Pub Date : 2021-07-01DOI: 10.1109/ICNISC54316.2021.00086
X. Ye, Yanmei Wang, Zhichun Jia
For web services, QoS (Quality of Service, quality of service) is an important indicator for judging whether a web service is efficient. How to better predict the QoS value of the service to make appropriate service recommendations is the entire recommendation system and Issues that are being discussed in the service forecasting academia. At the same time, the timeliness and time relevance of QoS values are also affecting the prediction accuracy of Web services. A large amount of QoS data has potentially time-related attributes. This provides a new inspiration and thinking for service forecasting. Add the time characteristics of the data to the learning of the predictive model. Inspired by these factors, this paper proposes a deep neural network combination model that is sensitive to the time characteristics of QoS. At the same time, based on the final experimental results, the model proposed in this paper has obvious effects on the prediction of QoS values with time attributes.
对于web服务来说，QoS (Quality of Service，服务质量)是判断web服务是否高效的重要指标。如何更好地预测服务的QoS值，做出合适的服务推荐，是整个推荐系统和服务预测学术界正在讨论的问题。同时，QoS值的时效性和时间相关性也影响着Web服务的预测精度。大量的QoS数据具有潜在的时间相关属性。这为服务预测提供了新的启示和思路。将数据的时间特征加入到预测模型的学习中。受这些因素的启发，本文提出了一种对QoS时间特性敏感的深度神经网络组合模型。同时，根据最终的实验结果，本文提出的模型对具有时间属性的QoS值的预测效果明显。
{"title":"Web Service Quality Prediction Method Based on Recurrent Neural Network","authors":"X. Ye, Yanmei Wang, Zhichun Jia","doi":"10.1109/ICNISC54316.2021.00086","DOIUrl":"https://doi.org/10.1109/ICNISC54316.2021.00086","url":null,"abstract":"For web services, QoS (Quality of Service, quality of service) is an important indicator for judging whether a web service is efficient. How to better predict the QoS value of the service to make appropriate service recommendations is the entire recommendation system and Issues that are being discussed in the service forecasting academia. At the same time, the timeliness and time relevance of QoS values are also affecting the prediction accuracy of Web services. A large amount of QoS data has potentially time-related attributes. This provides a new inspiration and thinking for service forecasting. Add the time characteristics of the data to the learning of the predictive model. Inspired by these factors, this paper proposes a deep neural network combination model that is sensitive to the time characteristics of QoS. At the same time, based on the final experimental results, the model proposed in this paper has obvious effects on the prediction of QoS values with time attributes.","PeriodicalId":396802,"journal":{"name":"2021 7th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130633608","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 : 2021-07-01DOI: 10.1109/ICNISC54316.2021.00127
Quchao Cheng, Jiaojie Li, Guochao Shen, Qingmin Du
In this paper, a digital image soil analysis model based on machine learning is established.According to the mean value of HSV and image foreground, two algorithms, MLP and SVM, were used to predict the drug content in the same soil, which proved the accuracy of image analysis by MLP network and support vector machine. Drug content detection by image can be applied to land management, which provides a new idea and effective reference for comprehensive soil analysis in many aspects.
{"title":"Digital Image Soil Analysis based on Machine Learning","authors":"Quchao Cheng, Jiaojie Li, Guochao Shen, Qingmin Du","doi":"10.1109/ICNISC54316.2021.00127","DOIUrl":"https://doi.org/10.1109/ICNISC54316.2021.00127","url":null,"abstract":"In this paper, a digital image soil analysis model based on machine learning is established.According to the mean value of HSV and image foreground, two algorithms, MLP and SVM, were used to predict the drug content in the same soil, which proved the accuracy of image analysis by MLP network and support vector machine. Drug content detection by image can be applied to land management, which provides a new idea and effective reference for comprehensive soil analysis in many aspects.","PeriodicalId":396802,"journal":{"name":"2021 7th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130997449","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 : 2021-07-01DOI: 10.1109/ICNISC54316.2021.00083
Lei Liang, Xiaolei Zhou
With the booming development of social media, many people use social software to share their life experiences and express their opinions, viewpoints and experiences on social hot spots, thus forming a huge amount of information. This paper takes microblog topic comments as the research object and makes visual analysis of microblog comments from the perspective of emotional orientation, which is of great research significance for relevant departments to timely grasp the changes in the masses' thoughts and timely control and deal with emergencies. In this study, the Bert-LSTM model was used for sentiment classification of microblog comments, and the complex and sparse data sets were visualized to convert the disordered data signals into graphic representations. Through in-depth emotional mining of public opinion comments, the importance and effectiveness of online public opinion analysis in the era of data explosion are verified.
