Pub Date : 2020-08-01DOI: 10.1109/ICSS50103.2020.00021
Weiqiang Guo, Zhuofeng Zhao, Zhentao Zheng, Yao Xu
With the widespread application of AIS (Automatic Ship Identification System), ship trajectory data is being collected and becoming increasingly available. Consequently, a lot of ship trajectory data applications have become feasible that mine the value from the data. In this paper, based on massive ship trajectory data, we aim to classify two kinds of ship stay behavior for recognizing different areas in the port, namely berth and anchorage. The traditional trajectory data classification model mainly distinguishes the moving and staying state of moving objects, but there is little research on the classification of different kinds of stay behavior, especially for ship stay behavior classification. In this work, we propose an extraction algorithm based on the cloud storage and distributed computing frameworks to extract classification features by analyzing the behavioral characteristics of ships at berths and anchors. Second, with the consideration of the low precision, drift and sparsity characteristics of ship trajectory data, we design a series of experiments based on ten-fold cross-validation method for evaluating five classical classification models, such as XGBoost, Random Forest and so on. Third, experimental verifications of various classification models are conducted based on a real ship trajectory dataset, and the effectiveness of different models for recognizing ship stay area are compared.
{"title":"A Cloud-based Approach for Ship Stay Behavior Classification using Massive Trajectory Data","authors":"Weiqiang Guo, Zhuofeng Zhao, Zhentao Zheng, Yao Xu","doi":"10.1109/ICSS50103.2020.00021","DOIUrl":"https://doi.org/10.1109/ICSS50103.2020.00021","url":null,"abstract":"With the widespread application of AIS (Automatic Ship Identification System), ship trajectory data is being collected and becoming increasingly available. Consequently, a lot of ship trajectory data applications have become feasible that mine the value from the data. In this paper, based on massive ship trajectory data, we aim to classify two kinds of ship stay behavior for recognizing different areas in the port, namely berth and anchorage. The traditional trajectory data classification model mainly distinguishes the moving and staying state of moving objects, but there is little research on the classification of different kinds of stay behavior, especially for ship stay behavior classification. In this work, we propose an extraction algorithm based on the cloud storage and distributed computing frameworks to extract classification features by analyzing the behavioral characteristics of ships at berths and anchors. Second, with the consideration of the low precision, drift and sparsity characteristics of ship trajectory data, we design a series of experiments based on ten-fold cross-validation method for evaluating five classical classification models, such as XGBoost, Random Forest and so on. Third, experimental verifications of various classification models are conducted based on a real ship trajectory dataset, and the effectiveness of different models for recognizing ship stay area are compared.","PeriodicalId":292795,"journal":{"name":"2020 International Conference on Service Science (ICSS)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127259400","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 : 2020-08-01DOI: 10.1109/icss50103.2020.00005
{"title":"Message from the Program Committee Chairs ICSS 2020","authors":"","doi":"10.1109/icss50103.2020.00005","DOIUrl":"https://doi.org/10.1109/icss50103.2020.00005","url":null,"abstract":"","PeriodicalId":292795,"journal":{"name":"2020 International Conference on Service Science (ICSS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114126798","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 : 2020-08-01DOI: 10.1109/ICSS50103.2020.00010
Shengye Pang, Jianwei Yin, Bangpeng Zheng, Tao Zheng, Qunxi Tian
The deep integration and innovation of cross-over services across the boundaries of different industries, organizations and individuals will provide developers with multidimensional, high-quality and valuable cross-over services, which has become an important innovation approach for the development of modern service industry. With the further development of this trend, services in the form of processes play an increasingly important role in the field of service computing research. However, with the rise of digitization and the escalation of cross-industry, cross-over participants face two tough questions: (l) What kind of service process can solve the complex business we face.(2) How can we access these service processes quickly and conveniently. In this paper, we propose the concept of reference service process to solve the problems above. The reference service process is a normalized cross-over service collaboration paradigm. On the one hand, reference service process of different functional topics can solve most complex businesses, eliminating the need for developers to design service processes. On the other hand, each reference service process establishes a mapping relationship with multiple general service processes, which solves the problem of selection by automatically selecting the optimal service process for developers.
