Pub Date : 2020-10-01DOI: 10.1109/SMDS49396.2020.00010
Yanhong Zhu, Tao Sun, Qin Li, Lu Lu, Xiaodong Duan, Weiyuan Li
Quality of experience (QoE) serves as a direct evaluation of users' experience in mobile video transmission and is critical to ensure good network service. Although many efforts have been made to predict QoE based on network parameters of the user terminal equipment, it is difficult to predict QoE based on Quality of Service (QoS) offered by the network servers. In this paper, a machine learning based QoE evaluation method is proposed to evaluate user QoE in real-time by analyzing the QoS characteristics for mobile video transmission. For this purpose, we construct a large-scale dataset by collecting more than 300 thousand pieces of metrics data with two kinds of key quality indicators (KQIs) describing the QoE and 91 key performance indicators (KPIs) describing the QoS. A two-process feature subset selection (FSS) method consisting of single parameter pre-FSS and multi-parameter FSS is then proposed to find the KPIs related to KQIs. An Extra-Trees model is finally developed to learn the relationships between the KPIs and KQIs. By employing machine learning and data analytics on network data with the data-driven framework, the proposed method can predict the user QoE according to the QoS of network servers. The results prove that our proposed method can outperform other state-of-the-art approaches.
体验质量(Quality of experience, QoE)是对用户移动视频传输体验的直接评价，是保证良好网络服务的关键。虽然基于用户终端设备的网络参数来预测QoE已经做了很多努力，但是基于网络服务器提供的服务质量(QoS)来预测QoE是很困难的。本文通过分析移动视频传输的QoS特性，提出了一种基于机器学习的QoE评价方法，对用户的QoE进行实时评价。为此，我们通过收集30多万条指标数据构建了一个大规模数据集，其中包括描述QoE的两种关键质量指标(kqi)和描述QoS的91种关键绩效指标(kpi)。然后提出了一种由单参数预特征子集选择和多参数特征子集选择组成的两过程特征子集选择(FSS)方法来寻找与kpi相关的kpi。最后建立了一个Extra-Trees模型来学习kpi和kqi之间的关系。该方法在数据驱动框架下对网络数据进行机器学习和数据分析，根据网络服务器的QoS预测用户的QoE。结果证明，我们提出的方法可以优于其他最先进的方法。
{"title":"Machine Learning based User QoE Evaluation for Video Streaming over Mobile Network","authors":"Yanhong Zhu, Tao Sun, Qin Li, Lu Lu, Xiaodong Duan, Weiyuan Li","doi":"10.1109/SMDS49396.2020.00010","DOIUrl":"https://doi.org/10.1109/SMDS49396.2020.00010","url":null,"abstract":"Quality of experience (QoE) serves as a direct evaluation of users' experience in mobile video transmission and is critical to ensure good network service. Although many efforts have been made to predict QoE based on network parameters of the user terminal equipment, it is difficult to predict QoE based on Quality of Service (QoS) offered by the network servers. In this paper, a machine learning based QoE evaluation method is proposed to evaluate user QoE in real-time by analyzing the QoS characteristics for mobile video transmission. For this purpose, we construct a large-scale dataset by collecting more than 300 thousand pieces of metrics data with two kinds of key quality indicators (KQIs) describing the QoE and 91 key performance indicators (KPIs) describing the QoS. A two-process feature subset selection (FSS) method consisting of single parameter pre-FSS and multi-parameter FSS is then proposed to find the KPIs related to KQIs. An Extra-Trees model is finally developed to learn the relationships between the KPIs and KQIs. By employing machine learning and data analytics on network data with the data-driven framework, the proposed method can predict the user QoE according to the QoS of network servers. The results prove that our proposed method can outperform other state-of-the-art approaches.","PeriodicalId":385149,"journal":{"name":"2020 IEEE International Conference on Smart Data Services (SMDS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129777692","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 : 2020-10-01DOI: 10.1109/smds49396.2020.00004
Lixin Gao, Guang Cheng, M. Sapino
Message from the SERVICES 2020 Steering Committee Chair viii Message from the SERVICES 2020 Symposia General Chair ix Welcome Message from Congress 2020 General Chairs x Message from the SERVICES 2020 Program Chairs in Chief xii Message from the SERVICES 2020 Technical Committee Chair on Services Computing of IEEE Computer Society xiii Welcome Message from the SERVICES 2020 Women in Services Computing Symposium Chair xiv Symposium on Women in Services Computing Program xv SERVICES 2020 Steering Committee xvii SERVICES 2020 Program Committee xxi Message from the SMDS 2020 Chairs xxii SMDS 2020 Organizing Committee xxiii
{"title":"2020 IEEE International Conference on Smart Data Services (SMDS) SMDS 2020","authors":"Lixin Gao, Guang Cheng, M. Sapino","doi":"10.1109/smds49396.2020.00004","DOIUrl":"https://doi.org/10.1109/smds49396.2020.00004","url":null,"abstract":"Message from the SERVICES 2020 Steering Committee Chair viii Message from the SERVICES 2020 Symposia General Chair ix Welcome Message from Congress 2020 General Chairs x Message from the SERVICES 2020 Program Chairs in Chief xii Message from the SERVICES 2020 Technical Committee Chair on Services Computing of IEEE Computer Society xiii Welcome Message from the SERVICES 2020 Women in Services Computing Symposium Chair xiv Symposium on Women in Services Computing Program xv SERVICES 2020 Steering Committee xvii SERVICES 2020 Program Committee xxi Message from the SMDS 2020 Chairs xxii SMDS 2020 Organizing Committee xxiii","PeriodicalId":385149,"journal":{"name":"2020 IEEE International Conference on Smart Data Services (SMDS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121168998","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 : 2020-10-01DOI: 10.1109/smds49396.2020.00002
