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

{"title":"Automatic Adjustment Method for Rotor Dynamic Balance System","authors":"Yi-Hao Chung, Chao-Wei Yu, Bo-Rui Wen, Yen-Lin Chen","doi":"10.1109/IS3C50286.2020.00023","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00023","url":null,"abstract":"This paper aims to develop an automatic adjustment method (AAM) that integrates 3D sensor and dynamic balancing platform using 3D computer vision technology and dynamic balance algorithm to improve the efficiency of rotor dynamic balancing. Active rotor dynamic balancing process relies on technicians to mount washers on particular balance columns based on their experience, therefore uncertainty causes productivity decline. The proposed AAM introduce 3D sensors on active rotor dynamic balance machine to get 3D point cloud of rotor and balance columns. First, by 3D depth data, the background noise can be removed to detect the positions of axis center, key phasor and balance columns of rotor automatically. Second, combine with unbalance vector from dynamic balancing machine, the AAM system calculated the optimal balance configuration by the vector analysis algorithm. Experiments in industrial examples showed that, compared to conventional method, the proposed AAM requires fewer rounds to achieve acceptance. In contrast, the industrial rotor balancing method previously used by operators requires more than three rounds in average. That is, the proposed AAM can accurately analyze the dynamic balance and greatly reduce the redundant dynamic balance operations. In conclusion, compared to the conventional approach, the proposed AAM is superior in terms of efficiency, effectiveness and robustness in online optimization of rotor dynamic balance. Notably, the effectiveness of the AAM has also been confirmed by Taiwan manufacturers that use rotor dynamic balance machines.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"6 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":"116862865","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":"DDSnet: A Deep Document Segmentation with Hybrid Blocks Architecture Network","authors":"Jing-Ming Guo, Li-Ying Chang, Hao-Hsuan Lee","doi":"10.1109/IS3C50286.2020.00031","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00031","url":null,"abstract":"In recent years, the development of document segmentation technology is gaining more and more attention in the area of semantic segmentation, which plays an important role in the task of understanding the structure of documents. Although this demand applying deep learning approaches has undergone continuing advancement, the document segmentation systems still suffer from low accuracy rate. This paper presents a new high-performance document segmentation algorithm, namely Deep Document Segmentation Network (DDSnet), which incorporates advanced end-to-end deep learning methods for segmenting four different types of document features, including background, texts, tables, and figures. To overcome the small receptive fields, the atrous residual block is proposed, which is efficiently boosted by the adoption of multi-branches structure. For the better fine-grained output, the proposed atrous convolution residual block is conducted to achieve high accuracy. Moreover, this paper also releases the brand-new large-scale database, namely PPSD2019, for document segmentation that provides a pixel-level database for another benchmark. As documented in the experimental results, the proposed document segmentation method achieves a superior segmentation rate than that of the former competitive schemes. As a result, the proposed method and database can be considered as a very competitive candidate for the document segmentation applications.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"77 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":"114245988","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":"Applying Hybrid Passive Current-Sharing Components to Non-Isolated LED Driver","authors":"W. Jiang, K. Hwu, H. H. Chen","doi":"10.1109/IS3C50286.2020.00074","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00074","url":null,"abstract":"The capacitive current balancing LED driver based on the boost converter features simple structure and high-precision LED current balance. However, when the number of the LED strings is increased, the output voltage will also increase because the output voltage is the sum of total LED string voltages. Consequently, the duty cycle will increase to achieve the requirement of a high output voltage. In this paper, an improved non-isolated single-switch four-channel LED driver with automatic current balance is presented. Although there are four LED strings, the output voltage is only the sum of two LED strings. Thus, more LED strings can be used. In the proposed LED driver, the currents flowing through the LED string 1 and LED string 2 are balanced by one current sharing capacitor, and the currents flowing through the LED string 3 and LED string 4 are balanced by the other current sharing capacitor. Owing to the manufacturing deviation of LEDs and different trace impedance, the sum of the currents in LED string 1 and LED string 2 are not equal to the sum of the currents in LED string 3 and LED string 4. Therefore, a differential-mode transformer is connected between the two current sharing capacitors to balance the four LED currents. Since each winding of the differential-mode transformer is connected in series with a current sharing capacitor, the leakage inductors of the differential-mode transformer can limit the current peak. Also, the dc magnetizing inductance current is zero. Thus, no extra demagnetizing circuit is required. Furthermore, only one LED string current is sensed and controlled. Finally, the operating principles, analyses and experimental results are offered to verify the effectiveness of the proposed four-channel LED driver.