Pub Date : 2016-09-01DOI: 10.1109/ICDIM.2016.7829783
Peron R. de Sousa, Antonio A. Rocha, S. C. D. Lucena, Morganna C. Diniz, D. Menasché
In P2P video streaming systems, the neighbor selection algorithm is one of the fundamental components that affects performance. Although a few neighbor selection methodologies have been proposed, none of them takes into consideration QoE metrics reported by peers as a parameter for decisions. In this work, we present a new metric that quantifies the QoE as a function of the number of absences of pieces of a video during playback, referred to as stress level. A peer is stable if its stress level remains constant over a certain interval of time. Then, we propose a new neighbor selection algorithm for P2P streaming. The algorithm promotes exchanges of lists of stable peers, in order to get shorter download times and minimum interruption during video playback. The performance results show that our proposal is competitive against other state-of-the-art algorithms, reducing the number of absences of video pieces during playback by at least 19% and the average stress level by up to 32%.
{"title":"S4Q: Searching for QoE in P2P streaming neighborhoods","authors":"Peron R. de Sousa, Antonio A. Rocha, S. C. D. Lucena, Morganna C. Diniz, D. Menasché","doi":"10.1109/ICDIM.2016.7829783","DOIUrl":"https://doi.org/10.1109/ICDIM.2016.7829783","url":null,"abstract":"In P2P video streaming systems, the neighbor selection algorithm is one of the fundamental components that affects performance. Although a few neighbor selection methodologies have been proposed, none of them takes into consideration QoE metrics reported by peers as a parameter for decisions. In this work, we present a new metric that quantifies the QoE as a function of the number of absences of pieces of a video during playback, referred to as stress level. A peer is stable if its stress level remains constant over a certain interval of time. Then, we propose a new neighbor selection algorithm for P2P streaming. The algorithm promotes exchanges of lists of stable peers, in order to get shorter download times and minimum interruption during video playback. The performance results show that our proposal is competitive against other state-of-the-art algorithms, reducing the number of absences of video pieces during playback by at least 19% and the average stress level by up to 32%.","PeriodicalId":146662,"journal":{"name":"2016 Eleventh International Conference on Digital Information Management (ICDIM)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125344547","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 : 2016-09-01DOI: 10.1109/ICDIM.2016.7829774
Daiki Matsuoka, Manabu Ohta, A. Takasu, J. Adachi
Metadata such as bibliographic information about documents are indispensable in the effective use of digital libraries. In particular, the reference fields of academic papers contain much bibliographic information such as authors' names and document titles. We are therefore developing a method for automatically extracting bibliographic information from reference strings using a conditional random field (CRF). The features used by the CRF determine the accuracy of this method. We examine effective features for accurate extraction by experimentally changing the features used. The experiments showed that lexical features were quite effective in accurate extraction and augmenting lexicons properly could lead to further improvements in accuracy.
{"title":"Examination of effective features for CRF-based bibliography extraction from reference strings","authors":"Daiki Matsuoka, Manabu Ohta, A. Takasu, J. Adachi","doi":"10.1109/ICDIM.2016.7829774","DOIUrl":"https://doi.org/10.1109/ICDIM.2016.7829774","url":null,"abstract":"Metadata such as bibliographic information about documents are indispensable in the effective use of digital libraries. In particular, the reference fields of academic papers contain much bibliographic information such as authors' names and document titles. We are therefore developing a method for automatically extracting bibliographic information from reference strings using a conditional random field (CRF). The features used by the CRF determine the accuracy of this method. We examine effective features for accurate extraction by experimentally changing the features used. The experiments showed that lexical features were quite effective in accurate extraction and augmenting lexicons properly could lead to further improvements in accuracy.","PeriodicalId":146662,"journal":{"name":"2016 Eleventh International Conference on Digital Information Management (ICDIM)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128842146","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 : 2016-08-01DOI: 10.1109/FGCT.2016.7605093
M. Öztürk, A. Zengin
Class imbalance is a common problem in defect prediction data sets. In order to cope with this problem, over-sampling and under sampling methods are employed. However, these methods are designed for instance based alteration and not specialized for feature space. Also there is not any distinctive approach to cope with class imbalance in defect prediction data sets. We develop HSDD (hybrid sampling for defect data sets) to solve this problem. HSDD comprises not only derivation of low-level metrics, but also reduction processes of repeated data points. The method was evaluated on industrial and open source project data sets by using Bayes, naive Bayes, random forest, and J48 in terms of g-mean and training time. Obtained results show that HSDD produces promising training performance especially in large-scale data sets.
