Pub Date : 2020-04-01DOI: 10.1109/SIEDS49339.2020.9106637
Bailey Biber, Max Dodge, Melanie M. Gonzalez, Raymond Huang, Olivia Johnson, Zachary A Martin, Amanda Sieger, Vy Lan Tran, Sophia Xiao, Laura E. Barnes
This paper explores the combination of Attention Restoration Theory and immersive virtual technology as a novel therapy for short-term stress reduction in the workplace. The goal of this work is to understand how various immersive technologies impact the effect of both nature and urban environments on acute stress. In order to assess this, study participants were guided through “micro-vacations,” or a series of virtual nature or urban images, after being induced with stress. The micro-vacations were presented via three different virtual immersive technologies: a virtual reality (VR) experience using a headset in a booth, a GeoDome experience, or a 2D experience which acted as a control. Biometric, subjective mood and comfort data were gathered from the participants throughout the study in order to measure the changes in stress and mood before, during, and after the microvacation experiences. We hypothesize that the nature environments are more relaxing than the urban environments, and that both the VR booth and GeoDome will reduce stress levels in participants to a greater degree than the 2D images.
{"title":"Investigating the Efficacy of Virtual Experiences on Stress Reduction","authors":"Bailey Biber, Max Dodge, Melanie M. Gonzalez, Raymond Huang, Olivia Johnson, Zachary A Martin, Amanda Sieger, Vy Lan Tran, Sophia Xiao, Laura E. Barnes","doi":"10.1109/SIEDS49339.2020.9106637","DOIUrl":"https://doi.org/10.1109/SIEDS49339.2020.9106637","url":null,"abstract":"This paper explores the combination of Attention Restoration Theory and immersive virtual technology as a novel therapy for short-term stress reduction in the workplace. The goal of this work is to understand how various immersive technologies impact the effect of both nature and urban environments on acute stress. In order to assess this, study participants were guided through “micro-vacations,” or a series of virtual nature or urban images, after being induced with stress. The micro-vacations were presented via three different virtual immersive technologies: a virtual reality (VR) experience using a headset in a booth, a GeoDome experience, or a 2D experience which acted as a control. Biometric, subjective mood and comfort data were gathered from the participants throughout the study in order to measure the changes in stress and mood before, during, and after the microvacation experiences. We hypothesize that the nature environments are more relaxing than the urban environments, and that both the VR booth and GeoDome will reduce stress levels in participants to a greater degree than the 2D images.","PeriodicalId":331495,"journal":{"name":"2020 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133538816","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}
Pub Date : 2020-04-01DOI: 10.1109/SIEDS49339.2020.9106676
J. M. Howerton, Benjamin Leo Schenck
The goals of this project are to implement a LoRaWAN-based network of air quality sensors in Charlottesville and to use its data to generate a comparative spatial model of air quality before and during the COVID-19 outbreak. The implementation of this network required the distribution of “The Things Network” (TTN) LoRa gateways and our own custom-made sensor kits to volunteers distributed throughout the city. Our sensor kits measure temperature, humidity, CO2, and Particulate Matter (PM) 2.5 and 10, allowing us to take measurements in line with the EPA’s air quality index as well as to keep up with modern trends in research showing the importance of CO2 as an air quality metric. Preliminary spatial analysis comparing air quality before and after March 11, 2020, the day that UVA announced all classes would move online, shows a near universal decline in carbon dioxide levels, but inconclusive changes in particulate matter.
