2020 International Symposium on Computer, Consumer and Control (IS3C)最新文献

{"title":"Efficiency analysis of light emitting diodes based on material properties and structures","authors":"Wen-Chieh Wu, C. Ho","doi":"10.1109/IS3C50286.2020.00070","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00070","url":null,"abstract":"Studies on efficiency and performance of light-emitting diodes (LEDs) involves the complicated interactions of optic, electronic, magnetic, quantum and thermal characteristics of materials and structures of LEDs. Therefore, efficiency and performance of LEDs are generally investigated by measurements and aided via theoretical analysis. While the analytical formulas of material properties and structures of LEDs are sensitive and difficult to obtain for calculating the efficiency and performance of LEDs, it is still essential for academic and technological developments to propose the analytical model of efficiency study based on material properties and structures of LEDs. With the progress in the analytical formulas of material properties and structures of LEDs, the analytical method for the study on the efficiency of LEDs is proposed in this paper and applied to the efficiency predictions of AlGaInP and InGaN QW LEDs. The results are compared with the available measured data and agree with these obtained by measurements. The results indicate that the variation of efficiency of InGaN LED with forward current increases very rapidly at initial forward current and then slowly decreases with the increasing forward current. However, efficiency of AlGaInP LED hardly decreases with the increasing forward current after the rapid increase of efficiency at the initial forward current. The possible reason is that the series resistance of AlGaInP LED is lower than that of InGaN LED.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129193400","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}

{"title":"Relation between Environment Color and Image Processing Performance at Design Development Stage","authors":"Eva Chang, Rain Chen, C. Lin, Pin-Yun Hsiao","doi":"10.1109/IS3C50286.2020.00008","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00008","url":null,"abstract":"Lacking inspiration is a major challenge for designers when performing a design task, and the number and the quality of design ideas are critical indicators of the performance of a designer. With 60 volunteered participants, 70% women and 30% men, who in average had more than three years of design experience, this study tested whether environment color (red, green, and white) affects designers' image processing performance at the design development stage. The data collected were submitted to ANOVA, and the result shows (1) no significant effect of environment color on the number of design ideas (F = 0.553; P = 0.578), (2) no significant effect of environment color on the quality of design ideas (F = 0.156; P = 0.856), and (3) a weak correlation (r = 0.277) between the number of design ideas and the quality of design ideas. A suggestion for future research exploring the effect of environment color on enhancing image processing performance is to refine the experimental control.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115896756","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}

{"title":"Probabilistic Wind Power Forecasts Considering Different NWP Models","authors":"Sheng-Hong Wu, Yuan-Kang Wu","doi":"10.1109/IS3C50286.2020.00116","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00116","url":null,"abstract":"The intermittency of wind power generation is regarded as an obstacle to use wind energy for electricity. Accurate wind power forecasting is one of the direct methods to reduce the risk about wind intermittent. Compared with deterministic forecasting, probabilistic forecasting provides additional information about uncertainty, allowing power system operators to minimize operating costs for unit scheduling and power transactions. Numerical weather prediction (NWP) plays an important role on probabilistic wind power forecasting. Thus, this paper uses three different NWP models to generate the NWP wind speeds, and these NWP wind speeds and historical wind power measurements are used as the inputs for wind power generation. The used NWP models include decisive forecast (WRFD), ensemble forecast (WEPS), and real-time forecast (RWRF). These NWPs were obtained from the Taiwan Central Meteorological Bureau (CWB). Additionally, in this work, several deep learning models and traditional artificial neural networks were applied for wind power forecasting, in which the distribution of forecasting errors is used to construct a reliable prediction interval, and the lower limit upper limit estimation (LUBE) method is used. Based on the forecasting results, the use of NWP models has significantly improved the forecasting performance.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132617841","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}

{"title":"Object Recognition and Classification of 2D-SLAM using Machine Learning and Deep Learning Techniques","authors":"Yu-Fu Lin, Lee-Jang Yang, Chun-Yen Yu, Chao-Chung Peng, Der-Chen Huang","doi":"10.1109/IS3C50286.2020.00129","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00129","url":null,"abstract":"Reviewing two-dimensional simultaneous localization and mapping (2D-SLAM) studies in these decades, many researchers focused on the algorithm enhancement for real-time localization and mapping. The related techniques of 2D-SLAM have been investigated deeply. However, most of the researches focus on the SLAM. Less concentration is put on 2D grid map object recognitions and labeling. Therefore, this paper dedicates to integrate recent popular machining learning techniques with 2D-SLAM technology to come out with an application for 2D object segmentation, feature extraction, as well as pattern recognition. Based on a given 2D grid map and a couple of pre-trained patterns, a clustering method and a machining learning based pattern recognition were presented. Experiments show that the proposed process is able to provide satisfactory object identification accuracy.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"1991 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130842318","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}

