Pub Date : 2022-04-28DOI: 10.1109/sieds55548.2022.9799313
M. Caruso, J. Jabbour, C. Neale, Alden Summerville, A. Walters, Arsalan Heydarian, Arthur Small, Mahsa Pahlavikhah Varnosfaderani
A robust heating, ventilation, and air conditioning (HVAC) system is needed to maintain a healthy and comfortable indoor environment. However, HVAC systems are responsible for significant energy usage in the United States, and enhancing current systems and implementing additional HVAC sensing are primary strategies for reducing energy consumption. This research developed an HVAC control algorithm (CA) that optimized ventilation operations within a conference room in the University of Virginia Link Lab. Using indoor air quality (IAQ), occupancy, weather, and HVAC operation data streams, the CA recommended a decision to ventilate or not ventilate the conference room every 15 minutes by comparing the cost of lost occupant productivity due to poor IAQ to the energy cost of ventilating the space. The ventilation decision with lower total cost was recommended. This project addressed scheduling inefficiencies of the current HVAC control system, which operates at full power throughout the day regardless of occupancy status. The CA reduced ventilation during unoccupied periods. The CA was tested over two months of historical data from October to December 2021 and recommended ventilating the conference room 15.13 percent of the time. During the same period, the standard system ventilated the conference room 49 percent of the time. Energy savings due to decreased operation were considerable and averaged 424 dollars per month, although these energy savings came at the cost of lost occupant productivity totaling 522 dollars per month. Future work on lost occupant performance will more accurately model the effects of reduced ventilation. However, annual energy savings of 5,000 dollars from a single conference room is encouraging, and scaling a similar CA to consider a set of rooms or an entire floor of a building could result in substantial energy conservation.
{"title":"Developing a Dynamic Control Algorithm to Improve Ventilation Efficiency in a University Conference Room","authors":"M. Caruso, J. Jabbour, C. Neale, Alden Summerville, A. Walters, Arsalan Heydarian, Arthur Small, Mahsa Pahlavikhah Varnosfaderani","doi":"10.1109/sieds55548.2022.9799313","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799313","url":null,"abstract":"A robust heating, ventilation, and air conditioning (HVAC) system is needed to maintain a healthy and comfortable indoor environment. However, HVAC systems are responsible for significant energy usage in the United States, and enhancing current systems and implementing additional HVAC sensing are primary strategies for reducing energy consumption. This research developed an HVAC control algorithm (CA) that optimized ventilation operations within a conference room in the University of Virginia Link Lab. Using indoor air quality (IAQ), occupancy, weather, and HVAC operation data streams, the CA recommended a decision to ventilate or not ventilate the conference room every 15 minutes by comparing the cost of lost occupant productivity due to poor IAQ to the energy cost of ventilating the space. The ventilation decision with lower total cost was recommended. This project addressed scheduling inefficiencies of the current HVAC control system, which operates at full power throughout the day regardless of occupancy status. The CA reduced ventilation during unoccupied periods. The CA was tested over two months of historical data from October to December 2021 and recommended ventilating the conference room 15.13 percent of the time. During the same period, the standard system ventilated the conference room 49 percent of the time. Energy savings due to decreased operation were considerable and averaged 424 dollars per month, although these energy savings came at the cost of lost occupant productivity totaling 522 dollars per month. Future work on lost occupant performance will more accurately model the effects of reduced ventilation. However, annual energy savings of 5,000 dollars from a single conference room is encouraging, and scaling a similar CA to consider a set of rooms or an entire floor of a building could result in substantial energy conservation.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116201244","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 : 2022-04-28DOI: 10.1109/sieds55548.2022.9799403
T. A. Malapane, Nkanyiso Ndlovu
Globally, Artificial Intelligence (AI) in e-commerce has been widely accepted. A developing country like South Africa is expected to adopt AI especially in its e-commerce spaces. Notwithstanding the evidence that e-commerce is growing rapidly, South Africa's use of e-commerce is still growing with potential to grow further. This current study makes use of systematic review using snowballing approach. A total of 107 papers were searched and discovered for this study. These are papers related to e-commerce and AI fields. Iterations were applied to eliminate papers that were not relevant to this study. This was performed by using backward and forward snowballing. The paper also reviews the status of AI adoption in e-commerce and its application to the business landscape in South African context as well as the effectiveness on online shopping. The results of this review exercise show that South Africa has adopted Ai in -ecommerce over the past decades. However, it was further discovered that South Africa's e-commerce space is confronted with complex challenges and factors including the role played by the Internet of Things (IoT), Big Data analytics, ethical issues including privacy matters confronting e-commerce spaces. The role of government in the process is also notable as a factor and game changer in response to legislation and policy direction. The key outcome of the study shows that there is a need for a development of a framework for e-commerce in the context of South Africa.
