2016 IEEE Systems and Information Engineering Design Symposium (SIEDS)最新文献

{"title":"Optimizing multi-channel health information delivery for behavioral change","authors":"Michael Buhl, James Famulare, Christopher Glazier, Jennifer Harris, Alan McDowell, Gregory Waldrip, L. Barnes, M. Gerber","doi":"10.1109/SIEDS.2016.7489285","DOIUrl":"https://doi.org/10.1109/SIEDS.2016.7489285","url":null,"abstract":"The healthcare field is facing new challenges and opportunities with an upsurge of telehealth and remote monitoring solutions. Hospitals are working with the private industry to develop Web-based solutions that augment primary care once patients leave the clinical setting. As technology enables healthcare to shift from treatment centers to home environments, new approaches are needed to tailor health-related content and delivery at the individual level. This paper presents methods for personalizing communications for a web-based behavioral change support system. Research has shown patients are more likely to continually use systems that present personally relevant content closely resembling traditional healthcare. We performed a two-part feasibility study to investigate the hypothesis that personalized content leads to higher continued use of a telehealth system. In the study, participants interacted with a Web-based application that presents questions and information concerning exercise. Logistic regression and collaborative filtering were used to develop personalized content strategies for participants in the second part of the study. We successfully implemented the content strategies in an existing third-party software system, but the study was small and lacked proper power to draw significant, externally valid results.","PeriodicalId":426864,"journal":{"name":"2016 IEEE Systems and Information Engineering Design Symposium (SIEDS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130492700","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":"Designing a radiation sensing UAV system","authors":"Carina Cai, Bryan Carter, M. Srivastava, Joseph Tsung, John Vahedi-Faridi, Caroline Wiley","doi":"10.1109/SIEDS.2016.7489292","DOIUrl":"https://doi.org/10.1109/SIEDS.2016.7489292","url":null,"abstract":"Gathering radiation information in the event of a nuclear disaster is limited by the vulnerability of static sensor networks and the safety of human data collectors. A remotely controlled drone that can combine locational and radiological data gives emergency responders a safe and efficient alternative in the event of damaged or destroyed static sensor networks. The goal of this project is to develop a prototype radiation detection and mapping unmanned aerial vehicle system to safely identify irradiated areas in the event of a nuclear emergency. The UAV platform for this project is the EDF-8, a small ducted-fan UAV, developed by AVID LLC. Our team is responsible for developing the hardware necessary to integrate the radiation sensor into the EDF-8 platform. The main tasks in this project include programming microcontrollers to communicate with the radiation sensor as well as EDF-8's on board communication protocols, building housings for both the sensor and circuit boards, building simulation programs for testing, and the manipulation of collected data for presentation in a GIS software program. Upon project completion, AVID will have a prototype system for adapting EDF-8 into a radiological detection system for commercial or governmental use.","PeriodicalId":426864,"journal":{"name":"2016 IEEE Systems and Information Engineering Design Symposium (SIEDS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116178836","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":"Predicting mortality risk associated with serious treatable surgical complications at the University of Virginia health system","authors":"Jason Adams, Sharath Pingula, Akshat Verma, Abigail A. Flower","doi":"10.1109/SIEDS.2016.7489279","DOIUrl":"https://doi.org/10.1109/SIEDS.2016.7489279","url":null,"abstract":"This study focuses on predicting the risk of occurrence of serious but treatable complications and subsequent risk of mortality using a patient's preoperative conditions. Serious treatable complications include deep vein thrombosis/ pulmonary embolism, pneumonia, sepsis, and shock/cardiac arrest. These complications, if not identified and treated in time, can cause lengthened hospital stays, morbidity, and in some cases, mortality. We have modeled the risk of developing complications, and mortality due to complications, using a hierarchical prediction approach. In the first level of the hierarchy, extreme gradient boosted trees with cost sensitive weighting was used to model the risk of each complication and to identify the factors responsible for each type of complication. In the second