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"77 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":"114726648","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 Two-Stage Feature Extraction Gated Recurrent Unit for Wind Power Prediction","authors":"Jung-Bin Li, Yi-Zhu Huang","doi":"10.1109/IS3C50286.2020.00054","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00054","url":null,"abstract":"With the rise of environmental awareness, approaches of power generation other than traditional ones are receiving much attention. Therefore, renewable energy power generation and its integration with other power generators in a smart grid is becoming an important issue. In an environment with the nature of dynamic and real-time, data increases both in volume and variety. There are studies in literature using deep learning models to make data prediction, and many of them have good results. However, issues such as overcomplicated data dimension may occur when deep learning models are dealing with big data. This study proposes a model combining association analysis, sequence analysis, and Gated Recurrent Unit (GRU) to predict the amount of power generated by wind turbines in Taiwan. Our experiment shows that association rule analysis keeps computation efficiency and also improves model accuracy at the same time.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"61 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":"121696459","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 Posture Evaluation System for Fitness Videos based on Recurrent Neural Network","authors":"An-Lun Liu, W. Chu","doi":"10.1109/IS3C50286.2020.00055","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00055","url":null,"abstract":"We present a posture evaluation system especially for fitness. Given a fitness video where a user repetitively performs a movement for fitness, we first detect human posture at each video frame. The evolution of posture in consecutive frames is then characterized by a recurrent neural network (RNN). This RNN examines this movement and outputs the degree of goodness (badness). This examination is important for users because prompt inspection of bad movement avoids injury and improves effectiveness of fitness. We demonstrate that the proposed system can accurately detect bad postures when the users perform two movements called Dumbbell Lateral Raise and Biceps Curl. We believe this work is one of the very few studies of using deep neural networks for fitness evaluation.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"44 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":"122808905","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":"RoboRIO-based Crop Harvesting Robot","authors":"K. Hsia, Zengji Huang, Bo-Jun Yang, Jia-Ming Hsiao","doi":"10.1109/IS3C50286.2020.00122","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00122","url":null,"abstract":"Due to the change in life style and the gradual rise of health awareness, more and more people have given up their jobs, returned to the countryside, and bought or rented a small piece of land to live the life of small farmers. Therefore, small agricultural machinery will gradually have a place in the future market. In this paper, aiming at small and medium-sized farmers of cucumber planting, we have designed a prototype of a mobile robot for harvesting low-hanging crop like cucumbers. It is based on the NI roboRIO controller, and Mecanum-wheels are used as the moving wheel. After preliminary real-machine simulation, it was verified that the designed robot can meet the needs of assisting the harvesting of hanging crops.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"1 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120878143","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 Novel Single-Stage High-Power-Factor LED Power Supply with Soft-Switching Feature for Streetlight Applications","authors":"Chun‐An Cheng, Hung-Liang Cheng, Chien-Hsuan Chang, E. Chang, Wei-Shiang Hung, Long-Fu Lan","doi":"10.1109/IS3C50286.2020.00012","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00012","url":null,"abstract":"This paper presents a novel single-stage LED power supply with soft-switching feature suitable for streetlight applications. The proposed AC-DC LED power supply integrates an interleaved buck converter with coupled inductors and a half-bridge LLC resonant converter into a single-stage power-conversion circuit with reduced voltage stress on the DC-bus capacitor and power switches. Furthermore, coupled inductors in the interleaved buck converter are designed to be operated in discontinuous-conduction mode (DCM) for carrying on power-factor-correction, and the half-bridge LLC resonant converter features zero-voltage switching (ZVS) to reduce switching losses of power switches, and zero-current switching (ZCS) to decrease conduction losses of power diodes. A 144 W (36V14A)-rated LED prototype circuit is successfully developed and implemented for supplying an LED streetlight module and operating with a utility-line input voltage of 110 V. High power factor and satisfying efficiency are achieved in the proposed LED power supply for streetlight applications.