{"title":"Research on Public Sentiment of Weibo Topics Based on Emotional Tendency-Taking “LaBiXiaoQiu Was Detained” as an Example","authors":"Lei Liang, Xiaolei Zhou","doi":"10.1109/ICNISC54316.2021.00083","DOIUrl":"https://doi.org/10.1109/ICNISC54316.2021.00083","url":null,"abstract":"With the booming development of social media, many people use social software to share their life experiences and express their opinions, viewpoints and experiences on social hot spots, thus forming a huge amount of information. This paper takes microblog topic comments as the research object and makes visual analysis of microblog comments from the perspective of emotional orientation, which is of great research significance for relevant departments to timely grasp the changes in the masses' thoughts and timely control and deal with emergencies. In this study, the Bert-LSTM model was used for sentiment classification of microblog comments, and the complex and sparse data sets were visualized to convert the disordered data signals into graphic representations. Through in-depth emotional mining of public opinion comments, the importance and effectiveness of online public opinion analysis in the era of data explosion are verified.","PeriodicalId":396802,"journal":{"name":"2021 7th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128135165","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 : 2021-07-01DOI: 10.1109/ICNISC54316.2021.00053
Zoubaydat Dahirou, Mao Zheng
Recently, the field of artificial intelligence has seen many advances thanks to deep learning and image processing. It is now possible to recognize images or even find objects inside an image with a standard GPU. Image processing is a recent science that aims to provide specialists from different areas, as to the general public, tools for manipulating these digital data from the real world. The detection of moving objects is a crucial step for systems based on image processing. The movements detected by the classic algorithms are not necessarily interesting for a thorough information search, and the need to distinguish the coherent movements of parasitic movements exists in most cases. In this paper we are going to use a simply webcam and YOLO algorithm for this implementation. The YOLOv3 (Version 3) model makes predictions with a single network evaluation, making this method extremely fast, running in real time with a capable GPU. From there we'll use OpenCV, Python, and deep learning to apply the YOLOv3 object to images and apply YOLOv3 to video streams.
{"title":"Motion Detection and Object Detection: Yolo (You Only Look Once)","authors":"Zoubaydat Dahirou, Mao Zheng","doi":"10.1109/ICNISC54316.2021.00053","DOIUrl":"https://doi.org/10.1109/ICNISC54316.2021.00053","url":null,"abstract":"Recently, the field of artificial intelligence has seen many advances thanks to deep learning and image processing. It is now possible to recognize images or even find objects inside an image with a standard GPU. Image processing is a recent science that aims to provide specialists from different areas, as to the general public, tools for manipulating these digital data from the real world. The detection of moving objects is a crucial step for systems based on image processing. The movements detected by the classic algorithms are not necessarily interesting for a thorough information search, and the need to distinguish the coherent movements of parasitic movements exists in most cases. In this paper we are going to use a simply webcam and YOLO algorithm for this implementation. The YOLOv3 (Version 3) model makes predictions with a single network evaluation, making this method extremely fast, running in real time with a capable GPU. From there we'll use OpenCV, Python, and deep learning to apply the YOLOv3 object to images and apply YOLOv3 to video streams.","PeriodicalId":396802,"journal":{"name":"2021 7th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128414131","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 : 2021-07-01DOI: 10.1109/ICNISC54316.2021.00153
Na Gong, Haiyan Fu, Chi Gong
In recent years, the promotion of smart tourism has not only improved the level of information technology in tourist destinations, but also brought various conveniences to self-service tourists to a certain extent. However, the improvement of self-service tourists' satisfaction with the tourist destination experience has not been obvious. This article analyzes the influencing factors between self-service tourists' satisfaction with the authenticity of tourist destinations and the data information of smart tourism platforms from the perspective of tourist perception in the development of big data modernization. It is found that first, the incomplete information on the smart tourism platform reduces the authenticity of experience of self-service tourists; second, the lack of innovation in smart tourism information platforms affects the authenticity of tourist destinations; last, there is a conflict between the limitations of cultural resources and the perception of the perception of authenticity, and so on. The satisfaction of college students majoring in tourism from the place of origin and the local perception provides suggestions for the development of smart tourism, and is expected to play a corresponding guiding role in the development of tourist destinations. Therefore, it is proposed to provide sustainable and thorough suggestions for the development of smart tourism by utilizing the perception of satisfaction of tourism major students and residents from the local region, which can be expected that it can play a corresponding guiding role for the development of tourism destinations.
