检索结果-内蒙古大学图书馆

Wireless Service Pricing Competition under Network Effect, Congestion Effect, and Bounded Rationality

学校读者我要写书评

暂无评论

Wireless Service Pricing Competition under Network Effect, C...

作者： Zhang, Mengyuan Yang, Lei Gong, Xiaowen He, Shibo Zhang, Junshan State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China Department of Computer Science and Engineering University of Nevada RenoNV89557 United States Department of Electrical and Computer Engineering Auburn University AuburnAL36849 United States School of Electrical Computer and Energy Engineering Arizona State University TempeAZ85287 United States

Mobile social networks have greatly strengthened people's online social interactions, generating massive volume of mobile data traffic, and bringing remarkable revenues to the wireless service providers. Meanwhile, the potential revenue growth is restrained by the network capacity of physical communication infrastructure and also challenged by the competition among service providers. In this paper, we study the pricing strategies of multiple service providers in a competitive data service market, where mobile users' data consumption behaviors are influenced by two effects: the positive network effect and the congestion effect. To analyze the strategic interactions between mobile users and service providers, we devise a two-stage Stackelberg game consisting a pricing game in Stage I and a usage game in Stage II, respectively. In particular, for the usage game, we characterize the equilibrium solution and establish its uniqueness. For the pricing game, our analysis indicates that a mixed-strategy equilibrium solution is guaranteed for the scenario with rational providers as well as the scenario with providers of bounded rationality. We further develop a distributed learning algorithm for finding a mixed-strategy equilibrium solution in the second scenario. Our numerical results provide insights into how positive the network effect and the congestion effect would impact the system performance, and demonstrate that the bounded rational behavior incurs degradation to service providers' revenues. © 1967-2012 IEEE.

关键词： Game theory

Fast online reinforcement learning control using state-space dimensionality reduction

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Sadamoto, Tomonori Chakrabortty, Aranya Imura, Jun-Ichi Department of Mechanical and Intelligent Systems Engineering Graduate School of Informatics and Engineering University of Electro Communications 1-5-1 Chofugaoka Chofu Tokyo182-8585 Japan Electrical and Computer Engineering North Carolina State University RaleighNC27695 United States Department of Systems and Control Engineering Graduate School of Engineering Tokyo Institute of Technology Oh-Okayama Meguro Tokyo2-12-1 Japan

Reinforcement Learning (RL) is an effective way of designing model-free linear quadratic regulator (LQR) controller for linear time-invariant (LTI) networks with unknown state-space models. However, when the network size is large, conventional RL can result in unacceptably long learning time. In this paper we resolve this problem by developing an alternative approach for RL-based LQR that combines dimensionality reduction with RL theory. The approach is to construct a compressed state vector by projecting the measured state through a projective matrix. This matrix is constructed from the state measurements, and can be viewed as an empirical controllability gramian that captures the level of redundancy in the controllability of the open-loop network model. Next, a RL-controller is learned using the reduced-dimensional state instead of the original state such that the resultant cost is close to the optimal LQR cost. Numerical benefits as well as the cyber-physical implementation benefits of the proposed approach are verified using illustrative examples including an example of wide-area control of the IEEE benchmark power system. Copyright © 2019, The Authors. All rights reserved.

关键词： controllers

Fuzzy Q-learning obstacle avoidance algorithm of humanoid robot in unknown environment 37

学校读者我要写书评

暂无评论

Fuzzy Q-learning obstacle avoidance algorithm of humanoid ro...

37th Chinese control Conference, CCC 2018

作者： Wen, Shuhuan Chen, Jianhua Li, Zhen Rad, Ahmad B. Mohammed Othman, Kamal Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao066004 China School of Engineering Sciences Simon Fraser University SurreyBCV3T 0A3 Canada

ISBN: (纸本)9789881563941

This paper proposes a fuzzy Q-learning (FQL) algorithm to solve the problem of the robot obstacle avoidance in unknown environment. FastSLAM algorithm is used to localize the position of the robot. Traditional Q-learning algorithm, optimized Q-learning algorithm, FQL algorithm are compared. The simulation results show that FQL algorithm has a faster learning speed than other two algorithms and the results demonstrate that the fuzzy Q-learning obstacle avoidance algorithm is effective. © 2018 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Anthropomorphic robots

Optimization of Missile Path Planning Based on APMO-HV Algorithm

学校读者我要写书评

暂无评论

Optimization of Missile Path Planning Based on APMO-HV Algor...