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"43 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":"116437184","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":"Based on machine learning for personalized skin care products recommendation engine","authors":"Hsiao-Hui Li, Yuan-Hsun Liao, Yennun Huang, Po-Jen Cheng","doi":"10.1109/IS3C50286.2020.00125","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00125","url":null,"abstract":"With the economic development and the aging trend, the use of cosmetic products has expanded rapidly. In an ever-expanding skin care market, facial skin care product was the most popular product of skin care product. However, thousands of skin care products are available in the market. With endless options, shoppers are confronted confused and tired. Because everyone's skin condition is not the same, using unsuitable skin care products can damage the skin. Frequent problems with face skin are wrinkles, spots, acne vulgaris, pores, etc. The causes of facial lines, such as dryness, facial expressions, aging, etc., are cause different shades and different types of wrinkles. Therefore, it is very important to know your skin quality and use skin care products correctly. According to the application of different levels of image processing, it can be divided into image classification, positioning, object detection and object segmentation in the field of image vision. This paper will focus on the application of machine learning and deep learning algorithm development on human face and skin intelligence recommendation platform. That uses YOLOv4's novel object recognition algorithm to detect key features in face images, and intercept sub-images of regions of interest (ROI) as input information for multi-label models. Each sub-image detects the defective part through the YOLOv4 identifier of the second layer, and calculates the ratio of the pixel area of the local block to the main body to evaluate the correlation between feature parts and degree to establish a reference for the optimization of subsequent multi-label model. The skin condition classification uses the image processing algorithm to preprocess automatically remove, reduce noise, enhance, normalize and extract features to obtain the feature vectors of the sub-images for training the multi-label classification model. The prediction results of machine learning can provide suitable maintenance knowledge and product recommendations for users to recommend the suitable skin care products and maintenance ingredients for the user's skin condition.","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":"129529044","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":"Applied the Software of MATLAB to Calculate the Balanced Three-Phase Fault Using Impedance Matrix","authors":"Ming-Jong Lin","doi":"10.1109/IS3C50286.2020.00026","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00026","url":null,"abstract":"The key point of this article narrates the balanced three-phase fault occurs on a bus in power system that is been calculated from impedance matrix using MATLAB application software. Its purpose is to solve the problem of changing buses voltage and lines current. During the calculation, the impedance value of each device is only taken from the positive sequence impedance value. This paper is divided two parts - one for handwriting and other for computer program algorithm to narrate, the latter purpose is to facilitate the accuracy and effectiveness up so that avoid clerical errors caused by complicated steps of handwriting, it was been verified from practical cases. The manuscript algorithm and the execute steps of the computer program are simultaneously describe it in order to see the pros or cons. For clearly explain what these steps of calculation, these calculation steps of program were been shown on the bottom of paper. In order to promote interesting learning and shorten the time of calculation and design, this method has become a convenient and effective tool for the calculation of balanced failure in the field of power system.","PeriodicalId":143430,"journal":{"name":"2020 International Symposium on Computer, Consumer and Control (IS3C)","volume":"71 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":"131052395","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":"Applying ant algorithm to the automatic control system of freight load","authors":"Te-Kwei Wang, Yu-Hsun Lin, Chih-Hao Chuan, Jia-Ming Lin","doi":"10.1109/IS3C50286.2020.00072","DOIUrl":"https://doi.org/10.1109/IS3C50286.2020.00072","url":null,"abstract":"The purpose of the present is to develop an automatic control system of freight load, thereby not only reducing transportation costs but also improving the delivery ability of schedulers. Ant algorithm was employed to perform the optimal calculation of vehicle route to lever a higher load capacity of each truck and meet the requirement of the operator. While optimizing the route, the application of the ant algorithm needs to balance the vehicle capacity of each route. The proposed system has been realized and validated the system performance of vehicle dispatch that can reduce the logistics cost. In conclusion, the realized system by ant algorithm can meet the operator's requirements.","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":"130772381","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}