Pub Date : 2022-02-01DOI: 10.1109/ICTech55460.2022.00072
Junxian Yang, Ronghua Zhou, Min Zhang, Yijun Shan
This article takes Dujiangyan Xianzai: Houshe, an Internet celebrity homestay as an example. We collected online reviews of the homestay as the textual data, and use ROST CM6 software to analysis. The cognitive image of the homestay is divided into six main categories: overall cognition, room facilities, personalized service, geographic location, service attitude, and cost performance. The affective image of the homestay is mainly positive and the overall image shows that the homestay has a high degree of satisfaction. Finally, we summarize some of its experiences and suggestions to obtain consumer satisfaction for other homestay owners to learn and refer to.
{"title":"Analysis of Online Reviews Data for Perceiving Image of Homestay","authors":"Junxian Yang, Ronghua Zhou, Min Zhang, Yijun Shan","doi":"10.1109/ICTech55460.2022.00072","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00072","url":null,"abstract":"This article takes Dujiangyan Xianzai: Houshe, an Internet celebrity homestay as an example. We collected online reviews of the homestay as the textual data, and use ROST CM6 software to analysis. The cognitive image of the homestay is divided into six main categories: overall cognition, room facilities, personalized service, geographic location, service attitude, and cost performance. The affective image of the homestay is mainly positive and the overall image shows that the homestay has a high degree of satisfaction. Finally, we summarize some of its experiences and suggestions to obtain consumer satisfaction for other homestay owners to learn and refer to.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125325097","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00053
Bo-quan Yu, Hanting Wei, Wei Wang
With the development and application of deep learning in computer vision, the performance of many basic visual tasks such as object detection and semantic segmentation has been greatly improved. However, most of networks are based on standard illumination, which results in poor performance in low illumination scenarios, and it is difficult to collect datasets with different illumination levels in restricted scenes. In this paper, GAN and related derived networks are systematically studied and summarized, and based on the idea of generation-antagonism of GAN, the design of day-night cross-domain converter is completed on the basis of the structure of CycleGAN. Based on this, Inception layer is added to optimize the structure of the converter, and the performance of the day-night cross-domain converters before and after optimization are compared through experiments. The results show that the optimized day-night converter can make the converted image more realistic. It is of great significance for enhancing the quality of datasets in restricted scenes, improving the performance of object detection and segmentation models in low illumination scenes.
{"title":"GAN-Based Day and Night Image Cross-Domain Conversion Research and Application","authors":"Bo-quan Yu, Hanting Wei, Wei Wang","doi":"10.1109/ICTech55460.2022.00053","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00053","url":null,"abstract":"With the development and application of deep learning in computer vision, the performance of many basic visual tasks such as object detection and semantic segmentation has been greatly improved. However, most of networks are based on standard illumination, which results in poor performance in low illumination scenarios, and it is difficult to collect datasets with different illumination levels in restricted scenes. In this paper, GAN and related derived networks are systematically studied and summarized, and based on the idea of generation-antagonism of GAN, the design of day-night cross-domain converter is completed on the basis of the structure of CycleGAN. Based on this, Inception layer is added to optimize the structure of the converter, and the performance of the day-night cross-domain converters before and after optimization are compared through experiments. The results show that the optimized day-night converter can make the converted image more realistic. It is of great significance for enhancing the quality of datasets in restricted scenes, improving the performance of object detection and segmentation models in low illumination scenes.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122084288","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00118
Jinyan Shi, Yongchao Xie
Under the background of diagnosis and improvement of teaching work in higher vocational colleges, it is urgent to construct a set of scientific and complete evaluation index system of diagnosis and improvement in classroom teaching so as to improve the quality of classroom teaching. This paper constructs an evaluation index system for the diagnosis and improvement of classroom teaching, it is composed of five first-class evaluation indexes such as classroom teaching goal, classroom teaching design, classroom teaching resources, classroom teaching organization, classroom teaching quality and 18 second-class indexes such as clarity of teaching goal. This paper carries out practical research on the diagnosis and improvement of the evaluation index system of classroom teaching, obtains the diagnosis conclusion of classroom teaching, and puts forward the direction of classroom teaching optimization based on the diagnosis conclusion, it provides a certain reference for higher vocational colleges to carry out the work of classroom teaching diagnosis and reform. The practice shows that the diagnosis and improvement of the evaluation index system of classroom teaching in higher vocational colleges are highly operative, can measure the quality of classroom teaching comprehensively, and can promote the quality of classroom teaching effectively.