{"title":"Reference Service Process: A Normalized Cross-Over Service Collaboration Paradigm","authors":"Shengye Pang, Jianwei Yin, Bangpeng Zheng, Tao Zheng, Qunxi Tian","doi":"10.1109/ICSS50103.2020.00010","DOIUrl":"https://doi.org/10.1109/ICSS50103.2020.00010","url":null,"abstract":"The deep integration and innovation of cross-over services across the boundaries of different industries, organizations and individuals will provide developers with multidimensional, high-quality and valuable cross-over services, which has become an important innovation approach for the development of modern service industry. With the further development of this trend, services in the form of processes play an increasingly important role in the field of service computing research. However, with the rise of digitization and the escalation of cross-industry, cross-over participants face two tough questions: (l) What kind of service process can solve the complex business we face.(2) How can we access these service processes quickly and conveniently. In this paper, we propose the concept of reference service process to solve the problems above. The reference service process is a normalized cross-over service collaboration paradigm. On the one hand, reference service process of different functional topics can solve most complex businesses, eliminating the need for developers to design service processes. On the other hand, each reference service process establishes a mapping relationship with multiple general service processes, which solves the problem of selection by automatically selecting the optimal service process for developers.","PeriodicalId":292795,"journal":{"name":"2020 International Conference on Service Science (ICSS)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114934533","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 : 2020-08-01DOI: 10.1109/ICSS50103.2020.00031
Chan Liu, T. He, Yingjie Xiong, Huazhen Wang, Jian Chen
The goal of the question-answering (QA) system is to understand the questions from users and return their accurate answers. In the medical field, the question-answering system amis to understand patients' questions and return the correct answers. The existed knowledge base question-answering (KB-QA) systems mainly rely on hand-crafted features and ignore structure information of knowledge base which accordingly lead to the answers with low accuracy. In this paper, a novel KB-QA model is put forward based on knowledge representation and recurrent convolutional neural network. This model has three parts, candidate answers generation, entity relationships extraction and knowledge representation learning based on knowledge base. In addition, an algorithm is also developed to compute the scores of linking candidate answers and knowledge base. Experimental results show that the presented model achieves better performance compared with the baseline systems.
{"title":"A Novel Knowledge Base Question Answering Model Based on Knowledge Representation and Recurrent Convolutional Neural Network","authors":"Chan Liu, T. He, Yingjie Xiong, Huazhen Wang, Jian Chen","doi":"10.1109/ICSS50103.2020.00031","DOIUrl":"https://doi.org/10.1109/ICSS50103.2020.00031","url":null,"abstract":"The goal of the question-answering (QA) system is to understand the questions from users and return their accurate answers. In the medical field, the question-answering system amis to understand patients' questions and return the correct answers. The existed knowledge base question-answering (KB-QA) systems mainly rely on hand-crafted features and ignore structure information of knowledge base which accordingly lead to the answers with low accuracy. In this paper, a novel KB-QA model is put forward based on knowledge representation and recurrent convolutional neural network. This model has three parts, candidate answers generation, entity relationships extraction and knowledge representation learning based on knowledge base. In addition, an algorithm is also developed to compute the scores of linking candidate answers and knowledge base. Experimental results show that the presented model achieves better performance compared with the baseline systems.","PeriodicalId":292795,"journal":{"name":"2020 International Conference on Service Science (ICSS)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123452380","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 : 2020-08-01DOI: 10.1109/ICSS50103.2020.00020
Min Liu, Tonghua Su, Zhiying Tu, Zhongjie Wang
Ever since smart speakers became popular, the functions that can help users complete a series of tasks through voice interaction are called “skills”. The market integrates all “skills” is called “skill market”. There is a serious imbalance in the distribution of hot spots and user concerns in the skill market, and the research on the distribution of user needs satisfied by skills and points of interest(POI) that users pay attention to is insufficient. User needs and POIs are contained in unstructured data, in order to analyze the distribution of user needs and POIs from unstructured data, this paper conducted an empirical study that used the BERT multi-label classification model to extract the user needs that meets the Maslow's hierarchy of needs from the skill description, and used RAKE algorithm to extract user POIs from user reviews and used knowledge graph to extract the relationships between POIs. Using the analysis results of the extracted data, the paper gives suggestions related to the development direction and POIs that should pay attention to in development for skill developers.