{"title":"The Deployment of a LoRaWAN-Based IoT Air Quality Sensor Network for Public Good","authors":"J. M. Howerton, Benjamin Leo Schenck","doi":"10.1109/SIEDS49339.2020.9106676","DOIUrl":"https://doi.org/10.1109/SIEDS49339.2020.9106676","url":null,"abstract":"The goals of this project are to implement a LoRaWAN-based network of air quality sensors in Charlottesville and to use its data to generate a comparative spatial model of air quality before and during the COVID-19 outbreak. The implementation of this network required the distribution of “The Things Network” (TTN) LoRa gateways and our own custom-made sensor kits to volunteers distributed throughout the city. Our sensor kits measure temperature, humidity, CO2, and Particulate Matter (PM) 2.5 and 10, allowing us to take measurements in line with the EPA’s air quality index as well as to keep up with modern trends in research showing the importance of CO2 as an air quality metric. Preliminary spatial analysis comparing air quality before and after March 11, 2020, the day that UVA announced all classes would move online, shows a near universal decline in carbon dioxide levels, but inconclusive changes in particulate matter.","PeriodicalId":331495,"journal":{"name":"2020 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133213339","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}
Pub Date : 2020-04-01DOI: 10.1109/SIEDS49339.2020.9106683
Ben Carper, Dillon McGowan, S. Miller, Joe Nelson, Leah Palombi, Lina Romeo, Kayla Spigelman, Afsaneh Doryab
The human body is composed of various biological clocks that impact physical and mental health functioning. Modeling biological rhythms provides the means to understand the effect of internal and external factors on human mental and physical performance. So far, biological rhythms have mostly been studied in controlled laboratory settings thus limiting the long term study and modeling of these rhythms. This paper presents the results of our exploratory study of modeling human rhythms with longitudinal physiological data collected from consumer devices in the wild. We used data from four people continuously wearing Empatica (E4) wristbands and Oura smart rings for approximately four months to build models of human rhythms. We then used those model parameters in a machine learning approach to predict mental and physical readiness. Our results showed that most models built with a combination of sensors and rhythmic features obtained a prediction accuracy above the baseline measure of 66% (Max accuracy = 82.7%). These results provide insights into the feasibility of using consumer devices to model biological rhythms and use them to assess human and performance and health.
{"title":"Modeling Biological Rhythms to Predict Mental and Physical Readiness","authors":"Ben Carper, Dillon McGowan, S. Miller, Joe Nelson, Leah Palombi, Lina Romeo, Kayla Spigelman, Afsaneh Doryab","doi":"10.1109/SIEDS49339.2020.9106683","DOIUrl":"https://doi.org/10.1109/SIEDS49339.2020.9106683","url":null,"abstract":"The human body is composed of various biological clocks that impact physical and mental health functioning. Modeling biological rhythms provides the means to understand the effect of internal and external factors on human mental and physical performance. So far, biological rhythms have mostly been studied in controlled laboratory settings thus limiting the long term study and modeling of these rhythms. This paper presents the results of our exploratory study of modeling human rhythms with longitudinal physiological data collected from consumer devices in the wild. We used data from four people continuously wearing Empatica (E4) wristbands and Oura smart rings for approximately four months to build models of human rhythms. We then used those model parameters in a machine learning approach to predict mental and physical readiness. Our results showed that most models built with a combination of sensors and rhythmic features obtained a prediction accuracy above the baseline measure of 66% (Max accuracy = 82.7%). These results provide insights into the feasibility of using consumer devices to model biological rhythms and use them to assess human and performance and health.","PeriodicalId":331495,"journal":{"name":"2020 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121851683","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}
Pub Date : 2020-04-01DOI: 10.1109/SIEDS49339.2020.9106632
Sneha Choudhary, Haritha Guttikonda, Dibyendu Roy Chowdhury, G. Learmonth
Document Retrieval has seen significant advancements in the last few decades. Latest developments in Natural Language Processing have made it possible to incorporate context and complex lexical patterns to document representations. This opens new possibilities for developing advanced retrieval systems. Traditional approaches for indexing documents suggest averaging word and sentence encoding to form fixed-length document embeddings. However, the common bag-of-word approach fails to incorporate the semantic context, which can be critical for understanding document-query relevancy. We address this by leveraging Bidirectional Encoder Representations from Transformers (BERT) to create semantically rich document embeddings. BERT compensates the limitations of the Term Frequency Inverse Document Frequency (TF-IDF) by incorporating contextual embeddings. In this paper, we propose an ensemble of BERT and TF-IDF for a document retrieval system, where TFIDF and BERT together score the documents against a query, to retrieve a final set of top K documents. We critically compare our model against the standard TF-IDF method and demonstrate a significant performance improvement on MS MARCO data (Microsoft-curated data of Bing queries).