{"title":"Study of Diagnosis and Improvement Index System of Higher Vocational Classroom Teaching Based upon AHP","authors":"Jinyan Shi, Yongchao Xie","doi":"10.1109/ICTech55460.2022.00118","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00118","url":null,"abstract":"Under the background of diagnosis and improvement of teaching work in higher vocational colleges, it is urgent to construct a set of scientific and complete evaluation index system of diagnosis and improvement in classroom teaching so as to improve the quality of classroom teaching. This paper constructs an evaluation index system for the diagnosis and improvement of classroom teaching, it is composed of five first-class evaluation indexes such as classroom teaching goal, classroom teaching design, classroom teaching resources, classroom teaching organization, classroom teaching quality and 18 second-class indexes such as clarity of teaching goal. This paper carries out practical research on the diagnosis and improvement of the evaluation index system of classroom teaching, obtains the diagnosis conclusion of classroom teaching, and puts forward the direction of classroom teaching optimization based on the diagnosis conclusion, it provides a certain reference for higher vocational colleges to carry out the work of classroom teaching diagnosis and reform. The practice shows that the diagnosis and improvement of the evaluation index system of classroom teaching in higher vocational colleges are highly operative, can measure the quality of classroom teaching comprehensively, and can promote the quality of classroom teaching effectively.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125650788","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00020
Ying Li, Zhuohuai Guan
This paper introduces the main functions of CAE system, expounding the general situation of computer aided engineering technology at home and abroad, and analyzes the problems existing in the application of domestic CAE technology and the future development direction.
{"title":"Development and Prospect of Computer Aided Engineering","authors":"Ying Li, Zhuohuai Guan","doi":"10.1109/ICTech55460.2022.00020","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00020","url":null,"abstract":"This paper introduces the main functions of CAE system, expounding the general situation of computer aided engineering technology at home and abroad, and analyzes the problems existing in the application of domestic CAE technology and the future development direction.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132868280","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00046
K. X. Cui, Xiaojun Xia
Aiming at the problems of low feature extraction efficiency and low detection accuracy of traditional ECG signal detection algorithms, this paper proposes a convolutional neural network (CNN) and bi-directional long short-term memory (Bi-directional long short-term memory, LSTM) network hybrid ECG signal anomaly detection algorithm. This model effectively utilizes the ability of CNN to automatically extract features and BiLSTM's ability to efficiently process time series data. Through experimental verification on the arrhythmia data set in the MIT -BIH database, the overall accuracy of the model is 98.56%. Compared with support vector machine (SVM) and bidirectional long short-term memory neural network (BiLSTM), the accuracy and F1 value of this model are improved.
