Pub Date : 2019-04-26DOI: 10.1109/SIEDS.2019.8735591
Corinne Brady, Faldo Jatmoko, B. Mansoor, Daniel I. Castaneda, Heather Kirkvold, B. Striebig
A series of pedestrian bridges in the Mossy Creek area in Mount Solon, VA, were washed away after historic flooding in May and September 2018. There is a need to rebuild the bridges so that community members and visitors can access both sides of the creek's banks, specifically for the creek's primarily recreational activity of fly fishing. To respond to this problem, seven engineering students joined a special projects class coordinated by three engineering faculty members at James Madison University (JMU). In this class, students engaged with community stakeholders, developed a preliminary design of a bridge, and researched stabilization techniques of the streambed that can protect a new pedestrian bridge and trout habitat during future flood events. During this engineering process, the students sought to understand the partnership among Trout Unlimited (a non-profit), the private landowners, and the VA Department of Game and Inland Fisheries (DGIF). In that partnership, there are posted restrictions against wading through the environmentally-sensitive creek to prevent contaminants and invasive species from entering and harming the creek's ecosystem. This class is an extracurricular course offering in the JMU (non-discipline specific) engineering program, primarily centered as a problem-based approach to a specific realworld problem in the local community bounded by various constraints (e.g., community needs, environmental regulations, timeliness of construction, etc.). Through this class, students are participating in a course designed to encourage experiential learning and support interest in the engineering disciplines of civil and environmental engineering.
{"title":"Bridge over Mossy Creek","authors":"Corinne Brady, Faldo Jatmoko, B. Mansoor, Daniel I. Castaneda, Heather Kirkvold, B. Striebig","doi":"10.1109/SIEDS.2019.8735591","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735591","url":null,"abstract":"A series of pedestrian bridges in the Mossy Creek area in Mount Solon, VA, were washed away after historic flooding in May and September 2018. There is a need to rebuild the bridges so that community members and visitors can access both sides of the creek's banks, specifically for the creek's primarily recreational activity of fly fishing. To respond to this problem, seven engineering students joined a special projects class coordinated by three engineering faculty members at James Madison University (JMU). In this class, students engaged with community stakeholders, developed a preliminary design of a bridge, and researched stabilization techniques of the streambed that can protect a new pedestrian bridge and trout habitat during future flood events. During this engineering process, the students sought to understand the partnership among Trout Unlimited (a non-profit), the private landowners, and the VA Department of Game and Inland Fisheries (DGIF). In that partnership, there are posted restrictions against wading through the environmentally-sensitive creek to prevent contaminants and invasive species from entering and harming the creek's ecosystem. This class is an extracurricular course offering in the JMU (non-discipline specific) engineering program, primarily centered as a problem-based approach to a specific realworld problem in the local community bounded by various constraints (e.g., community needs, environmental regulations, timeliness of construction, etc.). Through this class, students are participating in a course designed to encourage experiential learning and support interest in the engineering disciplines of civil and environmental engineering.","PeriodicalId":265421,"journal":{"name":"2019 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126640089","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 : 2019-04-26DOI: 10.1109/SIEDS.2019.8735608
Charles Rogers, John Bugg, C. Nyheim, Will Gebhardt, Brian Andris, Evan Heitman, C. Fleming
In overhead object detection, computers are increasingly replacing humans at spotting and identifying specific items within images through the use of machine learning (ML). These ML programs must be both accurate and robust. Accuracy means the results must be trusted enough to substitute for the manual deduction process. Robustness is the magnitude to which the network can handle discrepancies within the images. One way to gauge the robustness is through the use of adversarial networks. Adversarial algorithms are trained using perturbations of the image to reduce the accuracy of an existing classification model. The greater degree of perturbations a model can withstand, the more robust it is. In this paper, comparisons of existing deep neural network models and the advancement of adversarial AI are explored. While there is some published research about AI and adversarial networks, very little discusses this particular utilization for overhead imagery. This paper focuses on overhead imagery, specifically that of ships. Using a public Kaggle dataset, we developed multiple models to detect ships in overhead imagery, specifically ResNet50, DenseNet201, and InceptionV3. The goal of the adversarial works is to manipulate an image so that its contents are misclassified. This paper focuses specifically on producing perturbations that can be recreated in the physical world. This serves to account for physical conditions, whether intentional or not, that could reduce accuracy within our network. While there are military applications for this specific research, the general findings can be applied to all AI overhead image classification topics. This work will explore both the vulnerabilities of existing classifier neural net models and the visualization of these vulnerabilities.