{"title":"The Adoption of Artificial Intelligence in the South African E-Commerce Space: A Systematic Review","authors":"T. A. Malapane, Nkanyiso Ndlovu","doi":"10.1109/sieds55548.2022.9799403","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799403","url":null,"abstract":"Globally, Artificial Intelligence (AI) in e-commerce has been widely accepted. A developing country like South Africa is expected to adopt AI especially in its e-commerce spaces. Notwithstanding the evidence that e-commerce is growing rapidly, South Africa's use of e-commerce is still growing with potential to grow further. This current study makes use of systematic review using snowballing approach. A total of 107 papers were searched and discovered for this study. These are papers related to e-commerce and AI fields. Iterations were applied to eliminate papers that were not relevant to this study. This was performed by using backward and forward snowballing. The paper also reviews the status of AI adoption in e-commerce and its application to the business landscape in South African context as well as the effectiveness on online shopping. The results of this review exercise show that South Africa has adopted Ai in -ecommerce over the past decades. However, it was further discovered that South Africa's e-commerce space is confronted with complex challenges and factors including the role played by the Internet of Things (IoT), Big Data analytics, ethical issues including privacy matters confronting e-commerce spaces. The role of government in the process is also notable as a factor and game changer in response to legislation and policy direction. The key outcome of the study shows that there is a need for a development of a framework for e-commerce in the context of South Africa.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"37 19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125705044","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 : 2022-04-28DOI: 10.1109/sieds55548.2022.9799384
Sarah M. Cassway, M. Burch, M. Dean
Protecting critical assets, people, and information in defense agency operation centers requires teams to respond, respond correctly, and respond quickly to situations that arise on a 24/7 basis. It is important to measure success while also reducing risks that can jeopardize the mission, to consistently improve the processes that directly influence specific objectives. Scalable and affordable decision-support tools are not always readily available for large, mission-critical organizations. These off-the-shelf solutions that define and measure success and reveal areas for improvement are often not attainable due to budget and resource constraints. Additionally, many organizations rely on anecdotal evidence rather than real response data to make critical decisions. To address this, the Quality Assurance and Assessment tool (QAAT) was developed to allow team leaders to review their team's operational response performance. The QAAT is designed to not only understand the confidence level of a team or individual's performance, but it can also provoke change through optimized training procedures and key performance indicators. Working with the resources on hand, the tool was built with two main components: an operational performance review and an analytic data breakdown of performance results. Ultimately, this quality assurance solution will allow organizations to define and measure their success, identify risk factors that may influence their standard operations, and motivate organizational change from the ground up.
{"title":"Developing a Quality Assurance Tool for Mission Critical Facilities","authors":"Sarah M. Cassway, M. Burch, M. Dean","doi":"10.1109/sieds55548.2022.9799384","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799384","url":null,"abstract":"Protecting critical assets, people, and information in defense agency operation centers requires teams to respond, respond correctly, and respond quickly to situations that arise on a 24/7 basis. It is important to measure success while also reducing risks that can jeopardize the mission, to consistently improve the processes that directly influence specific objectives. Scalable and affordable decision-support tools are not always readily available for large, mission-critical organizations. These off-the-shelf solutions that define and measure success and reveal areas for improvement are often not attainable due to budget and resource constraints. Additionally, many organizations rely on anecdotal evidence rather than real response data to make critical decisions. To address this, the Quality Assurance and Assessment tool (QAAT) was developed to allow team leaders to review their team's operational response performance. The QAAT is designed to not only understand the confidence level of a team or individual's performance, but it can also provoke change through optimized training procedures and key performance indicators. Working with the resources on hand, the tool was built with two main components: an operational performance review and an analytic data breakdown of performance results. Ultimately, this quality assurance solution will allow organizations to define and measure their success, identify risk factors that may influence their standard operations, and motivate organizational change from the ground up.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127463990","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 : 2022-04-28DOI: 10.1109/sieds55548.2022.9799326
S. Keniston, G. Vasquez-Ramirez, E. Garcia, S. Solis
The Lynchburg Drag RC club meets regularly to host amateur street races using 1/7 scale cars that they construct, develop, and maintain. The lack of any concrete timing system or conclusive means of determining a winner in these races is the primary motivation for the work. The team will be constructing a fully automatic racing system for the RC club. The system will consist of two-boxes, governed by Arduino UNO microcontrollers, that will be wirelessly connected over Bluetooth along the 132 ft. of paved racing track. Each box will use two HC-SR04 ultrasonic proximity sensors along either side to detect the passage of a car independently and feed results to an LCD. The sensors should detect an object within 1 to 30 – 40 cm from the box. The first passage of any car will trigger the race time that will independently cut-off after cars pass the second box, with results being displayed likewise. The timing results for the races should produce 0.0001 second resolution as per customer requirements. The final system (as a whole) should also allow for the detection of false-starting cars, delay starting times along a side for slower cars, and have results uploaded to an iOS/Android app developed for car improvement and for members to schedule meets. The system will be tested by measuring the threshold triggering of the timer, evaluating the accuracy of the sensors in different atmospheric conditions by comparing results to controlled indoor fluorescent lighted races, and other tests as needed.