{"title":"HSDD: A hybrid sampling strategy for class imbalance in defect prediction data sets","authors":"M. Öztürk, A. Zengin","doi":"10.1109/FGCT.2016.7605093","DOIUrl":"https://doi.org/10.1109/FGCT.2016.7605093","url":null,"abstract":"Class imbalance is a common problem in defect prediction data sets. In order to cope with this problem, over-sampling and under sampling methods are employed. However, these methods are designed for instance based alteration and not specialized for feature space. Also there is not any distinctive approach to cope with class imbalance in defect prediction data sets. We develop HSDD (hybrid sampling for defect data sets) to solve this problem. HSDD comprises not only derivation of low-level metrics, but also reduction processes of repeated data points. The method was evaluated on industrial and open source project data sets by using Bayes, naive Bayes, random forest, and J48 in terms of g-mean and training time. Obtained results show that HSDD produces promising training performance especially in large-scale data sets.","PeriodicalId":146662,"journal":{"name":"2016 Eleventh International Conference on Digital Information Management (ICDIM)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132772124","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 : 2016-07-14DOI: 10.1109/ICDIM.2016.7829775
Georgina Esteves, João Mendes-Moreira
Telecommunication companies are acknowledging the existing connection between customer satisfaction and company revenues. Customer churn in telecom refers to a customer that ceases his relationship with a company. Churn prediction in telecom has recently gained substantial interest of stakeholders, who noticed that retaining a customer is substantially cheaper that gaining a new one. This research compares six approaches using different algorithms that identify the clients who are closer to abandon their telecom provider. Those algorithms are: KNN, Naive Bayes, C4.5, Random Forest, Ada Boost and ANN. The use of real data provided by We Do technologies extended the refinement time necessary, but ensured that the developed algorithm and model can be applied to real world situations. The models are evaluated according to three criteria: are under curve, sensitivity and specificity, with special weight to the first two criteria. The Random Forest algorithm proved to be the most adequate in all the test cases.
{"title":"Churn perdiction in the telecom business","authors":"Georgina Esteves, João Mendes-Moreira","doi":"10.1109/ICDIM.2016.7829775","DOIUrl":"https://doi.org/10.1109/ICDIM.2016.7829775","url":null,"abstract":"Telecommunication companies are acknowledging the existing connection between customer satisfaction and company revenues. Customer churn in telecom refers to a customer that ceases his relationship with a company. Churn prediction in telecom has recently gained substantial interest of stakeholders, who noticed that retaining a customer is substantially cheaper that gaining a new one. This research compares six approaches using different algorithms that identify the clients who are closer to abandon their telecom provider. Those algorithms are: KNN, Naive Bayes, C4.5, Random Forest, Ada Boost and ANN. The use of real data provided by We Do technologies extended the refinement time necessary, but ensured that the developed algorithm and model can be applied to real world situations. The models are evaluated according to three criteria: are under curve, sensitivity and specificity, with special weight to the first two criteria. The Random Forest algorithm proved to be the most adequate in all the test cases.","PeriodicalId":146662,"journal":{"name":"2016 Eleventh International Conference on Digital Information Management (ICDIM)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126841461","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 : 1900-01-01DOI: 10.1109/ICDIM.2016.7829768
Toki Takeda, Taketoshi Ushiama
Mobile devices equipped with cameras, such as smartphones, have become extremely popular in recent years, and have motivated users to capture an increasing number of digital photos in their daily lives. Users often invoke these photos during in-person interactions or conversations with others. In the context of a conversation between two people related to or involving reference to a photo, one of them might be inclined to show the photograph on his/her smartphone. However, it is difficult for users to search for a photo that they want to reference in the brief period during a conversation for which it might be relevant. Hence, in this study, we propose a system that shows users the photos relevant to the topic that they want to discuss in a given conversation according to their preferences. In the method of ranking photos used in our system, the index of the adequacy of a photo in the context of a conversation is defined as the degree of similarity to the photo that is used in the current conversation. Photos on each user's device are sorted by their degree of similarity with a given photo. We show that there is a strong relationship between our proposed ranking and those based on subjective assessment tasks, and confirmed the effectiveness of our system through experiments involving seven subjects.