{"title":"Empirical Study on the Skill Market of Virtual Personal Assistants (VPA)","authors":"Min Liu, Tonghua Su, Zhiying Tu, Zhongjie Wang","doi":"10.1109/ICSS50103.2020.00020","DOIUrl":"https://doi.org/10.1109/ICSS50103.2020.00020","url":null,"abstract":"Ever since smart speakers became popular, the functions that can help users complete a series of tasks through voice interaction are called “skills”. The market integrates all “skills” is called “skill market”. There is a serious imbalance in the distribution of hot spots and user concerns in the skill market, and the research on the distribution of user needs satisfied by skills and points of interest(POI) that users pay attention to is insufficient. User needs and POIs are contained in unstructured data, in order to analyze the distribution of user needs and POIs from unstructured data, this paper conducted an empirical study that used the BERT multi-label classification model to extract the user needs that meets the Maslow's hierarchy of needs from the skill description, and used RAKE algorithm to extract user POIs from user reviews and used knowledge graph to extract the relationships between POIs. Using the analysis results of the extracted data, the paper gives suggestions related to the development direction and POIs that should pay attention to in development for skill developers.","PeriodicalId":292795,"journal":{"name":"2020 International Conference on Service Science (ICSS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122697498","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 : 2020-08-01DOI: 10.1109/ICSS50103.2020.00017
Zhuohao Wang, Dongju Yang, Hanshuo Zhang
The key problem in the fine management of science and technology is to model the behavior characteristics of scientific and technical personnel and then find groups through various related cooperative relationships. Aiming at the analysis of team relationship of scientific and technical personnel data, this paper proposed a method to recognize the group of scientific and technological personnel based on relational graph. The relationship model of scientific and technological personnel was designed, and based on this, the relational graph was constructed with the relationship identification and extraction from source data. A frequent item mining algorithm based on Hadoop was proposed, which enabled getting the group of scientific and technological personnel by mining and analysis of data in relational graph. In this paper, the proposed method was experimented on both open and private data sets, and compared with several classical algorithms. The results showed that the method proposed in this paper has a significant improvement in execution efficiency.
{"title":"A Group Recognition Method of Scientific and Technological Personnel based on Relational Graph","authors":"Zhuohao Wang, Dongju Yang, Hanshuo Zhang","doi":"10.1109/ICSS50103.2020.00017","DOIUrl":"https://doi.org/10.1109/ICSS50103.2020.00017","url":null,"abstract":"The key problem in the fine management of science and technology is to model the behavior characteristics of scientific and technical personnel and then find groups through various related cooperative relationships. Aiming at the analysis of team relationship of scientific and technical personnel data, this paper proposed a method to recognize the group of scientific and technological personnel based on relational graph. The relationship model of scientific and technological personnel was designed, and based on this, the relational graph was constructed with the relationship identification and extraction from source data. A frequent item mining algorithm based on Hadoop was proposed, which enabled getting the group of scientific and technological personnel by mining and analysis of data in relational graph. In this paper, the proposed method was experimented on both open and private data sets, and compared with several classical algorithms. The results showed that the method proposed in this paper has a significant improvement in execution efficiency.","PeriodicalId":292795,"journal":{"name":"2020 International Conference on Service Science (ICSS)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124995641","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 : 2020-08-01DOI: 10.1109/ICSS50103.2020.00025
Xuequan Zhou, Chunshan Li, Hua Zhang, F. Meng, Dianhui Chu
Typically, a service platform of SaaS provides a specific domain of application services for tenants having the same or similar business needs, such as enterprise resource planning, customer relationship management or warehouse management, etc. Tenants customize and use application services in the SaaS platform according to their own business requirements and quality of service (QoS), and to achieve the targets of low-cost, on-demand, and rapid deployment. To meet the requirements of multi-tenant SaaS application customization, we analyze the related concepts and issues involved in tenants' application customization from service integration perspective and QoS perspective. Then we proposed a feature tree and dynamic QoS based model for multi-tenant SaaS application. The feature tree is used to decompose the fuzzy tenants' requirements and construction integrate rules to gather scattered services on SaaS platform. Dynamic QoS supports tenants to customize their applications' functions and service quality. Finally, to demonstrate the effectiveness of the model, this paper run a customization process of SaaS application on the case of warehouse management system in the field of logistics distribution.
