Pub Date : 2022-10-28DOI: 10.1109/ECICE55674.2022.10042885
Yung-Hsiang Chen, C. Chao, Yung-Yue Chen
An adaptive fuzzy control design is developed in this investigation. The main objective of the proposed method will solve the trajectory tracking problem of mobile robots which are with a symmetrical schematic property and modelling uncertainties. This proposed control law combines a nonlinear optimal control which is used for the purpose of saving energy consumption and a fuzzy eliminator utilized to model the uncertainties. This proposed control method facilitates to implement in practice since the analytical solution of this tracking problem of mobile robot is found. From the simulation results, this proposed control design delivers really promising control performance for mobile robots.
{"title":"An Adaptive Optimal Control Design for Mobile Robots with A Symmetrical Schematic","authors":"Yung-Hsiang Chen, C. Chao, Yung-Yue Chen","doi":"10.1109/ECICE55674.2022.10042885","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042885","url":null,"abstract":"An adaptive fuzzy control design is developed in this investigation. The main objective of the proposed method will solve the trajectory tracking problem of mobile robots which are with a symmetrical schematic property and modelling uncertainties. This proposed control law combines a nonlinear optimal control which is used for the purpose of saving energy consumption and a fuzzy eliminator utilized to model the uncertainties. This proposed control method facilitates to implement in practice since the analytical solution of this tracking problem of mobile robot is found. From the simulation results, this proposed control design delivers really promising control performance for mobile robots.","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":"133006667","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/ECICE55674.2022.10042921
Yi Wang, Haoran Yang, Jun Wang
A series of sleep disorders such as insomnia and sleep apnea is common among the elderly. Currently, machine vision perception and contact perception monitoring are widely used. This study proposed a new system that is applied to home vital signs monitoring with commercial WiFi. The system uses commercial WiFi to perceive and identify sleep time segments through motion detection algorithms. The segments are divided into large and small-amplitude random motion states and filtered out into small-amplitude segments. Then, the CSI ratio model is used for instantaneous respiratory rate estimation. The CSI ratio model has an accuracy of over 97% and provides excellent real-time sleep safety monitoring, outperforming other popular solutions such as the maximum ratio combining technology.
{"title":"Analysis and Research on Performance of Sleep Safety Monitoring System Based on WiFi Sensing","authors":"Yi Wang, Haoran Yang, Jun Wang","doi":"10.1109/ECICE55674.2022.10042921","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042921","url":null,"abstract":"A series of sleep disorders such as insomnia and sleep apnea is common among the elderly. Currently, machine vision perception and contact perception monitoring are widely used. This study proposed a new system that is applied to home vital signs monitoring with commercial WiFi. The system uses commercial WiFi to perceive and identify sleep time segments through motion detection algorithms. The segments are divided into large and small-amplitude random motion states and filtered out into small-amplitude segments. Then, the CSI ratio model is used for instantaneous respiratory rate estimation. The CSI ratio model has an accuracy of over 97% and provides excellent real-time sleep safety monitoring, outperforming other popular solutions such as the maximum ratio combining technology.","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":"133935530","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/ECICE55674.2022.10042945
Youjoun He, Li Yan
We analyzed the characteristics of the landscape structure and spatial distribution of the green space of the wetland park. The result provides a reference for the ecological planning and reasonable design of the urban wetland park landscape. Based on Arc GIS software, the landscape pattern of Houguanhu Wetland Park was quantified, and the landscape patch data were extracted. The results show that the connectivity of the dominant landscape must be strengthened and the balance of different landscape types must be paid attention to in future landscape protection and upgrading construction.
{"title":"Study on Landscape Pattern of Houguan Lake Wetland Park in Wuhan Based on Data Analysis of Arc GIS Software","authors":"Youjoun He, Li Yan","doi":"10.1109/ECICE55674.2022.10042945","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042945","url":null,"abstract":"We analyzed the characteristics of the landscape structure and spatial distribution of the green space of the wetland park. The result provides a reference for the ecological planning and reasonable design of the urban wetland park landscape. Based on Arc GIS software, the landscape pattern of Houguanhu Wetland Park was quantified, and the landscape patch data were extracted. The results show that the connectivity of the dominant landscape must be strengthened and the balance of different landscape types must be paid attention to in future landscape protection and upgrading construction.","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":"124442044","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/ECICE55674.2022.10042815
Gowda A G Aishwarya, Hui-Kai Su, W. Kuo
The analysis of interviewing a candidate is a crucial part of building an efficient team for any organization. The right choice can effectively help produce quality work. As the interviewing environment is diversified into online and offline, based on the recent pandemic issues. The tracking of individuals validity and their work quality is often unclear. This has created a substantial loss for the organization choosing wrong candidates during this interview process. There are several hardships through remote hiring, where companies often find it difficult to validate their real identity due to proxysomeone else speaks in the background. Whereas offline hiring sometimes does not produce potential initial screening, making it difficult to find the right candidate. To solve all these hiring issues and help both companies and candidates we are producing a potential algorithm which helps review candidates and analyses their curriculum vitae and monitors the candidates throughout the interview process and furnishes detail report. The report will provide the candidates technical ability, culture fit data and many more factors that help choose the best one for the open position. The candidates can also reproduce such data along with their resume to companies to strengthen their ability of talent. This helps job searching candidates monitor and work through the gaps and make the best out of their skillset. The obtained data can be stored on to blockchain based on candidates’ choice, where several hiring organizations can find talents with less efforts.