针对传统心电信号检测算法特征提取效率低、检测精度低等问题，本文提出了一种卷积神经网络(CNN)与双向长短期记忆(bi-directional long short-term memory, LSTM)网络混合的心电信号异常检测算法。该模型有效地利用了CNN自动提取特征的能力和BiLSTM高效处理时间序列数据的能力。通过MIT -BIH数据库中心律失常数据集的实验验证，该模型的总体准确率为98.56%。与支持向量机(SVM)和双向长短期记忆神经网络(BiLSTM)相比，该模型的准确率和F1值都有所提高。
{"title":"ECG Signal Anomaly Detection Algorithm Based on CNN-BiLSTM","authors":"K. X. Cui, Xiaojun Xia","doi":"10.1109/ICTech55460.2022.00046","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00046","url":null,"abstract":"Aiming at the problems of low feature extraction efficiency and low detection accuracy of traditional ECG signal detection algorithms, this paper proposes a convolutional neural network (CNN) and bi-directional long short-term memory (Bi-directional long short-term memory, LSTM) network hybrid ECG signal anomaly detection algorithm. This model effectively utilizes the ability of CNN to automatically extract features and BiLSTM's ability to efficiently process time series data. Through experimental verification on the arrhythmia data set in the MIT -BIH database, the overall accuracy of the model is 98.56%. Compared with support vector machine (SVM) and bidirectional long short-term memory neural network (BiLSTM), the accuracy and F1 value of this model are improved.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130015483","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00056
Jiayao Lv, Bihui Yu, Huajun Sun
Complex Event Processing (CEP) is an effective method to find the time and causality relationship between various events in the stream data. Its purpose is to match the low-level events in the event stream into complex events according to a certain pattern. CEP has a wide range of applications in the Internet of Things, cloud computing, finance and cyber security. Currently, in CEP design, event matching rules are mainly formulated by domain experts according to their professional knowledge and subjective judgment. However, with the increase of the complexity of event flow data, it is increasingly difficult to formulate rules. To solve this problem, a CEP rule extraction framework based on an evolutionary algorithm is proposed in this study to realize automatic learning of CEP rules, and test data are used for verification, and high-precision experimental results are obtained.
{"title":"CEP Rule Extraction Framework Based on Evolutionary Algorithm","authors":"Jiayao Lv, Bihui Yu, Huajun Sun","doi":"10.1109/ICTech55460.2022.00056","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00056","url":null,"abstract":"Complex Event Processing (CEP) is an effective method to find the time and causality relationship between various events in the stream data. Its purpose is to match the low-level events in the event stream into complex events according to a certain pattern. CEP has a wide range of applications in the Internet of Things, cloud computing, finance and cyber security. Currently, in CEP design, event matching rules are mainly formulated by domain experts according to their professional knowledge and subjective judgment. However, with the increase of the complexity of event flow data, it is increasingly difficult to formulate rules. To solve this problem, a CEP rule extraction framework based on an evolutionary algorithm is proposed in this study to realize automatic learning of CEP rules, and test data are used for verification, and high-precision experimental results are obtained.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122023530","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00063
Ruomu Miao, Wenlin Yao
With the rapid development of network intelligent platform, users can download and watch network videos from different video platforms. At this time, how to master users' personal preferences and recommend video programs from mass data resources has become the focus of innovation exploration of film and television enterprises. Therefore, on the basis of understanding the collaborative filtering recommendation algorithm, this paper analyzes how to achieve accurate recommendation of film and television resources based on the improved matrix decomposition model of convolutional neural network.
{"title":"Research on Collaborative Recommendation Algorithm Based on Film and Television Big Data","authors":"Ruomu Miao, Wenlin Yao","doi":"10.1109/ICTech55460.2022.00063","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00063","url":null,"abstract":"With the rapid development of network intelligent platform, users can download and watch network videos from different video platforms. At this time, how to master users' personal preferences and recommend video programs from mass data resources has become the focus of innovation exploration of film and television enterprises. Therefore, on the basis of understanding the collaborative filtering recommendation algorithm, this paper analyzes how to achieve accurate recommendation of film and television resources based on the improved matrix decomposition model of convolutional neural network.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121045278","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00081
Qian Wang, Baocai Guo, Churila Sa, Bo Hu, Lu Zhang
In the development of Internet technology, the state grid enterprises of electric power began to use big data analysis technology to identify the multi-dimensional value of users at the same time of technological innovation, and put forward more accurate marketing operation countermeasures. Because the electricity customers in the electricity market belong to a relatively large group, so the analysis service based on the actual electricity consumption of customers, power demand and other content can not only provide effective basis for the actual management decision, but also improve the operation quality and efficiency of the computer system. Therefore, on the basis of understanding the functions and technical implementation of precision marketing platform based on big data technology, this paper conducts in-depth research on the power butler service model of residential customers based on cluster analysis of user types, and finally conducts empirical analysis on the basis of constructing ADTM-AI model. The results show that the stochastic forest classification method is more suitable to identify the multi-dimensional value of users in the state grid of electric power, and can provide effective basis for the accurate operation of the actual system.
