Proceedings of the ... International Florida AI Research Society Conference. Florida AI Research Symposium最新文献

{"title":"Online Conditional Outlier Detection in Nonstationary Time Series.","authors":"Siqi Liu,&nbsp;Adam Wright,&nbsp;Milos Hauskrecht","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>The objective of this work is to develop methods for detecting outliers in time series data. Such methods can become the key component of various monitoring and alerting systems, where an outlier may be equal to some adverse condition that needs human attention. However, real-world time series are often affected by various sources of variability present in the environment that may influence the quality of detection; they may (1) explain some of the changes in the signal that would otherwise lead to false positive detections, as well as, (2) reduce the sensitivity of the detection algorithm leading to increase in false negatives. To alleviate these problems, we propose a new two-layer outlier detection approach that first tries to model and account for the nonstationarity and periodic variation in the time series, and then tries to use other observable variables in the environment to explain any additional signal variation. Our experiments on several data sets in different domains show that our method provides more accurate modeling of the time series, and that it is able to significantly improve outlier detection performance.</p>","PeriodicalId":88964,"journal":{"name":"Proceedings of the ... International Florida AI Research Society Conference. Florida AI Research Symposium","volume":"2017 ","pages":"86-91"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5891145/pdf/nihms873687.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"36000502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Examining Healthcare Utilization Patterns of Elderly Middle-Aged Adults in the United States.","authors":"Cilia E Zayas,&nbsp;Zhe He,&nbsp;Jiawei Yuan,&nbsp;Mildred Maldonado-Molina,&nbsp;William Hogan,&nbsp;François Modave,&nbsp;Yi Guo,&nbsp;Jiang Bian","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Elderly patients, aged 65 or older, make up 13.5% of the U.S. population, but represent 45.2% of the top 10% of healthcare utilizers, in terms of expenditures. Middle-aged Americans, aged 45 to 64 make up another 37.0% of that category. Given the high demand for healthcare services by the aforementioned population, it is important to identify high-cost users of healthcare systems and, more importantly, ineffective utilization patterns to highlight where targeted interventions could be placed to improve care delivery. In this work, we present a novel multi-level framework applying machine learning (ML) methods (i.e., random forest regression and hierarchical clustering) to group patients with similar utilization profiles into clusters. We use a vector space model to characterize a patient's utilization profile as the number of visits to different care providers and prescribed medications. We applied the proposed methods using the 2013 Medical Expenditures Panel Survey (MEPS) dataset. We identified clusters of healthcare utilization patterns of elderly and middle-aged adults in the United States, and assessed the general and clinical characteristics associated with these utilization patterns. Our results demonstrate the effectiveness of the proposed framework to model healthcare utilization patterns. Understanding of these patterns can be used to guide healthcare policy-making and practice.</p>","PeriodicalId":88964,"journal":{"name":"Proceedings of the ... International Florida AI Research Society Conference. Florida AI Research Symposium","volume":"2016 ","pages":"361-366"},"PeriodicalIF":0.0,"publicationDate":"2016-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4946167/pdf/nihms798881.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"34742103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-Agent Area Coverage Control Using Reinforcement Learning","authors":"Adekunle A. Adepegba, Md. Suruz Miah, D. Spinello","doi":"10.20381/RUOR-5715","DOIUrl":"https://doi.org/10.20381/RUOR-5715","url":null,"abstract":"An area coverage control law in cooperation with reinforcement learning techniques is proposed for deploying multiple autonomous agents in a two-dimensional planar area. A scalar field characterizes the risk density in the area to be covered yielding nonuniform distribution of agents while providing optimal coverage. This problem has traditionally been addressed in the literature to date using locational optimization and gradient descent techniques, as well as proportional and proportional-derivative controllers. In most cases, agents’ actuator energy required to drive them in optimal configurations in the workspace is not considered. Here the maximum coverage is achieved with minimum actuator energy required by each agent. Similar to existing coverage control techniques, the proposed algorithm takes into consideration time-varying risk density. These density functions represent the probability of an event occurring (e.g., the presence of an intruding target) at a certain location or point in the workspace indicating where the agents should be located. To this end, a coverage control algorithm using reinforcement learning that moves the team of mobile agents so as to provide optimal coverage given the density functions as they evolve over time is being proposed. Area coverage is modeled using Centroidal Voronoi Tessellation (CVT) governed by agents. Based on [1, 2] and [3], the application of Centroidal Voronoi tessellation is extended to a dynamic changing harbour-like environment. The proposed multi-agent area coverage control law in conjunction with reinforcement learning techniques is implemented in a distributed manner whereby the multi-agent team only need to access information from adjacent agents while simultaneously providing dynamic target surveillance for single and multiple targets and feedback control of the