{"title":"Senior Capstone Design - RC Timing System","authors":"S. Keniston, G. Vasquez-Ramirez, E. Garcia, S. Solis","doi":"10.1109/sieds55548.2022.9799326","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799326","url":null,"abstract":"The Lynchburg Drag RC club meets regularly to host amateur street races using 1/7 scale cars that they construct, develop, and maintain. The lack of any concrete timing system or conclusive means of determining a winner in these races is the primary motivation for the work. The team will be constructing a fully automatic racing system for the RC club. The system will consist of two-boxes, governed by Arduino UNO microcontrollers, that will be wirelessly connected over Bluetooth along the 132 ft. of paved racing track. Each box will use two HC-SR04 ultrasonic proximity sensors along either side to detect the passage of a car independently and feed results to an LCD. The sensors should detect an object within 1 to 30 – 40 cm from the box. The first passage of any car will trigger the race time that will independently cut-off after cars pass the second box, with results being displayed likewise. The timing results for the races should produce 0.0001 second resolution as per customer requirements. The final system (as a whole) should also allow for the detection of false-starting cars, delay starting times along a side for slower cars, and have results uploaded to an iOS/Android app developed for car improvement and for members to schedule meets. The system will be tested by measuring the threshold triggering of the timer, evaluating the accuracy of the sensors in different atmospheric conditions by comparing results to controlled indoor fluorescent lighted races, and other tests as needed.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122343027","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 : 2022-04-28DOI: 10.1109/sieds55548.2022.9799349
M. Albery, Audrey Crowder, Santiago Leon, Ben Ryan
Buildings within the United States account for 21% of the nation's building energy consumption, contributing to the emission of CO2, among other pollutants. Approaching home design through energy efficient systems and green technologies is a critical step towards the reduction of the Greenhouse Effect and the creation of a cleaner world. We are competing on behalf of the Wake Forest University Engineering Department in the Department of Energy Solar Decathlon Design Challenge. The Design Challenge challenges students to excel in 10 competitions: Architecture, Engineering, Market Analysis, Durability and Resilience, Embodied Environmental Impact, Integrated Performance, Occupant Experience, Comfort and Environmental Quality, and Energy Performance. Our submission consists of a zero-carbon home design that is accessible to the average middle-class family in Charlotte, NC; however, the design is suitable for any location with a humid subtropical climate, which accounts for about 20% of the United States. This paper presents our final home design, which generates 1100 kWh of energy per month and achieves a Home Energy Rating System (HERS) score of less than 50 before renewables. These metrics have been assessed through energy modeling, thermal envelope analysis, and heating and cooling loads evaluation. To further evaluate our design, a market/cost analysis, daylight analysis, and embodied-energy evaluation have also been considered. Within our 1700 ft2 design, strategic bedroom design and dual-use spaces provide homeowners with flexible living spaces, additionally decreasing the energy that would be required for a more spacious home. Heat-pump technologies, a well-insulated thermal envelope, and opportunities for passive solar gain also reduce energy-generation requirements. Our future project outlook is to design a home that can be replicated in mass quantities across the US and the world, providing a significant platform for addressing climate change.
