检索结果-内蒙古大学图书馆

IEEE International Conference on Web Services (ICWS)

作者： Yuchang Xu Jian Cao Tao Liu Yudong Tan Quanwu Xiao Data Science Dep. of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Ctrip Ltd. Company Shanghai China

Online periodic prediction is very common in practical problems like stock index analysis or traffic status estimation, where a prediction service is invoked at every time point. However, due to the potential communication cost, service overheads or the expenditure incurred by every prediction service invocation, it is valuable to reduce the number of invocation times without sacrificing too much precision. Therefore, we present an approach based on reinforcement learning to select the timing for prediction service invocations, which still guarantees high quality in capturing the regularity in a future time series. Extensive experiments are conducted on a real-world airfare search volume dataset of multiple routes. The experiment results prove that our algorithms show superiority over other solutions.

关键词： Prediction algorithms Time series analysis Timing Reliability Learning (artificial intelligence) Predictive models Load modeling

来源：评论

学校读者我要写书评

暂无评论

EXPLORING MOTOR IMAGERY EEG PATTERNS FOR STROKE PATIENTS WITH DEEP NEURAL NETWORKS

EXPLORING MOTOR IMAGERY EEG PATTERNS FOR STROKE PATIENTS WIT...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Dawei Cheng Ye Liu Liqing Zhang Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Dep. of Computer Science and Engineering Shanghai Jiao Tong University China

ISBN: (纸本)9781538646595

Studies show that motor imagery based Brain-computer Interface (BCI) systems can be utilized therapeutically in stroke rehabilitation. Efficient decoding of subjects' motor intentions is essential in BCI-based rehabilitation systems to manipulate a neural prosthesis or other devices for motor relearning. However, due to cortical reorganization, the desynchronization potential evoked by the motor imagery of patients with brain lesions is quite different from that evoked by the motor imagery of normal subjects. These differences can be attributed to active cortex regions, frequency bands and amplitude. In this paper, we use a deep learning method to explore the EEG patterns of key channels and the frequency band for stroke patients. The EEG data is bandpass filtered into multiple sub-bands split by a sliding window strategy. Under these sub-bands, diverse spatial-spectral features are extracted and fed into a deep neural network for classification, uncovering the spectral patterns (bandpass filters) and spatial patterns (spatial weights). Experimental results from five stroke patients show that our method has higher classification accuracy than several state-of-the-art approaches. By tracking gradual changes in EEG patterns during rehabilitation, we try to uncover the neurophysiological plasticity mechanism in the impaired cortexes of stroke patients.

关键词： Deep Learning Brain-computer Interface (BCI) EEG Stroke Stroke Electroencephalography Motor images Frequency bands stroke patient Neural network Neural Prostheses Patients Stroke Rehabilitation Imagery (Psychotherapy) sliding windows Bandpass

来源：评论

学校读者我要写书评

暂无评论

A secure mutual trust scheme for wireless sensor networks 26

A secure mutual trust scheme for wireless sensor networks

引用

26th IEEE International Symposium on Industrial Electronics, ISIE 2017

作者： Dahgwo Yein, Alan Lin, Chih-Hsueh Hsieh, Wen-Shyong Dep. of Information Management Shu-Te University Kaohsiung Taiwan Dep. of Computer and Communication Shu-Te University Kaohsiung Taiwan Dep. of Computer Science and Engineering National Sun Yat-sen University Kaohsiung Taiwan