{"title":"Efficient Hiring Analysis and Management Using Artificial Intelligence and Blockchain","authors":"Gowda A G Aishwarya, Hui-Kai Su, W. Kuo","doi":"10.1109/ECICE55674.2022.10042815","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042815","url":null,"abstract":"The analysis of interviewing a candidate is a crucial part of building an efficient team for any organization. The right choice can effectively help produce quality work. As the interviewing environment is diversified into online and offline, based on the recent pandemic issues. The tracking of individuals validity and their work quality is often unclear. This has created a substantial loss for the organization choosing wrong candidates during this interview process. There are several hardships through remote hiring, where companies often find it difficult to validate their real identity due to proxysomeone else speaks in the background. Whereas offline hiring sometimes does not produce potential initial screening, making it difficult to find the right candidate. To solve all these hiring issues and help both companies and candidates we are producing a potential algorithm which helps review candidates and analyses their curriculum vitae and monitors the candidates throughout the interview process and furnishes detail report. The report will provide the candidates technical ability, culture fit data and many more factors that help choose the best one for the open position. The candidates can also reproduce such data along with their resume to companies to strengthen their ability of talent. This helps job searching candidates monitor and work through the gaps and make the best out of their skillset. The obtained data can be stored on to blockchain based on candidates’ choice, where several hiring organizations can find talents with less efforts.","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":"128695367","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}
Generally, high-end battery devices estimate the remaining battery life through the chip, but such devices lack in providing life information for portable devices. Therefore, we develop an algorithm with an ACS-712 chip module to achieve this purpose. The ACS-712 module is powered by 5 V and measures the current within ±20 amps, and the corresponding output per amp is 100 millivolts. In this study, a small vehicle controlled by Arduino is adopted to collect the signals from ACS-712. The relationship between the remaining power and the starting current curve is discovered by analyzing the generated data. After experiments, the remaining power can be predicted by detecting the instantaneous current change during startup, and the accuracy reaches higher than 90%. In addition, we add different weights as control variables in the experiment and test the remaining power of various weights. It also achieves an accuracy of more than 85%.
{"title":"Prediction of Remaining Battery Life for Light Vehicles","authors":"Nian-Ze Hu, You-Xing Zeng, Bo-An Lin, Ruo-Wei Wu, You-Shin Lin, Kai-Hsun Hsu, Shang-Wei Liu, Tun-Chuan Chang, Chun-Min Tsai","doi":"10.1109/ECICE55674.2022.10042949","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042949","url":null,"abstract":"Generally, high-end battery devices estimate the remaining battery life through the chip, but such devices lack in providing life information for portable devices. Therefore, we develop an algorithm with an ACS-712 chip module to achieve this purpose. The ACS-712 module is powered by 5 V and measures the current within ±20 amps, and the corresponding output per amp is 100 millivolts. In this study, a small vehicle controlled by Arduino is adopted to collect the signals from ACS-712. The relationship between the remaining power and the starting current curve is discovered by analyzing the generated data. After experiments, the remaining power can be predicted by detecting the instantaneous current change during startup, and the accuracy reaches higher than 90%. In addition, we add different weights as control variables in the experiment and test the remaining power of various weights. It also achieves an accuracy of more than 85%.","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":"126240693","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/ECICE55674.2022.10042935
Nan Lin, Kui Deng, Xu Zhou
Target tracking is widely used in automatic monitoring, vehicle navigation, video marking, humancomputer interaction, and automatic driving scenes. However, the accuracy of target tracking is limited by the influence of object deformation, lighting, occlusion, background interference, and other factors. In this study, the tracking accuracy of the twin network target tracking algorithm is reduced under the conditions of object deformation, illumination, occlusion, background interference, and so on. SiamUNet is a three-twin network target tracking framework proposed in this study. The basic network structure of SiamUNet is U-NET. The algorithm uses four-layer feature extraction, and after feature fusion and a four-step up-sampling process, the semantic information and background information of the target is fully utilized. At the same time, SiamUNetjudges whether each pixel belongs to the target by predicting the binary segmentation mask of the target in each frame of the video to obtain more accurate target information. SiamUNet was evaluated on VOT-2021, OTBIOO, and OTB50 datasets and compared with five popular trackers. Experimental results showed that SiamUNet had better tracking.
