Pub Date : 2022-10-28DOI: 10.1109/ECICE55674.2022.10042913
Liqing Yang, Qicheng Wang, Tianyu Wang, Xintong Ma
The research aim of this paper is to evaluate the digital competence of international Chinese teachers.In order to accurately and objectively evaluate the international Chinese teachers’ digital competence standards, we used methods of data mining.The research procedure included the establishment of indicators of teachers’ digital competence and the construction of models.We chose the European Teachers’ Digital Competence Framework which includes 22 research indicators as the index dimension and used a developed convolutional neural network, k clustering and the fuzzy clustering algorithm. We created an evaluation model as a result. The results of several tests show that the model is stable and plausible. The model can be used to analyze the trend and distribution of digital ability among international Chinese teachers, as well as to evaluate international Chinese teachers’ s digital ability. The innovation of the result is the creation of a theoretical evaluation model to evaluate teachers’ digital ability.
{"title":"Study on Evaluation Model of International Chinese Teachers’ Digital Competence in Online Teaching Based on K-Means Clustering Algorithm","authors":"Liqing Yang, Qicheng Wang, Tianyu Wang, Xintong Ma","doi":"10.1109/ECICE55674.2022.10042913","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042913","url":null,"abstract":"The research aim of this paper is to evaluate the digital competence of international Chinese teachers.In order to accurately and objectively evaluate the international Chinese teachers’ digital competence standards, we used methods of data mining.The research procedure included the establishment of indicators of teachers’ digital competence and the construction of models.We chose the European Teachers’ Digital Competence Framework which includes 22 research indicators as the index dimension and used a developed convolutional neural network, k clustering and the fuzzy clustering algorithm. We created an evaluation model as a result. The results of several tests show that the model is stable and plausible. The model can be used to analyze the trend and distribution of digital ability among international Chinese teachers, as well as to evaluate international Chinese teachers’ s digital ability. The innovation of the result is the creation of a theoretical evaluation model to evaluate teachers’ digital ability.","PeriodicalId":282635,"journal":{"name":"2022 IEEE 4th Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133957695","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 : 2022-10-28DOI: 10.1109/ECICE55674.2022.10042892
Xing-Chen Mai, Xiu-Yuan Yang, Shen-Li Chen, Ting-En Lin, Yu-Jie Chung
A TSMC $0.18- mu mathrm{m}50 -mathrm{V}$ process is used to realize high-voltage nLDMOS devices. The floating-poly (poly-2) shows a spiral shape in the layout diagram. Commonly, the electric field in an nLDMOS decreases if the area is occupied by the poly-2 increases. However, the method used in this study is to increase or decrease the number of turns with the same occupied area of poly-2. Therefore, we studied whether the electric field rises or falls depending on the number of turns or the area occupied without changing the area occupied by poly-2. The reference device had the poly-2 with seven turns, and the other groups had 9 turns or 3 and 5 turns. Eventually, the highest electric field of the 9-turn device was 2.76 x 108 (V/cm), and its occupied area is the most dispersed distribution. For the 3 circles device is the most concentrated, the lowest electric field is 3.39 x 106 (v/cm). If the occupied area remains unchanged, the electric field is greatly reduced with the concentrated poly-2.
