2017 IEEE International Conference on Data Mining Workshops (ICDMW)最新文献_第5页

Deep Learning Solutions to Computational Phenotyping in Health Care 医疗保健中计算表型的深度学习解决方案

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-11-01 DOI: 10.1109/ICDMW.2017.156

Zhengping Che, Yan Liu

引用次数: 22

Analyzing Dynamical Activities of Co-occurrence Patterns for Cooking Ingredients 烹饪原料共现模式的动态活动分析

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-11-01 DOI: 10.1109/ICDMW.2017.10

Y. Kikuchi, Masahito Kumano, M. Kimura

{"title":"Analyzing Dynamical Activities of Co-occurrence Patterns for Cooking Ingredients","authors":"Y. Kikuchi, Masahito Kumano, M. Kimura","doi":"10.1109/ICDMW.2017.10","DOIUrl":"https://doi.org/10.1109/ICDMW.2017.10","url":null,"abstract":"Due to the increasing popularity of cooking-recipe sharing sites and the success of complex network science, attention has recently been devoted to developing an effective networkbased method of analyzing the characteristics of ingredient combinations used in recipes. Unlike previous approaches dealing with static properties, we aim at analyzing the dynamical changes in ingredient pairs jointly used in recipes, and propose an efficient method of extracting the change patterns for co-occurrence activities of ingredients. Based on the extracted change patterns, we build an active network among ingredients at every timestep, and identify active co-occurrence patterns. Moreover, we provide a method of interpreting active co-occurrence patterns in terms of recipes, and present a framework for visually analyzing their dynamical changes. Using real data from a Japanese recipe sharing site, we quantitatively demonstrate the effectiveness of the proposed method for extracting the activity change patterns for ingredient pairs, and uncover the characteristics of the seasonal changes in ingredient pairs jointly used in Japanese recipes by applying the proposed method.","PeriodicalId":389183,"journal":{"name":"2017 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121126726","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}

引用次数: 5

Finding the Best Job Applicants for a Job Posting: A Comparison of Human Resources Search Strategies 为招聘启事寻找最佳求职者:人力资源搜索策略的比较

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-11-01 DOI: 10.1109/ICDMW.2017.31

Christopher G. Harris

引用次数: 18

Twitter Stance Detection — A Subjectivity and Sentiment Polarity Inspired Two-Phase Approach 推特姿态检测——主观性和情感极性启发的两阶段方法

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-11-01 DOI: 10.1109/ICDMW.2017.53

K. Dey, Ritvik Shrivastava, Saroj Kaushik

{"title":"Twitter Stance Detection — A Subjectivity and Sentiment Polarity Inspired Two-Phase Approach","authors":"K. Dey, Ritvik Shrivastava, Saroj Kaushik","doi":"10.1109/ICDMW.2017.53","DOIUrl":"https://doi.org/10.1109/ICDMW.2017.53","url":null,"abstract":"The problem of stance detection from Twitter tweets, has recently gained significant research attention. This paper addresses the problem of detecting the stance of given tweets, with respect to given topics, from user-generated text (tweets). We use the SemEval 2016 stance detection task dataset. The labels comprise of positive, negative and neutral stances, with respect to given topics. We develop a two-phase feature-driven model. First, the tweets are classified as neutral vs. non-neutral. Next, non-neutral tweets are classified as positive vs. negative. The first phase of our work draws inspiration from the subjectivity classification and the second phase from the sentiment classification literature. We propose the use of two novel features, which along with our streamlined approach, plays a key role deriving the strong results that we obtain. We use traditional support vector machine (SVM) based machine learning. Our system (F-score: 74.44 for SemEval 2016 Task A and 61.57 for Task B) significantly outperforms the state of the art (F-score: 68.98 for Task A and 56.28 for Task B). While the performance of the system on Task A shows the effectiveness of our model for targets on which the model was trained upon, the performance of the system on Task B shows the generalization that our model achieves. The stance detection problem in Twitter is applicable for user opinion mining related applications and other social influence and information flow modeling applications, in real life.","PeriodicalId":389183,"journal":{"name":"2017 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"194 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126988835","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}

引用次数: 29

Survival Random Forest to Predict Time to Fill 生存随机森林预测时间填充

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-11-01 DOI: 10.1109/ICDMW.2017.32

Summer M. Husband, J. Roberts

引用次数: 2

Development and Use of an Activity Model Based on Structured Knowledge: A Music Teaching Support System 基于结构化知识的活动模型的开发与应用:音乐教学支持系统

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-11-01 DOI: 10.1109/ICDMW.2017.82

Nami Iino, Satoshi Nishimura, Ken Fukuda, Kentaro Watanabe, Kristiina Jokinen, Takuichi Nishimura

