Pub Date : 2022-10-14DOI: 10.1109/IET-ICETA56553.2022.9971643
Chenghua Fan, Chih-Yung Chang, Chun-Chieh Fan
This research develops a cheap and multi-functional environment sensing and APP display system. The sensing end of this system is composed of CO2 sensor, PM2.5 sensor, GPS module, memory module, microprocessor, Bluetooth,,,,,etc.. The sensed information can be stored in the memory module, and then use computer and mobile phone to observe the curve of data changes, and proceed further analyze, discuss, and decision-making. This research mainly writes a mobile APP program, uses Bluetooth to control the sensor memory module data, and then displays them on the mobile phone. The values sensed by various sensors can be observed from the mobile phone screen, and the changing curve can be present. In addition, it can also display the sensing time and location of a sensing value in map mode, so that the complete sensing data information can be clearly understood from the mobile phone.
{"title":"An Environmental Sensing and APP Display System Based on IoT","authors":"Chenghua Fan, Chih-Yung Chang, Chun-Chieh Fan","doi":"10.1109/IET-ICETA56553.2022.9971643","DOIUrl":"https://doi.org/10.1109/IET-ICETA56553.2022.9971643","url":null,"abstract":"This research develops a cheap and multi-functional environment sensing and APP display system. The sensing end of this system is composed of CO2 sensor, PM2.5 sensor, GPS module, memory module, microprocessor, Bluetooth,,,,,etc.. The sensed information can be stored in the memory module, and then use computer and mobile phone to observe the curve of data changes, and proceed further analyze, discuss, and decision-making. This research mainly writes a mobile APP program, uses Bluetooth to control the sensor memory module data, and then displays them on the mobile phone. The values sensed by various sensors can be observed from the mobile phone screen, and the changing curve can be present. In addition, it can also display the sensing time and location of a sensing value in map mode, so that the complete sensing data information can be clearly understood from the mobile phone.","PeriodicalId":46240,"journal":{"name":"IET Networks","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89937002","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}
Pub Date : 2022-10-14DOI: 10.1109/IET-ICETA56553.2022.9971602
Winggun Wong, Meng-Yuan Tsai, Hung-Kuei Chang
This study is based on the Kubeflow machine learning development platform in order to deploy a real-time roll call system. Kubeflow is based on Kubernetes, which is convenient for container management and portability. Face recognition is done in three steps. First, MTCNN detects a face in the image. Then, FaceNet extracts the features from the face. Finally, SVM finds out the identity of the face closest to the detected face. The average accuracy of the 30 classes in this study is approximately 94.2%, and the execution speed is about 35fps, with Intel Core i7-10700 CPU and NVIDIA GeForce RTX 3060 GPU.
{"title":"Designing a Roll Call System with Facial Recognition on Kubeflow","authors":"Winggun Wong, Meng-Yuan Tsai, Hung-Kuei Chang","doi":"10.1109/IET-ICETA56553.2022.9971602","DOIUrl":"https://doi.org/10.1109/IET-ICETA56553.2022.9971602","url":null,"abstract":"This study is based on the Kubeflow machine learning development platform in order to deploy a real-time roll call system. Kubeflow is based on Kubernetes, which is convenient for container management and portability. Face recognition is done in three steps. First, MTCNN detects a face in the image. Then, FaceNet extracts the features from the face. Finally, SVM finds out the identity of the face closest to the detected face. The average accuracy of the 30 classes in this study is approximately 94.2%, and the execution speed is about 35fps, with Intel Core i7-10700 CPU and NVIDIA GeForce RTX 3060 GPU.","PeriodicalId":46240,"journal":{"name":"IET Networks","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90193966","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}
Pub Date : 2022-10-14DOI: 10.1109/IET-ICETA56553.2022.9971498
Li Wang, Zhi-Hong Huang, Jui-Tse Lai, Ruibin Wu, Ching-Chuan Tseng
This paper designs an adaptive fuzzy logic controller (AFLC)for power management of a hybrid energy-storage system (HESS) containing a vanadium redox flow battery (VRFB) and a supercapacitor (SC). The studied hybrid wind-PV microgrid (MG) is connected to the IEEE 14-bus multimachine system using optimal designed capacity of the proposed HESS. The main research includes the design of an AFLC for the HESS and the design of the optimal capacity for the HESS. A probability approach is used to determine the rated power and capacity of the HESS, while an AFLC for power distribution of the HESS is designed to effectively utilize individual ESS’s characteristics. Different cases of the studied system are analyzed to investigate the effects of the selected capacity joined with the designed AFLC on smoothing power for the studied system.