{"title":"2020 IEEE International Conference on Smart Data Services","authors":"","doi":"10.1109/smds49396.2020.00002","DOIUrl":"https://doi.org/10.1109/smds49396.2020.00002","url":null,"abstract":"","PeriodicalId":385149,"journal":{"name":"2020 IEEE International Conference on Smart Data Services (SMDS)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127012848","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 : 2020-10-01DOI: 10.1109/SMDS49396.2020.00017
Zhan Wang, Chunyang Ye, Hui Zhou
Information in social networks plays an important role in many fields such as event detection, disaster warning, etc. However, due to the lack of geographic metadata, the information is often unusable. Therefore, the geolocation using social network data has gradually become a hot research topic. Existing methods mainly use textual contents, and thus poorly exploit the available data, especially the hidden information in the link. To address this issue, we propose two Multiview learning models, M-GAT and M-GCN, based on the Graph Attention and Graph Convolution Network to fuse both the text and link information. By extracting the text features from multiple angles to extend the feature space, our models achieve the best results on the baseline dataset. The visual display of representations collected from a hidden layer illustrates the validity of our models. Experiments on different feature combination show the effectiveness of our proposal.
{"title":"Geolocation using GAT with Multiview Learning","authors":"Zhan Wang, Chunyang Ye, Hui Zhou","doi":"10.1109/SMDS49396.2020.00017","DOIUrl":"https://doi.org/10.1109/SMDS49396.2020.00017","url":null,"abstract":"Information in social networks plays an important role in many fields such as event detection, disaster warning, etc. However, due to the lack of geographic metadata, the information is often unusable. Therefore, the geolocation using social network data has gradually become a hot research topic. Existing methods mainly use textual contents, and thus poorly exploit the available data, especially the hidden information in the link. To address this issue, we propose two Multiview learning models, M-GAT and M-GCN, based on the Graph Attention and Graph Convolution Network to fuse both the text and link information. By extracting the text features from multiple angles to extend the feature space, our models achieve the best results on the baseline dataset. The visual display of representations collected from a hidden layer illustrates the validity of our models. Experiments on different feature combination show the effectiveness of our proposal.","PeriodicalId":385149,"journal":{"name":"2020 IEEE International Conference on Smart Data Services (SMDS)","volume":"158 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134348908","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 : 2020-10-01DOI: 10.1109/smds49396.2020.00001
{"title":"2020 IEEE International Conference on Smart Data Services SMDS 2020","authors":"","doi":"10.1109/smds49396.2020.00001","DOIUrl":"https://doi.org/10.1109/smds49396.2020.00001","url":null,"abstract":"","PeriodicalId":385149,"journal":{"name":"2020 IEEE International Conference on Smart Data Services (SMDS)","volume":"267 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133889737","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 : 2020-10-01DOI: 10.1109/SMDS49396.2020.00015
Chengmin Wu, Lei Chen
Recently, much effort has been paid to relation extraction during the construction of large ontological knowledge bases (KBs). However, most of the traditional relation extraction systems rely on human-annotated data for training, which requires expensive human effort. Therefore, Distant supervision is proposed to assist the creation of large amounts of labeled data. By this method, an existing KB is heuristically aligned to texts, and the alignment data are treated as training data. Nevertheless, the noise in the training data may cause two serious problems. First, the heuristic label alignment may fail and cause the wrong label problem. Second, the existing statistical models are applied to ad-hoc features, and hence perform poorly due to the dynamic features of noisy data. To address these two problems, in this paper, we propose a novel framework for automatic relation extraction from unstructured text corpora. Specifically, to solve the first problem, we propose a fine-grained entity typing technique to filter wrong data by choosing positive entity type pairs and conduct joint instance-type selection over bag of instances. To solve the second problem, instead of directly defining manually crafted features, we propose a deep neural architecture with attention mechanism to automatically learn positive and negative instance features. Extensive experiments on real-world datasets demonstrate that our method outperforms the competitive state-of-the-art techniques in terms of effectiveness.
