Pub Date : 2022-02-01DOI: 10.1109/ICTech55460.2022.00096
Xinxin Huang, Zhenyu Yin, Chao Fan
Pedestrian detection is a significant research direction in the computer vision, but the detection performance of existing pedestrian detection algorithms is inadequate. Therefore, this article proposes a novel algorithm to improve the anchor-free pedestrian detection algorithm. First, the multi-scale CSPN module is used to deepen the network depth, further extract semantic information on multiple scales, and improve detection performance. Moreover, the dual attention module based on feature fusion is used to effectively fuse features of different scales, assigning new weights to the fused features in the two dimensions of space and channel. Experiments show our method reduces MR−2 by 0.10%, 2.60% and 0.98% on the Reasonable, Heavy Occlusion and ALL of the Caltech pedestrian dataset, which is better than the existing algorithms.
{"title":"Towards Better Pedestrian Detection Using Multi-Scale CSPN and Dual Attention","authors":"Xinxin Huang, Zhenyu Yin, Chao Fan","doi":"10.1109/ICTech55460.2022.00096","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00096","url":null,"abstract":"Pedestrian detection is a significant research direction in the computer vision, but the detection performance of existing pedestrian detection algorithms is inadequate. Therefore, this article proposes a novel algorithm to improve the anchor-free pedestrian detection algorithm. First, the multi-scale CSPN module is used to deepen the network depth, further extract semantic information on multiple scales, and improve detection performance. Moreover, the dual attention module based on feature fusion is used to effectively fuse features of different scales, assigning new weights to the fused features in the two dimensions of space and channel. Experiments show our method reduces MR−2 by 0.10%, 2.60% and 0.98% on the Reasonable, Heavy Occlusion and ALL of the Caltech pedestrian dataset, which is better than the existing algorithms.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"7 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":"126876222","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}
As a way of wireless energy collection, radiofrequency energy collection technology is attracting wide attention in academic circles. In the previous research on RF energy collection, many achievements have been made in the 2.4-2.5GHz band. In the field of higher-frequency millimeter waves, there has been corresponding research abroad, but the radiofrequency energy absorption of the millimeter-wave band in China needs to be developed. In the era of the Internet of everything, to obtain RF energy efficiently in the traditional frequency band and the latest 5G band, a five-band rectifier composed of two single series diode rectifiers is designed in this paper. The simulation results show that when the input power level is-20dBm~0dBm, the maximum RF-DC conversion efficiency of the rectifier in 1.9GHz, 3.53GHz, and 4.83GHz is 67%, 63%, 54%, 48%, and 38%, respectively. It makes the rectifier make full use of the radio frequency energy in the space and can be widely used in the future.
{"title":"Modeling of Five-Band High efficiency Rectifier for RF Energy Acquisition","authors":"Yang-Hoe Song, Chao-Lung Huang, Zixuan Wang, Jiayi Zhang","doi":"10.1109/ICTech55460.2022.00105","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00105","url":null,"abstract":"As a way of wireless energy collection, radiofrequency energy collection technology is attracting wide attention in academic circles. In the previous research on RF energy collection, many achievements have been made in the 2.4-2.5GHz band. In the field of higher-frequency millimeter waves, there has been corresponding research abroad, but the radiofrequency energy absorption of the millimeter-wave band in China needs to be developed. In the era of the Internet of everything, to obtain RF energy efficiently in the traditional frequency band and the latest 5G band, a five-band rectifier composed of two single series diode rectifiers is designed in this paper. The simulation results show that when the input power level is-20dBm~0dBm, the maximum RF-DC conversion efficiency of the rectifier in 1.9GHz, 3.53GHz, and 4.83GHz is 67%, 63%, 54%, 48%, and 38%, respectively. It makes the rectifier make full use of the radio frequency energy in the space and can be widely used in the future.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"88 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":"115245100","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/ICTech55460.2022.00098
Peng Wang, Juanjuan Li, Hao Wang, Huaizhen Chen, Junjie Cao, Yi Xu, Junyue He
This system used STM32H750XBH6 as the main control, and ART -Pi multimedia expansion board equipped with ILI9488 capacitive touch screen, WM8988 audio chip and GC0328C camera. It realizes recording, recognition, display, imposter capture and telescopic rod connection for door lock control. Based on convolutional neural network (CNN) and STM32 Cube. AI toolkit, voiceprint model was built and deployed to STM32H750XBH6. Combining Mel-Frequency Cepstral Coefficients (MFCC) and DTW algorithm, voice recognition function was realized. Through dual authentication of voiceprint verification and voice recognition, the system guaranteed high security. What is more, the system was equipped with a WIFI module, and the administrator can log in to the Onenet website to view the access control information. If there are three consecutive recognition errors, the system automatically capture the person and save the fake authentication certificate. After several improvements, the system can operate normally. The accuracy rate of voiceprint recognition and voice recognition were 97.83% and 96.00% respectively and the overall accuracy rate was 93.50%. Compared with traditional password access and card access, the system did not have problems of leak and lose. It provided users with high-security, true-intention, low-cost, and weak-privacy authentication services.