{"title":"Document Retrieval Using Deep Learning","authors":"Sneha Choudhary, Haritha Guttikonda, Dibyendu Roy Chowdhury, G. Learmonth","doi":"10.1109/SIEDS49339.2020.9106632","DOIUrl":"https://doi.org/10.1109/SIEDS49339.2020.9106632","url":null,"abstract":"Document Retrieval has seen significant advancements in the last few decades. Latest developments in Natural Language Processing have made it possible to incorporate context and complex lexical patterns to document representations. This opens new possibilities for developing advanced retrieval systems. Traditional approaches for indexing documents suggest averaging word and sentence encoding to form fixed-length document embeddings. However, the common bag-of-word approach fails to incorporate the semantic context, which can be critical for understanding document-query relevancy. We address this by leveraging Bidirectional Encoder Representations from Transformers (BERT) to create semantically rich document embeddings. BERT compensates the limitations of the Term Frequency Inverse Document Frequency (TF-IDF) by incorporating contextual embeddings. In this paper, we propose an ensemble of BERT and TF-IDF for a document retrieval system, where TFIDF and BERT together score the documents against a query, to retrieve a final set of top K documents. We critically compare our model against the standard TF-IDF method and demonstrate a significant performance improvement on MS MARCO data (Microsoft-curated data of Bing queries).","PeriodicalId":331495,"journal":{"name":"2020 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125810597","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}
Pub Date : 2020-04-01DOI: 10.1109/SIEDS49339.2020.9106686
J. Bishop, Jaylen Burgess, Cooper Ramos, Jade Driggs, T. Williams, Chad C. Tossell, Elizabeth Phillips, Tyler H. Shaw, E. D. Visser
This paper introduces a new testbed called Cooking with Humans and Autonomy in Overcooked!2 for studying Performance and Teaming (CHAOPT). A validation study was conducted to examine the viability of Overcooked!2 as a research platform to explore teamwork and communication in humanautonomy teams. Unique measures derived from this platform such as productive chef actions (PCA), team expertise score and chef role contribution (CRC) distinguished performance between levels and players. Our findings demonstrate that we can derive meaningful team process, performance and communication measures and that the interactions within Overcooked!2 meet the requirements of psychological fidelity of teaming research.
{"title":"CHAOPT: A Testbed for Evaluating Human-Autonomy Team Collaboration Using the Video Game Overcooked!2","authors":"J. Bishop, Jaylen Burgess, Cooper Ramos, Jade Driggs, T. Williams, Chad C. Tossell, Elizabeth Phillips, Tyler H. Shaw, E. D. Visser","doi":"10.1109/SIEDS49339.2020.9106686","DOIUrl":"https://doi.org/10.1109/SIEDS49339.2020.9106686","url":null,"abstract":"This paper introduces a new testbed called Cooking with Humans and Autonomy in Overcooked!2 for studying Performance and Teaming (CHAOPT). A validation study was conducted to examine the viability of Overcooked!2 as a research platform to explore teamwork and communication in humanautonomy teams. Unique measures derived from this platform such as productive chef actions (PCA), team expertise score and chef role contribution (CRC) distinguished performance between levels and players. Our findings demonstrate that we can derive meaningful team process, performance and communication measures and that the interactions within Overcooked!2 meet the requirements of psychological fidelity of teaming research.","PeriodicalId":331495,"journal":{"name":"2020 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123801903","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}
Pub Date : 2020-04-01DOI: 10.1109/SIEDS49339.2020.9106666
H.J. Bramham, Claire Deaver, Sean Domnick, E. Hand, Emily Ledwith, Noah O’Neill, Carolyn Weiler, Michael C. Smith, K. P. White, L. Alonzi, Neal Goodloe
Closure of psychiatric hospitals in favor of community-based treatment methods (Torrey, 1997), resulted in jails and prisons becoming the “new asylums” of the United States (National Institute of Corrections, 2014). Over the past decade, research teams in Charlottesville, Virginia, have studied data from the region to better understand the nature and extent of the individuals in the criminal justice system who suffer from severe mental illnesses (Boland et al., 2019). The work presented here extends this prior research by enlarging the study population to cover a longer time period, by characterizing the dynamic paths individuals follow through various periods of incarceration, mental health services, homelessness, and probation/supervision, and by incorporating geocoding to explore whether proximity to treatment centers has an impact on linkage to mental health services.Under an approved Institutional Review Board (IRB) protocol, the research team partnered with multiple local criminal justice agencies and community service providers (CSPs) to share data. These agencies interact through the Albemarle-Charlottesville Evidence Based Decision Making (EBDM) Policy Team, where