{"title":"Target Tracking Algorithm Combining Twin Network and Semantic Segmentation","authors":"Nan Lin, Kui Deng, Xu Zhou","doi":"10.1109/ECICE55674.2022.10042935","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042935","url":null,"abstract":"Target tracking is widely used in automatic monitoring, vehicle navigation, video marking, humancomputer interaction, and automatic driving scenes. However, the accuracy of target tracking is limited by the influence of object deformation, lighting, occlusion, background interference, and other factors. In this study, the tracking accuracy of the twin network target tracking algorithm is reduced under the conditions of object deformation, illumination, occlusion, background interference, and so on. SiamUNet is a three-twin network target tracking framework proposed in this study. The basic network structure of SiamUNet is U-NET. The algorithm uses four-layer feature extraction, and after feature fusion and a four-step up-sampling process, the semantic information and background information of the target is fully utilized. At the same time, SiamUNetjudges whether each pixel belongs to the target by predicting the binary segmentation mask of the target in each frame of the video to obtain more accurate target information. SiamUNet was evaluated on VOT-2021, OTBIOO, and OTB50 datasets and compared with five popular trackers. Experimental results showed that SiamUNet had better tracking.","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":"125818847","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/ECICE55674.2022.10042839
Chun-Ching Hsiao, Han Chen
Smart technology for textiles has been developed so that functional socks can achieve waterproof and warm effects by a permeation process. Using PLC (Programmable Logic Controller) and human-machine integrated control equipment for the hosiery waterproof coating production equipment, the remote monitoring technology assists operators to catch the equipment status, tracks the manufacturing progress, improves manufacturing efficiency, and further extends the lifetime of automation equipment. The human machine interaction interface is used to present output, production capacity, progress, temperature distribution, wind speed, liquid level, transmission speed, operation cycle, and production utilization rate. Producers do not need to spend additional time and manpower to record and measure data. The interface for graphical programming and visual operation to reduce personnel education costs and achieve the purpose of improving production efficiency.
{"title":"Development of Human-machine Interactive Interface for Hosiery Waterproof Coating Production Line","authors":"Chun-Ching Hsiao, Han Chen","doi":"10.1109/ECICE55674.2022.10042839","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042839","url":null,"abstract":"Smart technology for textiles has been developed so that functional socks can achieve waterproof and warm effects by a permeation process. Using PLC (Programmable Logic Controller) and human-machine integrated control equipment for the hosiery waterproof coating production equipment, the remote monitoring technology assists operators to catch the equipment status, tracks the manufacturing progress, improves manufacturing efficiency, and further extends the lifetime of automation equipment. The human machine interaction interface is used to present output, production capacity, progress, temperature distribution, wind speed, liquid level, transmission speed, operation cycle, and production utilization rate. Producers do not need to spend additional time and manpower to record and measure data. The interface for graphical programming and visual operation to reduce personnel education costs and achieve the purpose of improving production efficiency.","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":"125820513","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/ECICE55674.2022.10042933
Muyang Lin, Zhiwen Wang, Lincai Huang
An algorithm based on improved YOLOv5s is proposed to solve the problems of false and missing vehicle detections. Firstly, a coordinate-attention (CA) module is added to the backbone feature of an extraction network to obtain more important information during feature extraction and improve object detection accuracy. Then, the weighted bi-directional feature pyramid network (BiFPN) is adopted to replace the original PANet structure in the YOLOv5s network. This method enhances the multi-scale feature fusion of the model and improves the fusion efficiency. Experiment results present that the mean average precision (mAP) of the improved YOLOv5s algorithm on the BIT-Vehicle Dataset reaches 94.S%, which is 2.S% higher than that of the original YOLOv5s network, and the processing frame rate reaches 136.9, which allows real-time detection by satisfying its requirements.