{"title":"Study of Turns Impact on ESD-immunity of High-voltage nLDMOSs with a Constant Floating-poly","authors":"Xing-Chen Mai, Xiu-Yuan Yang, Shen-Li Chen, Ting-En Lin, Yu-Jie Chung","doi":"10.1109/ECICE55674.2022.10042892","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042892","url":null,"abstract":"A TSMC $0.18- mu mathrm{m}50 -mathrm{V}$ process is used to realize high-voltage nLDMOS devices. The floating-poly (poly-2) shows a spiral shape in the layout diagram. Commonly, the electric field in an nLDMOS decreases if the area is occupied by the poly-2 increases. However, the method used in this study is to increase or decrease the number of turns with the same occupied area of poly-2. Therefore, we studied whether the electric field rises or falls depending on the number of turns or the area occupied without changing the area occupied by poly-2. The reference device had the poly-2 with seven turns, and the other groups had 9 turns or 3 and 5 turns. Eventually, the highest electric field of the 9-turn device was 2.76 x 108 (V/cm), and its occupied area is the most dispersed distribution. For the 3 circles device is the most concentrated, the lowest electric field is 3.39 x 106 (v/cm). If the occupied area remains unchanged, the electric field is greatly reduced with the concentrated poly-2.","PeriodicalId":282635,"journal":{"name":"2022 IEEE 4th Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134237387","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 : 2022-10-28DOI: 10.1109/ECICE55674.2022.10042899
Yu-An Shao, C. Chao
The Internet of Things (IoT) is indispensable to modern society. It has entered the mainstream trend recently owing to its ability to read data and connect systems. IoT network platforms comprise various applications, leading to an influx of heavy and varying network traffic, allowing hackers to launch large-scale network attacks easily. When hackers gain control of an IoT device, they can initiate large-scale botnet attacks even through nonconventional computing devices such as cameras and routers. For example, Dyn, a domain name system provider, experienced large-scale distributed denial-of-service attacks on its IoT devices in 2016, causing companies, such as Twitter and Amazon, to suffer the consequences. Therefore, adapting to large-scale changes in network traffic in real-time is imperative. Firewalls are the foundation of device security. Therefore, when large-scale changes in network traffic occur, it is necessary to ensure the effectiveness of firewalls to reduce the probability of successful attacks. This study proposes a system that can adjust the order of firewall rules in real-time to monitor the traffic in high-speed IoT networks. When the system detects a sudden increase in the number of packets, the firewall rules are reordered and applied immediately to ensure security. Additionally, the original filtering effect of the firewall is maintained without being compromised. The test results indicate that high-speed network firewall performance has improved significantly with no abnormality detected in the filtering effect.
{"title":"Real-Time Dynamic Configuration of Firewall Rules for High-Speed IoT Networks","authors":"Yu-An Shao, C. Chao","doi":"10.1109/ECICE55674.2022.10042899","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042899","url":null,"abstract":"The Internet of Things (IoT) is indispensable to modern society. It has entered the mainstream trend recently owing to its ability to read data and connect systems. IoT network platforms comprise various applications, leading to an influx of heavy and varying network traffic, allowing hackers to launch large-scale network attacks easily. When hackers gain control of an IoT device, they can initiate large-scale botnet attacks even through nonconventional computing devices such as cameras and routers. For example, Dyn, a domain name system provider, experienced large-scale distributed denial-of-service attacks on its IoT devices in 2016, causing companies, such as Twitter and Amazon, to suffer the consequences. Therefore, adapting to large-scale changes in network traffic in real-time is imperative. Firewalls are the foundation of device security. Therefore, when large-scale changes in network traffic occur, it is necessary to ensure the effectiveness of firewalls to reduce the probability of successful attacks. This study proposes a system that can adjust the order of firewall rules in real-time to monitor the traffic in high-speed IoT networks. When the system detects a sudden increase in the number of packets, the firewall rules are reordered and applied immediately to ensure security. Additionally, the original filtering effect of the firewall is maintained without being compromised. The test results indicate that high-speed network firewall performance has improved significantly with no abnormality detected in the filtering effect.","PeriodicalId":282635,"journal":{"name":"2022 IEEE 4th Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132827429","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 : 2022-10-28DOI: 10.1109/ECICE55674.2022.10042868
Chien-Chang Chen, Yu-Yang Lin, Jing-Chung Shen
The purpose of the study was to discuss how a tilted license plate (LP) affects the accuracy of LP recognition and how to improve a recognition system. The character segmentation on tilted LP usually causes character segmentation to be incomplete or out of range, which leads to a decrease in the accuracy rate of character recognition. We propose a method to improve the accuracy of LP recognition and reduce the prediction model training time for the recognition system. The study has four steps which are LP location, LP correction, character segmentation, and character recognition. Firstly, LP was located and zoomed in with YOLOv4 to reduce irrelevant noise and background value. Secondly, the system analyzed pixel changes of each angle with a horizontal projection and corrected the horizontal tilt angle for the LP. Then, the system used vertical projection to move the upper and lower half pixels of the LP in opposite directions. By analyzing the projection status of each angle, the system then corrected the vertical tilt angle for the LP. Thirdly, the system performed character segmentation on the corrected LP. This was done by extracting each character. Lastly, given more than 9,000 character images from step three, the recognition system with Convolutional Neural Network (CNN) trained the prediction model with the feature selection of the maximum pooling layer. Finally, the recognition system accuracy of predicting the uncorrected LP is 96.1% after 25 epochs, while the recognition accuracy of predicting corrected LP is 99% after 10 epochs. The accuracy of LP recognition was increased from 96.1 to 99% after LP tilt correction. CNN training time was decreased from 25 epochs to 10 epochs.