regular monthly meetings are held to discuss issues in the criminal justice system. The research team analyzed data across 48 months from July 2015 to June 2019. These data comprise 8,332 individuals booked into Albemarle/Charlottesville Regional Jail (ACRJ), 13,340 individuals who received Region Ten Community Services Board (R10) mental health or substance abuse services, 2,117 individuals in a locally maintained database of homeless individuals, and 4,345 individuals who received services from Offender Aid and Restoration (OAR), which supervises individuals on local probation. Of the individuals booked into ACRJ, 18 percent “screened in” for referral for mental health services according to the Brief Jail Mental Health Screener (BJMHS). Key findings and outcomes of this study include:•Of the 8,332 individuals booked into ACRJ, 5,499 individuals (67%;) were administered the BJMHS.•Of those 5,499 individuals administered the BJMHS, 1,534 screened in for referral to mental health services, which is 28%; of individuals who received the screener and 18%; of all individuals at ACRJ.These findings support the results of prior research with greater statistical confidence. New findings include:•Individuals who associate their current legal trouble with drugs and alcohol have a 12%; higher screening-in rate than those who do not.•63%; of individuals in ACRJ who screened in and were available to be treated once released ultimately were linked to R10 services.In previous years, BJMHS results showed that there were nearly three times as many people with severe mental illness in jail than previously estimated by the state, and that linkage to mental health services could be improved. These findings led to the development of the Therapeutic Docket, an alternative to the standard judicial pr
{"title":"Linkages Between Community Mental Health Services, Homelessness, and Inmates and Probationers with Severe Mental Illness: An Evidence-Based Assessment","authors":"H.J. Bramham, Claire Deaver, Sean Domnick, E. Hand, Emily Ledwith, Noah O’Neill, Carolyn Weiler, Michael C. Smith, K. P. White, L. Alonzi, Neal Goodloe","doi":"10.1109/SIEDS49339.2020.9106666","DOIUrl":"https://doi.org/10.1109/SIEDS49339.2020.9106666","url":null,"abstract":"Closure of psychiatric hospitals in favor of community-based treatment methods (Torrey, 1997), resulted in jails and prisons becoming the “new asylums” of the United States (National Institute of Corrections, 2014). Over the past decade, research teams in Charlottesville, Virginia, have studied data from the region to better understand the nature and extent of the individuals in the criminal justice system who suffer from severe mental illnesses (Boland et al., 2019). The work presented here extends this prior research by enlarging the study population to cover a longer time period, by characterizing the dynamic paths individuals follow through various periods of incarceration, mental health services, homelessness, and probation/supervision, and by incorporating geocoding to explore whether proximity to treatment centers has an impact on linkage to mental health services.Under an approved Institutional Review Board (IRB) protocol, the research team partnered with multiple local criminal justice agencies and community service providers (CSPs) to share data. These agencies interact through the Albemarle-Charlottesville Evidence Based Decision Making (EBDM) Policy Team, where regular monthly meetings are held to discuss issues in the criminal justice system. The research team analyzed data across 48 months from July 2015 to June 2019. These data comprise 8,332 individuals booked into Albemarle/Charlottesville Regional Jail (ACRJ), 13,340 individuals who received Region Ten Community Services Board (R10) mental health or substance abuse services, 2,117 individuals in a locally maintained database of homeless individuals, and 4,345 individuals who received services from Offender Aid and Restoration (OAR), which supervises individuals on local probation. Of the individuals booked into ACRJ, 18 percent “screened in” for referral for mental health services according to the Brief Jail Mental Health Screener (BJMHS). Key findings and outcomes of this study include:•Of the 8,332 individuals booked into ACRJ, 5,499 individuals (67%;) were administered the BJMHS.•Of those 5,499 individuals administered the BJMHS, 1,534 screened in for referral to mental health services, which is 28%; of individuals who received the screener and 18%; of all individuals at ACRJ.These findings support the results of prior research with greater statistical confidence. New findings include:•Individuals who associate their current legal trouble with drugs and alcohol have a 12%; higher screening-in rate than those who do not.•63%; of individuals in ACRJ who screened in and were available to be treated once released ultimately were linked to R10 services.In previous years, BJMHS results showed that there were nearly three times as many people with severe mental illness in jail than previously estimated by the state, and that linkage to mental health services could be improved. These findings led to the development of the Therapeutic Docket, an alternative to the standard judicial pr","PeriodicalId":331495,"journal":{"name":"2020 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124219649","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}