{"title":"The management control system for plant factory that uses the IoT technology in combination with Augmented Reality technology","authors":"Tai-Hung Wang, Xue-Ru Dai, Peirui Wang, Yu-Xiang Hong, Zi-Xiang Su, Sheng-Wei Gao, Shi-Lun Wang","doi":"10.1109/IS3C50286.2020.00007","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00007","url":null,"abstract":"The Internet of Things (IoT) technology is widely used in various fields and continues to develop rapidly. However, the IoT has always been confined to the stage where things are connected by things. This plan applies IoT technology in combination with Augmented Reality(AR) technology into management control system for plant factory. This system includes an environmental parameter monitoring system and a navigation information system. The IoT technology is used to integrate environmental parameters and the status of various equipment in the control parameters to achieve things and things connection. Using augmented reality technology can directly integrate various information Intuitive feedback to the operator that complete the connection between people and things. This project uses the ESP8266 development platform as the main control core of device, The system uses a cloud database to receive, store, and judge information. The WiFi is used for wirelessly transmit data. The ESP8266 development platform is expected to be used in the environmental parameter monitoring system to complete offline sensors and equipment control units. The AR technology is used in the navigation information system to provide real-time interactive information. You can use APP on the mobile device to inquire about the growth analysis and related information of various crops in plant factories in real time. The plan uses IoT technology and AR technology that can reduce the manpower requirements and improve the control performance of plant factories.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131218421","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}

{"title":"Vehicle Distance Estimation Method Based on Monocular Camera","authors":"Tzu-Yun Tseng, Jian-Jiun Ding","doi":"10.1109/IS3C50286.2020.00034","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00034","url":null,"abstract":"Advanced driver assistance system (ADASs) are important on traffic safety. In ADASs, vehicle distance estimation methods can be classified into sensor based, multiple-camera based, and monocular-vision based methods. However, sensor-based methods mainly apply radar information and are sensitive to the interference of buildings. Multiple-camera based methods require more computation loading. Monocular-vision based methods are more practical, however, their performance need to be improved. In this study, we proposed several techniques to improve the accuracy of the monocular-vision based distance estimation. The proposed algorithm is divided into two stages: feature point extraction, and vehicle distance estimation. In feature point extraction, we find the Harris corners and perform road extraction and find the masks by segmenting the road lane and the tire regions according to their colors and relative locations. Then, polygon approximation is applied to get four corners of the lane. After getting critical feature points, we use the geometric relationship between the camera and the tire bottoms to estimate the distance. However, the tilting angle of the camera may highly affect the accuracy of monocular vehicle distance estimation. In practice, the tilting angle is hard to known explicitly. To solve the problem, we adjust the camera angle according to the standard length of road lanes using yellow and blue feature points. Simulations show that the average error of the proposed algorithm is much lower than that of state-of-the-art methods, which indicates the feasibility of the proposed method.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125676460","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}

{"title":"Performance Demands based Servo Motor Speed Control: A Genetic Algorithm Proportional-Integral Control Parameters Design","authors":"Chao-Chung Peng, Chia-Ling Lee","doi":"10.1109/IS3C50286.2020.00128","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00128","url":null,"abstract":"This paper presents an analytic Proportional-Integral (PI) controller design for a servo motor speed control under given control performance demands. When designing the classical linear controllers, standard 2nd order systems are often considered to simplify the design problems. Realistically, however, most of the systems are usually non-standard 2nd order systems and assuming them as standard 2nd order systems could sometimes cause designing mismatches. To solve this issue, this study derived analytical PI controller formulas, where the control gains were determined by applying Genetic Algorithm (GA) with the aim of approaching the desired performances including overshoot and settling time as close as possible. A numerical simulation is also performed to attest the results. The main contributions of this paper include the accuracy of achieving the control performance demands by taking the exact analytical solutions, eliminating the model discrepancies between the exact closed-loop model and the standard 2nd order system, and the proposed method can be extended to a wide variety of process control topics.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117351591","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}