{"title":"Intelligent Access Control System Based on Voiceprint and Voice Technology","authors":"Peng Wang, Juanjuan Li, Hao Wang, Huaizhen Chen, Junjie Cao, Yi Xu, Junyue He","doi":"10.1109/ICTech55460.2022.00098","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00098","url":null,"abstract":"This system used STM32H750XBH6 as the main control, and ART -Pi multimedia expansion board equipped with ILI9488 capacitive touch screen, WM8988 audio chip and GC0328C camera. It realizes recording, recognition, display, imposter capture and telescopic rod connection for door lock control. Based on convolutional neural network (CNN) and STM32 Cube. AI toolkit, voiceprint model was built and deployed to STM32H750XBH6. Combining Mel-Frequency Cepstral Coefficients (MFCC) and DTW algorithm, voice recognition function was realized. Through dual authentication of voiceprint verification and voice recognition, the system guaranteed high security. What is more, the system was equipped with a WIFI module, and the administrator can log in to the Onenet website to view the access control information. If there are three consecutive recognition errors, the system automatically capture the person and save the fake authentication certificate. After several improvements, the system can operate normally. The accuracy rate of voiceprint recognition and voice recognition were 97.83% and 96.00% respectively and the overall accuracy rate was 93.50%. Compared with traditional password access and card access, the system did not have problems of leak and lose. It provided users with high-security, true-intention, low-cost, and weak-privacy authentication services.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"37 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":"122845312","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/ICTech55460.2022.00097
Meihong Li, Li Lv, Bihui Yu
According to the application characteristics of wavelet transform to time series, the wavelet coefficients of time series of force in the process of tool use are extracted by wavelet transform as features, fused with support vector regression and back propagation neural network, and applied to tool condition monitoring. Savitzky-Golay convolution smoothing algorithm is added to obtain better experimental results.
{"title":"Tool Condition Monitoring Using Wavelet Analysis with Savitzky-Golay Filter","authors":"Meihong Li, Li Lv, Bihui Yu","doi":"10.1109/ICTech55460.2022.00097","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00097","url":null,"abstract":"According to the application characteristics of wavelet transform to time series, the wavelet coefficients of time series of force in the process of tool use are extracted by wavelet transform as features, fused with support vector regression and back propagation neural network, and applied to tool condition monitoring. Savitzky-Golay convolution smoothing algorithm is added to obtain better experimental results.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"17 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":"121905170","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/ictech55460.2022.00002
{"title":"2022 11th International Conference of Information and Communication Technology ICTech 2022","authors":"","doi":"10.1109/ictech55460.2022.00002","DOIUrl":"https://doi.org/10.1109/ictech55460.2022.00002","url":null,"abstract":"","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"58 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":"117312736","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/ICTech55460.2022.00100
Dawei Fan, Yi Hu, Yanxin Li, Weiran Liu
Temperature can change the chemical composition and internal structure of metals during heat treatment processing, which is the decisive factor affecting the quality of processing devices. Aiming at the trend change of temperature in the process of heat treatment, a state recognition method based on piecewise linear representation of time series is proposed. The method first extracts the turning point according to the angle change of the time series temperature data, then divides the trend segment of the original data by turning point, then uses bottom-Up algorithm to merge the trend segment to obtain the segmented linear representation, trains the SVM classification by the statistical characteristics of the segmented data, and finally obtains the processing state of the heat treatment process. Taking the actual data of a unit heat treatment workshop site as an example, the effectiveness of this method is verified by experimenting with the proposed method.