Pub Date : 2020-04-01DOI: 10.1109/SIEDS49339.2020.9106655
Hailey Simon, Hannah Smitherman, A. Atchley, Jacob Davis, N. Tenhundfeld
Robotic systems are becoming more relevant in our daily lives. Robots are built in such a way that manufacturers hope consumers will feel comfortable integrating the robot into their everyday lives. Companies take into account physical traits, social cues, and responses given by the robot, to design a system that is fit for the task at hand. Many robots are built without consideration of gender and how that could affect users’ perceptions of the robots. In the present study, participants were shown a video in which a robot walked to a box, picked it up, and placed it on the table, while narrating what it was doing. Robot body, gait, and voice were manipulated, independently of one another, to reflect masculine or feminine features. The users’ perceptions of gender were measured, along with trust in the system, amount of liking, and perceived competence of the robot. Finally, participants were shown pictures of eight different robots of ambiguous form and were asked to indicate perceived gender on a continuum from “very feminine” to “very masculine”. Results indicated that robot voice strongly predicted perceptions of gender, whereas the body and gait of the robot did not. Additionally, participants ranked the Amazon Echo as being the most feminine of the eight additional robots shown, despite having no obvious feminine physical characteristics.
{"title":"Nuts and Bolts About You: Finding the Right Match in Gendered Robots","authors":"Hailey Simon, Hannah Smitherman, A. Atchley, Jacob Davis, N. Tenhundfeld","doi":"10.1109/SIEDS49339.2020.9106655","DOIUrl":"https://doi.org/10.1109/SIEDS49339.2020.9106655","url":null,"abstract":"Robotic systems are becoming more relevant in our daily lives. Robots are built in such a way that manufacturers hope consumers will feel comfortable integrating the robot into their everyday lives. Companies take into account physical traits, social cues, and responses given by the robot, to design a system that is fit for the task at hand. Many robots are built without consideration of gender and how that could affect users’ perceptions of the robots. In the present study, participants were shown a video in which a robot walked to a box, picked it up, and placed it on the table, while narrating what it was doing. Robot body, gait, and voice were manipulated, independently of one another, to reflect masculine or feminine features. The users’ perceptions of gender were measured, along with trust in the system, amount of liking, and perceived competence of the robot. Finally, participants were shown pictures of eight different robots of ambiguous form and were asked to indicate perceived gender on a continuum from “very feminine” to “very masculine”. Results indicated that robot voice strongly predicted perceptions of gender, whereas the body and gait of the robot did not. Additionally, participants ranked the Amazon Echo as being the most feminine of the eight additional robots shown, despite having no obvious feminine physical characteristics.","PeriodicalId":331495,"journal":{"name":"2020 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127401037","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}
Pub Date : 2020-04-01DOI: 10.1109/SIEDS49339.2020.9106668
Peter Shevchenko, Noah Faurot, C. Barentine, Anthony J. Ries
This study proposes a solution to improve data quality from remote desktop eye trackers. Poor data quality from these systems regularly occurs as a result of participants unknowingly moving outside of the functional data collection area, i.e. the eye tracking box. Researchers are often not aware of the low quality data until after it has been recorded. As a result potentially large amounts of data are unusable. To alleviate this concern, we propose a real-time feedback system that alerts participants when poor eye tracking data are detected, thus enabling them to adjust their position in front of the eye tracker as soon as they move out of the functional data collection area. This capability allows researchers to acquire a higher percentage of useful data over the course of an experiment. Our approach utilized a Raspberry Pi that collected and interpreted data quality from an eye tracker in real time. Data quality from each eye was mapped to a light emitting diode (LED) placed above the computer monitor. The color of LED reflected the current quality of eye tracking data with green and red indicating high and low quality respectively. To determine if the system was effective, we compared the data quality for participants who used the system relative to participants who did not while they performed a cognitive task. Results show increased data quality for those participants using the feedback system. Our results suggest that future studies using remote desktop eye trackers can increase data quality by providing real-time data quality feedback to the participants.