environment. This distributed approach describes how automatic flocking behaviour of a team of mobile agents can be achieved by leveraging the geometrical properties of centroidal Voronoi tessellation in area coverage control while enabling multiple targets tracking without the need of consensus between individual agents. Agent deployment using a time-varying density model is being introduced which is a function of the position of some unknown targets in the environment. A nonlinear derivative of the error coverage function is formulated based on the single-integrator agent dynamics. The agent, aware of its local coverage control condition, learns a value function online while leveraging the same from its neighbours. Moreover, a novel computational adaptive optimal control methodology based on work by [4] is proposed that employs the approximate dynamic programming technique online to iteratively solve the algebraic Riccati equation with completely unknown system dynamics as a solution to linear quadratic regulator problem. Furthermore, an online tuning adaptive optimal control algorithm is implemented using an actor-critic neura","PeriodicalId":88964,"journal":{"name":"Proceedings of the ... International Florida AI Research Society Conference. Florida AI Research Symposium","volume":"1 1","pages":"368-373"},"PeriodicalIF":0.0,"publicationDate":"2016-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73351308","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":"Computational Notebooks for AI Education","authors":"Keith J. O'Hara, Douglas S. Blank, James B. Marshall","doi":"10.13140/2.1.2434.5928","DOIUrl":"https://doi.org/10.13140/2.1.2434.5928","url":null,"abstract":"Computational notebooks are documents that serve dual purposes: they serve as an archive format containing code, text, images and equations; but they can also be run like computer programs. This paper explores the use of these new computational notebooks to teach AI and introduces tools that we have developed — ICalico and Calysto — to facilitate that use. Not only do these new tools broaden the languages and contexts available to students exploring notebook-based AI computing, but they offer a new mode of teaching and learning for the AI classroom.","PeriodicalId":88964,"journal":{"name":"Proceedings of the ... International Florida AI Research Society Conference. Florida AI Research Symposium","volume":"17 1","pages":"263-268"},"PeriodicalIF":0.0,"publicationDate":"2015-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88178724","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":"A Multi-Label Classification Approach for Coding Cancer Information Service Chat Transcripts.","authors":"Anthony Rios,&nbsp;Robin Vanderpool,&nbsp;Pam Shaw,&nbsp;Ramakanth Kavuluru","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>National Cancer Institute's (NCI) Cancer Information Service (CIS) offers online instant messaging based information service called LiveHelp to patients, family members, friends, and other cancer information consumers. A cancer information specialist (IS) 'chats' with a consumer and provides information on a variety of topics including clinical trials. After a LiveHelp chat session is finished, the IS codes about 20 different elements of metadata about the session in electronic contact record forms (ECRF), which are to be later used for quality control and reporting. Besides straightforward elements like age and gender, more specific elements to be coded include the purpose of contact, the subjects of interaction, and the different responses provided to the consumer, the latter two often taking on multiple values. As such, ECRF coding is a time consuming task and automating this process could help ISs to focus more on their primary goal of helping consumers with valuable cancer related information. As a first attempt in this task, we explored multi-label and multi-class text classification approaches to code the purpose, subjects of interaction, and the responses provided based on the chat transcripts. With a sample dataset of about 673 transcripts, we achieved example-based F-scores of 0.67 (for subjects) and 0.58 (responses). We also achieved label-based micro F-scores of 0.65 (for subjects), 0.62 (for responses), and 0.61 (for purpose). To our knowledge this is the first attempt in automatic coding of Live-Help transcripts and our initial results on the smaller corpus indicate promising future directions in this task.</p>","PeriodicalId":88964,"journal":{"name":"Proceedings of the ... International Florida AI Research Society Conference. Florida AI Research Symposium","volume":"2013 ","pages":"338-343"},"PeriodicalIF":0.0,"publicationDate":"2013-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5521986/pdf/nihms877783.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35192145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Compositional Belief Update","authors":"J. Delgrande, F. J. Pelletier, M. Suderman","doi":"10.1613/jair.2539","DOIUrl":"https://doi.org/10.1613/jair.2539","url":null,"abstract":"Arc suppressing gas in a high voltage circuit breaker system is collected, filtered and compressed. The compressed gas is passed through a series of oil and desiccant filters and returned to a high pressure vessel for storage. The oil and desiccant filtering system is combined in a single, separable casing including baffles and a check valve.","PeriodicalId":88964,"journal":{"name":"Proceedings of the ... International Florida AI Research Society Conference. Florida AI Research Symposium","volume":"250 1","pages":"68-73"},"PeriodicalIF":0.0,"publicationDate":"2008-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75094714","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":"Distance Metric Learning for Conditional Anomaly Detection.","authors":"Michal Valko, Milos Hauskrecht","doi":"10.1901/jaba.2008.21-684","DOIUrl":"10.1901/jaba.2008.21-684","url":null,"abstract":"<p><p>Anomaly detection methods can be very useful in identifying