{"title":"A Deep Learning Co-training Framework for e-book Classification","authors":"Tsui-Ping Chang, Hung-Ming Chen, Jian-Qun Chen","doi":"10.1109/IS3C50286.2020.00103","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00103","url":null,"abstract":"Automatic e-book classification is an important research issue since more and more people read and acquire information on their mobile devices (i.e., smartphones). Many writers digitize their works for users to acquire data on their mobile devices and result in the number of e-books has grown significantly. An e-book is a digital or electronic book that is formatted into a file that can be read on a mobile device. Some features of books are used in e-books. However, the important difference is that an e-book has a lot of images to describe the contents or knowledge of writers. Many researches proposed their methods of e-book classification to make users easily to find out and then read an e-book on their mobile devices. In these methods, an e-book can be categorized by several criteria. One of it is based on its type, i.e., novel, reference, and encyclopedia. Another is based on its topic, i.e., economy, religion, and technical. The classification systems based on the topics usually use well-known methodology such as Dewey Decimal Classification, in which, every category reflected by a decimal. These researches use Naïve Bayes Classifier and focus on automatic thesis classification. As deep learning proves its usefulness in an ever greater number of applications, there is a rise in demand for faster computational resources to train ever complex learning-based models. Based on the concept of deep learning, some researches proposed their methods to automatic e-book classification. W. A. Wiegand proposed a convolutional-neural-network (CNN) book label recognition algorithm to find out the misplaced books. On the other hand, four steps are illustrated in X. Yang et al. First, the keywords are extracted from the description data of e-books. Then, the description data is modeled as vectors of keywords. Third, the statistical categorization rules are obtained from meta-information of e-books. Finally, the vectors and the statistical categorization rules are combined to obtain an classification model. In this paper, a deep learning co-training framework (namely DLC) is proposed for improving the accuracy of automatic e-book classification. DLC combines the features of texts and images in e-books to co-training an e-book classifier. In order to increase the variety of feature sets, the texts in e-books are represented as vectors by Word2Vec. The images in e-books are translated and then combined into the vectors. Furthermore, DLC adopts the softmax regression function to co-train the combined features (i.e., vectors and images) in CNN to improve the accuracy of e-book classification. The experimental results demonstrate that our DLC has higher accuracy than other e-book classifiers.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129442961","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}

{"title":"Application of Vehicle Detection Based On Deep Learning in Headlight Control","authors":"Zixun Huang, Chuin-Mu Wang, Wun-Ciang Wu, Wun-Syun Jhang","doi":"10.1109/IS3C50286.2020.00053","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00053","url":null,"abstract":"When driving at night, vehicle lights are the greatest guarantee for driving safety. Drivers often turn on the high beams to make the oncoming vehicle unclear, turn on the high beams of the oncoming vehicle to reduce their visual range or turn on the high beam when driving behind. The lights prevent themselves from being able to check the rear view through the rear mirror and cause traffic accidents. In addition, drivers often fail to keep a safe distance from the traffic, which causes serial accidents. In response to this problem, this paper proposes a deep learning-based image recognition in the headlight control system. Vehicles using this system can detect the vehicle ahead in real time when the driver is driving the vehicle, and calculate the safety distance of the vehicle ahead, and judge at night Whether there are vehicles in the front and oncoming lanes to determine whether to turn on the high beam, so as to reduce light damage and safe distance traffic accidents.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121407547","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}

{"title":"Exploring Consistency of C++/CLI Programming Models with Migration Design from Hand-Made to Wizard-Readable Codes","authors":"Gao-Wei Chang","doi":"10.1109/IS3C50286.2020.00052","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00052","url":null,"abstract":"With a series of C++/CLI programming models, this paper is to propose an object-oriented framework to establish and explore the consistency of the migration design from hand-made to wizard readable codes in an integrated development environment (IDE), e.g., Microsoft Visual Studio (VS). To demonstrate the effectiveness of the migration approach, a sufficient-as-possible hand-made project is devised, where the controls include menu-strip, dialog box, and picture box, to achieve the command-driven graphics functionalities with numeric data.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"4979 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116272661","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}