{"title":"Adversarial Artificial Intelligence for Overhead Imagery Classification Models","authors":"Charles Rogers, John Bugg, C. Nyheim, Will Gebhardt, Brian Andris, Evan Heitman, C. Fleming","doi":"10.1109/SIEDS.2019.8735608","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735608","url":null,"abstract":"In overhead object detection, computers are increasingly replacing humans at spotting and identifying specific items within images through the use of machine learning (ML). These ML programs must be both accurate and robust. Accuracy means the results must be trusted enough to substitute for the manual deduction process. Robustness is the magnitude to which the network can handle discrepancies within the images. One way to gauge the robustness is through the use of adversarial networks. Adversarial algorithms are trained using perturbations of the image to reduce the accuracy of an existing classification model. The greater degree of perturbations a model can withstand, the more robust it is. In this paper, comparisons of existing deep neural network models and the advancement of adversarial AI are explored. While there is some published research about AI and adversarial networks, very little discusses this particular utilization for overhead imagery. This paper focuses on overhead imagery, specifically that of ships. Using a public Kaggle dataset, we developed multiple models to detect ships in overhead imagery, specifically ResNet50, DenseNet201, and InceptionV3. The goal of the adversarial works is to manipulate an image so that its contents are misclassified. This paper focuses specifically on producing perturbations that can be recreated in the physical world. This serves to account for physical conditions, whether intentional or not, that could reduce accuracy within our network. While there are military applications for this specific research, the general findings can be applied to all AI overhead image classification topics. This work will explore both the vulnerabilities of existing classifier neural net models and the visualization of these vulnerabilities.","PeriodicalId":265421,"journal":{"name":"2019 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124168549","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 : 2019-04-26DOI: 10.1109/SIEDS.2019.8735643
T. A. Malapane
Globally, online shopping is on the rise with cybercrimes expected to rise. This study presents a risk analysis of the online shopping's e-commerce in South Africa using data collected through a variety of platforms where incidents and intelligence are reported and collected. Data was collected through a self-administered web-based online survey. A randomized sample size of 459 was used to analyze perceived risks associated with online shopping. This paper further outlines perceived risk results and findings by categorizing impact type, attack vector and threat type. Results of this study show that risks associated with finance losses impact the online shopping in the e-commerce space. This has not yet been fully realized in South Africa. Results analyzed in this study also look at the online shopping confidence across the retail industry, hospitality industry and other industries aggregated in this study. Financial loss is highlighted as the major perceived risk recording a highest confidence level in terms of the results which are further categorized in terms of impact type, attack vector and threat type. A conclusion has been drawn which indicate that there is a correlation around recognized risks, impact type, attack vector and threat type in the online shopping space in South Africa.
{"title":"A Risk Analysis of E-Commerce: A Case of South African Online Shopping Space","authors":"T. A. Malapane","doi":"10.1109/SIEDS.2019.8735643","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735643","url":null,"abstract":"Globally, online shopping is on the rise with cybercrimes expected to rise. This study presents a risk analysis of the online shopping's e-commerce in South Africa using data collected through a variety of platforms where incidents and intelligence are reported and collected. Data was collected through a self-administered web-based online survey. A randomized sample size of 459 was used to analyze perceived risks associated with online shopping. This paper further outlines perceived risk results and findings by categorizing impact type, attack vector and threat type. Results of this study show that risks associated with finance losses impact the online shopping in the e-commerce space. This has not yet been fully realized in South Africa. Results analyzed in this study also look at the online shopping confidence across the retail industry, hospitality industry and other industries aggregated in this study. Financial loss is highlighted as the major perceived risk recording a highest confidence level in terms of the results which are further categorized in terms of impact type, attack vector and threat type. A conclusion has been drawn which indicate that there is a correlation around recognized risks, impact type, attack vector and threat type in the online shopping space in South Africa.","PeriodicalId":265421,"journal":{"name":"2019 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121787649","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 : 2019-04-26DOI: 10.1109/SIEDS.2019.8735616
Sophia Lam, Charles B. Chen, Kristi Kim, George Wilson, J. H. Crews, M. Gerber
Efficient and successful customer service is an integral aspect of all businesses. In 2017, U.S. businesses lost $75 billion through poor customer service, where customers encountered unhelpful staff or spent too much time on unresolved issues. Customer experience management software companies analyze call center customer-agent transcriptions using methods such as sentiment analysis and topic modeling to improve their clients' customer service. However, these approaches are not optimized to account for the sequential nature of these customer-agent interactions. For example, while it is important to know how many customers cancel a service, businesses also need to understand how agents respond to a cancellation request and how certain actions may lead to a positive or negative outcome. To analyze the progression of conversations and understand actions that maximize positive outcomes, our research represents each contact center dialogue as a Markov decision process (MDP). For each conversation, we annotated whether the problem was resolved and whether the outcome was good or bad from a business perspective. We employed natural language processing (NLP) to extract the customer states and agent actions from call transcriptions. Our results identify and visualize the most frequent transcription sequences from successful conversations and estimate the expected probability of an outcome when an agent takes an action given a certain customer state. Such an approach may be used to develop programs to train agents for improved customer service in call centers.