{"title":"Improving Data Quality from Remote Eye Tracking Systems Using Real Time Feedback","authors":"Peter Shevchenko, Noah Faurot, C. Barentine, Anthony J. Ries","doi":"10.1109/SIEDS49339.2020.9106668","DOIUrl":"https://doi.org/10.1109/SIEDS49339.2020.9106668","url":null,"abstract":"This study proposes a solution to improve data quality from remote desktop eye trackers. Poor data quality from these systems regularly occurs as a result of participants unknowingly moving outside of the functional data collection area, i.e. the eye tracking box. Researchers are often not aware of the low quality data until after it has been recorded. As a result potentially large amounts of data are unusable. To alleviate this concern, we propose a real-time feedback system that alerts participants when poor eye tracking data are detected, thus enabling them to adjust their position in front of the eye tracker as soon as they move out of the functional data collection area. This capability allows researchers to acquire a higher percentage of useful data over the course of an experiment. Our approach utilized a Raspberry Pi that collected and interpreted data quality from an eye tracker in real time. Data quality from each eye was mapped to a light emitting diode (LED) placed above the computer monitor. The color of LED reflected the current quality of eye tracking data with green and red indicating high and low quality respectively. To determine if the system was effective, we compared the data quality for participants who used the system relative to participants who did not while they performed a cognitive task. Results show increased data quality for those participants using the feedback system. Our results suggest that future studies using remote desktop eye trackers can increase data quality by providing real-time data quality feedback to the participants.","PeriodicalId":331495,"journal":{"name":"2020 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121318516","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}
Objective: The objective of this study is to gather and analyze data through the use of psychometric instruments regarding several theoretical constructs, including Team Cohesion, Team Familiarity, and Team Effectiveness in order to determine their differential impact on Team Performance outcomes. Background: The annual Sandhurst competition, held at the United States Military Academy, provides cadets the opportunity to function as a small unit. Data collected before, during, and after the competition is used to study the performance of each team in order to gain insights on how Team Cohesion, textit{TeamFamiliarity}, and Team Effectiveness influence their final rankings. In addition, this study develops and tests a Soldier Lethality proxy measure using numerical data collected before and during the competition, which is also used to predict Team Performance. Methods: Psychometric instruments and linear regression models are used to determine the significance of the theoretical constructs and the Soldier Lethality measure on Team Performance outcomes. Results: A total of 194 cadets out of the 456 cadets that participated in the Sandhurst Competition completed the survey. Our findings show that the theoretical constructs were not statistically significant when evaluating Team Performance. However, the Soldier Lethality measure yields a significant result (p-value =0.002; β=0.5; R2=0.22). Conclusions: In this study, raw physical data (denoted here as secondary data) is more effective in predicting Team Performance outcomes in a combatlike setting as opposed to using psychometric instruments due to non-response error (failure to respond to one, or all of the survey questions) and response bias (untruthfully or misleadingly responses). Application: This study shows how objective, detailed data on teamwork may be used to provide insights into questions of the performance of teams.