level, similar statistical methods were used but on a smaller population set of patients, specifically those who developed one or more complications, to predict the risk of mortality. In our population of 32,202 patients, 963 developed one of the complications of interest, and of those with complications 174 died. Our predictions for sepsis, pneumonia, cardiac shock, and deep vein thrombosis/ pulmonary embolism, resulted in mean AUC values of 0.815, 0.935, 0.854, and 0.879 respectively. When making mortality predictions we achieved a mean AUC of 0.921. A propensity score analysis of patients that were predicted to be low risk but actually developed a complication was also performed. The framework proposed in this study provides hospitals with a way to more closely examine patient data regarding quality metrics by enabling them to identify patient born risks before surgical procedures are performed.","PeriodicalId":426864,"journal":{"name":"2016 IEEE Systems and Information Engineering Design Symposium (SIEDS)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124064135","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":"Use of biomarkers in depression diagnostics","authors":"Ashna Raiker, Jana Latayan, S. Pagsuyoin, Aaron Mathieu","doi":"10.1109/SIEDS.2016.7489307","DOIUrl":"https://doi.org/10.1109/SIEDS.2016.7489307","url":null,"abstract":"Depression is a major and costly global health burden that affects millions of people. The current diagnostic screen for depression relies on subjective structured interviews, but there is growing interest in exploring objective methods that involve depression biomarkers. In the current paper we perform a systematic review of recent articles on depression biomarkers that were published from 2012 to 2016. A screening procedure was developed and implemented to identify articles that have examined and compared biomarker levels in control (healthy) and study (diagnosed with major depressive disorder) groups. Seven biomarkers from three research articles were identified: vascular endothelial growth factor (VEGF) and Neutrophil gelatinase-associated lipocalin (NGAL) in plasma; and citrate, tyrosine, hippurate, phenylalanine, and alanine in urine. 95% confidence intervals were calculated for biomarker levels in control and study groups. Differences in measured biomarker levels between these two groups were statistically significant for all biomarkers, and trends were consistent with prior studies. We also note that the detected levels vary widely (up to several orders of magnitude) across biomarkers. For low-level biomarkers, this can present an analytical challenge in regions where the required instrument for analysis is too costly or the analytical technique is too complex to perform. For the scientific community, this presents an opportunity for pursuing analytical methods development in tandem with research on identifying suitable biomarkers for depression diagnostics.","PeriodicalId":426864,"journal":{"name":"2016 IEEE Systems and Information Engineering Design Symposium (SIEDS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122844575","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":"Simultaneous removal of anions using moringa-functionalized adsorbents","authors":"J. Barajas, S. Pagsuyoin, Jana Latayan","doi":"10.1109/SIEDS.2016.7489283","DOIUrl":"https://doi.org/10.1109/SIEDS.2016.7489283","url":null,"abstract":"Nitrates, phosphates, and many other anionic chemical species are among the most problematic and widespread contaminants in water sources. Currently, technologies for removing them in water involve biological and physico-chemical processes. In this study, we test the extent to which the cationic protein from Moringa Oleifera (MO) seeds can effectively sequester anionic contaminants in water. The protein was isolated from the MO seed through selective adsorption onto two carbon adsorbents: rice husk ash and commercial activated carbon. This step was designed to eliminate the co-release of soluble organics in MO seeds, which can shorten the storage life of the treated water. The MO-functionalized adsorbents were then tested for their removal efficiency of five anions: chloride, nitrite, nitrate, phosphate and sulfate. A semi-factorial experimental design was adopted to evaluate the effect of contact time and adsorbent dose on the anion removal efficiencies. As a control, experiments were also run in parallel using bare carbon adsorbents. The aqueous MO protein concentrations were measured using an optical density meter (280 nm) and ion concentrations were measured using an ion chromatograph. ANOVA analysis was performed to determine the effectiveness of Moringa-functionalized carbon adsorbents compared to bare carbon adsorbents. Results show that MO protein adsorbs well on the carbon adsorbents, and