{"title":"License Plate Recognition Model For Tilt Correction Based on Convolutional Neural Network","authors":"Chien-Chang Chen, Yu-Yang Lin, Jing-Chung Shen","doi":"10.1109/ECICE55674.2022.10042868","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042868","url":null,"abstract":"The purpose of the study was to discuss how a tilted license plate (LP) affects the accuracy of LP recognition and how to improve a recognition system. The character segmentation on tilted LP usually causes character segmentation to be incomplete or out of range, which leads to a decrease in the accuracy rate of character recognition. We propose a method to improve the accuracy of LP recognition and reduce the prediction model training time for the recognition system. The study has four steps which are LP location, LP correction, character segmentation, and character recognition. Firstly, LP was located and zoomed in with YOLOv4 to reduce irrelevant noise and background value. Secondly, the system analyzed pixel changes of each angle with a horizontal projection and corrected the horizontal tilt angle for the LP. Then, the system used vertical projection to move the upper and lower half pixels of the LP in opposite directions. By analyzing the projection status of each angle, the system then corrected the vertical tilt angle for the LP. Thirdly, the system performed character segmentation on the corrected LP. This was done by extracting each character. Lastly, given more than 9,000 character images from step three, the recognition system with Convolutional Neural Network (CNN) trained the prediction model with the feature selection of the maximum pooling layer. Finally, the recognition system accuracy of predicting the uncorrected LP is 96.1% after 25 epochs, while the recognition accuracy of predicting corrected LP is 99% after 10 epochs. The accuracy of LP recognition was increased from 96.1 to 99% after LP tilt correction. CNN training time was decreased from 25 epochs to 10 epochs.","PeriodicalId":282635,"journal":{"name":"2022 IEEE 4th Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113947563","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 : 2022-10-28DOI: 10.1109/ECICE55674.2022.10042858
Chien-Chung Tsai, Chih-Chun Chan
This work proposes a brand-new approach for the laser ablation study of Si3 N4 film based upon unsupervised machine learning (ML) in the CMOS-MEMS process. The study demonstrates that energy and interval time dominate laser ablation quality for green light 532nm. There are four rational classes for this task by the k-means algorithm. While the interval time is longer than 70 s, the mean laser ablation quality (reb) is more than 80%. The interval time is shorter than the 50s which reb is less than 74%. The result shows energy 0.318mJ, interval time 84 seconds, pulse shots 5 times, and left pad position to have the maximum reb of 88.64% compared to other conditions. Finally, there is a statistically significant relationship between energy and reb based on the P-value of OLS regression. Typical ensemble learners Decision Tree and Random Forest have the appropriate classification ability.
