2019 International Automatic Control Conference (CACS)最新文献

Convergence Improvement of Q-learning Based on a Personalized Recommendation System 基于个性化推荐系统的q学习收敛改进

2019 International Automatic Control Conference (CACS) Pub Date : 2019-11-01 DOI: 10.1109/CACS47674.2019.9024742

Chia-Ling Chiang, M. Cheng, Ting-Yu Ye, Ya-Ling Chen, Pin-Hsuan Huang

{"title":"Convergence Improvement of Q-learning Based on a Personalized Recommendation System","authors":"Chia-Ling Chiang, M. Cheng, Ting-Yu Ye, Ya-Ling Chen, Pin-Hsuan Huang","doi":"10.1109/CACS47674.2019.9024742","DOIUrl":"https://doi.org/10.1109/CACS47674.2019.9024742","url":null,"abstract":"Reinforcement Learning (RL) – a research branch of artificial intelligence – exploits the concept of reward/penalty from human learning so that the feedback information of the environment can be used for self-learning without previous knowledge. Although RL has been applied to many research fields, there are difficulties when implementing it in some real world applications. One difficulty is the tradeoff between exploration and exploitation for the agent of RL in choosing a proper action. An improper action may lead to a learning failure or an increase in learning cost. Another difficulty is that the learning agent of RL needs to interact with the environment to attain a real-time reward/penalty; however, the learning time spent in the interaction process may be too long. In order to overcome the aforementioned difficulties, this paper proposes an approach that employs a personalized recommendation system to provide a feedforward candidate action for RL to implement self-adaptive learning through teaching. A real visual tracking experiment using a pan-tilt camera system is conducted to assess the performance of the proposed approach. Experimental results show that the proposed personalized recommendation system-based approach is able to improve the effectiveness and practicality of RL.","PeriodicalId":247039,"journal":{"name":"2019 International Automatic Control Conference (CACS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127646155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Sea Testing of Automatic Motion Control System for a Quad-Maran Unmanned Vessel 四maran无人船自动运动控制系统的海上试验

2019 International Automatic Control Conference (CACS) Pub Date : 2019-11-01 DOI: 10.1109/CACS47674.2019.9024363

Makoto Komizo, Kota Mukai, N. Hara, Y. Nihei, K. Konishi

引用次数: 0

Design and Implementation of a Cross-Camera Suspect Tracking System 跨摄像机嫌疑人跟踪系统的设计与实现

2019 International Automatic Control Conference (CACS) Pub Date : 2019-11-01 DOI: 10.1109/CACS47674.2019.9024367

Yu-Hsueh Chuo, Ruey-Kai Sheu, Lun-Chi Chen

{"title":"Design and Implementation of a Cross-Camera Suspect Tracking System","authors":"Yu-Hsueh Chuo, Ruey-Kai Sheu, Lun-Chi Chen","doi":"10.1109/CACS47674.2019.9024367","DOIUrl":"https://doi.org/10.1109/CACS47674.2019.9024367","url":null,"abstract":"Surveillance systems are everywhere deployed for criminal prevention and suspect tracking for specific security events. The recognition of the target person cross multiple cameras remains a challenge because of the large spatio-temporal uncertainty, which means the entry and the exit of persons in cameras are unpredictable. Therefore, this study design and implement a software system that help users to continuous and stable track of the same target person across multiple cameras. Firstly, the system leverages YOLO and Correlation filter to track the suspicious in single camera. The features of the target suspect are also collected in this stage. Once the target person leaves the scope of a camera, the camera network topology is used to predict the candidate entrance cameras based on the geographical information and tracking path in the first stage. In the second stage, the person re-identification algorithm is used to calculate the similarity possibility and help to identify the person automatically between cameras. Experimental results on public datasets show our system can accurately recognize the target suspect across cameras with acceptable system performance.","PeriodicalId":247039,"journal":{"name":"2019 International Automatic Control Conference (CACS)","volume":"499 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117025906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Performance evaluation of temporal features for detection of mild cognitive impairment: An fNIRS study 时间特征对轻度认知障碍检测的性能评价:一项近红外光谱研究