{"title":"A Research on the Perception of Authenticity of Self-service Tourists Based on the Background of Smart Tourism","authors":"Na Gong, Haiyan Fu, Chi Gong","doi":"10.1109/ICNISC54316.2021.00153","DOIUrl":"https://doi.org/10.1109/ICNISC54316.2021.00153","url":null,"abstract":"In recent years, the promotion of smart tourism has not only improved the level of information technology in tourist destinations, but also brought various conveniences to self-service tourists to a certain extent. However, the improvement of self-service tourists' satisfaction with the tourist destination experience has not been obvious. This article analyzes the influencing factors between self-service tourists' satisfaction with the authenticity of tourist destinations and the data information of smart tourism platforms from the perspective of tourist perception in the development of big data modernization. It is found that first, the incomplete information on the smart tourism platform reduces the authenticity of experience of self-service tourists; second, the lack of innovation in smart tourism information platforms affects the authenticity of tourist destinations; last, there is a conflict between the limitations of cultural resources and the perception of the perception of authenticity, and so on. The satisfaction of college students majoring in tourism from the place of origin and the local perception provides suggestions for the development of smart tourism, and is expected to play a corresponding guiding role in the development of tourist destinations. Therefore, it is proposed to provide sustainable and thorough suggestions for the development of smart tourism by utilizing the perception of satisfaction of tourism major students and residents from the local region, which can be expected that it can play a corresponding guiding role for the development of tourism destinations.","PeriodicalId":396802,"journal":{"name":"2021 7th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134350649","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 : 2021-07-01DOI: 10.1109/ICNISC54316.2021.00182
Pengfei Shen, Luke Yan, Yanan Xu, Jiaqing Wu, Ting Cai
The continuous breakthrough of deep learning model in image processing, natural language processing and other fields is mainly due to the strong ability of deep neural network in feature extraction. Based on the idea of capsule neural network, this paper proposes a capsule neural network for general classification problems, and explores the learning ability of capsule network model for classification problems of discrete feature. In order to evaluate the capsule network model, this paper verifies the effect of the model on real datasets, and makes a comparative analysis with common machine learning classification algorithms.