{"title":"Ensemble and Unsupervised Machine Learning Applied on Laser Ablation Quality Study of Silicon Nitride during CMOS-MEMS Post Processing","authors":"Chien-Chung Tsai, Chih-Chun Chan","doi":"10.1109/ECICE55674.2022.10042858","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042858","url":null,"abstract":"This work proposes a brand-new approach for the laser ablation study of Si3 N4 film based upon unsupervised machine learning (ML) in the CMOS-MEMS process. The study demonstrates that energy and interval time dominate laser ablation quality for green light 532nm. There are four rational classes for this task by the k-means algorithm. While the interval time is longer than 70 s, the mean laser ablation quality (reb) is more than 80%. The interval time is shorter than the 50s which reb is less than 74%. The result shows energy 0.318mJ, interval time 84 seconds, pulse shots 5 times, and left pad position to have the maximum reb of 88.64% compared to other conditions. Finally, there is a statistically significant relationship between energy and reb based on the P-value of OLS regression. Typical ensemble learners Decision Tree and Random Forest have the appropriate classification ability.","PeriodicalId":282635,"journal":{"name":"2022 IEEE 4th Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116773387","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 : 2022-10-28DOI: 10.1109/ECICE55674.2022.10042890
Jenn‐Yih Chen, Yi-Ling Lin, B. Lee
To maintain process stability and yield improvement in a small and diverse market, digitization equipment and managing tools intelligently through the IoT are necessary. Although many traditional manufacturing factories have used IoT technologies, they cannot control the tracking flow and condition of each cutting tool owing to a lack of systematic tools. This easily causes machine downtime or even damage to the machine spindle due to tool-related problems. Therefore, the tool management system (TMS) in this study is designed based on a browser/server (B/S) web architecture and is designed to use a non-relational database for storing tool data with a non-fixed structure. The TMS is proposed to integrate two management modes: tool management and engineering development. The functions of tool management are mainly about querying the database through specific codes and keeping the usage records oftools. It enables processing staff, purchasing staff, warehousing staff, and administrators to have useful information on each tool at each stage. In addition to recording the usage of the tools, when the inventory level of the tools is lower than the safety level, the purchaser is immediately notified to place an order with the tool supplier for shortening the tool preparation time. On the other hand, the functions of the engineering development are designed for CAD/CAM manufacturing staff to query the tool inventory through the TMS to obtain suitable matching components in real-time. DXF files are used to assemble tool components and generate 3D models in CAM software for simulation tests. Then, the production staffprepares the tools according to the tool list from the simulation. The staff of the measurement department also measures and updates the tool compensation data of the TMS. Thus, the operator quickly places the tool into the corresponding number on the tool magazine (or turret head) and update the correct compensation value of the CNC controller via TCP/IP.
{"title":"Development of Tool Management System based on Django Web Framework","authors":"Jenn‐Yih Chen, Yi-Ling Lin, B. Lee","doi":"10.1109/ECICE55674.2022.10042890","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042890","url":null,"abstract":"To maintain process stability and yield improvement in a small and diverse market, digitization equipment and managing tools intelligently through the IoT are necessary. Although many traditional manufacturing factories have used IoT technologies, they cannot control the tracking flow and condition of each cutting tool owing to a lack of systematic tools. This easily causes machine downtime or even damage to the machine spindle due to tool-related problems. Therefore, the tool management system (TMS) in this study is designed based on a browser/server (B/S) web architecture and is designed to use a non-relational database for storing tool data with a non-fixed structure. The TMS is proposed to integrate two management modes: tool management and engineering development. The functions of tool management are mainly about querying the database through specific codes and keeping the usage records oftools. It enables processing staff, purchasing staff, warehousing staff, and administrators to have useful information on each tool at each stage. In addition to recording the usage of the tools, when the inventory level of the tools is lower than the safety level, the purchaser is immediately notified to place an order with the tool supplier for shortening the tool preparation time. On the other hand, the functions of the engineering development are designed for CAD/CAM manufacturing staff to query the tool inventory through the TMS to obtain suitable matching components in real-time. DXF files are used to assemble tool components and generate 3D models in CAM software for simulation tests. Then, the production staffprepares the tools according to the tool list from the simulation. The staff of the measurement department also measures and updates the tool compensation data of the TMS. Thus, the operator quickly places the tool into the corresponding number on the tool magazine (or turret head) and update the correct compensation value of the CNC controller via TCP/IP.","PeriodicalId":282635,"journal":{"name":"2022 IEEE 4th Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129292524","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 : 2022-10-28DOI: 10.1109/ECICE55674.2022.10042835
Yan Ke, Yun-Shuai Yu, Cheng-Tung Sun, Chia-Yen Wu
In this study, we proposed an elevator scheduling algorithm based on a Dueling Double Deep Q Network (D3QN) for robots. The rewards for the elevator car allocation decision are estimated based on the robots’ journey time, the number of floors an empty car traverses, and how the car allocation meets the robots’ priorities. The Robotics Middleware Framework (RMF) was adopted to be the simulator. The performance of the proposed algorithm was compared to an existing LOOK algorithm. The simulation results show that the proposed method outperforms the existing LOOK method in terms of the robots’ journey time and how the car allocation meets the robots’ priorities at the cost of a higher number of floors traversed by an empty car.