2019 International Automatic Control Conference (CACS) Pub Date : 2019-11-01 DOI: 10.1109/CACS47674.2019.9024353

U. Ghafoor, M. A. Yaqub, K. Hong

{"title":"Performance evaluation of temporal features for detection of mild cognitive impairment: An fNIRS study","authors":"U. Ghafoor, M. A. Yaqub, K. Hong","doi":"10.1109/CACS47674.2019.9024353","DOIUrl":"https://doi.org/10.1109/CACS47674.2019.9024353","url":null,"abstract":"A decline in cognition characterized by the deficit in memory, judgment, and language is known as mild cognitive impairment (MCI). This deficiency has great likelihood of developing Alzheimer’s disease (AD). Hence, the recognition of MCI or an early stage of AD is critical at earliest for evaluation and treatment. In this study, functional near-infrared spectroscopy (fNIRS) was used to measure the concentration changes of oxygenated hemoglobin (ΔHbO) from the pre-frontal cortex of six healthy controls (HC) and six MCI patients during a working memory task. Various temporal features of ΔHbO, such as mean, slope, kurtosis, skewness, and peak-values, were tested for distinguishing MCI patients from HCs. We further investigated the impact of intervention (i.e., acupuncture treatment) on MCI patients (i.e., MCI-1: before intervention, MCI-2: after intervention). Both groups went through fNIRS recording procedure with a gap of 45 days. Before the second fNIRS measurement, only the patient group underwent interventions twice per week for six weeks. The results showed that the mean ΔHbO response of MCI-1 was significantly less than (p < 0.05) that of HC but similar (p > 0.05) with MCI-2. Out of tested temporal features, signal mean and peak values of HC were significantly different (p = 0.0409, p = 0.0430) in comparison to MCI-1 but no significant difference (p = 0.4885, p = 0.4437) if MCI-2. Moreover, these fNIRS results were positively correlated with cognitive test scores. These preliminary results showed that fNIRS can be used for distinguishing MCI patients from HCs using mean hemodynamic response as well as temporal features.","PeriodicalId":247039,"journal":{"name":"2019 International Automatic Control Conference (CACS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123681272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Parametric synthesis of a robust controller on a base of D-partition and method of dominant poles 基于d划分和优势极点法的鲁棒控制器参数综合

2019 International Automatic Control Conference (CACS) Pub Date : 2019-11-01 DOI: 10.1109/CACS47674.2019.9024735

S. Gayvoronskiy, T. Ezangina, I. Khozhaev

引用次数: 1

Torque Control of the Floating Vertical Axis Wind Turbine with a Frictional Power Take-off System 带摩擦动力输出系统的浮式垂直轴风力机转矩控制

2019 International Automatic Control Conference (CACS) Pub Date : 2019-11-01 DOI: 10.1109/CACS47674.2019.9024733

Shunsuke Maura, N. Hara, H. Akimoto, K. Konishi

引用次数: 1

The studies on Automated Road Safety Monitoring System and Real-Time Traffic Reporting System of an Automatic Vehicle 自动道路安全监控系统与自动车辆实时交通报告系统的研究

2019 International Automatic Control Conference (CACS) Pub Date : 2019-11-01 DOI: 10.1109/CACS47674.2019.9024356

Sheng-Fuu Lin, Nien-Tzu Hsieh, Y. Jiang, Yuan-Cheng Hsieh

引用次数: 2

A study on Machine Learning Approaches for Predicting and Analyzing the Drying Process in the Textile Industry 纺织工业干燥过程预测与分析的机器学习方法研究

2019 International Automatic Control Conference (CACS) Pub Date : 2019-11-01 DOI: 10.1109/CACS47674.2019.9024364

Ke-Haur Taur, Xiang-Yun Deng, Mi-Huo Chou, Jing-Wei Chen, Yi-Hsiu Lee, Wen-June Wang

引用次数: 2

Synchronized Motion Control for Electronic Differential System via Planetary Gear Mechanism 基于行星齿轮机构的电子差动系统同步运动控制

2019 International Automatic Control Conference (CACS) Pub Date : 2019-11-01 DOI: 10.1109/CACS47674.2019.9024359

Guowei Chen, Trieu-Khang Tu, Chun-Lin Chen, M. Tsai

引用次数: 0

Development of Key Technologies for Autonomous Driving Vehicles 自动驾驶汽车关键技术的发展

2019 International Automatic Control Conference (CACS) Pub Date : 2019-11-01 DOI: 10.1109/CACS47674.2019.9024730

J. Tsai, J. Juang, Chia-Heng Tu, T. Tsai, P. Chung, Chih-Chung Hsu, Chao-Yang Lee, Ching-Fu Lin

引用次数: 4