IEEE International Conference on Unmanned Systems (ICUS)

作者： Hu Zhang Shuai Wang Tonglin Liu Aimin Zhou Yi Zhang Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing Electro-mechanical Engineering Institute Beijing China School of Mechanical Engineering Changzhou University Changzhou China Shanghai Key Laboratory of Multidimensional Information Processing School of Computer Science and Technology East China Normal University Shanghai China

In this paper, with considerations of low efficiency of missile path planning (MPP) by traditional aggregation technology, it uses affinity propagation based multi-objective evolutionary algorithm with hypervolume environment selection (APMO-HV) to solve the problem of MPP after establishing the MPP model. The experimental part compares and analyzes APMO-HV with six state-of-the-art algorithms, and applies it to address the MPP problem. The experimental results show that compared with the other six algorithms, APMO-HV has achieved the best solution performance in both the GLT test suite and MPP problem. This not only validates the effect of the proposed algorithm, but also enriches and improves the research results of MPP.

关键词： Missiles Optimization Path planning Turning Planning Target tracking Sociology

学校读者我要写书评

暂无评论

Network Resilience

arXiv 2020年

作者： Liu, Xueming Li, Daqing Ma, Manqing Szymanski, Boleslaw K. Eugene Stanley, H. Gao, Jianxi Key Laboratory of Image Information Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China School of Reliability and Systems Engineering Beihang University Beijing100191 China College of Safety Science and Engineering Civil Aviation University of China Tianjin 300300 China Department of Computer Science Rensselaer Polytechnic Institute TroyNY12180 United States Network Science and Technology Center Rensselaer Polytechnic Institute TroyNY12180 United States Center for Polymer Studies Department of Physics Boston University BostonMA02215 United States

Many systems on our planet shift abruptly and irreversibly from the desired state to an undesired state when forced across a "tipping point". Some examples are mass extinctions within ecosystems, cascading failures in infrastructure systems, and changes in human and animal social networks. The ability to avoid such regime shifts or to recover quickly from such a non-resilient state demonstrates a system's resilience;system resilience is a quality that enables a system to adjust its activities to retain its basic functionality when errors and failures occur. In the past 50 years, attention has been paid almost exclusively to low-dimensional systems;scholars have focused on the calibration of the resilience functions of such systems and the identification of indicators of early warning signals based on two to three connected components. In recent years, taking advantage of network theory and the availability of lavish real datasets, network scientists have begun to explore real-world complex networked multidimensional systems, as well as their resilience functions and early warning indicators. This report presents a comprehensive review of resilience functions and regime shifts in complex systems in domains such as ecology, biology, society, and infrastructure. The research approach includes empirical observations, experimental studies, mathematical modeling, and theoretical analysis. We also review the definitions of some ambiguous terms, including robustness, resilience, and stability. Copyright © 2020, The Authors. All rights reserved.

关键词： Complex networks

Deep learning for image and point cloud fusion in autonomous driving: A review

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Cui, Yaodong Chen, Ren Chu, Wenbo Chen, Long Tian, Daxin Li, Ying Cao, Dongpu The Waterloo CogDrive Lab Department of Mechanical and Mechatronics Engineering University of Waterloo 200 University Ave West WaterlooONN2L3G1 Canada Research Institute Co. Ltd. Beijing100176 China School of Data and Computer Science Sun Yat-sen University Zhuhai519082 China Waytous Inc. Qingdao266109 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang University Beijing100191 China

Autonomous vehicles were experiencing rapid development in the past few years. However, achieving full autonomy is not a trivial task, due to the nature of the complex and dynamic driving environment. Therefore, autonomous vehicles are equipped with a suite of different sensors to ensure robust, accurate environmental perception. In particular, the camera-LiDAR fusion is becoming an emerging research theme. However, so far there has been no critical review that focuses on deep-learning-based camera-LiDAR fusion methods. To bridge this gap and motivate future research, this paper devotes to review recent deep-learning-based data fusion approaches that leverage both image and point cloud. This review gives a brief overview of deep learning on image and point cloud data processing. Followed by in-depth reviews of camera-LiDAR fusion methods in depth completion, object detection, semantic segmentation, tracking and online cross-sensor calibration, which are organized based on their respective fusion levels. Furthermore, we compare these methods on publicly available datasets. Finally, we identified gaps and over-looked challenges between current academic researches and real-world applications. Based on these observations, we provide our insights and point out promising research directions. Copyright © 2020, The Authors. All rights reserved.