{"title":"D3QN-based Elevator Scheduling Algorithm for Robots","authors":"Yan Ke, Yun-Shuai Yu, Cheng-Tung Sun, Chia-Yen Wu","doi":"10.1109/ECICE55674.2022.10042835","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042835","url":null,"abstract":"In this study, we proposed an elevator scheduling algorithm based on a Dueling Double Deep Q Network (D3QN) for robots. The rewards for the elevator car allocation decision are estimated based on the robots’ journey time, the number of floors an empty car traverses, and how the car allocation meets the robots’ priorities. The Robotics Middleware Framework (RMF) was adopted to be the simulator. The performance of the proposed algorithm was compared to an existing LOOK algorithm. The simulation results show that the proposed method outperforms the existing LOOK method in terms of the robots’ journey time and how the car allocation meets the robots’ priorities at the cost of a higher number of floors traversed by an empty car.","PeriodicalId":282635,"journal":{"name":"2022 IEEE 4th Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127770199","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}
Taiwan is frequently affected by typhoons. Typhoons bring heavy rainfall and cause rapid river level rise and even flooding. In the past, high-accuracy but costly equipment, which could not be widely distributed, was used for hydrological observation. It caused us unable to obtain regional hydrological information in real-time. Currently, CCTV has been widely distributed in rivers in Taiwan, and real-time weather information can be accessed through the Internet by the public. Using CCTV and public weather information, we analyzed the images of the water level gauge to provide real-time regional hydrological information for early flood warnings. The image binarization is used for the analysis of water levels. However, because of the differences in environmental factors such as time, weather, and sunrise/sunset time, a set of different thresholds must be used for the binarization in image processing. In this study, a polynomial regression model for predicting the binarization threshold was proposed. According to the changes in environmental factors, the threshold required for image binarization was predicted in real-time, thereby improving the image recognition rate of water gauges.
{"title":"Image Recognition of River Water Gauges Using Polynomial Regression Model for Predicting Binarization Threshold","authors":"Jui-Fa Chen, Po-Chun Wang, Sin-Man Wong, Yu-Ting Liao","doi":"10.1109/ECICE55674.2022.10042942","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042942","url":null,"abstract":"Taiwan is frequently affected by typhoons. Typhoons bring heavy rainfall and cause rapid river level rise and even flooding. In the past, high-accuracy but costly equipment, which could not be widely distributed, was used for hydrological observation. It caused us unable to obtain regional hydrological information in real-time. Currently, CCTV has been widely distributed in rivers in Taiwan, and real-time weather information can be accessed through the Internet by the public. Using CCTV and public weather information, we analyzed the images of the water level gauge to provide real-time regional hydrological information for early flood warnings. The image binarization is used for the analysis of water levels. However, because of the differences in environmental factors such as time, weather, and sunrise/sunset time, a set of different thresholds must be used for the binarization in image processing. In this study, a polynomial regression model for predicting the binarization threshold was proposed. According to the changes in environmental factors, the threshold required for image binarization was predicted in real-time, thereby improving the image recognition rate of water gauges.","PeriodicalId":282635,"journal":{"name":"2022 IEEE 4th Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129800702","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 : 2022-10-28DOI: 10.1109/ECICE55674.2022.10042896
L. Liao, Wei Huang
The fuzzy inference system with expert knowledge can propose interpretable solutions for the uncertainties of clinic data. The learning concept of perceptron networks is simple and close to human thinking. In this study, we used fuzzy inference systems and perceptron learning networks (FIS-PLN) to detect and predict diabetes. For diagnosis of diabetes, insulin, glucose, and BMI are critical and relevant indices. In the detection system, the medical data of insulin, glucose, and BMI were sent to the fuzzy system in advance before training the PLN. The fuzzy system inferred a cross-effect grade that revealed the impact of the medical features on diabetes. The cross-effect grade and other medical data were combined and applied to train the PLN. The testing results demonstrated that under the same simulation conditions and medical features, the FIS-PLN model performed better predictions than PLN. The prediction accuracy approached 79.4% and the AUC of the FIS-PLN model was near 0.843.