unusual or interesting patterns in data. A recently proposed conditional anomaly detection framework extends anomaly detection to the problem of identifying anomalous patterns on a subset of attributes in the data. The anomaly always depends (is conditioned) on the value of remaining attributes. The work presented in this paper focuses on instance-based methods for detecting conditional anomalies. The methods depend heavily on the distance metric that lets us identify examples in the dataset that are most critical for detecting the anomaly. To optimize the performance of the anomaly detection methods we explore and study metric learning methods. We evaluate the quality of our methods on the Pneumonia PORT dataset by detecting unusual admission decisions for patients with the community-acquired pneumonia. The results of our metric learning methods show an improved detection performance over standard distance metrics, which is very promising for building automated anomaly detection systems for variety of intelligent monitoring applications.</p>","PeriodicalId":88964,"journal":{"name":"Proceedings of the ... International Florida AI Research Society Conference. Florida AI Research Symposium","volume":"21 ","pages":"684-689"},"PeriodicalIF":0.0,"publicationDate":"2008-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2871323/pdf/nihms117190.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"29002413","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Semantic Method for Textual Entailment","authors":"A. Neel, M. Garzon, V. Rus","doi":"10.4018/978-1-60960-741-8.CH028","DOIUrl":"https://doi.org/10.4018/978-1-60960-741-8.CH028","url":null,"abstract":"The problem of recognizing textual entailment (RTE) has been recently addressed using syntactic and lexical models with some success. Here, we further explore this problem, this time using the world knowledge captured in large semantic graphs such as WordNet. We show that semantic graphs made of synsets and selected relationships between them enable fairly simple methods that provide very competitive performance. First, assuming a solution to word sense disambiguation, we report on the performance of these methods in the four basic areas of information retrieval (IR), information extraction (IE), question answering (QA), and multi-document summarization (SUM), as described using benchmark datasets designed to test the entailment problem in the 2006 RTE (Recognizing Textual Entailment) challenge. We then show how the same methods yield a solution to word sense disambiguation, which combined with the previous solution yields a fully automated solution with about the same performance.","PeriodicalId":88964,"journal":{"name":"Proceedings of the ... International Florida AI Research Society Conference. Florida AI Research Symposium","volume":"1 1","pages":"171-176"},"PeriodicalIF":0.0,"publicationDate":"2008-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89092597","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":"Annotation of Children's Oral Narrations: Modeling Emergent Narrative Skills for Computational Applications","authors":"R. Passonneau, Adam Goodkind, E. T. Levy","doi":"10.7916/D8D22631","DOIUrl":"https://doi.org/10.7916/D8D22631","url":null,"abstract":"We present an annotation method for developing a model of children’s comprehension that differentiates between their recall for the objective content of a story and inferred content. We apply the annotation method to a corpus of retellings, in which children retell the same story on three successive days. Our results indicate differences over time: on Day three, children have a more evenly distributed recall of events throughout the story, and include significantly more inferences. The results suggest a cognitive bootstrapping effect. We discuss the potential for application to diagnostic assessment of children’s narrative skills and tutorial applications.","PeriodicalId":88964,"journal":{"name":"Proceedings of the ... International Florida AI Research Society Conference. Florida AI Research Symposium","volume":"23 1","pages":"253-258"},"PeriodicalIF":0.0,"publicationDate":"2007-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72594057","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":"Mining Sequences in Distributed Sensors Data for Energy Production","authors":"M. Kantardzic, John Gant","doi":"10.18297/ETD/477","DOIUrl":"https://doi.org/10.18297/ETD/477","url":null,"abstract":"The desire to predict power generation at a given point in time is essential to power scheduling, energy trading, and availability modeling. The research conducted within is concerned with sequence mining on power generation data and has the intent of modeling power generation. The data streams analyzed are average hourly power generation that is reported to the EPA. A global statistical model is proven impractical for the data streams, and local modeling via sequence mining is performed. The methodology presented, Uniform Sequence Discovery, implements the idea of uniform population coding, stream mining, and cross-stream mining. 1671 streams from years 2002 through 2004 are coded, mined for sequences, and cross-mined for matching sequences. 486 and 270 frequent sequences were extracted from the learning and testing data respectively. Association rules and the accompanying confidence and support values are used to create local models for power generation prediction. 159 local models were confirmed in the testing phase with a minimum confidence of 0.60. Power traders, concerned with predicting available generation, would then use the local models for prediction of natural gas-fired power generation.","PeriodicalId":88964,"journal":{"name":"Proceedings of the ... International Florida AI Research Society Conference. Florida AI Research Symposium","volume":"195 1","pages":"484-489"},"PeriodicalIF":0.0,"publicationDate":"2007-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75186645","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}