{"title":"Development and Use of an Activity Model Based on Structured Knowledge: A Music Teaching Support System","authors":"Nami Iino, Satoshi Nishimura, Ken Fukuda, Kentaro Watanabe, Kristiina Jokinen, Takuichi Nishimura","doi":"10.1109/ICDMW.2017.82","DOIUrl":"https://doi.org/10.1109/ICDMW.2017.82","url":null,"abstract":"To collect and explicate meaningful knowledge of a community, we propose an Activity Model based on structured knowledge. The following issues arise related to the model development: (a) difficulties in capturing activities; (b) difficulty of acquiring knowledge; and (c) difficulty in optimizing the activities to newly adopted technologies. Therefore, we are developing technologies that use on-site activities and knowledge as a knowledge-based Activity Model to enhance community intelligence (observation, judgment, cooperation). As an example of its application domain, we chose classical guitar. Classical guitar was established in the late 19th century, and systematization of classical guitar rendition has not yet been completed. Therefore, instructions for playing the guitar sometimes differ greatly among teachers, which confuses students. We thus aim at developing an instruction support system which collects the knowledge of guitar rendition while recording the student improvement process. For this study, we conducted workshops by professional guitarists and structured a knowledge model that systematizes the latest acquisition process of guitar rendition. The model will allow structuring of various activities and help improve and reconstruct music teaching services.","PeriodicalId":389183,"journal":{"name":"2017 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"770 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116412135","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}

引用次数: 5

Exploiting PubMed for Protein Molecular Function Prediction via NMF Based Multi-label Classification 利用PubMed基于NMF的多标签分类进行蛋白质分子功能预测

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-11-01 DOI: 10.1109/ICDMW.2017.64

S. Fodeh, Aditya Tiwari, Hong Yu

{"title":"Exploiting PubMed for Protein Molecular Function Prediction via NMF Based Multi-label Classification","authors":"S. Fodeh, Aditya Tiwari, Hong Yu","doi":"10.1109/ICDMW.2017.64","DOIUrl":"https://doi.org/10.1109/ICDMW.2017.64","url":null,"abstract":"Gene ontology (GO) defines terms and classes used to describe gene functions and relationships between them. GO has been the standard to describing the functions of specific genes in different model organisms. GO annotation which tags genes with GO terms has mostly been a manual and timeconsuming curation process. In this paper we describe the development and evaluation of an innovative predictive system to automatically assign a gene its molecular functions (GO terms) using biomedical literature as a resource. We treated a GO term assignment as a multi-label multi-class classification problem. Rather than the commonly used bag-of-words approach, we used non-negative matrix factorization (NMF) for feature reduction and then performed the classification of genes. To address the multi-label aspect of the data, we used the binary-relevance method. We experimented with different classifiers and found that the combination of binary relevance and K-nearest neighbor (KNN) classifier gave the best performance. Our evaluation on UniProtKB/Swiss-Prot dataset showed the best performance of .83 in terms of F-measure.","PeriodicalId":389183,"journal":{"name":"2017 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"222 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115529164","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}

引用次数: 4

Mobile E-Commerce Data Processing Using Relational Memory 基于关系记忆的移动电子商务数据处理

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-11-01 DOI: 10.1109/ICDMW.2017.125

P. Aarabi

引用次数: 0

Mining Human Mobility to Quantify Performance Status 挖掘人员流动性以量化绩效状态

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-11-01 DOI: 10.1109/ICDMW.2017.168

Minh Nguyen, Zaki Hasnain, Ming Li, T. Dorff, David Quinn, S. Purushotham, Luciano Nocera, P. Newton, P. Kuhn, J. Nieva, C. Shahabi

{"title":"Mining Human Mobility to Quantify Performance Status","authors":"Minh Nguyen, Zaki Hasnain, Ming Li, T. Dorff, David Quinn, S. Purushotham, Luciano Nocera, P. Newton, P. Kuhn, J. Nieva, C. Shahabi","doi":"10.1109/ICDMW.2017.168","DOIUrl":"https://doi.org/10.1109/ICDMW.2017.168","url":null,"abstract":"Human mobility has been studied extensively in various biomedical contexts with applications in clinical rehabilitation, disease diagnosis, health risk prognosis, and general performance assessments. In this paper, we present ATOMHP (Analytical Technologies to Objectively Measure Human Performance) Kinect: a system to objectively quantify human performance using the Microsoft Kinect as a single camera sensor to capture human mobility. We explore the viability of this noninvasive performance assessment system by studying a cohort of cancer patients undergoing various therapy regimens who are assigned a performance score based on a qualitative clinical test. The ATOM-HP Kinect is a clinically usable system which consists of tools for Kinect, clinical data collection, data quality validation, and mobility feature extraction, which can be used for downstream analysis of performance. Preliminary results based on the clinical case study indicate that ATOM-HP Kinect can quantify changes in kinematic parameters, and that these features are correlated with clinically measured risk factors which could be used for early prediction of diseases, or making decision on treatment modification.","PeriodicalId":389183,"journal":{"name":"2017 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125771519","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}

引用次数: 4

Learning-Based Method with Valence Shifters for Sentiment Analysis 基于学习的价移情感分析方法

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-11-01 DOI: 10.1109/ICDMW.2017.52

Ruihua Cheng, J. Loh

引用次数: 2