{"title":"A Feature Tree and Dynamic QoS based Service Integration and Customization Model for Multi-tenant SaaS Application","authors":"Xuequan Zhou, Chunshan Li, Hua Zhang, F. Meng, Dianhui Chu","doi":"10.1109/ICSS50103.2020.00025","DOIUrl":"https://doi.org/10.1109/ICSS50103.2020.00025","url":null,"abstract":"Typically, a service platform of SaaS provides a specific domain of application services for tenants having the same or similar business needs, such as enterprise resource planning, customer relationship management or warehouse management, etc. Tenants customize and use application services in the SaaS platform according to their own business requirements and quality of service (QoS), and to achieve the targets of low-cost, on-demand, and rapid deployment. To meet the requirements of multi-tenant SaaS application customization, we analyze the related concepts and issues involved in tenants' application customization from service integration perspective and QoS perspective. Then we proposed a feature tree and dynamic QoS based model for multi-tenant SaaS application. The feature tree is used to decompose the fuzzy tenants' requirements and construction integrate rules to gather scattered services on SaaS platform. Dynamic QoS supports tenants to customize their applications' functions and service quality. Finally, to demonstrate the effectiveness of the model, this paper run a customization process of SaaS application on the case of warehouse management system in the field of logistics distribution.","PeriodicalId":292795,"journal":{"name":"2020 International Conference on Service Science (ICSS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126764719","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 : 2020-08-01DOI: 10.1109/ICSS50103.2020.00030
Yaoming Yue, Xueliang Fu
The research of blockchain technology in the field of supply chain management has received extensive attention, but the research results and decision-making model of the perfect blockchain technology to solve the supervision of medical equipment supply chain have not yet been formed. This research analyzes and designs a full life cycle supply chain management method for medical equipment based on blockchain technology. A medical equipment supply chain supervision model based on blockchain technology was constructed, and a medical equipment supply chain supervision system based on blockchain technology was formed based on the full life cycle supply chain management model. Combining full life cycle theory with blockchain technology, a medical equipment management information system covering the entire process of production, supply, tendering, procurement, storage, application, export, use, destruction, and traceability of medical equipment was designed.
{"title":"Research on Medical Equipment Supply Chain Management Method Based on Blockchain Technology","authors":"Yaoming Yue, Xueliang Fu","doi":"10.1109/ICSS50103.2020.00030","DOIUrl":"https://doi.org/10.1109/ICSS50103.2020.00030","url":null,"abstract":"The research of blockchain technology in the field of supply chain management has received extensive attention, but the research results and decision-making model of the perfect blockchain technology to solve the supervision of medical equipment supply chain have not yet been formed. This research analyzes and designs a full life cycle supply chain management method for medical equipment based on blockchain technology. A medical equipment supply chain supervision model based on blockchain technology was constructed, and a medical equipment supply chain supervision system based on blockchain technology was formed based on the full life cycle supply chain management model. Combining full life cycle theory with blockchain technology, a medical equipment management information system covering the entire process of production, supply, tendering, procurement, storage, application, export, use, destruction, and traceability of medical equipment was designed.","PeriodicalId":292795,"journal":{"name":"2020 International Conference on Service Science (ICSS)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126782541","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 : 2020-08-01DOI: 10.1109/icss50103.2020.00004
Zhongjie Wang, Xiao Wang, Lanshun Nie, Xiaofei Xu Harbin
{"title":"2020 International Conference on Service Science (ICSS) ICSS 2020","authors":"Zhongjie Wang, Xiao Wang, Lanshun Nie, Xiaofei Xu Harbin","doi":"10.1109/icss50103.2020.00004","DOIUrl":"https://doi.org/10.1109/icss50103.2020.00004","url":null,"abstract":"","PeriodicalId":292795,"journal":{"name":"2020 International Conference on Service Science (ICSS)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133631930","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 : 2020-08-01DOI: 10.1109/ICSS50103.2020.00019
Hongyu Jiang, Chunyang Ye, X. Deng, Haoran Hu, Hui Zhou
The development of intelligent transportation systems usually needs to predict the traffic conditions under a large data volume. Existing approaches usually use a single source of data and the impacts of the neighborhood road sections are not concerned. As a result, their prediction accuracy is usually compromised. To address this issue, we propose a recurrent neural network to predict the road conditions simultaneously concerning the information of multiple road sections at the same time. By perceiving the connectivity between multiple road sections and capturing their mutual influence, our model can significantly improve the prediction accuracy. The experiments based on two real-life dataset shows that our model outperforms the baseline model.
{"title":"Deep Learning for Short-term Traffic Conditions Prediction","authors":"Hongyu Jiang, Chunyang Ye, X. Deng, Haoran Hu, Hui Zhou","doi":"10.1109/ICSS50103.2020.00019","DOIUrl":"https://doi.org/10.1109/ICSS50103.2020.00019","url":null,"abstract":"The development of intelligent transportation systems usually needs to predict the traffic conditions under a large data volume. Existing approaches usually use a single source of data and the impacts of the neighborhood road sections are not concerned. As a result, their prediction accuracy is usually compromised. To address this issue, we propose a recurrent neural network to predict the road conditions simultaneously concerning the information of multiple road sections at the same time. By perceiving the connectivity between multiple road sections and capturing their mutual influence, our model can significantly improve the prediction accuracy. The experiments based on two real-life dataset shows that our model outperforms the baseline model.","PeriodicalId":292795,"journal":{"name":"2020 International Conference on Service Science (ICSS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129288676","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：