{"title":"Optimizing Customer-Agent Interactions with Natural Language Processing and Machine Learning","authors":"Sophia Lam, Charles B. Chen, Kristi Kim, George Wilson, J. H. Crews, M. Gerber","doi":"10.1109/SIEDS.2019.8735616","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735616","url":null,"abstract":"Efficient and successful customer service is an integral aspect of all businesses. In 2017, U.S. businesses lost $75 billion through poor customer service, where customers encountered unhelpful staff or spent too much time on unresolved issues. Customer experience management software companies analyze call center customer-agent transcriptions using methods such as sentiment analysis and topic modeling to improve their clients' customer service. However, these approaches are not optimized to account for the sequential nature of these customer-agent interactions. For example, while it is important to know how many customers cancel a service, businesses also need to understand how agents respond to a cancellation request and how certain actions may lead to a positive or negative outcome. To analyze the progression of conversations and understand actions that maximize positive outcomes, our research represents each contact center dialogue as a Markov decision process (MDP). For each conversation, we annotated whether the problem was resolved and whether the outcome was good or bad from a business perspective. We employed natural language processing (NLP) to extract the customer states and agent actions from call transcriptions. Our results identify and visualize the most frequent transcription sequences from successful conversations and estimate the expected probability of an outcome when an agent takes an action given a certain customer state. Such an approach may be used to develop programs to train agents for improved customer service in call centers.","PeriodicalId":265421,"journal":{"name":"2019 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128841043","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 : 2019-04-26DOI: 10.1109/SIEDS.2019.8735592
Charu Rawat, Arnab Sarkar, Sameer Singh, Raf Alvarado, Lane Rasberry
Today's digital landscape is characterized by the pervasive presence of online communities. One of the persistent challenges to the ideal of free-flowing discourse in these communities has been online abuse. Wikipedia is a case in point, as it's large community of contributors have experienced the perils of online abuse ranging from hateful speech to personal attacks to spam. Currently, Wikipedia has a human-driven process in place to identify online abuse. In this paper, we propose a framework to understand and detect such abuse in the English Wikipedia community. We analyze the publicly available data sources provided by Wikipedia. We discover that Wikipedia's XML dumps require extensive computing power to be used for temporal textual analysis, and, as an alternative, we propose a web scraping methodology to extract user-level data and perform extensive exploratory data analysis to understand the characteristics of users who have been blocked for abusive behavior in the past. With these data, we develop an abuse detection model that leverages Natural Language Processing techniques, such as character and word n-grams, sentiment analysis and topic modeling, and generates features that are used as inputs in a model based on machine learning algorithms to predict abusive behavior. Our best abuse detection model, using XGBoost Classifier, gives us an AUC of ∼84%.