{"title":"A Cut Above the Rest: Team Performance as a Function of Team Cohesion, Team Familiarity, Team Effectiveness, and Soldier Lethality","authors":"Foster Dittmer, Hays Greer, Hannah Homsy, Connor Long, Kathryn Seyer, J. Eaton","doi":"10.1109/SIEDS49339.2020.9106660","DOIUrl":"https://doi.org/10.1109/SIEDS49339.2020.9106660","url":null,"abstract":"Objective: The objective of this study is to gather and analyze data through the use of psychometric instruments regarding several theoretical constructs, including Team Cohesion, Team Familiarity, and Team Effectiveness in order to determine their differential impact on Team Performance outcomes. Background: The annual Sandhurst competition, held at the United States Military Academy, provides cadets the opportunity to function as a small unit. Data collected before, during, and after the competition is used to study the performance of each team in order to gain insights on how Team Cohesion, textit{TeamFamiliarity}, and Team Effectiveness influence their final rankings. In addition, this study develops and tests a Soldier Lethality proxy measure using numerical data collected before and during the competition, which is also used to predict Team Performance. Methods: Psychometric instruments and linear regression models are used to determine the significance of the theoretical constructs and the Soldier Lethality measure on Team Performance outcomes. Results: A total of 194 cadets out of the 456 cadets that participated in the Sandhurst Competition completed the survey. Our findings show that the theoretical constructs were not statistically significant when evaluating Team Performance. However, the Soldier Lethality measure yields a significant result (p-value =0.002; β=0.5; R2=0.22). Conclusions: In this study, raw physical data (denoted here as secondary data) is more effective in predicting Team Performance outcomes in a combatlike setting as opposed to using psychometric instruments due to non-response error (failure to respond to one, or all of the survey questions) and response bias (untruthfully or misleadingly responses). Application: This study shows how objective, detailed data on teamwork may be used to provide insights into questions of the performance of teams.","PeriodicalId":331495,"journal":{"name":"2020 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122603297","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}
Pub Date : 2020-04-01DOI: 10.1109/SIEDS49339.2020.9106673
Winfred Hills, William Daniel, Mo Yang Lu, Oliver Schaer, Stephen Adams
With the widespread adoption of customer relationship management (CRM) systems such as Salesforce, HubSpot and Oracle, businesses are becoming increasingly aware of their customer churn rates. Churn rates describe how many customers stop using a product or service within a certain time period and provide a sense of the businesses’ long-term viability. Business-to-Business (B2B) firms place high value on the ability to predict individual customer churn, as it presents an opportunity to retain key clients in an inherently limited customer portfolio. These predictions must be both actionable and timely if a manager hopes to retain their client, since a client’s churn decision occurs months before the observed churn event. This study explores the HubSpot data of a B2B organization. The objective is to determine the client characteristics that predict sustained product usage and to analyze the indicators of potential churn. Our approach was to model the predictive features of client churn, which would allow managers to directly map churn probability to business strategies. Our final models flagged a handful of management-adjustable features that were significant for predicting customer churn and survival times.
{"title":"Modeling Client Churn for Small Business-to-Business Firms","authors":"Winfred Hills, William Daniel, Mo Yang Lu, Oliver Schaer, Stephen Adams","doi":"10.1109/SIEDS49339.2020.9106673","DOIUrl":"https://doi.org/10.1109/SIEDS49339.2020.9106673","url":null,"abstract":"With the widespread adoption of customer relationship management (CRM) systems such as Salesforce, HubSpot and Oracle, businesses are becoming increasingly aware of their customer churn rates. Churn rates describe how many customers stop using a product or service within a certain time period and provide a sense of the businesses’ long-term viability. Business-to-Business (B2B) firms place high value on the ability to predict individual customer churn, as it presents an opportunity to retain key clients in an inherently limited customer portfolio. These predictions must be both actionable and timely if a manager hopes to retain their client, since a client’s churn decision occurs months before the observed churn event. This study explores the HubSpot data of a B2B organization. The objective is to determine the client characteristics that predict sustained product usage and to analyze the indicators of potential churn. Our approach was to model the predictive features of client churn, which would allow managers to directly map churn probability to business strategies. Our final models flagged a handful of management-adjustable features that were significant for predicting customer churn and survival times.","PeriodicalId":331495,"journal":{"name":"2020 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115229998","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：