{"title":"Utber: Utilizing Fine-Grained Entity Types to Relation Extraction with Distant Supervision","authors":"Chengmin Wu, Lei Chen","doi":"10.1109/SMDS49396.2020.00015","DOIUrl":"https://doi.org/10.1109/SMDS49396.2020.00015","url":null,"abstract":"Recently, much effort has been paid to relation extraction during the construction of large ontological knowledge bases (KBs). However, most of the traditional relation extraction systems rely on human-annotated data for training, which requires expensive human effort. Therefore, Distant supervision is proposed to assist the creation of large amounts of labeled data. By this method, an existing KB is heuristically aligned to texts, and the alignment data are treated as training data. Nevertheless, the noise in the training data may cause two serious problems. First, the heuristic label alignment may fail and cause the wrong label problem. Second, the existing statistical models are applied to ad-hoc features, and hence perform poorly due to the dynamic features of noisy data. To address these two problems, in this paper, we propose a novel framework for automatic relation extraction from unstructured text corpora. Specifically, to solve the first problem, we propose a fine-grained entity typing technique to filter wrong data by choosing positive entity type pairs and conduct joint instance-type selection over bag of instances. To solve the second problem, instead of directly defining manually crafted features, we propose a deep neural architecture with attention mechanism to automatically learn positive and negative instance features. Extensive experiments on real-world datasets demonstrate that our method outperforms the competitive state-of-the-art techniques in terms of effectiveness.","PeriodicalId":385149,"journal":{"name":"2020 IEEE International Conference on Smart Data Services (SMDS)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124009023","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 : 2020-10-01DOI: 10.1109/SMDS49396.2020.00020
Jane Lin, Ouri E. Wolfson
This paper describes an information service that personalizes air pollution monitoring by considering the fine grained user location, her microenvironment, and her activity. Personalization is obtained by integrating a large number of information sources including the Environmental Protection Agency (EPA) monitoring stations, traffic, weather, portable air pollution data from sensors carried by a small fraction of the population, smartphone sensors, vehicle sensors data captured via on-board diagnostics.
{"title":"MY-AIR: A Personalized Air-quality Information Service","authors":"Jane Lin, Ouri E. Wolfson","doi":"10.1109/SMDS49396.2020.00020","DOIUrl":"https://doi.org/10.1109/SMDS49396.2020.00020","url":null,"abstract":"This paper describes an information service that personalizes air pollution monitoring by considering the fine grained user location, her microenvironment, and her activity. Personalization is obtained by integrating a large number of information sources including the Environmental Protection Agency (EPA) monitoring stations, traffic, weather, portable air pollution data from sensors carried by a small fraction of the population, smartphone sensors, vehicle sensors data captured via on-board diagnostics.","PeriodicalId":385149,"journal":{"name":"2020 IEEE International Conference on Smart Data Services (SMDS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130799462","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}
It is our great pleasure to welcome you to the 2020 edition of the IEEE World Congress on Services. This year edition represents an important milestone as the Congress is held virtually, although preserving a strong organizational and scientific link to Beijing, where the Congress was scheduled to take place. The success of the Congress recognizes the strong research communities around the world that focus on foundations, systems, methodologies, and applications of computing-based services. This is a field that over the years has evolved and expanded to encompass new areas, including edge computing, IoT, and smart data services.