{"title":"Automatic Detection of Online Abuse and Analysis of Problematic Users in Wikipedia","authors":"Charu Rawat, Arnab Sarkar, Sameer Singh, Raf Alvarado, Lane Rasberry","doi":"10.1109/SIEDS.2019.8735592","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735592","url":null,"abstract":"Today's digital landscape is characterized by the pervasive presence of online communities. One of the persistent challenges to the ideal of free-flowing discourse in these communities has been online abuse. Wikipedia is a case in point, as it's large community of contributors have experienced the perils of online abuse ranging from hateful speech to personal attacks to spam. Currently, Wikipedia has a human-driven process in place to identify online abuse. In this paper, we propose a framework to understand and detect such abuse in the English Wikipedia community. We analyze the publicly available data sources provided by Wikipedia. We discover that Wikipedia's XML dumps require extensive computing power to be used for temporal textual analysis, and, as an alternative, we propose a web scraping methodology to extract user-level data and perform extensive exploratory data analysis to understand the characteristics of users who have been blocked for abusive behavior in the past. With these data, we develop an abuse detection model that leverages Natural Language Processing techniques, such as character and word n-grams, sentiment analysis and topic modeling, and generates features that are used as inputs in a model based on machine learning algorithms to predict abusive behavior. Our best abuse detection model, using XGBoost Classifier, gives us an AUC of ∼84%.","PeriodicalId":265421,"journal":{"name":"2019 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128406618","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 : 2019-04-26DOI: 10.1109/SIEDS.2019.8735622
Akarapan Rojjanapinun, S. Pagsuyoin, Jiayue Luo
Pharmaceuticals are a class of emerging micropollutants whose detection in surface waters have been attributed to domestic effluent discharges. Although concerns over potential ecological and health impacts have been raised for certain pharmaceutical groups (e.g., antibiotics), to date there are no discharge standards for these chemicals. Given that most ecotoxicity studies for pharmaceuticals were performed in laboratory settings that may differ from environmental conditions, there is a need to establish their actual environmental concentrations. In the current study, we performed a systematic review of literature to examine the influent sewage concentrations of erythromycin (prescription antibiotic) and ibuprofen (over-the counter pain reliever) in municipal wastewater treatment plants (WWTPs). The literature search and screening procedure yielded datasets from a total of 250 WWTPs which were grouped according to plant capacity (small, < 10 mega gallons per day, MGD; medium, 10–100 MGD; and large, > 100 MGD) and geographic location (Asia, Europe, North America). Measured erythromycin levels in the influent ranged from $10^{-1} {mu} mathrm{g}/mathrm{L}$ to $1 {mu} mathrm{g}/mathrm{L}$, while ibuprofen levels ranged from $10^{-1} {mu} mathrm{g}/mathrm{L}$ to $10^{2} {mu} mathrm{g}/mathrm{L}$. Average erythromycin levels were about the same across all WWTP sizes and regions. Average ibuprofen levels were significantly higher in small WWTPs than in large WWTPs ($mathrm{p} < 0.01$). Average ibuprofen levels were highest in North America −102 times higher than in Europe and 10 times higher than in Asia. With respect to WWTP operation, research findings suggest that small WWTPs should receive the same consideration as larger WWTPs where the level of treatment (i.e., degree of removal) for pharmaceuticals is concerned. Furthermore, the summarized occurrence data presented in this study provide insights to WWTP managers in assessing if enhanced WWTP treatment or downstream risks assessment for receiving streams are needed.
{"title":"Occurrence of Pharmaceuticals in WWTP Influents","authors":"Akarapan Rojjanapinun, S. Pagsuyoin, Jiayue Luo","doi":"10.1109/SIEDS.2019.8735622","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735622","url":null,"abstract":"Pharmaceuticals are a class of emerging micropollutants whose detection in surface waters have been attributed to domestic effluent discharges. Although concerns over potential ecological and health impacts have been raised for certain pharmaceutical groups (e.g., antibiotics), to date there are no discharge standards for these chemicals. Given that most ecotoxicity studies for pharmaceuticals were performed in laboratory settings that may differ from environmental conditions, there is a need to establish their actual environmental concentrations. In the current study, we performed a systematic review of literature to examine the influent sewage concentrations of erythromycin (prescription antibiotic) and ibuprofen (over-the counter pain reliever) in municipal wastewater treatment plants (WWTPs). The literature search and screening procedure yielded datasets from a total of 250 WWTPs which were grouped according to plant capacity (small, < 10 mega gallons per day, MGD; medium, 10–100 MGD; and large, > 100 MGD) and geographic location (Asia, Europe, North America). Measured erythromycin levels in the influent ranged from $10^{-1} {mu} mathrm{g}/mathrm{L}$ to $1 {mu} mathrm{g}/mathrm{L}$, while ibuprofen levels ranged from $10^{-1} {mu} mathrm{g}/mathrm{L}$ to $10^{2} {mu} mathrm{g}/mathrm{L}$. Average erythromycin levels were about the same across all WWTP sizes and regions. Average ibuprofen levels were significantly higher in small WWTPs than in large WWTPs ($mathrm{p} < 0.01$). Average ibuprofen levels were highest in North America −102 times higher than in Europe and 10 times higher than in Asia. With respect to WWTP operation, research findings suggest that small WWTPs should receive the same consideration as larger WWTPs where the level of treatment (i.e., degree of removal) for pharmaceuticals is concerned. Furthermore, the summarized occurrence data presented in this study provide insights to WWTP managers in assessing if enhanced WWTP treatment or downstream risks assessment for receiving streams are needed.","PeriodicalId":265421,"journal":{"name":"2019 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134316296","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 : 2019-04-26DOI: 10.1109/SIEDS.2019.8735647