ISBN: (纸本)9781509014125

In this paper, we propose a secure mutual trust scheme based on the concept of chameleon hash function, for wireless sensor networks (WSNs). In the proposed scheme, the base station (BS), holding two common secrets, issues an identity to every dep.oyed sensor node. An identity contains a public data and a private key. The public data is used to present a node, and the private key is used to make mutual trust keys with other node's public data. A public data can be used in verifying the legitimacy of the node. The mutual trust key is the evidence that a node owns the related public data. At any time, or after finding malicious nodes or dep.oying new nodes, BS will broadcast new group key to all sensor nodes by multiple hopping. Following the group key broadcasting and rebroadcasting, the still-legal nodes can set new information in their public data, private key, hop counters, public parameters, and neighbor nodes set, which contains the public data and hop counter of its neighboring nodes. Based on the new information, a sensor node can make the mutual trust keys with its neighboring nodes to do message authentication and secure communicating, or to set up a secure path to forward the sensed information to BS by multiple relaying. The security analysis shows that the proposed scheme can revoke the right of malicious sensor nodes, dep.oy new sensor nodes, and work well under malicious attacking. As the result of performance comparison, the proposed secure scheme is superior to the related works. © 2017 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Motion Analysis on dep.h Camera Data to Quantify Parkinson’s Disease Patients’ Motor Status Within the Framework of I-Prognosis Personalized Game Suite

Motion Analysis on Depth Camera Data to Quantify Parkinson’...

引用

IEEE International Conference on Image Processing

作者： Sofia B. Dias Athina Grammatikopoulou Nikos Grammalidis José A. Diniz Theodore Savvidis Evdokimos Konstantinidis Panagiotis Bamidis Michael Stadtschnitzer Dhaval Trivedi Lisa Klingelhoefer Zoe Katsarou Sevasti Bostantzopoulou Kosmas Dimitropoulos Leontios J. Hadjileontiadis CIPER Faculdade de Motricidade Humana Universidade de Lisboa Lisbon Portugal Centre for Research and Technology Hellas Information Technologies Institute Thessaloniki Greece Lab of Medical Physics Aristotle University of Thessaloniki (AUTH) Thessaloniki Greece Sankt Augustin Fraunhofer Institute IAIS Germany International Parkinson Excellence Research Centre King’s College Hospital NHS Foundation Trust London United Kingdom Department of Neurology Technical University Dresden Dresden Germany Third Neurological Clinic G. Papanikolaou Hospital AUTH Thessaloniki Greece Dep. of Electrical Engineering and Computer Science Khalifa University Abu Dhabi UAE

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

The primary manifestations of Parkinson Disease (PD) concern abnormalities of movement associated with the constant deterioration of motor skills. Such motor impairment affects patients' movement accuracy and coordination, disrupting their daily life. Taking into account recent studies stating that computer-based physical therapy games can be used as a PD rehabilitation option, we propose a novel Exergame, the iPrognosis Warming up Game (http://***/), as a user-friendly tool that could both serve as a computer-based physical therapy game, as well as a means of accurately and automatically identifying the severity of PD motor symptoms. To this regard, we propose a novel deep learning methodology for motor impairment stage prediction that relies solely on human body motion data extracted from the recorded game sessions. Experimental results using a dataset of both early and advanced PD patients reveal a good classification performance of the proposed methodology, predicting the motor impairment stage of PD patients and paving the way for additional research in the field.

关键词： Cameras Parkinson's disease Games Physics Indexes Predictive models

来源：评论

学校读者我要写书评

暂无评论

FF-CMNET: A CNN-BASED MODEL FOR FINE-GRAINED CLASSIFICATION OF CAR MODELS BASED ON FEATURE FUSION

FF-CMNET: A CNN-BASED MODEL FOR FINE-GRAINED CLASSIFICATION ...

引用

IEEE International Conference on Multimedia and Expo

作者： Ye Yu Qiang Jin Chang Wen Chen Dep. of Computer Science and Engineering State University of New York at Buffalo Buffalo USA School of Computer and Information Hefei University of Technology Hefei China School of Science and Engineering Chinese University of Hong Kong at Shenzhen Shenzhen China

We present in this paper a novel scheme for fine-grained car model classification based on convolutional neural network and feature fusion. This scheme is called FF-CMNET (Feature Fusion based Car Model Classification Net) and is based on the principle that the car frontal images can be partitioned into upper and lower parts that exhibit distinct feature distributions but are still structurally correlated to allow feature fusion. The characteristics of FF-CMNET include: (1) the design of two separate branches, named UpNet and DownNet, for extracting the features of upper parts and lower parts of the car frontal images separately;(2) a two-step fusion of features at the output of UpNet and DownNet and then again in FusionNet;and (3) the adoption of small convolution kernels and global average pooling. Extensive experiments conducted on a benchmark dataset, CompCars, show favorable results which demonstrate that the proposed FF-CMNET is able to outperform the state-of-the-art models in the classification of large datasets.

