{"title":"Microcontroller-Based Intelligent Control for Reaction Wheel Pendulums Using a Fuzzy Broad-Learning System","authors":"Bo-Rui Chen, Chun-Fei Hsu, Bing-Fei Wu","doi":"10.1109/iFUZZY55320.2022.9985220","DOIUrl":"https://doi.org/10.1109/iFUZZY55320.2022.9985220","url":null,"abstract":"This study presents an adaptive fuzzy broad-learning neural control (AFBNC) system applied to a reaction wheel pendulum without knowing its dynamic model. The AFBNC system uses a fuzzy broad-learning system (FBLS) to approximate an ideal controller online with keeping the reaction wheel pendulum balance. Moreover, the gradient descent method and chain rule are applied to online adjust all parameters of the FBLS with keeping the closed-loop control system stable. Finally, to implement the control algorithms and conduct experiments, a prototype of the reaction wheel pendulum is designed using a low-cost microcontroller. The experimental results demonstrate the effectiveness of the proposed AFBNC system using low-cost hardware.","PeriodicalId":233153,"journal":{"name":"2022 International Conference on Fuzzy Theory and Its Applications (iFUZZY)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116272284","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":"Brain-Computer Interface for Multi-Parameter Mental State Evaluation","authors":"Congying He, Yang Chang, L. Ko","doi":"10.1109/iFUZZY55320.2022.9985229","DOIUrl":"https://doi.org/10.1109/iFUZZY55320.2022.9985229","url":null,"abstract":"With the increasing development of wireless devices in the field of Brain-Computer Interface (BCI), it is very important to evaluate the mental state of users using BCI products in daily life. There have been many studies on mental states in the past, such as studies related to concentration, fatigue, or stress, but most of them are studies of a single mental state. We proposed a multi-mental state indicator based on EEG signals which can real-time reflect the subject's mental states, including fatigue, attention, stress, and the left and right brain activity changes. For validating the effectiveness of the proposed evaluation system, we also designed a complex mixed-object search experiment. Results showed that attention levels while performing the objective searching task were significantly higher than during rest periods. Contrast, the fatigue level while rest periods gradually increased and steady by the third rest period. Stress levels, similar to attention levels, decreased as the experiment progressed. The proposed indicator is applicable to potential BCI applications for evaluating the subject's mental state change in real-time.","PeriodicalId":233153,"journal":{"name":"2022 International Conference on Fuzzy Theory and Its Applications (iFUZZY)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125342451","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":"Interactive Drone Control with Gesture and Posture on the Edge Computing Platform","authors":"Pei-Shan Hsiao, Ping Cheng, Yan-Sheng Huang, Cheng-Ta Chuang","doi":"10.1109/iFUZZY55320.2022.9985230","DOIUrl":"https://doi.org/10.1109/iFUZZY55320.2022.9985230","url":null,"abstract":"This paper designs a system that combines sensor and multiple neural network models to achieve the function of interactive drones, such as user tracking, gesture and posture control of the drone, and emergency safety protection. To run on the edge computing platform, Jetson Nano, and control the drone, the neural network models such as object detection, face recognition, and gesture recognition were optimized. The drone could be controlled by the user's gestures and postures successfully.","PeriodicalId":233153,"journal":{"name":"2022 International Conference on Fuzzy Theory and Its Applications (iFUZZY)","volume":"506 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123416724","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}
Yi-You Hou, Kuang-Sheng Liu, J. Lin, Ming-Hung Lin, Lou-Yang Tin
{"title":"Evaluation of Critical Factors in Urban Matrix Environment from the Perspective of Ecological Design","authors":"Yi-You Hou, Kuang-Sheng Liu, J. Lin, Ming-Hung Lin, Lou-Yang Tin","doi":"10.1109/iFUZZY55320.2022.9985223","DOIUrl":"https://doi.org/10.1109/iFUZZY55320.2022.9985223","url":null,"abstract":"The ecological environment of human-centered habitats, cities, is gradually emphasized that the idea of sustainable development is proposed to stress on the integration of development and conservation. Besides, under current resource-applied environment, long-term management of resources is planned and used for preventing resources from shortage. Current development of urban central areas is about saturated, and the rapid expansion of urban fringe is about out of control. Effective recovery of urban landscape ecological structure and function as well as retention, restoration, and regeneration of urban natural environment to balance urban ecosystem and natural ecosystem are primary issues to improve urban environmental quality. Aiming at residents in Kaohsiung City, as the questionnaire objects, 360 copies of questionnaire are distributed as the research samples, and 294 valid copies are retrieved, with the retrieval rate 82%. The research results show 1.natural ecology as the most emphasized dimension in the evaluation of urban matrix environment from the perspective of ecological design, and 2.top five mostly emphasized indicators, among 20, are green coverage ratio, provision of learning opportunities, diversity of plant species, recoverable materials, and participation ways. According to the results to propose the conclusion. It is expected to dig out specific opportunities for the sustainable use and development of urban matrix and to develop a complete and systematic landscape ecological network, with the combination with other landscape elements, to promote urban ecological quality.","PeriodicalId":233153,"journal":{"name":"2022 International Conference on Fuzzy Theory and Its Applications (iFUZZY)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122891809","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}