{"title":"A Big Data Based Analysis of Accurate Operation for User Multidimensional Value Identification","authors":"Qian Wang, Baocai Guo, Churila Sa, Bo Hu, Lu Zhang","doi":"10.1109/ICTech55460.2022.00081","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00081","url":null,"abstract":"In the development of Internet technology, the state grid enterprises of electric power began to use big data analysis technology to identify the multi-dimensional value of users at the same time of technological innovation, and put forward more accurate marketing operation countermeasures. Because the electricity customers in the electricity market belong to a relatively large group, so the analysis service based on the actual electricity consumption of customers, power demand and other content can not only provide effective basis for the actual management decision, but also improve the operation quality and efficiency of the computer system. Therefore, on the basis of understanding the functions and technical implementation of precision marketing platform based on big data technology, this paper conducts in-depth research on the power butler service model of residential customers based on cluster analysis of user types, and finally conducts empirical analysis on the basis of constructing ADTM-AI model. The results show that the stochastic forest classification method is more suitable to identify the multi-dimensional value of users in the state grid of electric power, and can provide effective basis for the accurate operation of the actual system.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116443463","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00027
Mingrui Sha, Zhenhao Gu
With the rapid development of electric power industry and the acceleration of the marketization process of electric power system reform, the importance of electric power safety production is more prominent. The traditional electronic fence mostly adopts radio frequency or infrared monitoring, which cannot be accurately identified. False positives will be generated when animals or inanimate objects enter the monitoring area. This paper aims to use interval capture method to extract feature through HOG, PCA and other feature extraction methods in real time, and then use SVM classifier to discriminate for the transgression detection system in key monitoring areas of power grid. In order to achieve the key areas of personnel crossing the precise monitoring.
{"title":"Research and Application of HOG Feature Based Power Grid Key Area Out of Bounds Detection","authors":"Mingrui Sha, Zhenhao Gu","doi":"10.1109/ICTech55460.2022.00027","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00027","url":null,"abstract":"With the rapid development of electric power industry and the acceleration of the marketization process of electric power system reform, the importance of electric power safety production is more prominent. The traditional electronic fence mostly adopts radio frequency or infrared monitoring, which cannot be accurately identified. False positives will be generated when animals or inanimate objects enter the monitoring area. This paper aims to use interval capture method to extract feature through HOG, PCA and other feature extraction methods in real time, and then use SVM classifier to discriminate for the transgression detection system in key monitoring areas of power grid. In order to achieve the key areas of personnel crossing the precise monitoring.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129844825","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 : 2022-02-01DOI: 10.1109/ICTech55460.2022.00037
Qiongwei Zhang, Lunxing Li, Liaomo Zheng, Beibei Li
The rapidly-exploring random tree (RRT) algorithm can quickly complete the task of path planning through random sampling. However, only part of the cost is considered in the selection process of RRT nodes, which may cause inefficiency in some environments. In response to this problem, this paper proposes a new hybrid path planning algorithm based on the rapid expansion of random tree algorithm. This algorithm introduces heuristic search ideas on the basis of RRT's random expansion search to ensure the overall efficiency of the search. Experiments show that in some environments, the algorithm can plan a more efficient path in a shorter time.
{"title":"An Improved Path Planning Algorithm Based on RRT","authors":"Qiongwei Zhang, Lunxing Li, Liaomo Zheng, Beibei Li","doi":"10.1109/ICTech55460.2022.00037","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00037","url":null,"abstract":"The rapidly-exploring random tree (RRT) algorithm can quickly complete the task of path planning through random sampling. However, only part of the cost is considered in the selection process of RRT nodes, which may cause inefficiency in some environments. In response to this problem, this paper proposes a new hybrid path planning algorithm based on the rapid expansion of random tree algorithm. This algorithm introduces heuristic search ideas on the basis of RRT's random expansion search to ensure the overall efficiency of the search. Experiments show that in some environments, the algorithm can plan a more efficient path in a shorter time.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121755259","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：