关键词： Fine-grained car model classification CNNs Feature fusion Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Classification of Hand Movements from EMG Signals using Optimized MLP

Classification of Hand Movements from EMG Signals using Opti...

引用

2018 International Joint Conference on Neural Networks, IJCNN 2018

作者： Lima, Aron A. Martins Araujo, Rafael M. Santos, Fábio A. Guidotti Dos Yoshizumi, Victor H. De Barros, Fábio K. H. Spatti, Danilo H. Liboni, Luisa H. B. Dajer, Maria E. Department of Electrical Engineering Federal University of Technology Paraná Cornélio Procópio Brazil Department of Computational Engineering Federal University of Technology Paraná Cornélio Procópio Brazil Department of Computational Systems University of São Paulo São Carlos Brazil Dep. Of Electrical and Computer Engineering Federal Institute of Education Science and Technology of São Paulo Sertãozinho Brazil

ISBN: (纸本)9781509060146

The emergence of artificial neural networks (ANNs) caused a great revolution in the knowledge area of pattern-classification and contributed to the fast development of intelligent systems. For an ANN to be effective, its topology parameters must be set up, such as learning rate, number of layers, and number of neurons. Therefore, optimization algorithms can be used to produce more efficient ANNs. In this paper, we propose a genetic algorithm (GA) to better estimate parameters of an ANN applied to the classification of the type, strength, and orientation of different hand movements from electromyography signals. Acquired data signals were first processed with the Wavelet Transform (WT) to extract the most important features. These features were presented to the optimized hybrid intelligent system (HIS) composed of ANNs and the optimization GA. Classification results are promising, presenting accuracy rates above 90% and reliability rate of 98%. These results support the use of HIS in practical applications such as smart prostheses and automatic medical evaluations. © 2018 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Controlling symmetries and clustered dynamics of complex networks

arXiv

引用

arXiv 2020年

作者： Gambuzza, Lucia Valentina Frasca, M. Sorrentino, F. Pecora, L.M. Boccaletti, S. Dipartimento di Ingegneria Elettrica Elettronica e Informatica University of Catania Catania95029 Italy Dipartimento di Ingegneria Elettrica Elettronica e Informatica University of Catania Catania95029 Italy CNR-IASI Institute for Systems Analysis and Computer Science A. Ruberti Rome00185 Italy Department of Mechanical Engineering Univ. of New Mexico AlbuquerqueNM87131 United States Dep. of Electrical and Computer Engineering Univ. of New Mexico AlbuquerqueNM87131 United States U.S. Naval Research Laboratory WashingtonDC20375 United States CNR Institute of Complex Systems Via Madonna del Piano 10 Florence50019 Italy Unmanned Systems Research Institute Northwestern Polytechnical University Xi’an710072 China Moscow Institute of Physics and Technology Dolgoprudny Moscow Region141701 Russia

Symmetries are an essential feature of complex networks as they regulate how the graph collective dynamics organizes into clustered states. We here show how to control network symmetries, and how to enforce patterned states of synchronization with nodes clustered in a desired way. Our approach consists of perturbing the original network connectivity, either by adding new edges or by adding/removing links together with modifying their weights. By solving suitable optimization problems, we furthermore guarantee that changes made on the existing topology are minimal. The conditions for the stability of the enforced pattern are derived for the general case, and the performance of the method is illustrated with paradigmatic examples. Our results are relevant to all the practical situations in which coordination of the networked systems into diverse groups may be desirable, such as for teams of robots, unmanned autonomous vehicles, power grids and central pattern generators. Copyright © 2020, The Authors. All rights reserved.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Structure constant analyzing of SLG beam Kolmogorov in atmospheric slant path propagation