{"title":"Analysis and Research on YOLOv5s Vehicle Detection with CA and BiFPN Fusion","authors":"Muyang Lin, Zhiwen Wang, Lincai Huang","doi":"10.1109/ECICE55674.2022.10042933","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042933","url":null,"abstract":"An algorithm based on improved YOLOv5s is proposed to solve the problems of false and missing vehicle detections. Firstly, a coordinate-attention (CA) module is added to the backbone feature of an extraction network to obtain more important information during feature extraction and improve object detection accuracy. Then, the weighted bi-directional feature pyramid network (BiFPN) is adopted to replace the original PANet structure in the YOLOv5s network. This method enhances the multi-scale feature fusion of the model and improves the fusion efficiency. Experiment results present that the mean average precision (mAP) of the improved YOLOv5s algorithm on the BIT-Vehicle Dataset reaches 94.S%, which is 2.S% higher than that of the original YOLOv5s network, and the processing frame rate reaches 136.9, which allows real-time detection by satisfying its requirements.","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":"127514406","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/ECICE55674.2022.10042851
Shiyi Wu
Following the development of the Internet, the Internet of Things (IoT) has come to the stage of history. At present, the construction and application of the IoT are in the exploration stage. Through the literature research method and based on the construction experience of the IoT in CNPC, how to effectively apply the construction of the IoT platform in production management is studied, and the impact is analyzed on risk management. The case analysis method is used to analyze the motivation for the construction of the IoT. The production management system, inventory management system, and other management methods are studied, and the basic construction path of the IoT platform is analyzed, too. Through the case analysis of CNPC, the application scenarios and future development of IoT construction are proposed. The result provides a reference for the intelligent construction and management of enterprises.
{"title":"Research and Application of Internet of Things in Production and Risk Management","authors":"Shiyi Wu","doi":"10.1109/ECICE55674.2022.10042851","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042851","url":null,"abstract":"Following the development of the Internet, the Internet of Things (IoT) has come to the stage of history. At present, the construction and application of the IoT are in the exploration stage. Through the literature research method and based on the construction experience of the IoT in CNPC, how to effectively apply the construction of the IoT platform in production management is studied, and the impact is analyzed on risk management. The case analysis method is used to analyze the motivation for the construction of the IoT. The production management system, inventory management system, and other management methods are studied, and the basic construction path of the IoT platform is analyzed, too. Through the case analysis of CNPC, the application scenarios and future development of IoT construction are proposed. The result provides a reference for the intelligent construction and management of enterprises.","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":"120827989","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/ECICE55674.2022.10042904
Y. Zu
With the development and popularization of the network, the network plays an important role in people’s daily life, work, and the dissemination of social hot information. Most of the online Chinese English neologisms are widely disseminated through the Internet platform and are known and used by people. New word recognition plays an important role in Chinese word segmentation and information retrieval. With the emergence of a large number of new words in China English, the lack of a China English neologism database has become a major obstacle to the study of China English. New word recognition is a major technical issue in building a corpus. To solve the problem that the internal cohesion of words in the existing point mutual information and low adjacency entropy of new word recognition algorithms, a new word recognition algorithm of China English is proposed. The algorithm also solves the problem of the single threshold setting of point mutual information of the threshold invalid phrases, and the low threshold of new word groups by using point mutual information to identify new words. The experimental results show that, under the same data and experimental environment, the method improves the accuracy, recall, and F values, which is effective and feasible for corpus construction.
{"title":"Research on Intelligent Construction of China English Network New Words Database Based on Adjacent Entropy Recognition Algorithm","authors":"Y. Zu","doi":"10.1109/ECICE55674.2022.10042904","DOIUrl":"https://doi.org/10.1109/ECICE55674.2022.10042904","url":null,"abstract":"With the development and popularization of the network, the network plays an important role in people’s daily life, work, and the dissemination of social hot information. Most of the online Chinese English neologisms are widely disseminated through the Internet platform and are known and used by people. New word recognition plays an important role in Chinese word segmentation and information retrieval. With the emergence of a large number of new words in China English, the lack of a China English neologism database has become a major obstacle to the study of China English. New word recognition is a major technical issue in building a corpus. To solve the problem that the internal cohesion of words in the existing point mutual information and low adjacency entropy of new word recognition algorithms, a new word recognition algorithm of China English is proposed. The algorithm also solves the problem of the single threshold setting of point mutual information of the threshold invalid phrases, and the low threshold of new word groups by using point mutual information to identify new words. The experimental results show that, under the same data and experimental environment, the method improves the accuracy, recall, and F values, which is effective and feasible for corpus construction.","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":"131187745","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：