{"title":"Power Smooth of a Hybrid PV-Wind Microgrid Using a Hybrid Energy-storage System with a Designed Adaptive Fuzzy Logic Controller","authors":"Li Wang, Zhi-Hong Huang, Jui-Tse Lai, Ruibin Wu, Ching-Chuan Tseng","doi":"10.1109/IET-ICETA56553.2022.9971498","DOIUrl":"https://doi.org/10.1109/IET-ICETA56553.2022.9971498","url":null,"abstract":"This paper designs an adaptive fuzzy logic controller (AFLC)for power management of a hybrid energy-storage system (HESS) containing a vanadium redox flow battery (VRFB) and a supercapacitor (SC). The studied hybrid wind-PV microgrid (MG) is connected to the IEEE 14-bus multimachine system using optimal designed capacity of the proposed HESS. The main research includes the design of an AFLC for the HESS and the design of the optimal capacity for the HESS. A probability approach is used to determine the rated power and capacity of the HESS, while an AFLC for power distribution of the HESS is designed to effectively utilize individual ESS’s characteristics. Different cases of the studied system are analyzed to investigate the effects of the selected capacity joined with the designed AFLC on smoothing power for the studied system.","PeriodicalId":46240,"journal":{"name":"IET Networks","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76504891","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}
Pub Date : 2022-10-14DOI: 10.1109/IET-ICETA56553.2022.9971583
Ming Han Tsai, Jen-Yeu Chen, Wei-Che Chien
In the past, the process of transferring data collected by IoT devices or mobile devices has data leakage, personal privacy, and information security issues since object detection systems have mostly sent data to the cloud for processing and storage. To solve this problem, we implement object recognition and tracking function in JavaScript on the front end, and set up the CRUD operation API in Python on the back end, so that users can directly perform object recognition on the computer or mobile browser, and manage the database on the web through the API. It enables the process from deployment to data transfer in a very short time.
{"title":"Mobile Edge Computing for Rapid deployment Object Detection System","authors":"Ming Han Tsai, Jen-Yeu Chen, Wei-Che Chien","doi":"10.1109/IET-ICETA56553.2022.9971583","DOIUrl":"https://doi.org/10.1109/IET-ICETA56553.2022.9971583","url":null,"abstract":"In the past, the process of transferring data collected by IoT devices or mobile devices has data leakage, personal privacy, and information security issues since object detection systems have mostly sent data to the cloud for processing and storage. To solve this problem, we implement object recognition and tracking function in JavaScript on the front end, and set up the CRUD operation API in Python on the back end, so that users can directly perform object recognition on the computer or mobile browser, and manage the database on the web through the API. It enables the process from deployment to data transfer in a very short time.","PeriodicalId":46240,"journal":{"name":"IET Networks","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76597577","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}
To deal with the problems in the nonlinear system, the kernel adaptive filter (KAF) was proposed by processing data in the reproducing kernel Hilbert space (RKHS). However, the kernel method dramatically improves the amount of calculation of the filter, which limits its application in practical problems. Furthermore, a critical factor in a large amount of KAF computation is due to its slow convergence speed, which requires a large amount of training data to participate in the calculation. If we can accelerate the convergence speed of KAF, the amount of training data can be reduced, thereby reducing the amount of KAF computation. This paper proposes a fast kernel least mean square algorithm (FAST-KLMS) by adaptively updating step size to address this issue. To verify the superiority of FAST-KLMS, we have applied it to the simulations of nonlinear channel equalization. The simulation results show that FAST-KLMS needs less training data to complete the convergence, which has improved the filtering performance of KAF.