引用

AIP Conference Proceedings 2019年第1期2129卷

作者： Hussein Thary Khamees Assad H. Thary Al-Ghrairi Kadhim H. Suffer Hayder H. Thary Laser and Optoelectronic Dep. Engineering College Al-Nahrain University P.O. Box 64040 Baghdad Iraq Computer Engineering Dep. Engineering College Al Iraqia University Baghdad Iraq Mechanical Engineering Dep. Engineering College Al-Nahrain University P.O. Box 64040 Baghdad Iraq Al-Karkh University of Science Baghdad Iraq

In this paper, we can attempt the structure constant parameter to mitigate, the effects of the SLG beam (Super Lorentz Gaussian) in Kolmogorov spectra in a turbulent atmosphere at receiver plan in slant path. Here, a model is developed for the field of a Super Lorentz Gaussian beam as it propagates through atmospheric turbulence, and the resulting effects upon the scintillation index of the beam with different source sizes, different zenith angle between transmitter and receiver plan in slant path. As the reference point, the cartesian wave scintillation index in Kolmogorov medium is used and employ the Random Phase Screen Method by applying the Huygens Fresnel Integral. The relations of the structure constants are found to be functions of the power high of the turbulence mediums in the atmospheric layer and the Fresnel zone. This results in large savings in MATLAB computing time. It will be useful to employ the simulation of the link transmission of the structure constants in making performance comparisons found with different values of structure constants parameters C2n against the scintillation index.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design Monitoring Electrical Power Consumtion at computer Cluster

引用

Journal of Physics: Conference Series 2020年第1期1445卷

作者： Alfianto, Enggar Agustini, Siti Muharom, Syahri Rusydi, Febdian Puspitasari, Ira Department of Computer System Institut Teknologi Adhi Tama Surabaya Jl. Arief Rachman Hakim No 100 Surabaya Indonesia Electrical Engineering Department Institut Teknologi Adhi Tama Surabaya Jl. Arief Rachman Hakim No 100 Surabaya Indonesia Theoretical Physics Research Group Dep. of Physics Fac. of Science and Technology Airlangga University Jl. Mulyorejo Surabaya Indonesia 60115 Dep. of the information system Fac. of Science and Technology Airlangga University Jl. Mulyorejo Surabaya Indonesia 60115

Electricity is one of the basic needs in the era of technological development, where all equipment must use electricity to operate such as computer, so that it requires a system that can monitor power consumption at computer cluster. To monitoring power consumption using WCS1800 to current sensor and microcontroller Atmega32 to data sensor process, and serial communication to send data to display at personal computer. From test system having two result, first is power consumption at computer cluster starting, where current value range is 0 to 38A with power consumption is 0 to 8360 watt. And second is power consumtion at computer cluster execution progran, current value is 27 to 40 A, with power consumption 5940 to 8800 watt. From this system has been design, the power consumption at computer cluster can be monitored and known value of energy consumption.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On lennard-jones-type potentials on the half-line

arXiv

引用

arXiv 2018年

作者： Gregorio, Federica Kerner, Joachim Dep. of Information Engineering Electrical Engineering and Applied Mathematics Università degli Studi di Salerno FiscianoSA Italy Department of Mathematics and Computer Science FernUniversität in Hagen Hagen58084 Germany

In this paper we study a particle under the influence of a Lennard-Jones potential moving in a simple quantum wire modelled by the positive half-line. Despite its physical significance, this potential is only rarely studied in the literature and due to its singularity at the origin it cannot be considered as a standard perturbation of the one-dimensional Laplacian. It is therefore our aim to provide a thorough description of the full Hamiltonian in one dimension via the construction of a suitable quadratic form. Our results include a discussion of spectral and scattering properties which finally allows us to generalise some results from [Rob74] as well as [RS78].MSC Codes 81Q10, 81Q37, 81Q80, 81Q35, 47E05, 47D08 Copyright © 2018, The Authors. All rights reserved.

关键词： Number theory

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：