{"title":"Explore the Performance of Capsule Neural Network Learning Discrete Features","authors":"Pengfei Shen, Luke Yan, Yanan Xu, Jiaqing Wu, Ting Cai","doi":"10.1109/ICNISC54316.2021.00182","DOIUrl":"https://doi.org/10.1109/ICNISC54316.2021.00182","url":null,"abstract":"The continuous breakthrough of deep learning model in image processing, natural language processing and other fields is mainly due to the strong ability of deep neural network in feature extraction. Based on the idea of capsule neural network, this paper proposes a capsule neural network for general classification problems, and explores the learning ability of capsule network model for classification problems of discrete feature. In order to evaluate the capsule network model, this paper verifies the effect of the model on real datasets, and makes a comparative analysis with common machine learning classification algorithms.","PeriodicalId":396802,"journal":{"name":"2021 7th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114055008","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 : 2021-07-01DOI: 10.1109/ICNISC54316.2021.00162
Yinghui Wu, Ranran Guo
With the development of information technology, the traditional teaching model has emerged problems such as simply imparting knowledge and failing to meet students' personalized learning. Big data technology will provide richer learning resources, teaching methods and learning styles to drive new changes in education. In the era of big data, the blended teaching mode makes full use of the information-based teaching platform to break the drawbacks of the traditional teaching mode, which is of great value and significance to the reform of China's teaching mode. This paper will explore the specific application of blended teaching based on Chaoxing in practical teaching. As a blended teaching platform and analysis tool, Chaoxing can not only grasp students' learning in time and accurately complete learning evaluation, but also optimize teaching design and expand the time and space for teaching and learning. on this basis, this paper also proposes the application strategies of blended teaching mode such as increasing the strength and depth of integration of information technology and curriculum teaching in the era of big data to realize resource integration and make full use of information technology, strengthening teacher training and enhancing information technology application ability, so as to improve the quality of classroom teaching.
{"title":"Research on the Application and Practice of Blended Teaching Mode in Big Data Era","authors":"Yinghui Wu, Ranran Guo","doi":"10.1109/ICNISC54316.2021.00162","DOIUrl":"https://doi.org/10.1109/ICNISC54316.2021.00162","url":null,"abstract":"With the development of information technology, the traditional teaching model has emerged problems such as simply imparting knowledge and failing to meet students' personalized learning. Big data technology will provide richer learning resources, teaching methods and learning styles to drive new changes in education. In the era of big data, the blended teaching mode makes full use of the information-based teaching platform to break the drawbacks of the traditional teaching mode, which is of great value and significance to the reform of China's teaching mode. This paper will explore the specific application of blended teaching based on Chaoxing in practical teaching. As a blended teaching platform and analysis tool, Chaoxing can not only grasp students' learning in time and accurately complete learning evaluation, but also optimize teaching design and expand the time and space for teaching and learning. on this basis, this paper also proposes the application strategies of blended teaching mode such as increasing the strength and depth of integration of information technology and curriculum teaching in the era of big data to realize resource integration and make full use of information technology, strengthening teacher training and enhancing information technology application ability, so as to improve the quality of classroom teaching.","PeriodicalId":396802,"journal":{"name":"2021 7th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127812149","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 : 2021-07-01DOI: 10.1109/ICNISC54316.2021.00126
Qingbing Ji, Xiaoyan Deng, Lulin Ni
Shadowsocks (SS) is a new popular anonymous communication software in recent years. The traffic generated by SS is very difficult to identify. There is also an enhanced version of SS, called ShadowsocksR(SSR), which can disguise SS traffic as traditional protocol traffic, such as HTTP traffic, TLS traffic, etc. This makes the identification of SS traffic more difficult. In reference [16], an identification method of HTTP camouflaging traffic of SS is proposed for the first time. Here, a new identification method is proposed based on dart algorithm. Compared with reference [16], this method has more types and wider range of SSR obfuscated traffic, and has better identification effect for recent SSR obfuscated traffic, with the accuracy, the recall and the precision are all above 98.5%.
