检索结果-内蒙古大学图书馆

Dynamic Walking of AIBO with Hopf Oscillators

Chinese Journal of Mechanical Engineering 2011年第4期24卷 612-617页

作者： ZHANG Jiaqi TOMIZUKA Masayoshi CHEN Qijun LIU Chengju College of Electronic Information and Engineering Tongji University Shanghai 201804 China College of Electronic Information andEngineering Tongji University Shanghai 201804 China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 201804 China

More and more biological evidences have been found that neural networks in the spinal cord, referred to as ＂central pattern generators＂（CPGs）, govern locomotion. CPGs are capable of producing rhythmic movements, such as swimming, flying, and walking, even when isolated from the brain and sensory inputs. If we could build up any models that have similar functions as CPGs, it will be much easier to design better locomotion for robots. In this paper, a self-training environment is designed and through genetic algorithm （GA）, walking trajectories for every foot of AIBO are generated at first. With this acquired walking pattern, AIBO gets its fastest locomotion speed. Then, this walking pattern is taken as a reference to build CPGs with Hopf oscillators. By changing corresponding parameters, the frequencies and the amplitudes of CPGs＇ outputs can be adjusted online. The limit cycle behavior of Hopf oscillators ensures the online adjustment and the walking stability against perturbation as well. This property suggests a strong adaptive capacity to real environments for robots. At last, simulations are carried on in Webots and verify the proposed method.

关键词： central pattern generators(CPGs) Hopf Oscillators walking control AIBO Webots

来源：评论

学校读者我要写书评

暂无评论

Low frequency analysis of resting-state fMRI

Low frequency analysis of resting-state fMRI

引用

2012 International Conference on computer Science and Information Processing, CSIP 2012

作者： He, Lianghua Ji, Hongfei Wan, Meng Liu, Shuang Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China Center for Science and Technology Development of the Ministry Education Beijing China

ISBN: (纸本)9781467314114

Resting state functional magnetic resonance imaging (rsfMRI) is a relatively new and an powerful method for evaluating regional interactions that occur when a participant is not performing an explicit task. Because of sensitiveness to time delay and length of time courses, respectively, traditional methods of correlation and coherence based on region of interest are not very suitable for rsfMRI. In this paper, we analyzed low frequency property of rsfMRI data. Firstly, we calculated the low frequency of resting-state Blood-Oxygenation-Level-Dependent(BOLD) signal on every voxel using Welch method, based on which we analyzed the statistical distribution cross subjects and voxels. The low frequency feature is proved by a series of experiments to be more robust and consistent comparing with coorelation in time domain and coherency in frequency domain. We found that the property of low frequency statistical distribution is dominant on narrow band, which is around 0.0137HZ. © 2012 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Dynamic Graph Diffusion Convolutional Network for Traffic Flow Forecasting

Spatial-Temporal Dynamic Graph Diffusion Convolutional Netwo...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Li, Yang Zhang, Yaying Tongji University Key Laboratory of Embedded System and Service Computing Ministry of Education China Shanghai Artificial Intelligence Laboratory Shanghai China

ISBN: (纸本)9798350324457

Traffic forecasting plays a crucial role in intelligent transportation systems and finds application in various domains. Accurate traffic forecasting remains challenging due to the time-varying correlations within the data and the heterogeneous correlations between regions. Although various dynamic spatial-temporal graph models have been proposed to address these challenges in recent years, most of them are burdened by high computation costs and not intuitive to understand. In this paper, we propose a spatial-temporal graph model, Spatial-Temporal Dynamic Graph Diffusion Convolutional Network (SDGDN) that provides an effective and efficient approach to traffic forecasting. From the perspective of traffic flow transition probabilities, SDGDN learns dynamic graph structures to capture the time-varying traffic transition relationships. Besides dynamic graph structures, static node features are employed in diffusion convolution to better capture heterogeneous regional features. Furthermore, we utilize temporal encoding and also generate varying graphs in each stacked layer to enhance the forecasting performance. Experiments results on five real-world datasets demonstrate that SDGDN outperforms most baseline models in terms of both performance and computation efficiency. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Biometric-Based User Authentication for Wireless Sensor Networks

引用

Wuhan University Journal of Natural Sciences 2010年第3期15卷 272-276页

作者： YUAN Jianjun JIANG Changjun JIANG Zuowen School of Electronics and Information Engineering Tongji University / Key Laboratory of Embedded System and Service Computing of Ministry of Education Shanghai 201804 China

This paper proposes a biometric-based user authentication protocol for wireless sensor networks （WSN） when a user wants to access data from sensor nodes, since WSN are often deployed in an unattended environment. The protocol employs biometric keys and resists the threats of stolen verifier, of which many are logged-in users with the same login identity, guessing, replay, and impersonation. The protocol uses only Hash function and saves the computational cost, the communication cost, and the energy cost. In addition, the user＇s password can be changed freely using the proposed protocol.

关键词： authentication biometrics security wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Accelerating large-scale human action recognition with GPU-based spark 17th

Accelerating large-scale human action recognition with GPU-b...

引用

17th Pacific-Rim Conference on Multimedia, PCM 2016

作者： Wang, Hanli Zheng, Xiaobin Xiao, Bo Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

ISBN: (纸本)9783319488950

In this paper, a large-scale human action recognition system is proposed which is built upon the combination of the rising big data processing technology Spark and the powerful Graphics Processing Unit (GPU) in order to fully utilize the efficient in-memory computing ability of Spark and the fine-grained parallel computing capacity of GPU for visual data processing. A number of key algorithms for human action recognition including trajectory based feature extraction, Gaussian Mixture Model (GMM) generation and Fisher Vector (FV) encoding are performed with the proposed GPU-based Spark framework. The experimental results on the benchmark human action dataset Hollywood-2 demonstrate that the proposed GPU-based Spark framework is able to dramatically accelerate the process of human action recognition. © Springer International Publishing AG 2016.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

Learning how to avoiding obstacles for end-to-end driving with conditional imitation learning 2

Learning how to avoiding obstacles for end-to-end driving wi...