Kathryn Tomzcak, Adam Pelter, Corey Gutierrez, Thomas Stretch, Daniel Hilf, Bianca Donadio, N. Tenhundfeld, E. D. de Visser, Chad C. Tossell
The reality of highly automated vehicles on every road seems increasingly possible. With companies such as Tesla, Google, Toyota, and many others racing to provide a fully autonomous vehicle, the need for research on self-driving cars has never been greater. Until recently, however, most of this research had been conducted in a sterile lab environment devoid of any real consequences. For that reason, we join a host of other researchers in evaluating human-automation interaction in the real world associated with miscalibrated trust. As previous research has shown, drivers can either over- or under trust a vehicle's automated features. To evaluate this in these in a realistic setting, we had participants use the Autopark feature in a Tesla Model X or park the car themselves in both parallel and perpendicular scenarios. Parking times, driver trust, self-confidence in their own ability to park, and workload were all evaluated throughout the experiment. Preliminary analyses into the data are reported. Trends for the interactions between parking condition (self versus auto) and the parking type (parallel versus perpendicular) emerged for both trust/self-confidence and workload. Data collection is still ongoing to evaluate whether these trends hold, and if they emerge as significant. In all, this study contributes to the growing body of literature which seeks to understand the complexities of human-automation interaction in the real world.
{"title":"Let Tesla Park Your Tesla: Driver Trust in a Semi-Automated Car","authors":"Kathryn Tomzcak, Adam Pelter, Corey Gutierrez, Thomas Stretch, Daniel Hilf, Bianca Donadio, N. Tenhundfeld, E. D. de Visser, Chad C. Tossell","doi":"10.1109/SIEDS.2019.8735647","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735647","url":null,"abstract":"The reality of highly automated vehicles on every road seems increasingly possible. With companies such as Tesla, Google, Toyota, and many others racing to provide a fully autonomous vehicle, the need for research on self-driving cars has never been greater. Until recently, however, most of this research had been conducted in a sterile lab environment devoid of any real consequences. For that reason, we join a host of other researchers in evaluating human-automation interaction in the real world associated with miscalibrated trust. As previous research has shown, drivers can either over- or under trust a vehicle's automated features. To evaluate this in these in a realistic setting, we had participants use the Autopark feature in a Tesla Model X or park the car themselves in both parallel and perpendicular scenarios. Parking times, driver trust, self-confidence in their own ability to park, and workload were all evaluated throughout the experiment. Preliminary analyses into the data are reported. Trends for the interactions between parking condition (self versus auto) and the parking type (parallel versus perpendicular) emerged for both trust/self-confidence and workload. Data collection is still ongoing to evaluate whether these trends hold, and if they emerge as significant. In all, this study contributes to the growing body of literature which seeks to understand the complexities of human-automation interaction in the real world.","PeriodicalId":265421,"journal":{"name":"2019 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124593449","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 : 2019-04-26DOI: 10.1109/SIEDS.2019.8735652
E. Boland, C. O’Brien, John Henry Oliphant, Josh Williams, Neal Goodloe, L. Alonzi, Michael C. Smith, K. P. White
In the mid-20th century, deinstitutionalization of mental health hospitals in the United States led to a dramatic decline in the availability of centralized institutional services. As a result, a result, a significant portion of the inmate population at correctional facilities consists of individuals with serious mental illness. In Charlottesville, VA and surrounding counties, individuals suffering from serious mental illness often depend on local community service providers (CSPs) for treatment after their release from custody, but limited interagency coordination impedes access to treatment. To better understand the characteristics of the population of incarcerated individuals with serious mental illness, data spanning a 30-month period from July 2015 to December 2017 were obtained through research partnerships with criminal justice agencies and CSPs in the Charlottesville area. In order to evaluate who might benefit from mental health services, this paper characterizes the population of inmates who met screening criteria for further mental health evaluation relative to those who did not. In the Albemarle-Charlottesville Regional Jail (ACRJ) booking data, 5,284 unique individuals were identified, of which 3,064 (48%) were screened for serious mental illness. Of those screened, 32% met the screening criteria for further mental health evaluation. For individuals who met the screening criteria, 21% were linked to a local community service provider for further mental health services. Key findings of this study include: •individuals who met the screening criteria for serious mental illness spent a more time in jail during the study period than those who did not meet the criteria. •individuals who stayed more than 30 days for any given booking event were more likely to have met the criteria for serious mental illness, •individuals who returned to custody due to probation violations were more likely to have met the criteria for serious mental illness, •individuals who were returned to custody most frequently and spent the most time in jail were more likely to meet the criteria for serious mental illness. The paper also analyzes the linkages between the criminal justice system and these individuals who require further mental health evaluation and services. These findings help agencies and community stakeholders develop a better understanding of relationships and interactions and establish best practices for enhancing public safety while addressing the needs of individuals suffering from mental illness.