Wei-Tai Huang, Po-Hsun Shih, Yi-Cheng Lin, Jinn-Tsong Tsai, J. Chou
{"title":"Research on the Prediction Model of Milling Force and Temperature for High-Speed Milling of NAK80 Die Steel by Ultrasonic Atomization Micro-Lubrication Combined With Uniform Method and Back Propagation Neural Network","authors":"Wei-Tai Huang, Po-Hsun Shih, Yi-Cheng Lin, Jinn-Tsong Tsai, J. Chou","doi":"10.1109/iFUZZY55320.2022.9985233","DOIUrl":"https://doi.org/10.1109/iFUZZY55320.2022.9985233","url":null,"abstract":"In this study, the high-speed milling of NAK80 die steel was carried out using the nanofluid (graphene) ultrasonic atomization micro-lubrication system combined with the uniform method and back propagation neural network. This study investigates the effects of rotational speed, feed, and nano-concentration on milling force and temperature and uses back propagation neural network (BPNN) to build an accurate prediction model. The uniform experimental design was first adopted. Utilizing the uniform dispersion feature reduces the time cost by using a smaller number of experimental groups. Use form $mathrm{U}_{9}(9^{3})$ to design experiments and collect empirical data. Control factors include spindle speed, feed rate, and nanofluid concentration. Then, BPNN is used to establish the prediction model of milling force and temperature in high-speed milling process. To improve the prediction accuracy, the experiments will compare the effect of different hyperparameter settings on the accuracy of the BPNN model. Controlling and comparing hyperparameters includes using four other training functions: Levenberg-Marquardt, Trainglm, Traingda, Trainrp, and Trainscg, comparing the configuration of 5 and 10 neurons with different numbers of neurons to compare the accuracy and error value of the prediction model. The experimental results of the established model show that using the original nine sets of experimental data, the optimal hyperparameter settings of the milling force and milling temperature model are set to use Trainlm, the number of neurons is 10, and the MAPE value is 1.68%. To confirm the accuracy of the model, three different sets of experimental data were used and were not verified in the original parameter combination experiment. This verification part of the pre-model measured the best hyperparameters of the milling force and milling temperature model to use Trainlm. The number of neurons was 10, and the MAPE value was 4.45%. The results of this study show that a predictive model with high accuracy can be constructed using less experimental data, which can provide the industry with the ability to evaluate and adjust process parameters promptly to improve production efficiency when conducting related processes.","PeriodicalId":233153,"journal":{"name":"2022 International Conference on Fuzzy Theory and Its Applications (iFUZZY)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132587250","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":"Methodology details of signal processing to survey the electroencephalography dynamics during continuous performance for preschoolers with ADHD","authors":"R. Lin, I. Chen, L. Ko","doi":"10.1109/iFUZZY55320.2022.9985232","DOIUrl":"https://doi.org/10.1109/iFUZZY55320.2022.9985232","url":null,"abstract":"ADHD, the common neurodevelopmental disorder affecting children, is reported with a prevalence of 2.1% to 5.7% among preschool-aged children. To assist the early diagnosis, clinicians usually refer to the instrument, Conner's kiddie continuous performance test; however, the test lacks the event markers of the task stimuli, which are essential information for task-related EEG study. We conducted artifact removal, extracted, separated, and allocated the recorded raw EEG signals into resting, fast-rate task, and slow-rate task segments to investigate the dynamic changes between groups with ADHD and controls. The slow-rate task related band power and alpha power alterations within conditions were distinct between groups. The methodology in our study is practical for EEG data analysis regarding different task conditions.","PeriodicalId":233153,"journal":{"name":"2022 International Conference on Fuzzy Theory and Its Applications (iFUZZY)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125065569","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":"Developing Motion Editor for 3D Printed Humanoid Robot by VTK and Python","authors":"Cheng-Tiao Hsieh","doi":"10.1109/iFUZZY55320.2022.9985225","DOIUrl":"https://doi.org/10.1109/iFUZZY55320.2022.9985225","url":null,"abstract":"For satisfying the needs of Industry 4.0, STEM education gradually becomes important. The STEM education provides courses to educate students in four disciplines, i.e. science, technology, engineering, and mathematics. In addition, transforming current industry to a modern industry needs the support from a group of professional people who are familiar with the core technologies of ID 4.0, such as virtual and real Integration systems, cloud computing, Internet of Things (IoT), and artificial intelligence(AI). Programming is the key to make the above industrial revolution success. Thus, our previous project developed a low cost humanoid robot as a learning tool applied in STEM programs. With the assistance of the humanoid robot, young students can learn programming courses easily and efficiently. Currently, STEM education is often applied in elementary, junior-high and senior-high schools. It really improves students' learning circumstance in STEM fields. This paper introduced the STEAM education model to create a good learning circumstance for art students. Digital teaching aids, such as humanoid robot, and