Machine Intelligence and Sensor Networks Sun Yat-sen University China

ISBN: (纸本)9781450319645

This paper proposed an efficient discrete PSO algorithm. Following the general process of the recently proposed locally informed particle swarm (LIPS), the velocity update of each particle in the proposed algorithm depends on the pbests of its nearest neighbors. However, in order to achieve optimization in discrete space, the related arithmetic operators and the concept of 'distance' in LIPS are redefined based on set theory. Thus, the proposed algorithm is termed Set-based LIPS (S-LIPS). Moreover, a reset scheme is embedded in S-LIPS to further improve population diversity in S-LIPS. By using the locally informed update mechanism and the reset scheme, the proposed algorithm is able to have both high convergence speed and good global search ability. S-LIPS is compared with a set-based comprehensive learning PSO on TSP benchmark instances. The experimental result shows that S-LIPS is a very promising algorithm for solving discrete problems, especially in the case where the scale of the problem is large.

关键词： Traveling salesman problem

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：