2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI)最新文献

{"title":"Hand Gesture Recognition with Convolution Neural Networks","authors":"Felix Zhan","doi":"10.1109/IRI.2019.00054","DOIUrl":"https://doi.org/10.1109/IRI.2019.00054","url":null,"abstract":"Hand gestures are the most common forms of communication and have great importance in our world. They can help in building safe and comfortable user interfaces for a multitude of applications. Various computer vision algorithms have employed color and depth camera for hand gesture recognition, but robust classification of gestures from different subjects is still challenging. I propose an algorithm for real-time hand gesture recognition using convolutional neural networks (CNNs). The proposed CNN achieves an average accuracy of 98.76% on the dataset comprising of 9 hand gestures and 500 images for each gesture.","PeriodicalId":295028,"journal":{"name":"2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134554910","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}

{"title":"Scalable Action Mining for Recommendations to Reduce Hospital Readmission","authors":"A. Bagavathi, A. Tzacheva","doi":"10.1109/IRI.2019.00036","DOIUrl":"https://doi.org/10.1109/IRI.2019.00036","url":null,"abstract":"Hospital re-admission problem is one of the long-time issues of healthcares in USA. Unplanned re-admissions to hospitals not only increase cost for patients, but also for hospitals and taxpayers. Action mining is one of the data mining approaches to recommend actions to undertake for an organization or individual to achieve required condition or status. In this work, we propose a scalable action mining method to recommend hospitals and taxpayers on what actions would potentially reduce patient readmission to hospitals. We use the Healthcare Cost and Utilization Project(HCUP) databases to evaluate our approach. All our proposed scalable approaches are cloud based and use Apache Spark to handle data processing and to make recommendations.","PeriodicalId":295028,"journal":{"name":"2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117074264","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}

{"title":"Using BERT to Process Chinese Ellipsis and Coreference in Clinic Dialogues","authors":"Chuan-Jie Lin, Chao-Hsiang Huang, Chia-Hao Wu","doi":"10.1109/IRI.2019.00070","DOIUrl":"https://doi.org/10.1109/IRI.2019.00070","url":null,"abstract":"This paper focuses on ellipsis and coreference resolution in Chinese dialogue. The experimental data are real medical diagnosis dialogues. New features for machine learning, as well as deep learning approach such as BERT, were used to develop classifiers to detect, classify, and resolve ellipsis and coreference. The experimental results show that rule-based systems, BERT, and neural networks outperform one another in different tasks. The best F-scores of ellipsis and coreference detection were 70.61% and 89.09%, respectively. The best accuracy of ellipsis and coreference classification were 77.96% and 83.09%, respectively. The best accuracy of ellipsis and coreference detection were 80.06% and 82.69%, respectively.","PeriodicalId":295028,"journal":{"name":"2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI)","volume":"28 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124293095","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}

{"title":"Genetic Algorithm Based Deep Learning Model Selection for Visual Data Classification","authors":"Haiman Tian, Shu‐Ching Chen, M. Shyu","doi":"10.1109/IRI.2019.00032","DOIUrl":"https://doi.org/10.1109/IRI.2019.00032","url":null,"abstract":"Significant progress has been made by researchers in image classification mainly due to the accessibility of large-scale public visual datasets and powerful Convolutional Neural Network(CNN) models. Pre-trained CNN models can be utilized for learning comprehensive features from smaller training datasets, which support the transfer of knowledge from one source domain to different target domains. Currently, there are numerous frameworks to handle image classifications using transfer learning including preparing the preliminary features from the early layers of pre-trained CNN models, utilizing the mid-/high-level features, and fine-tuning the pre-trained CNN models to work for different targeting domains. In this work, we proposed to build a genetic algorithm-based deep learning model selection framework to address various detection challenges. This framework automates the process of identifying the most relevant and useful features generated by pre-trained models for different tasks. Each model differs in numerous ways depending on the number of layers.","PeriodicalId":295028,"journal":{"name":"2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130547229","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}

{"title":"3D Points Localization Using Defocused Images","authors":"Dongzhen Wang, Daqing Huang","doi":"10.1109/IRI.2019.00049","DOIUrl":"https://doi.org/10.1109/IRI.2019.00049","url":null,"abstract":"3D points reconstruction has attracted increasing attentions both in computer vision and robotic intelligence areas. However, the real depth measurement still much relies on depth measurement instruments. Although many measurement methods for depth exist, they usually need additional instruments which always increase the cost of the measurement system. To better localize the position of 3D points without use of other instruments, a direct method is proposed which acquires depth from defocus of current images in this paper. The method utilizes the property of camera lens system and mechanism of SFM to remove the ambiguity of structure scale and the relative error between these 3D points. In addition, a multiple images setting for improving the robustness of depth estimation is proposed which can further eliminate depth error from some kinds of nature noises. Experiments on the real scene are implemented, which shows that the proposed method outperforms the ordinary 3D points localization method.","PeriodicalId":295028,"journal":{"name":"2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI)","volume":"16 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120887955","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}

