2017 International Conference on Machine Learning and Data Science (MLDS)最新文献_第2页

Using LSTMs for Predicting Patient's Expenditure on Medications 利用LSTMs预测患者用药费用

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.9

S. Kaushik, Abhinav Choudhury, Nataraj Dasgupta, Sayee Natarajan, Larry A. Pickett, V. Dutt

{"title":"Using LSTMs for Predicting Patient's Expenditure on Medications","authors":"S. Kaushik, Abhinav Choudhury, Nataraj Dasgupta, Sayee Natarajan, Larry A. Pickett, V. Dutt","doi":"10.1109/MLDS.2017.9","DOIUrl":"https://doi.org/10.1109/MLDS.2017.9","url":null,"abstract":"Managing expenditure on medications is a serious challenge faced by patients, in particular for those who cannot afford costly health care. Predicting patient's spending on medications becomes crucial for efficient planning, budgeting, and decision-making. However, little attention has been given to predicting patient expenditure using deep time-series forecasting methods. The primary objective of this paper is the time-series forecasting of patient expenditures on medications using both traditional and deep time-series forecasting methods. A traditional Auto Regressive Integrated Moving Average (ARIMA) model; and, two deep models, a standard Long Short-Term Memory (LSTM) model and a stacked LSTM model were calibrated to predict the monthly expenditure on medication for 50,000+ patients in the US between 2011 and 2015. The first 48 months were used for training the models and the remaining 12 months were used for testing the models. Results revealed that the stacked LSTM model performed better than both the standard LSTM and ARIMA models during test conditions. Overall, both the deep time-series models performed better than the traditional time-series ARIMA model. We highlight the implications of our results for forecasting time-series data involving patient journeys.","PeriodicalId":248656,"journal":{"name":"2017 International Conference on Machine Learning and Data Science (MLDS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128341221","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: 14

JPEG Compression Detection Based on Edge-Corner Features Using SVM 基于支持向量机边角特征的JPEG压缩检测

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.25

Yongsoo Choi, Dongshik Kang, Jae-Jeong Hwang, K. Rhee

{"title":"JPEG Compression Detection Based on Edge-Corner Features Using SVM","authors":"Yongsoo Choi, Dongshik Kang, Jae-Jeong Hwang, K. Rhee","doi":"10.1109/MLDS.2017.25","DOIUrl":"https://doi.org/10.1109/MLDS.2017.25","url":null,"abstract":"This paper focuses on the detection of JPEG compression (JC) image forensics and extracts a feature vector that composed of the Hough line, peaks, and the Harris-Stephens corner features to classify the JC and the other type images. The longest Hough line is computed by the Hough transform with the Canny line, then the coordinates of the line’s endpoints would be the feature set. Also, the coordinates of the deep Hough peaks is defined as the feature set. Lastly, the coordinates of the Harris-Stephens corners would be the feature set, respectively. They are to be combined the feature vector for the JC detection. The defined feature vector is trained inSVM (Support Vector Machine) classifier for the JC detection of the forged images. The performance of the proposed JC detection is measured with the chose four types of the forged images in the experiment: unaltered, median filtering (3 × 3), averaging filter (3 × 3) and downscaling (0.9), respectively. Subsequently, the experimental items; the AUC (Area Under Curve) by the sensitivity and 1-specificity, PTP at PFP = 0.01, Pe (a minimal average decision error), and the classification are evaluating the performance of the proposed JC detector scheme. Thus, it confirmed that the grade evaluation of the proposed algorithm is 'Excellent (A)'.","PeriodicalId":248656,"journal":{"name":"2017 International Conference on Machine Learning and Data Science (MLDS)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114580321","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

Validation of Inspection Reviews over Variable Features Set Threshold 在可变特征集阈值上检验评审的验证

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.16

Maninder Singh, G. Walia, Anurag Goswami

引用次数: 6

INGC: Graph Clustering & Outlier Detection Algorithm Using Label Propagation 使用标签传播的图聚类和离群点检测算法

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.14

Vandana Bhatia, Bharti Saneja, Rinkle Rani

{"title":"INGC: Graph Clustering & Outlier Detection Algorithm Using Label Propagation","authors":"Vandana Bhatia, Bharti Saneja, Rinkle Rani","doi":"10.1109/MLDS.2017.14","DOIUrl":"https://doi.org/10.1109/MLDS.2017.14","url":null,"abstract":"In the last decade, the size of data have increased at tremendous rate. To extract knowledgeable insights from this huge amount of data, data mining has to be done. To get the useful insights the connection in between data is sometimes of high interest. This connection can be efficiently represented as graphs. It provides an influential way to provide efficient illustrations for many applications spanning from biological networks, social networks to web networks. Graph mining techniques such as clustering and outlier detection can be beneficial in gathering the useful information. In this paper, an efficient influence based graph clustering and outlier detection algorithm (INGC) is proposed based on label propagation. The proposed algorithm improves the performance of the traditional Label Propagation algorithm by making it more robust. The proposed INGC saves time by labeling only high influential vertices of network. Further the labels are propagated among the rest of the nodes of network. And, the nodes with same vertex label are gathered to form a cluster. The vertices to which no label has been assigned during clustering are identified as outliers. Experiments were carried out on three real life graph datasets. It is shown that the proposed INGC outperforms the state-of art clustering algorithms in terms of F-Measure and Modularity. INGC also proved to be efficient in terms of detection rate of outliers.","PeriodicalId":248656,"journal":{"name":"2017 International Conference on Machine Learning and Data Science (MLDS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133887253","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: 2