{"title":"Evidence-Based Practice for Characterizing the Mentally-Ill Inmate Population","authors":"E. Boland, C. O’Brien, John Henry Oliphant, Josh Williams, Neal Goodloe, L. Alonzi, Michael C. Smith, K. P. White","doi":"10.1109/SIEDS.2019.8735652","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735652","url":null,"abstract":"In the mid-20th century, deinstitutionalization of mental health hospitals in the United States led to a dramatic decline in the availability of centralized institutional services. As a result, a result, a significant portion of the inmate population at correctional facilities consists of individuals with serious mental illness. In Charlottesville, VA and surrounding counties, individuals suffering from serious mental illness often depend on local community service providers (CSPs) for treatment after their release from custody, but limited interagency coordination impedes access to treatment. To better understand the characteristics of the population of incarcerated individuals with serious mental illness, data spanning a 30-month period from July 2015 to December 2017 were obtained through research partnerships with criminal justice agencies and CSPs in the Charlottesville area. In order to evaluate who might benefit from mental health services, this paper characterizes the population of inmates who met screening criteria for further mental health evaluation relative to those who did not. In the Albemarle-Charlottesville Regional Jail (ACRJ) booking data, 5,284 unique individuals were identified, of which 3,064 (48%) were screened for serious mental illness. Of those screened, 32% met the screening criteria for further mental health evaluation. For individuals who met the screening criteria, 21% were linked to a local community service provider for further mental health services. Key findings of this study include: •individuals who met the screening criteria for serious mental illness spent a more time in jail during the study period than those who did not meet the criteria. •individuals who stayed more than 30 days for any given booking event were more likely to have met the criteria for serious mental illness, •individuals who returned to custody due to probation violations were more likely to have met the criteria for serious mental illness, •individuals who were returned to custody most frequently and spent the most time in jail were more likely to meet the criteria for serious mental illness. The paper also analyzes the linkages between the criminal justice system and these individuals who require further mental health evaluation and services. These findings help agencies and community stakeholders develop a better understanding of relationships and interactions and establish best practices for enhancing public safety while addressing the needs of individuals suffering from mental illness.","PeriodicalId":265421,"journal":{"name":"2019 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122817451","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 : 2019-04-26DOI: 10.1109/SIEDS.2019.8735644
T. A. Malapane
This study explores the impact of Artificial Intelligence (AI) and Internet of Things (IoT) in the transformation of E-Business Sector in South Africa. AI and IoT are beginning to shape the future of many industries globally by generating an unprecedented amount of data. In the case of South Africa, we observe that in e-business new value can be created by the ways in which transactions are enabled. In this study we use the principles and applications of AI and IoT to determine the impacts in the transformation of E-Business sector in South Africa. The objective of this study is not to reproduce experiments, but to investigate and quantify the impact AI and IoT has in the transformative process of change in the E-Business sector. This study employed a qualitative research approach and data was collected through a systematic literature review using the snowballing search method. 18 peer reviewed papers were identified and analyzed in relation to their relevance to the study.