that adsorption is higher in activated carbon than in rice husk. Equilibrium is achieved at 20 minutes of contact time. In all adsorbents (bare and MO-functionalized), the highest anion removal rate was observed for nitrate. Anion removal rates were generally higher in MO-functionalized adsorbents than in bare adsorbents. Phosphate removal was only observed in the MO-functionalized adsorbents, although it is noted that rice husk ash contained large amounts of soluble phosphate that contributed to a net positive increase of phosphate levels in the water. Overall, these findings suggest a strong potential for using MO protein as a low-cost water treatment technology, for example, in removing anionic dyes and surfactants. Further studies are needed to examine the surface interactions among anions, carbon adsorbents, and MO protein.","PeriodicalId":426864,"journal":{"name":"2016 IEEE Systems and Information Engineering Design Symposium (SIEDS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116659549","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":"Effect of order flow imbalance on market impact across market states","authors":"Andrew Kromkowski, Mason Montgomery, Kaustav Saha, F. Wu, P. Beling","doi":"10.1109/SIEDS.2016.7489318","DOIUrl":"https://doi.org/10.1109/SIEDS.2016.7489318","url":null,"abstract":"Every time a trader places an order to buy or sell a stock, this order causes reactions that change the market in highly complex ways. In theory these changes are always detrimental to the trader, causing the stock to become more expensive when buying and cheaper when selling. For large hedge funds, these costs have the potential to become a major obstruction to profitability when aggregated. Market impact models have been based on simple supply and demand, no arbitrage theory, and Brownian motion. These previous models have shown that the market impact of orders and trades can be largely explained using a linear model with Order Flow Imbalance (OFI), a simple measure of the buy/sell imbalance of quote orders placed to the National Best Bid and Offer (NBBO) in a window of time, as the sole predictor. By examining this relationship between OFI and price movement, previous studies have derived observable measures for the market impact of orders placed in a period of time, however these models are unsurprisingly noisy. Using a simple Brownian motion model for the movement of prices, we propose a new method for observing this price impact and compare it to previously accepted models. We then use this measure to examine how price impact varies across market states (i.e. volume, time of day, and spread).","PeriodicalId":426864,"journal":{"name":"2016 IEEE Systems and Information Engineering Design Symposium (SIEDS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126852782","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 online user behavior to predict demographics","authors":"Katie Owens, Conor Mettenburg, Evan Cohen, A. Ripley, Ruben Aghayan, W. Scherer","doi":"10.1109/SIEDS.2016.7489331","DOIUrl":"https://doi.org/10.1109/SIEDS.2016.7489331","url":null,"abstract":"Videology, an online video advertising company, is often unable to obtain gender information about incoming online advertisement requests. They purchase aggregate gender statistics on groups of requests from a third party. This project explores creating groups of requests in which at least 80% of the advertisement requests have the same gender using: 1) traditional clustering algorithms, 2) iterative linear regression algorithm - ITRA - and 3) qualitative clustering algorithm (ROCK). In all cases, the data used was either browsing history data or synthetic attributes created by dimensionality reduction to more simply describe that history. These three approaches were unable to consistently create the desired gender discrimination. None of these three approaches proved to be the preferred alternative as the performance of each varied drastically as the test data set, and even subsets of that test data set changed. However, amongst the data sets used, these methods were able in some instances to create small buckets (less than 3,000 requests) with the desired gender distribution. The success or failure of these algorithms was dependent upon how similar individual requests were to one another (i.e. how many attributes were on average shared between requests). The approaches performed better in those instances in which more attributes were shared between requests, i.e., the requests contained information that allowed for the classification of the requests.","PeriodicalId":426864,"journal":{"name":"2016 IEEE Systems and Information Engineering Design Symposium (SIEDS)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128464596","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}