关键词： Object detection

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Shen, Zhihao Du, Wan Zhao, Xi Zou, Jianhua School of Electronic and Information Engineering Xi'an Jiaotong University Shaanxi Engineering Research Center of Medical and Health Big Data Xi'an710049 China Department of Computer Science and Engineering University of California MercedCA95340 United States School of Management Xi'an Jiaotong University Key Lab of the Ministry of Education for Process Control & Efficiency Egineering Xi'an710049 China

Retrieving similar trajectories from a large trajectory dataset is important for a variety of applications, like transportation planning and mobility analysis. Unlike previous works based on fine-grained GPS trajectories, this paper investigates the feasibility of identifying similar trajectories from cellular data observed by mobile infrastructure, which provide more comprehensive coverage. To handle the large localization errors and low sample rates of cellular data, we develop a holistic system, cellSim, which seamlessly integrates map matching and similar trajectory search. A set of map matching techniques are proposed to transform cell tower sequences into moving trajectories on a road map by considering the unique features of cellular data, like the dynamic density of cell towers and bidirectional roads. To further improve the accuracy of similarity search, map matching outputs M trajectory candidates of different confidence, and a new similarity measure scheme is developed to process the map matching results. Meanwhile, M is dynamically adapted to maintain a low false positive rate of the similarity search, and two pruning schemes are proposed to minimize the computation overhead. Extensive experiments on a dataset of 3,186,000 mobile users and real-world trajectories of 1701 km reveal that cellSim provides high accuracy (precision 62.4% and recall of 89.8%). Copyright © 2019, The Authors. All rights reserved.

关键词： Trajectories

Motor Bearing Fault Diagnosis Based on Deep Learning

学校读者我要写书评

暂无评论

Motor Bearing Fault Diagnosis Based on Deep Learning

ACIS International Conference on Software engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD)

作者： Wei Zhang Yong Hu Deliang Zeng Wei Luo Gengda Li Miao Liu School of Control and Computer Engineering North China Electric Power University Beijing China Intelligent Power Generation Technology Research Center Guodian New Energy Technology Research Institute Co.Ltd Beijing China

ISBN: (纸本)9781728116525

The effective fault monitoring of the motor bearings not only can ensure the smooth and efficient operation of equipment, but also can detect and eliminate the running fault in time to prevent major accidents. Based on deep learning algorithm, this paper constructs a stacked auto-encoder (SAE) network. The input data are compressed by introduced sparsity constraint, so that the network can accurately extract the fault characteristics of the input data. And the fault recognition ability of the network can be improved by introducing random noise to reconstruct input data. The simulation result shows that the SAE network can not only overcome the shortcomings of traditional fault diagnosis methods that requires personnel to distinguish fault samples and needs a large number of prior knowledge; but also realize the self-learning of fault feature information. The accuracy rates of fault identification reach 98%, 94%, 96% and 95.5% in four different working conditions. What's more, the network can adapt to the actual multi-load cases, demonstrate strong robustness under different working conditions.

关键词： Fault diagnosis Vibrations Feature extraction Neurons Deep learning Biological neural networks Training

A Power Forecasting Approach for PV Plant based on Irradiance Index and LSTM

学校读者我要写书评

暂无评论

A Power Forecasting Approach for PV Plant based on Irradianc...

Chinese control Conference (CCC)

作者： Hui He Ran Hu Yaning Zhang Ying Zhang Runhai Jiao School of Control and Computer Engineering North China Electric Power University Beijing

A novel power forecasting approach for PV plant based on irradiance index and LSTM is presented in this paper. Firstly, we come up with a clustering algorithm according to the irradiance index after analyzing the periodic characteristics of PV plant daily power curves. Then, the Long Short-Term Memory (LSTM) is employed to build forecasting models for each type of weather. An empirical study on a real dataset shows that the proposed method can effectively use multivariate time series information to predict the power for PV plants and obtain better performance than Extreme Learning Machine (ELM) and Artificial Neural Networks (ANN).

关键词： Meteorology Forecasting Power generation Indexes Predictive models Time series analysis Prediction algorithms