{"title":"State Recognition Method of Heat Treatment Process Based on PLR","authors":"Dawei Fan, Yi Hu, Yanxin Li, Weiran Liu","doi":"10.1109/ICTech55460.2022.00100","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00100","url":null,"abstract":"Temperature can change the chemical composition and internal structure of metals during heat treatment processing, which is the decisive factor affecting the quality of processing devices. Aiming at the trend change of temperature in the process of heat treatment, a state recognition method based on piecewise linear representation of time series is proposed. The method first extracts the turning point according to the angle change of the time series temperature data, then divides the trend segment of the original data by turning point, then uses bottom-Up algorithm to merge the trend segment to obtain the segmented linear representation, trains the SVM classification by the statistical characteristics of the segmented data, and finally obtains the processing state of the heat treatment process. Taking the actual data of a unit heat treatment workshop site as an example, the effectiveness of this method is verified by experimenting with the proposed method.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"26 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":"128328838","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/ICTech55460.2022.00030
Xinyi Liang
At present, the human society is stepping into the era of the interconnection of everything, every moment there are massive data needs to be transmitted and processed. With the massive growth of data information, people put forward a higher demand for the information processing ability of network, so the photon information processing technology was put forward. Photonic information processing technology refers to the technology of processing optical information directly in the optical domain. It breaks through the bottleneck of bandwidth and rate of traditional electrical information processing, and has become a solution of ultra-high speed information processing. In addition, the latest technology makes quantum information processing technology possible, which provides a promising platform for applications and research in a variety of contexts. This paper begins with photon generation and transitions from photon information processing technology to quantum information processing technology. The purpose of this paper is to provide the reader with a comprehensive review of the field, showing a balance between theoretical and experimental technical results.
{"title":"A Review on The Photonic Quantum Information Processing Technology","authors":"Xinyi Liang","doi":"10.1109/ICTech55460.2022.00030","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00030","url":null,"abstract":"At present, the human society is stepping into the era of the interconnection of everything, every moment there are massive data needs to be transmitted and processed. With the massive growth of data information, people put forward a higher demand for the information processing ability of network, so the photon information processing technology was put forward. Photonic information processing technology refers to the technology of processing optical information directly in the optical domain. It breaks through the bottleneck of bandwidth and rate of traditional electrical information processing, and has become a solution of ultra-high speed information processing. In addition, the latest technology makes quantum information processing technology possible, which provides a promising platform for applications and research in a variety of contexts. This paper begins with photon generation and transitions from photon information processing technology to quantum information processing technology. The purpose of this paper is to provide the reader with a comprehensive review of the field, showing a balance between theoretical and experimental technical results.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"132 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":"128597876","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/ICTech55460.2022.00029
Jingang Yu, Yongkang Hou, Shu Li, Zhifeng Wen
Blockchain is also known as distributed ledger. All full nodes connected to the blockchain network participate in the maintenance of the data in the ledger. It is a technology in many fields such as computer science, cryptography, distributed storage, and finance. Industrial and academic research on blockchain technology has achieved great results, including research on blockchain networks, consensus mechanisms, and smart contracts. However, limited by the data storage mode and the characteristics of distributed storage at the bottom of the blockchain, there are still problems that need to be solved urgently, such as the single retrieval function and the low retrieval rate of the data retrieval on the blockchain. We focused on this problem, and based on the built-in index and external data warehouse method, we proposed a high-speed data retrieval model on blockchain. The model consists of three parts: a blockchain network with improved index storage, a data processing cluster, and application layer services. The new blockchain network improves the organization of transaction data in the traditional blockchain system, and designs a data structure suitable for high-speed retrieval to organize transaction data; the data processing cluster is responsible for ensuring data consistency and in accordance with high efficiency The synchronization strategy is to synchronize the data on the chain to the relational data warehouse under the chain; the application layer service encapsulates the rich query functions supported by the relational database, and finally provides services to the outside in the form of HTTP, RPC, etc. Experimental results show that the model can effectively expand the blockchain system in terms of query efficiency and query functions, improve the query rate of data on the blockchain, and meet people's needs for blockchain query functions.