{"title":"Detection and Prediction of Diabetes Using Simple Fuzzy-Perceptron Learning Network","authors":"L. Liao, Wei Huang","doi":"10.1109/ECICE55674.2022.10042896","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042896","url":null,"abstract":"The fuzzy inference system with expert knowledge can propose interpretable solutions for the uncertainties of clinic data. The learning concept of perceptron networks is simple and close to human thinking. In this study, we used fuzzy inference systems and perceptron learning networks (FIS-PLN) to detect and predict diabetes. For diagnosis of diabetes, insulin, glucose, and BMI are critical and relevant indices. In the detection system, the medical data of insulin, glucose, and BMI were sent to the fuzzy system in advance before training the PLN. The fuzzy system inferred a cross-effect grade that revealed the impact of the medical features on diabetes. The cross-effect grade and other medical data were combined and applied to train the PLN. The testing results demonstrated that under the same simulation conditions and medical features, the FIS-PLN model performed better predictions than PLN. The prediction accuracy approached 79.4% and the AUC of the FIS-PLN model was near 0.843.","PeriodicalId":282635,"journal":{"name":"2022 IEEE 4th Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126366983","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 : 2022-10-28DOI: 10.1109/ECICE55674.2022.10042822
Matthias Milan Strljic, Islam Younes, O. Riedel
Additive manufacturing technologies provided one of the most adaptable manufacturing processes for digital commissioning via the growing cloud manufacturing paradigm. This was facilitated by a low-complexity tool chain for the manufacturing process along the CAD-CAM chain and the process to be executed on the equipment. However, additive processes have grown far beyond the initial FDM processes and also offer more complex materials with unique properties in addition to other processes. The four most common manufacturing processes FDM, SLA, SLS, and SLM were used as a basis, and existing cloud manufacturing platforms offering all these four technologies as a bundle were gathered via a structured survey. Out of 42 platforms, 17 platforms were researched, filtered and analyzed using sample components and a catalog of requirements consisting of five requirement clusters: material, functional scope, final costs, delivery and user-friendliness. The results were weighted for each technology and finally evaluated in an overarching discussion. The achieved scores and the special features of a platform are discussed and a recommendation is made.
{"title":"Study on Available Cloud Manufacturing Platforms for Additive Manufacturing Technologies","authors":"Matthias Milan Strljic, Islam Younes, O. Riedel","doi":"10.1109/ECICE55674.2022.10042822","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042822","url":null,"abstract":"Additive manufacturing technologies provided one of the most adaptable manufacturing processes for digital commissioning via the growing cloud manufacturing paradigm. This was facilitated by a low-complexity tool chain for the manufacturing process along the CAD-CAM chain and the process to be executed on the equipment. However, additive processes have grown far beyond the initial FDM processes and also offer more complex materials with unique properties in addition to other processes. The four most common manufacturing processes FDM, SLA, SLS, and SLM were used as a basis, and existing cloud manufacturing platforms offering all these four technologies as a bundle were gathered via a structured survey. Out of 42 platforms, 17 platforms were researched, filtered and analyzed using sample components and a catalog of requirements consisting of five requirement clusters: material, functional scope, final costs, delivery and user-friendliness. The results were weighted for each technology and finally evaluated in an overarching discussion. The achieved scores and the special features of a platform are discussed and a recommendation is made.","PeriodicalId":282635,"journal":{"name":"2022 IEEE 4th Eurasia Conference on IOT, Communication and Engineering (ECICE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121506301","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：