{"title":"The Impact of Artificial Intelligence and Internet of Things in the Transformation of E-Business Sector","authors":"T. A. Malapane","doi":"10.1109/SIEDS.2019.8735644","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735644","url":null,"abstract":"This study explores the impact of Artificial Intelligence (AI) and Internet of Things (IoT) in the transformation of E-Business Sector in South Africa. AI and IoT are beginning to shape the future of many industries globally by generating an unprecedented amount of data. In the case of South Africa, we observe that in e-business new value can be created by the ways in which transactions are enabled. In this study we use the principles and applications of AI and IoT to determine the impacts in the transformation of E-Business sector in South Africa. The objective of this study is not to reproduce experiments, but to investigate and quantify the impact AI and IoT has in the transformative process of change in the E-Business sector. This study employed a qualitative research approach and data was collected through a systematic literature review using the snowballing search method. 18 peer reviewed papers were identified and analyzed in relation to their relevance to the study.","PeriodicalId":265421,"journal":{"name":"2019 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114360207","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 : 2019-04-26DOI: 10.1109/SIEDS.2019.8735645
Joana de Paiva Azevedo, Hannah Delaney, McKenna Epperson, Cassia Jbeili, Samantha Jensen, Chase McGrail, Haley Weaver, Anna N. Baglione, Laura E. Barnes
Approximately one in five people in the United States are affected by mental illness, with anxiety disorders being the most common. Barriers to treatment include limited access to trained professionals and high financial cost. eHealth applications are one alternative to treatment outside of a traditional clinical setting. Patients can readily access eHealth interventions on their own time via devices such as computers, tablets, and smartphones. Despite the scalability and accessibility of eHealth applications, their benefits are overshadowed by high attrition rates. MindTrails (MT), an existing eHealth platform, uses Cognitive Bias Modification (CBM) to treat anxiety through online interventions designed to change negative thinking patterns. The MindTrails program has the potential to treat a large population of anxious individuals. The objective of this work is to identify, analyze, and implement strategies to increase user engagement with MindTrails by exploring the integration of gamification/engagement strategies into the program. Our design for increasing engagement focuses on the Doherty Web Strategies, incorporating interactive, personal, supportive, and social elements. Using this new design, users will be able to set personalized goals that are clear, actionable, and reasonably challenging. To meet our objective, we developed high fidelity wireframes and prototypes, with the intent of utilizing user studies to evaluate the efficacy in MindTrails. Results of user tests are hypothesized to show the effectiveness of a personalized gamification feature in increasing user engagement while simultaneously reducing attrition. The improved design will be included in the next launch of the MindTrails program and demonstrates progress toward increasing the effectiveness of CBM treatment in eHealth applications.
{"title":"Gamification of eHealth Interventions to Increase User Engagement and Reduce Attrition","authors":"Joana de Paiva Azevedo, Hannah Delaney, McKenna Epperson, Cassia Jbeili, Samantha Jensen, Chase McGrail, Haley Weaver, Anna N. Baglione, Laura E. Barnes","doi":"10.1109/SIEDS.2019.8735645","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735645","url":null,"abstract":"Approximately one in five people in the United States are affected by mental illness, with anxiety disorders being the most common. Barriers to treatment include limited access to trained professionals and high financial cost. eHealth applications are one alternative to treatment outside of a traditional clinical setting. Patients can readily access eHealth interventions on their own time via devices such as computers, tablets, and smartphones. Despite the scalability and accessibility of eHealth applications, their benefits are overshadowed by high attrition rates. MindTrails (MT), an existing eHealth platform, uses Cognitive Bias Modification (CBM) to treat anxiety through online interventions designed to change negative thinking patterns. The MindTrails program has the potential to treat a large population of anxious individuals. The objective of this work is to identify, analyze, and implement strategies to increase user engagement with MindTrails by exploring the integration of gamification/engagement strategies into the program. Our design for increasing engagement focuses on the Doherty Web Strategies, incorporating interactive, personal, supportive, and social elements. Using this new design, users will be able to set personalized goals that are clear, actionable, and reasonably challenging. To meet our objective, we developed high fidelity wireframes and prototypes, with the intent of utilizing user studies to evaluate the efficacy in MindTrails. Results of user tests are hypothesized to show the effectiveness of a personalized gamification feature in increasing user engagement while simultaneously reducing attrition. The improved design will be included in the next launch of the MindTrails program and demonstrates progress toward increasing the effectiveness of CBM treatment in eHealth applications.","PeriodicalId":265421,"journal":{"name":"2019 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115198808","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：