{"title":"Research on ShadowsocksR Traffic Identification Based on DART Algorithm","authors":"Qingbing Ji, Xiaoyan Deng, Lulin Ni","doi":"10.1109/ICNISC54316.2021.00126","DOIUrl":"https://doi.org/10.1109/ICNISC54316.2021.00126","url":null,"abstract":"Shadowsocks (SS) is a new popular anonymous communication software in recent years. The traffic generated by SS is very difficult to identify. There is also an enhanced version of SS, called ShadowsocksR(SSR), which can disguise SS traffic as traditional protocol traffic, such as HTTP traffic, TLS traffic, etc. This makes the identification of SS traffic more difficult. In reference [16], an identification method of HTTP camouflaging traffic of SS is proposed for the first time. Here, a new identification method is proposed based on dart algorithm. Compared with reference [16], this method has more types and wider range of SSR obfuscated traffic, and has better identification effect for recent SSR obfuscated traffic, with the accuracy, the recall and the precision are all above 98.5%.","PeriodicalId":396802,"journal":{"name":"2021 7th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"303 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121154933","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 : 2021-07-01DOI: 10.1109/ICNISC54316.2021.00130
Lei Shao, Heyong Yuan, Xinfeng Wang, Wengang Liu, Qiao Zhang
Aiming at the problem of large deformation and soft fracture of soft rock in deep roadway, through theoretical analysis of deformation and failure characteristics of surrounding rock of deep roadway, the space-time evolution law of deformation and failure of surrounding rock of deep soft rock roadway is obtained by FLAC3D software simulation. The results show that: The deformation of surrounding rock in deep soft rock roadway is characterized by roof subsidence, two sides moving inward and floor bulging. Under the action of high stress, the deformation of surrounding rock of soft rock roadway has a certain timeliness. The deformation and failure of surrounding rock of roadway is a changing process with time. The damage degree of roof, floor and two sides of roadway increases with time, and finally tends to a stable state. The deformation presents a distribution law that the de-formation of floor is larger than that of roof and convergence of two sides.
{"title":"Study on Failure Law of Deformation and Instability of Surrounding Rock in Deep Soft Rock Roadway","authors":"Lei Shao, Heyong Yuan, Xinfeng Wang, Wengang Liu, Qiao Zhang","doi":"10.1109/ICNISC54316.2021.00130","DOIUrl":"https://doi.org/10.1109/ICNISC54316.2021.00130","url":null,"abstract":"Aiming at the problem of large deformation and soft fracture of soft rock in deep roadway, through theoretical analysis of deformation and failure characteristics of surrounding rock of deep roadway, the space-time evolution law of deformation and failure of surrounding rock of deep soft rock roadway is obtained by FLAC3D software simulation. The results show that: The deformation of surrounding rock in deep soft rock roadway is characterized by roof subsidence, two sides moving inward and floor bulging. Under the action of high stress, the deformation of surrounding rock of soft rock roadway has a certain timeliness. The deformation and failure of surrounding rock of roadway is a changing process with time. The damage degree of roof, floor and two sides of roadway increases with time, and finally tends to a stable state. The deformation presents a distribution law that the de-formation of floor is larger than that of roof and convergence of two sides.","PeriodicalId":396802,"journal":{"name":"2021 7th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"12 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115965495","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 : 2021-07-01DOI: 10.1109/ICNISC54316.2021.00183
Kaiwen Zhang, Zhiyang Yu, Liqin Qu
Sea state classification plays the important role in maritime safety, management of marine resources, and dynamic monitoring of sea areas. In this study, ResNetl52 model is used for sea states images classification. The data used in this research is the video data provided by the camera installed on the research vessel Dong Fang Hong III of Ocean University of China. The sea states are divided into ten categories according to the driving conditions of the ship and the undulating conditions of the sea. The results show that this method can classify the images of sea states effectively. This method has implications for follow-up studies of sea states, it can provide the basis for classification for the data processing of self-contained optical measuring instruments.
{"title":"Application of Deep Learning in Sea States Images Classification","authors":"Kaiwen Zhang, Zhiyang Yu, Liqin Qu","doi":"10.1109/ICNISC54316.2021.00183","DOIUrl":"https://doi.org/10.1109/ICNISC54316.2021.00183","url":null,"abstract":"Sea state classification plays the important role in maritime safety, management of marine resources, and dynamic monitoring of sea areas. In this study, ResNetl52 model is used for sea states images classification. The data used in this research is the video data provided by the camera installed on the research vessel Dong Fang Hong III of Ocean University of China. The sea states are divided into ten categories according to the driving conditions of the ship and the undulating conditions of the sea. The results show that this method can classify the images of sea states effectively. This method has implications for follow-up studies of sea states, it can provide the basis for classification for the data processing of self-contained optical measuring instruments.","PeriodicalId":396802,"journal":{"name":"2021 7th Annual International Conference on Network and Information Systems for Computers (ICNISC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114543201","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：