{"title":"A High-Speed Data Retrieval Model on Blockchain","authors":"Jingang Yu, Yongkang Hou, Shu Li, Zhifeng Wen","doi":"10.1109/ICTech55460.2022.00029","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00029","url":null,"abstract":"Blockchain is also known as distributed ledger. All full nodes connected to the blockchain network participate in the maintenance of the data in the ledger. It is a technology in many fields such as computer science, cryptography, distributed storage, and finance. Industrial and academic research on blockchain technology has achieved great results, including research on blockchain networks, consensus mechanisms, and smart contracts. However, limited by the data storage mode and the characteristics of distributed storage at the bottom of the blockchain, there are still problems that need to be solved urgently, such as the single retrieval function and the low retrieval rate of the data retrieval on the blockchain. We focused on this problem, and based on the built-in index and external data warehouse method, we proposed a high-speed data retrieval model on blockchain. The model consists of three parts: a blockchain network with improved index storage, a data processing cluster, and application layer services. The new blockchain network improves the organization of transaction data in the traditional blockchain system, and designs a data structure suitable for high-speed retrieval to organize transaction data; the data processing cluster is responsible for ensuring data consistency and in accordance with high efficiency The synchronization strategy is to synchronize the data on the chain to the relational data warehouse under the chain; the application layer service encapsulates the rich query functions supported by the relational database, and finally provides services to the outside in the form of HTTP, RPC, etc. Experimental results show that the model can effectively expand the blockchain system in terms of query efficiency and query functions, improve the query rate of data on the blockchain, and meet people's needs for blockchain query functions.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"16 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":"129488015","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/ICTech55460.2022.00099
Weiran Liu, Yi Hu, Dawei Fan
In the industrial production of digital workshops, workers need to wear safety helmets at all times. However, the accuracy of target detection is not high enough due to the characteristics of different light, angle of view, and people easily obstructing each other. To solve this problem, the real-time detection of helmets is realized by improving the YOLOv5 algorithm. The Dahua spherical camera is used to collect the data set, and the network is trained on the self-made data set through manual annotation. Pooling is carried out through softpool, so that it can retain more information of the feature map; meanwhile, improve the network structure of YOLOv5, add a layer of 9*9 feature layer, improve the recognition rate of the detection target, and use the DIoU loss function. According to the experimental results, the following results can be obtained. The average accuracy of the improved YoloV5algorithm in self-made data sets has improved a lot, above 97.3%. which is 4 % higher than the original algorithm, and the target detection speed is also correspondingly improved. It can effectively and real-time detect the wearing of helmets Condition.
{"title":"Safety Helmet Wearing Recognition Based on Improved YOLOv5","authors":"Weiran Liu, Yi Hu, Dawei Fan","doi":"10.1109/ICTech55460.2022.00099","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00099","url":null,"abstract":"In the industrial production of digital workshops, workers need to wear safety helmets at all times. However, the accuracy of target detection is not high enough due to the characteristics of different light, angle of view, and people easily obstructing each other. To solve this problem, the real-time detection of helmets is realized by improving the YOLOv5 algorithm. The Dahua spherical camera is used to collect the data set, and the network is trained on the self-made data set through manual annotation. Pooling is carried out through softpool, so that it can retain more information of the feature map; meanwhile, improve the network structure of YOLOv5, add a layer of 9*9 feature layer, improve the recognition rate of the detection target, and use the DIoU loss function. According to the experimental results, the following results can be obtained. The average accuracy of the improved YoloV5algorithm in self-made data sets has improved a lot, above 97.3%. which is 4 % higher than the original algorithm, and the target detection speed is also correspondingly improved. It can effectively and real-time detect the wearing of helmets Condition.","PeriodicalId":290836,"journal":{"name":"2022 11th International Conference of Information and Communication Technology (ICTech))","volume":"183 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":"121203094","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/ICTech55460.2022.00023
Zailong Tian
With continuous development of artificial intelligence, Natural Language Processing (NLP) has become an emerging research field. As an important branch of NLP, text sentiment analysis has drawn attention from many scholars. At present, the mainstream methods of text sentiment analysis include text sentiment analysis method based on sentiment dictionary, machine learning, deep learning, and mixed strategy. The method based on the sentiment dictionary is no longer commonly used because it requires a lot of manual annotation. Due to traditional machine learning methods cannot perform good classification and prediction of context semantics, but deep learning can solve this problem, more and more researches will adopt a combination of the two methods. By investigating the current research at home and abroad, this paper describes and compares the aforementioned four methods in detail, summarizing their advantages and disadvantages, and proposing possible challenges in future research.
{"title":"Research Methods and Progress of Text Sentiment Analysis Based on Machine Learning","authors":"Zailong Tian","doi":"10.1109/ICTech55460.2022.00023","DOIUrl":"https://doi.org/10.1109/ICTech55460.2022.00023","url":null,"abstract":"With continuous development of artificial intelligence, Natural Language Processing (NLP) has become an emerging research field. As an important branch of NLP, text sentiment analysis has drawn attention from many scholars. At present, the mainstream methods of text sentiment analysis include text sentiment analysis method based on sentiment dictionary, machine learning, deep learning, and mixed strategy. The method based on the sentiment dictionary is no longer commonly used because it requires a lot of manual annotation. Due to traditional machine learning methods cannot perform good classification and prediction of context semantics, but deep learning can solve this problem, more and more researches will adopt a combination of the two methods. By investigating the current research at home and abroad, this paper describes and compares the aforementioned four methods in detail, summarizing their advantages and disadvantages, and proposing possible challenges in future research.","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":"121522912","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：