quadruped mechanical animal, support students to learn STEM programs more intuitively. Those aids can help students to learn mechanical mechanisms, electronic motors, digital control and programming and so on. These teaching aids are all open source, and they can be printed by 3D printers. Students can learn mechanics, electronics, and programming via the course. In order to enable students to use the humanoid robot digital teaching aids more effectively and completely, a humanoid robot motion editor is developed. This editor was developed by python and VTK, and it also has a friendly window-based interface. Its main task is to provide students to edit the motion of the robots quickly and easily. Through this editor, students can learn more about multi-foot and humanoid robot motions.","PeriodicalId":233153,"journal":{"name":"2022 International Conference on Fuzzy Theory and Its Applications (iFUZZY)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123816044","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":"Sugar Beets and Weed Detection using Semantic Segmentation","authors":"Xin-Zhi Hu, Wang-Su Jeon, Sangyong Rhee","doi":"10.1109/iFUZZY55320.2022.9985222","DOIUrl":"https://doi.org/10.1109/iFUZZY55320.2022.9985222","url":null,"abstract":"Weeds have a big impact on beet growth. As a result, there is a growing public interest in weed detection and identification during crop growth. This paper describes a UNet++ method with deep supervision for detecting weeds in sugar beet fields trained on the dataset. The UNet++ architecture is an encoder-decoder network that closes the semantic gap between the feature maps of the encoder and decoder sub-networks through redesigned skip paths. When the feature maps of the encoder and decoder networks are semantically similar, the optimizer will handle the learning task more easily. We evaluate the comparison of UNet, UNet++, and UNet++ with deep supervision architectures on the dataset segmentation task. Experiments show that the mIoU values on UNet, UNet++ and UNet++ with deep supervision are about 90.81%, 92.00% and 92.34%. It turns out that UNet++ with deep supervision can detect the location of weeds more effectively.","PeriodicalId":233153,"journal":{"name":"2022 International Conference on Fuzzy Theory and Its Applications (iFUZZY)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129317314","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":"Evaluating Penghu Bus Timetable Performance of Flight Passenger Transit Service during Moon Consecutive Festival with Fuzzy Multi Objectives Model","authors":"S. L. Li","doi":"10.1109/iFUZZY55320.2022.9985231","DOIUrl":"https://doi.org/10.1109/iFUZZY55320.2022.9985231","url":null,"abstract":"This paper proposes fuzzy multi-objectives models, in order to evaluate the bus timetable service performance of the flight passenger transit airport. This model can evaluate bus serve level of airport arriving/departing time point which is based on the advantageous necessary enough transit time of flight-bus-relationship and given flight demand each time point during the consecutive holidays. This fuzzy multi-objectives model can be a best tool to measure standardized scores merits of different objective function, which can integrate and evaluate bus timetable performance both the waiting time of arrival/departure flight passenger and served arrival/departure flight passenger number. Meanwhile, by the regulated schedule parameters of passenger departure/arrival procedure to design the flight passenger how long time to arrival/departure airport and discuss the passengers' acceptable connection time between the flight timetable and optimal/ current bus timetable. The outcome shows the membership function difference of transit serving performance and degree between bus and flight during one week. The outcomes also suggest the current bus timetable to revise time-point to enhance the transit service during consecutive holidays and decrease carbon emissions.","PeriodicalId":233153,"journal":{"name":"2022 International Conference on Fuzzy Theory and Its Applications (iFUZZY)","volume":"195 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131184364","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}
Jin Yong Kim, Eunkyeong Kim, Minseok Kim, Sungshin Kim
{"title":"Analysis of the Influence of Meteorological Factor on Solar Irradiation Using DNN based Solar Irradiation Prediction","authors":"Jin Yong Kim, Eunkyeong Kim, Minseok Kim, Sungshin Kim","doi":"10.1109/iFUZZY55320.2022.9985234","DOIUrl":"https://doi.org/10.1109/iFUZZY55320.2022.9985234","url":null,"abstract":"Photovoltaic power generation has a problem in that the operation of the electrical power system is unstable due to output variability caused by weather changes. To resolve the instability of the electrical power system, it is necessary to predict the amount of photovoltaic power generation. Since photovoltaic power generation is a power generation technology that converts sunlight into electricity, solar irradiation is mainly used to predict the amount of photovoltaic power generation. And meteorological factors that affect solar irradiation are used incidentally. However, it is difficult to determine which meteorological factors influence solar irradiation and to what extent. Therefore, this paper proposes a method to analyze the influence of meteorological factor on solar irradiation using DNN based solar irradiation prediction. Experimental results, it was confirmed that 5 cm underground temperature, ground temperature, cloud cover, temperature, sunshine duration, and humidity showed high influence on solar irradiation in order.","PeriodicalId":233153,"journal":{"name":"2022 International Conference on Fuzzy Theory and Its Applications (iFUZZY)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124264274","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}