{"title":"Machine Learning Findings on Geospatial Data of Users from the TrackYourStress mHealth Crowdsensing Platform","authors":"R. Pryss, Dennis John, M. Reichert, Burkhard Hoppenstedt, L. Schmid, W. Schlee, M. Spiliopoulou, Johannes Schobel, Robin Kraft, Marc Schickler, B. Langguth, T. Probst","doi":"10.1109/IRI.2019.00061","DOIUrl":"https://doi.org/10.1109/IRI.2019.00061","url":null,"abstract":"Mobile apps are increasingly utilized to gather data for various healthcare aspects. Furthermore, mobile apps are used to administer interventions (e.g., breathing exercises) to individuals. In this context, mobile crowdsensing constitutes a technology, which is used to gather valuable medical data based on the power of the crowd and the offered computational capabilities of mobile devices. Notably, collecting data with mobile crowdsensing solutions has several advantages compared to traditional assessment methods when gathering data over time. For example, data is gathered with high ecological validity, since smartphones can be unobtrusively used in everyday life. Existing approaches have shown that based on these advantages new medical insights, for example, for the tinnitus disease, can be revealed. In the work at hand, data of a developed mHealth crowdsensing platform that assesses the stress level and fluctuations of the platform users in daily life was investigated. More specifically, data of 1797 daily measurements on GPS and stress-related data in 77 users were analyzed. Using this data source, machine learning algorithms have been applied with the goal to predict stress-related parameters based on the GPS data of the platform users. Results show that predictions become possible that (1) enable meaningful interpretations as well as (2) indicate the directions for further investigations. In essence, the findings revealed first insights into the stress situation of individuals over time in order to improve their quality of life. Altogether, the work at hand shows that mobile crowdsensing can be valuably utilized in the context of stress on one hand. On the other, machine learning algorithms are able to utilize geospatial data of stress measurements that was gathered by a crowdsensing platform with the goal to improve the quality of life of its participating crowd users.","PeriodicalId":295028,"journal":{"name":"2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131628149","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}

{"title":"Evaluation of a Reusable Technique for Refining Social Media Query Criteria for Crowd-Sourced Sentiment for Decision Making","authors":"Kimberley Hemmings-Jarrett, Julian Jarrett, M. Brian Blake","doi":"10.1109/IRI.2019.00065","DOIUrl":"https://doi.org/10.1109/IRI.2019.00065","url":null,"abstract":"There are three categories of users that consume social media data either for their personal use or for aggregation and presentation to others. These users rely on a preferential combination of Social Media Signals (SMS) that satisfies their information goals and aids in their decisionmaking. The research community is split on how to deal with some signals such as text originating from robotic voices; some suggest removing them while others are more interested in better identifying them. This paper statistically tests the SMS's in a dataset gathered during one of the political debates during the US Presidential Elections in 2016. It introduces a reusable technique aimed at contributing to the iterative and symbiotic user-system relationship, while improving the opportunity for arriving at empirically supported results for decision-making instances regardless of the consumer group.","PeriodicalId":295028,"journal":{"name":"2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI)","volume":"603 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134445214","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}

{"title":"Mimicking Human Behavior in Shared-Resource Computer Networks","authors":"Brian Ricks, B. Thuraisingham, P. Tague","doi":"10.1109/IRI.2019.00062","DOIUrl":"https://doi.org/10.1109/IRI.2019.00062","url":null,"abstract":"Among the many challenges in computer network trace data collection is the automation, or mimicking, of human users in situations where humans-in-the-loop are either impracticable or not possible. While client-side human behavior has been automated in various static settings, autonomous clients which dynamically change their behavior as the environment changes may result in a more accurate representation of human behavior in captured network trace data, and thus may be better suited for problems in which humans-in-the-loop are important. In this work, we set out to create dynamic autonomous client-side behavioral models, which we call agents, that can interact with the network environment in much the same way that humans do, and are scalable in shared-resource environments, such as emulated computer networks. We show through multiple experiments and a web crawling case study on an emulated network that our agents can mimic interactive human behavior, and do so at scale.","PeriodicalId":295028,"journal":{"name":"2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121465868","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}

{"title":"Scalable Analysis of Open Data Graphs","authors":"Andrei Stoica, Michael Valdron, K. Pu","doi":"10.1109/IRI.2019.00059","DOIUrl":"https://doi.org/10.1109/IRI.2019.00059","url":null,"abstract":"We have studied Open Data as a connected graph. Each data package is considered a vertex, and we studied the similarity graph induced by several different similarity measures. We analyzed the resulting similarity graph using different metrics to estimate its quality and informativeness. In order to cope with the size of the open data graph (over 6 billion edges), the graph constructions and analysis are done using a distributed computation framework, Apache Spark. The algorithms were implemented using the Spark resilient distributed data algebra, and executed on the Google Cloud Platform (GCP).","PeriodicalId":295028,"journal":{"name":"2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128542336","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}

{"title":"Data Clustering Using Online Variational Learning of Finite Scaled Dirichlet Mixture Models","authors":"Hieu Nguyen, Meeta Kalra, Muhammad Azam, N. Bouguila","doi":"10.1109/IRI.2019.00050","DOIUrl":"https://doi.org/10.1109/IRI.2019.00050","url":null,"abstract":"With a massive amount of data created on a daily basis, the ubiquitous demand for data analysis is obvious. Recent development of technology has made machine learning techniques applicable to various problems. In this paper, we emphasize on cluster analysis, an important aspect of data analysis. In other words, being able to automatically discover different groups containing similar data is crucial for further information retrieving and anomaly detection tasks. Thus, we propose an online variational inference framework for finite Scaled Dirichlet mixture models. By efficiently handling large scale data, online approach is capable of enhancing the scalability of finite mixture models for demanding applications in real time. The proposed method can simultaneously update the model's parameters and determine the optimal number of components without the complex computation of conventional Bayesian algorithm. The effectiveness of our model is affirmed with challenging problems including spam detection and image clustering.","PeriodicalId":295028,"journal":{"name":"2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117043721","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}