{"title":"A Fast Kernel Least Mean Square Algorithm","authors":"Yijie Tang, Hailong Yan, Jialong Tang, Ying-Ren Chien","doi":"10.1109/IET-ICETA56553.2022.9971688","DOIUrl":"https://doi.org/10.1109/IET-ICETA56553.2022.9971688","url":null,"abstract":"To deal with the problems in the nonlinear system, the kernel adaptive filter (KAF) was proposed by processing data in the reproducing kernel Hilbert space (RKHS). However, the kernel method dramatically improves the amount of calculation of the filter, which limits its application in practical problems. Furthermore, a critical factor in a large amount of KAF computation is due to its slow convergence speed, which requires a large amount of training data to participate in the calculation. If we can accelerate the convergence speed of KAF, the amount of training data can be reduced, thereby reducing the amount of KAF computation. This paper proposes a fast kernel least mean square algorithm (FAST-KLMS) by adaptively updating step size to address this issue. To verify the superiority of FAST-KLMS, we have applied it to the simulations of nonlinear channel equalization. The simulation results show that FAST-KLMS needs less training data to complete the convergence, which has improved the filtering performance of KAF.","PeriodicalId":46240,"journal":{"name":"IET Networks","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79087442","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}
Pub Date : 2022-10-14DOI: 10.1109/IET-ICETA56553.2022.9971646
Hsin-Liang Chen, Yin-Qin Ye, Jen-Shiun Chiang
A magnitude to digital converter is proposed using a latch-type comparator to replace the conventional opamp-based comparator. The PVT-dependent timing error can be relieved by employing the latch-type comparator and rearranging the decision control circuits. Besides, the power efficiency can be improved within the low and high speed operations. For increasing the linearity of the converting process, a dynamic current source is also developed to obtain the best coefficient of determination. A prototype of 10-bit converter was designed to operate at 40-kS/s with only 56.S-$mu$W of power dissipations, respectively.
{"title":"Magnitude to Digital Converter with Latch-Type Comparator and Dynamic Switching Current Scheme","authors":"Hsin-Liang Chen, Yin-Qin Ye, Jen-Shiun Chiang","doi":"10.1109/IET-ICETA56553.2022.9971646","DOIUrl":"https://doi.org/10.1109/IET-ICETA56553.2022.9971646","url":null,"abstract":"A magnitude to digital converter is proposed using a latch-type comparator to replace the conventional opamp-based comparator. The PVT-dependent timing error can be relieved by employing the latch-type comparator and rearranging the decision control circuits. Besides, the power efficiency can be improved within the low and high speed operations. For increasing the linearity of the converting process, a dynamic current source is also developed to obtain the best coefficient of determination. A prototype of 10-bit converter was designed to operate at 40-kS/s with only 56.S-$mu$W of power dissipations, respectively.","PeriodicalId":46240,"journal":{"name":"IET Networks","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76659624","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}
Pub Date : 2022-10-14DOI: 10.1109/IET-ICETA56553.2022.9971597
Kuan-Hung Liu, Ming-Fei Chen
Using the Open CASCADE source to develop a robotic arm simulation grinding path for the metal parts is the purpose of this research. Firstly, a metal parts CAD/CAM grinding script file is created and translated into a special format for driving the presented robot arm. Then the geometric dimensions of the robotic arm and the belt sander in the program are built. Secondly, the forward kinematics and inverse kinematics models of the robotic arm are imported. Finally, the simulation and testing of the metal parts grinding path by combining the above translation program are achieved. Compared with the traditional manual teaching and correction of robotic arm path planning, the grinding efficiency can be improved in this study.
{"title":"Research and development of robot arm applied to grinding path planning of metal parts","authors":"Kuan-Hung Liu, Ming-Fei Chen","doi":"10.1109/IET-ICETA56553.2022.9971597","DOIUrl":"https://doi.org/10.1109/IET-ICETA56553.2022.9971597","url":null,"abstract":"Using the Open CASCADE source to develop a robotic arm simulation grinding path for the metal parts is the purpose of this research. Firstly, a metal parts CAD/CAM grinding script file is created and translated into a special format for driving the presented robot arm. Then the geometric dimensions of the robotic arm and the belt sander in the program are built. Secondly, the forward kinematics and inverse kinematics models of the robotic arm are imported. Finally, the simulation and testing of the metal parts grinding path by combining the above translation program are achieved. Compared with the traditional manual teaching and correction of robotic arm path planning, the grinding efficiency can be improved in this study.","PeriodicalId":46240,"journal":{"name":"IET Networks","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76921273","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}
Pub Date : 2022-10-14DOI: 10.1109/IET-ICETA56553.2022.9971631
Xin-Yu Shih, Yao Lu
In this paper, we propose a systematic genetic-algorithm-based feature reduction method. It has a high design flexibility based on 5-tuple parameter adjustment. The users can decide these 5 parameters to satisfy the demands of making the focus on accuracy or reduced feature amount. The proposed algorithm is verified by decision-tree models with different data sets. As for the data set, ala, the number of features is reduced from 123 to 53 while the accuracy performance has an increase of 4.2%. In addition, for other data sets, the maximum accuracy loss is no more than 3.1% while the feature reduction ratio achieves 41.9%. Its advantage is to provide a design trade-off between accuracy and reduced feature amount.