{"title":"Private photo recommendation system for in-person conversation","authors":"Toki Takeda, Taketoshi Ushiama","doi":"10.1109/ICDIM.2016.7829768","DOIUrl":"https://doi.org/10.1109/ICDIM.2016.7829768","url":null,"abstract":"Mobile devices equipped with cameras, such as smartphones, have become extremely popular in recent years, and have motivated users to capture an increasing number of digital photos in their daily lives. Users often invoke these photos during in-person interactions or conversations with others. In the context of a conversation between two people related to or involving reference to a photo, one of them might be inclined to show the photograph on his/her smartphone. However, it is difficult for users to search for a photo that they want to reference in the brief period during a conversation for which it might be relevant. Hence, in this study, we propose a system that shows users the photos relevant to the topic that they want to discuss in a given conversation according to their preferences. In the method of ranking photos used in our system, the index of the adequacy of a photo in the context of a conversation is defined as the degree of similarity to the photo that is used in the current conversation. Photos on each user's device are sorted by their degree of similarity with a given photo. We show that there is a strong relationship between our proposed ranking and those based on subjective assessment tasks, and confirmed the effectiveness of our system through experiments involving seven subjects.","PeriodicalId":146662,"journal":{"name":"2016 Eleventh International Conference on Digital Information Management (ICDIM)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126510317","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}
The aim of the SCAM working conference is to bring together researchers and practitioners working on theory, techniques and applications that concern analysis and manipulation of the source code of computer systems. Software plays an enormous role in our lives, in ways both obvious and subtle. This role will continue to expand and evolve. While much attention in the wider software engineering community is directed towards other aspects of systems development and evolution, such as specification, design and requirements engineering, it is the source code that contains the precise, and sometimes only, definitive description of the behaviour of the system. SCAM focuses on the techniques and tools themselves what they can achieve, how they can be improved, refined and combined. SCAM is a working conference: paper presentations are kept short and focused, with ample time reserved for general discussion of issues raised during each session. This always leads to interesting and stimulating interactive discussions.
{"title":"Message from the chairs","authors":"P. Olivier, A. Krüger","doi":"10.1109/SCAM.2006.19","DOIUrl":"https://doi.org/10.1109/SCAM.2006.19","url":null,"abstract":"The aim of the SCAM working conference is to bring together researchers and practitioners working on theory, techniques and applications that concern analysis and manipulation of the source code of computer systems. Software plays an enormous role in our lives, in ways both obvious and subtle. This role will continue to expand and evolve. While much attention in the wider software engineering community is directed towards other aspects of systems development and evolution, such as specification, design and requirements engineering, it is the source code that contains the precise, and sometimes only, definitive description of the behaviour of the system. SCAM focuses on the techniques and tools themselves what they can achieve, how they can be improved, refined and combined. SCAM is a working conference: paper presentations are kept short and focused, with ample time reserved for general discussion of issues raised during each session. This always leads to interesting and stimulating interactive discussions.","PeriodicalId":146662,"journal":{"name":"2016 Eleventh International Conference on Digital Information Management (ICDIM)","volume":"178 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134319488","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：