{"title":"Net-Zero Energy Home in Charlotte, NC – DOE Solar Decathlon Design Challenge","authors":"M. Albery, Audrey Crowder, Santiago Leon, Ben Ryan","doi":"10.1109/sieds55548.2022.9799349","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799349","url":null,"abstract":"Buildings within the United States account for 21% of the nation's building energy consumption, contributing to the emission of CO2, among other pollutants. Approaching home design through energy efficient systems and green technologies is a critical step towards the reduction of the Greenhouse Effect and the creation of a cleaner world. We are competing on behalf of the Wake Forest University Engineering Department in the Department of Energy Solar Decathlon Design Challenge. The Design Challenge challenges students to excel in 10 competitions: Architecture, Engineering, Market Analysis, Durability and Resilience, Embodied Environmental Impact, Integrated Performance, Occupant Experience, Comfort and Environmental Quality, and Energy Performance. Our submission consists of a zero-carbon home design that is accessible to the average middle-class family in Charlotte, NC; however, the design is suitable for any location with a humid subtropical climate, which accounts for about 20% of the United States. This paper presents our final home design, which generates 1100 kWh of energy per month and achieves a Home Energy Rating System (HERS) score of less than 50 before renewables. These metrics have been assessed through energy modeling, thermal envelope analysis, and heating and cooling loads evaluation. To further evaluate our design, a market/cost analysis, daylight analysis, and embodied-energy evaluation have also been considered. Within our 1700 ft2 design, strategic bedroom design and dual-use spaces provide homeowners with flexible living spaces, additionally decreasing the energy that would be required for a more spacious home. Heat-pump technologies, a well-insulated thermal envelope, and opportunities for passive solar gain also reduce energy-generation requirements. Our future project outlook is to design a home that can be replicated in mass quantities across the US and the world, providing a significant platform for addressing climate change.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116199116","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 : 2022-04-28DOI: 10.1109/sieds55548.2022.9799308
Rachel Kreitzer, R. Dennis, Steven D. Wasserman, Zachary Kay, Jer-Her Lu, S. Roberts., Thomas Twomey, W. Scherer
The college sports industry has grown tremendously over the past decade, with NCAA athletic departments recruiting almost half-a-million students to 19,866 teams in 2019 and generating $18.9 billion of revenue the same year. Identifying and selecting the best student-athletes is critical to maintaining the power of these sports programs, aggrandizing the recruitment pipeline and necessitating the demand for novel use of existing technologies. Sports analytics is one response to these growing needs, as its primary use in junior recruitment has presented fruitful for college basketball and football teams across the nation. Golf analytics firm GameForge aims to provide the same insights to college golf coaches, streamlining the recruitment of junior golfers to U.S. universities from around the world. GameForge seeks to develop a two-sided recruiting system that provides insights to junior players and their coaches as well as strengthen its predictive models with the inclusion of new data. A systems-based approach was taken to develop data-driven machine learning models that would provide (a) a proprietary ranking system that compares junior athletes to one another; (b) a relative SWOT analysis that highlights each player's strengths and skill gaps; and (c) a recommender system that suggests potential recruits to college coaches and recommends colleges of best fit to junior players.
{"title":"Golf and GameForge: Innovative Analytics for Recommender Systems","authors":"Rachel Kreitzer, R. Dennis, Steven D. Wasserman, Zachary Kay, Jer-Her Lu, S. Roberts., Thomas Twomey, W. Scherer","doi":"10.1109/sieds55548.2022.9799308","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799308","url":null,"abstract":"The college sports industry has grown tremendously over the past decade, with NCAA athletic departments recruiting almost half-a-million students to 19,866 teams in 2019 and generating $18.9 billion of revenue the same year. Identifying and selecting the best student-athletes is critical to maintaining the power of these sports programs, aggrandizing the recruitment pipeline and necessitating the demand for novel use of existing technologies. Sports analytics is one response to these growing needs, as its primary use in junior recruitment has presented fruitful for college basketball and football teams across the nation. Golf analytics firm GameForge aims to provide the same insights to college golf coaches, streamlining the recruitment of junior golfers to U.S. universities from around the world. GameForge seeks to develop a two-sided recruiting system that provides insights to junior players and their coaches as well as strengthen its predictive models with the inclusion of new data. A systems-based approach was taken to develop data-driven machine learning models that would provide (a) a proprietary ranking system that compares junior athletes to one another; (b) a relative SWOT analysis that highlights each player's strengths and skill gaps; and (c) a recommender system that suggests potential recruits to college coaches and recommends colleges of best fit to junior players.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121040394","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 : 2022-04-28DOI: 10.1109/sieds55548.2022.9799398
H. Chang, Cole David, Clarence Harris, A. Salman
Communication between the professor and student are key to a successful learning experience. However, it can be difficult at times to schedule a meeting with a professor. The SmArt WhiteBoard Replacement Interactive Device (SAWBRID) is a system that facilitates the communication between professors and students. The system is composed an E- Paper device that mounts outside a professor's office and a mobile application. The E-paper device displays a professor's availability, scheduled meetings, and communicates messages such as being a little late for office hours. The mobile application allows students to check different professor's availability and schedule an appointment with their professor. It also allows professors to connect the system to their calendar, update their schedule, and relay messages to be displayed on the E-paper. The professors' and students' data are stored on an in house server. In this research we focus on providing a smooth user experience with the SAWBRID system as well as providing a fully secure communication channel using public-key and aecret-key encryption to ensure confidentiality and hash functions to ensure data and user integrity. The system will be evaluated for usability, security, and power and energy consumption.