引用

2nd International Conference on Signal Processing and Machine Learning, SPML 2019

作者： Zhang, Enwei Zhou, Hongtu Ding, Yongchao Zhao, Junqiao Ye, Chen Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University School of Electronics and Information Engineering Shanghai China

ISBN: (纸本)9781450372213

Obstacle avoiding is one of the most complex tasks for autonomous driving systems, which was also ignored by many cutting-edge end-to-end learning-based methods. The difficulties stem from the integrated process of detection and interpretation of environment and obstacles and generation of proper behaviors. We make the use of CARLA, a simulator for autonomous driving research, and collect massive human drivers' reactions to obstacles on road subjecting to given driving commands, i.e. follow, go straight, turn left and turn right for about 6 hours. A behavior-Cloning neural network architecture is proposed with the modified loss that enlarge the effects of errors for steer, which indicates the benefit to high an accuracy. We found the data augmentation of the image is crucial to the training of the proposed network. And a reasonable limit allows avoiding unexpected stop. The experiments demonstrate 3 obstacle avoidance cases: for the same type as the training dataset, other automobile and two-wheeled vehicles. Finally, the CARLA benchmark is also tested. © 2019 Association for Computing Machinery.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Improving bag-of-words representation with efficient twin feature integration 15

Improving bag-of-words representation with efficient twin fe...

引用

7th International Conference on Internet Multimedia Computing and service, ICIMCS 2015

作者： Wang, Lei Wang, Hanli Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

ISBN: (纸本)9781450335287

In recent years, the Bag-of-Words (BoW) model has been widely used in most state-of-the-art large-scale image re-trieval systems. However, the standard BoW based systems suffer from low discriminative power of local features as well as quantization errors that significantly affect the retrieval performance. In this paper, twin feature is employed and well combined with two advanced techniques including Ham-ming Embedding (HE) and Multiple Assignment (MA) to construct a discriminative image retrieval system on BoW representation in an efficient way. Experimental results on two benchmark datasets Oxford5k and Paris6k demonstrate that the proposed technique can greatly refine the visual matching process and enhance the final performance for im-age retrieval. © 2015 ACM.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Behavioral authentication method for mobile gesture against resilient user posture 3

Behavioral authentication method for mobile gesture against ...

引用

2016 3rd International Conference on systems and Informatics, ICSAI 2016

作者： Liu, Qiang Wang, Mimi Zhao, Peihai Yan, Chungang Ding, Zhijun Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Tongji University Ministry of Education Shanghai China

ISBN: (纸本)9781509055210

The password pattern has become a widely used mobile authentication method. However, there are still some potential security problems since the passwords are easy to be cracked by some malicious software. An important research direction of improving its security is adding behavior pattern into the password pattern. The existing methods mainly used user's gesture behavior data such as the location, pressure and contact area of finger collected by touch screen to build a behavior authentication model, which did not consider the influence of user's posture on user's gesture behavior. This paper aims to propose a gesture authentication construction method that is resilient against the change of user's posture. Firstly, for the posture behavior data collected by mobile's orientation sensor and acceleration sensor, we use K-means algorithm to get user's postures. Secondly, we train a gesture authentication sub-model for each posture based on the data collected by touch screen. Finally, we give a behavior authentication method based on these models. Our experimental result shows that the method achieves an effect of 4.36% False Acceptance Rate (FAR) and 5.03% False Rejection Rate (FRR) © 2016 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Two-dimensional color uncorrelated principal component analysis for feature extraction with application to face recognition

引用

2012 International Conference on service-Oriented Computing, ICSOC 2012

作者： Zhao, Cairong Miao, Duoqian Department of Computer Science and Technology Tongji University Shanghai 201804 China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai 7201804 China Ministry of Education Nanjing 210094 China

ISBN: (纸本)9783319029603

This paper proposes a two-dimensional color uncorrelated principal component analysis algorithm(2DCUPCA) for unsupervised subspace learning directly from color face images. The 2DCUPCA can be used to explore uncorrelated properties among color-based features, which contain minimum redundancy and ensure linear independence among features. Furthermore, the proposed 2DCUPCA provided the theoretical foundations analysis and proved the uncorrelated property between color-based features in theory. This makes it sure that the extracted features directly from three color image matrices will be uncorrelated. Finally, experimental results on the AR and FRGC-2 color face databases show that 2DCUPCA achieves better recognition performance than other color face recognition methods. © Springer International Publishing 2013.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Discretized Gaussian Mixture Hyperprior for Learned Image Compression with Mask Module

Discretized Gaussian Mixture Hyperprior for Learned Image Co...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Wang, Shengkai Wang, Hanli Tongji University Department of Computer Science and Technology Shanghai China Tongji University Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Learned image compression approaches have shown great potential with promising results. However, according to the commonly used measurement methods, there still lies a performance gap between learned compression methods and the latest compression standard versatile video coding (VVC), because of the remaining redundancy existing in contemporary algorithms. To obtain a more accurate entropy model for rate estimation, discretized Gaussian mixture hyperprior is proposed in this work to parameterize the distribution of latent codes. In addition, a proposed mask module is exploited to enhance the feature extraction ability of the encoder and adaptively allocate bit rates. In this case, the proposed learned image compression model achieves the state-of-the-art performance among the existing learned compression methods and most compression standards on both Kodak24 and CLIC Mobile Validation datasets. The proposed model also outperforms VVC under several bitrate scenarios. © 2022 IEEE.

关键词： Image compression

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：