Internet of Things and Decision Support System for eHealth - Applied to Cardiometabolic Diseases 电子健康的物联网和决策支持系统-应用于心脏代谢疾病

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.22

Parag Chatterjee, R. Armentano, L. Cymberknop

引用次数: 10

Spotted Hyena Optimizer for Solving Engineering Design Problems 斑点鬣狗优化解决工程设计问题

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.5

Gaurav Dhiman, A. Kaur

引用次数: 78

Data Driven Decision Support to Fund Graduate Studies in Abroad Universities 数据驱动决策支持在国外大学资助研究生学习

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.17

Shahriar Yazdipour, Nahid Taherian

{"title":"Data Driven Decision Support to Fund Graduate Studies in Abroad Universities","authors":"Shahriar Yazdipour, Nahid Taherian","doi":"10.1109/MLDS.2017.17","DOIUrl":"https://doi.org/10.1109/MLDS.2017.17","url":null,"abstract":"Each year, many undergraduate students from developing countries try to continue their graduate studies in foreign universities. Admission is not easy, especially for those who seek positions with full funding and scholarship. Chance of acceptance and getting fund is dependent on many factors like GPA, GRE, IELTS scores, and the field of study, university name and number of papers. Since the process of application is cost and time consuming, students should just apply for universities with a high chance of acceptance and funding. Students usually reach out to those who applied before and use their experience to have a smarter choice. In some countries like Iran, there are portals and websites in which previously admitted students share their experience and information. In this paper, we use the data provided by these students to build models for predicting the chance of a student for getting fund from different universities. After cleaning and preprocessing, we build decision trees which take the person data as input and calculate the probability of getting financial support from various universities. This model also helps us to find out the most important factors in succeeding to achieve funding. Also, admission seekers can follow the provided rules to estimate their chance of getting fund and obtain ideas about how to improve their profiles to increase their chances. Additionally, we use a k-nearest neighbor algorithm to find k most similar records to user's profile. These similar records are used to predict the chance of acceptance and getting fund. Undoubtedly these models1 are beneficial for students who have profound desire as well as students who are trying to pursue higher study abroad with financial support.","PeriodicalId":248656,"journal":{"name":"2017 International Conference on Machine Learning and Data Science (MLDS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132705733","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: 2

Learning to Filter Documents for Information Extraction Using Rapid Annotation 学习使用快速标注过滤文档以提取信息

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.24

Carlos Alejandro Aguirre, Sneha Gullapalli, María F. De la Torre, Alice Lam, J. Weese, W. Hsu

{"title":"Learning to Filter Documents for Information Extraction Using Rapid Annotation","authors":"Carlos Alejandro Aguirre, Sneha Gullapalli, María F. De la Torre, Alice Lam, J. Weese, W. Hsu","doi":"10.1109/MLDS.2017.24","DOIUrl":"https://doi.org/10.1109/MLDS.2017.24","url":null,"abstract":"Corpus-driven approaches to information extraction from documents face problems of relevance determination, namely determining which documents are of requisite type, structure, and content for a specified query and context. In this paper, we discuss the problem of learning to filter documents crawled from the web with respect to such relevance criteria, and in particular how to annotate document corpora for supervised classification learning approaches to this problem. For context, we describe a system aimed at extracting experimental data from scientific publications, with the long-term goal of extracting procedural information from relevant sections on experimental methodology. We consider motivating use cases for our learning filter, using the documents passed by the filter: marking up sections (or passages); capturing entities and relationships; and explaining to a domain expert why a document is relevant. These distinct use cases make the annotation task multi-faceted. Our approach focuses on speeding up annotation in learning to filter while minimizing loss of precision or recall on the learning task, using a reconfigurable user interface. We develop such an interface, report on its use in tandem with classification on a real extraction task, and discuss extensions of this work to visual scene filtering and annotation.","PeriodicalId":248656,"journal":{"name":"2017 International Conference on Machine Learning and Data Science (MLDS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115415724","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: 2

Classification of Cancerous Profiles Using Machine Learning 使用机器学习对癌症特征进行分类

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/mlds.2017.6

Aman Sharma, Rinkle Rani

引用次数: 19

Comprehensive Review On Supervised Machine Learning Algorithms 监督机器学习算法综述

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.11

Rishabh Choudhary, Hemant Kumar Gianey

引用次数: 90