{"title":"Message from the Program Chairs in Chief","authors":"H. Sato, M. Matskin, W. Claycomb","doi":"10.1109/COMPSAC.2016.14","DOIUrl":"https://doi.org/10.1109/COMPSAC.2016.14","url":null,"abstract":"It is our great pleasure to welcome you to the 2020 edition of the IEEE World Congress on Services. This year edition represents an important milestone as the Congress is held virtually, although preserving a strong organizational and scientific link to Beijing, where the Congress was scheduled to take place. The success of the Congress recognizes the strong research communities around the world that focus on foundations, systems, methodologies, and applications of computing-based services. This is a field that over the years has evolved and expanded to encompass new areas, including edge computing, IoT, and smart data services.","PeriodicalId":385149,"journal":{"name":"2020 IEEE International Conference on Smart Data Services (SMDS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129910392","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 : 2020-10-01DOI: 10.1109/smds49396.2020.00003
{"title":"Copyright","authors":"","doi":"10.1109/smds49396.2020.00003","DOIUrl":"https://doi.org/10.1109/smds49396.2020.00003","url":null,"abstract":"","PeriodicalId":385149,"journal":{"name":"2020 IEEE International Conference on Smart Data Services (SMDS)","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126707433","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 : 2020-10-01DOI: 10.1109/SMDS49396.2020.00016
Pei Guo, Achuna Ofonedu, Jianwu Wang
Causality discovery mines cause-effect relationships among different variables of a system and has been widely used in many disciplines including climatology and neuroscience. To discover causal relationships, many data-driven causality discovery methods, e.g., Granger causality, PCMCI and Dynamic Bayesian Network, have been proposed. Many of these causality discovery approaches mine time series data and generate a directed causality graph where each graph edge denotes a cause-effect relationship between the two connected graph nodes. Our benchmarking of different causality discovery approaches with real-world climate data shows these approaches often generate quite different causality results with the same input dataset due to their internal learning mechanism differences. Meanwhile, there are ever-increasing available data in virtually every discipline, which makes it more and more difficult to use existing causality discovery algorithms to produce causality results within reasonable time. To address these two challenges, this paper utilizes data partitioning and ensemble techniques, and proposes a two-phase hybrid causality ensemble framework. The framework first conducts phase 1 data ensemble for partitioned data and then conducts phase 2 algorithm ensemble from data ensemble results. To achieve scalability, we further parallelize the ensemble approaches via the Spark big data analytics engine. Our experiments show that our proposed approaches achieve good accuracy through ensemble and high scalability through data-parallelization in distributed computing environments.
{"title":"Scalable and Hybrid Ensemble-Based Causality Discovery","authors":"Pei Guo, Achuna Ofonedu, Jianwu Wang","doi":"10.1109/SMDS49396.2020.00016","DOIUrl":"https://doi.org/10.1109/SMDS49396.2020.00016","url":null,"abstract":"Causality discovery mines cause-effect relationships among different variables of a system and has been widely used in many disciplines including climatology and neuroscience. To discover causal relationships, many data-driven causality discovery methods, e.g., Granger causality, PCMCI and Dynamic Bayesian Network, have been proposed. Many of these causality discovery approaches mine time series data and generate a directed causality graph where each graph edge denotes a cause-effect relationship between the two connected graph nodes. Our benchmarking of different causality discovery approaches with real-world climate data shows these approaches often generate quite different causality results with the same input dataset due to their internal learning mechanism differences. Meanwhile, there are ever-increasing available data in virtually every discipline, which makes it more and more difficult to use existing causality discovery algorithms to produce causality results within reasonable time. To address these two challenges, this paper utilizes data partitioning and ensemble techniques, and proposes a two-phase hybrid causality ensemble framework. The framework first conducts phase 1 data ensemble for partitioned data and then conducts phase 2 algorithm ensemble from data ensemble results. To achieve scalability, we further parallelize the ensemble approaches via the Spark big data analytics engine. Our experiments show that our proposed approaches achieve good accuracy through ensemble and high scalability through data-parallelization in distributed computing environments.","PeriodicalId":385149,"journal":{"name":"2020 IEEE International Conference on Smart Data Services (SMDS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121495453","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：