{"title":"Systematic and Flexible Genetic-Algorithm-Based Feature Reduction for Decision Tree ML-Validation","authors":"Xin-Yu Shih, Yao Lu","doi":"10.1109/IET-ICETA56553.2022.9971631","DOIUrl":"https://doi.org/10.1109/IET-ICETA56553.2022.9971631","url":null,"abstract":"In this paper, we propose a systematic genetic-algorithm-based feature reduction method. It has a high design flexibility based on 5-tuple parameter adjustment. The users can decide these 5 parameters to satisfy the demands of making the focus on accuracy or reduced feature amount. The proposed algorithm is verified by decision-tree models with different data sets. As for the data set, ala, the number of features is reduced from 123 to 53 while the accuracy performance has an increase of 4.2%. In addition, for other data sets, the maximum accuracy loss is no more than 3.1% while the feature reduction ratio achieves 41.9%. Its advantage is to provide a design trade-off between accuracy and reduced feature amount.","PeriodicalId":46240,"journal":{"name":"IET Networks","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72614434","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}
Pub Date : 2022-10-14DOI: 10.1109/IET-ICETA56553.2022.9971648
Yen-Chung Chiang, Tai-Chung Wang
A low-noise amplifier (LNA) with three commonsource stages designed in a 90-nm CMOS process technology for V-band applications is proposed in this conference paper. By using the coupling effect between the gate biasing inductor and source degenerative inductor, we can boost the gain and reduce the noise figure. The proposed LNA achieved a peak measured gain of 11.14 dB at 67 GHz. The measured lowest noise Figure (NF) is 4.99 dB at 67 GHz. The proposed circuit draws a 17.64 mW dc-power from a 1.2-V supply.
{"title":"A V-band Low Noise Amplifier in 90-nm CMOS by Inductive Coupling Technique","authors":"Yen-Chung Chiang, Tai-Chung Wang","doi":"10.1109/IET-ICETA56553.2022.9971648","DOIUrl":"https://doi.org/10.1109/IET-ICETA56553.2022.9971648","url":null,"abstract":"A low-noise amplifier (LNA) with three commonsource stages designed in a 90-nm CMOS process technology for V-band applications is proposed in this conference paper. By using the coupling effect between the gate biasing inductor and source degenerative inductor, we can boost the gain and reduce the noise figure. The proposed LNA achieved a peak measured gain of 11.14 dB at 67 GHz. The measured lowest noise Figure (NF) is 4.99 dB at 67 GHz. The proposed circuit draws a 17.64 mW dc-power from a 1.2-V supply.","PeriodicalId":46240,"journal":{"name":"IET Networks","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72368533","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}
Pub Date : 2022-10-14DOI: 10.1109/IET-ICETA56553.2022.9971676
Mu-Yen Chen, Hsiu-Sen Chiang, Chih-Yung Chang
In recent years, renewable energy power generation has received more and more attention. Since the forecast of electricity generation is helpful for properly using and managing electricity. Therefore, this study uses time series analysis and deep learning methods, Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), and Gated Recurrent Unit (GRU), to forecast solar power generation. Furthermore, this study also uses different time intervals (every ten minutes, every thirty minutes, hourly, daily) to forecast the power generation and evaluate their performances. In comparing the four deep learning models, the prediction performance of LSTM is the best, while the performance of the TCN model is poor. In addition, the time interval length greatly influences the prediction performance. The time interval is divided into smaller, and the performance of various deep learning models is relatively good and stable; otherwise, the performance of the models is poor.
{"title":"Solar Photovoltaic Power Generation Prediction based on Deep Learning Methods","authors":"Mu-Yen Chen, Hsiu-Sen Chiang, Chih-Yung Chang","doi":"10.1109/IET-ICETA56553.2022.9971676","DOIUrl":"https://doi.org/10.1109/IET-ICETA56553.2022.9971676","url":null,"abstract":"In recent years, renewable energy power generation has received more and more attention. Since the forecast of electricity generation is helpful for properly using and managing electricity. Therefore, this study uses time series analysis and deep learning methods, Long Short-Term Memory (LSTM), Temporal Convolutional Network (TCN), and Gated Recurrent Unit (GRU), to forecast solar power generation. Furthermore, this study also uses different time intervals (every ten minutes, every thirty minutes, hourly, daily) to forecast the power generation and evaluate their performances. In comparing the four deep learning models, the prediction performance of LSTM is the best, while the performance of the TCN model is poor. In addition, the time interval length greatly influences the prediction performance. The time interval is divided into smaller, and the performance of various deep learning models is relatively good and stable; otherwise, the performance of the models is poor.","PeriodicalId":46240,"journal":{"name":"IET Networks","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72703858","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：