{"title":"SmArt WhiteBoard Replacement Interactive Device (SAWBRID) Enhancements and Optimizations","authors":"H. Chang, Cole David, Clarence Harris, A. Salman","doi":"10.1109/sieds55548.2022.9799398","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799398","url":null,"abstract":"Communication between the professor and student are key to a successful learning experience. However, it can be difficult at times to schedule a meeting with a professor. The SmArt WhiteBoard Replacement Interactive Device (SAWBRID) is a system that facilitates the communication between professors and students. The system is composed an E- Paper device that mounts outside a professor's office and a mobile application. The E-paper device displays a professor's availability, scheduled meetings, and communicates messages such as being a little late for office hours. The mobile application allows students to check different professor's availability and schedule an appointment with their professor. It also allows professors to connect the system to their calendar, update their schedule, and relay messages to be displayed on the E-paper. The professors' and students' data are stored on an in house server. In this research we focus on providing a smooth user experience with the SAWBRID system as well as providing a fully secure communication channel using public-key and aecret-key encryption to ensure confidentiality and hash functions to ensure data and user integrity. The system will be evaluated for usability, security, and power and energy consumption.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124718248","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 : 2022-04-28DOI: 10.1109/sieds55548.2022.9799382
Emily Cathey, Bezawit Delelegn, A. Landi, Suchetha Sharma, Johanna J. Loomba, S. Mazimba, Donald E. Brown
Roughly 6 million Americans have Heart Failure (HF), and this number could increase to 8 million by 2030 [1]. As of early 2022, about 76 million Americans have been diagnosed with novel coronavirus (COVID-19) and of those, around 900,000 have subsequently died [2]. Our goal for this paper is two-fold: 1) use machine learning (ML) algorithms to predict the development of HF during the post-acute COVID-19 period, with emphasis on race and ethnicity, and 2) determine how feature importance differs across the race and ethnicity groups. We apply Logistic Regression, Random Forest Classifier [3], and XGBoost Classifier [4] to predict the development of HF in patients of various races and ethnicities during the post-COVID period. These models show promising results for the use of ML algorithms to predict the development of HF in patients post-COVID.
{"title":"Using Machine Learning to Predict Development of Heart Failure, during Post-Acute COVID-19, by Race and Ethnicity","authors":"Emily Cathey, Bezawit Delelegn, A. Landi, Suchetha Sharma, Johanna J. Loomba, S. Mazimba, Donald E. Brown","doi":"10.1109/sieds55548.2022.9799382","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799382","url":null,"abstract":"Roughly 6 million Americans have Heart Failure (HF), and this number could increase to 8 million by 2030 [1]. As of early 2022, about 76 million Americans have been diagnosed with novel coronavirus (COVID-19) and of those, around 900,000 have subsequently died [2]. Our goal for this paper is two-fold: 1) use machine learning (ML) algorithms to predict the development of HF during the post-acute COVID-19 period, with emphasis on race and ethnicity, and 2) determine how feature importance differs across the race and ethnicity groups. We apply Logistic Regression, Random Forest Classifier [3], and XGBoost Classifier [4] to predict the development of HF in patients of various races and ethnicities during the post-COVID period. These models show promising results for the use of ML algorithms to predict the development of HF in patients post-COVID.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121813088","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 : 2022-04-28DOI: 10.1109/sieds55548.2022.9799367
Nicholas Landi, Elizabeth Lee, Karolina Naranjo-Velasco, Felipe Barraza
The scale of global art crime has been difficult to quantify due to the vast number of transactions and varying methods of trade. Although online marketplace platforms such as eBay offer promising data to study and track this illicit market, this relationship has not been systematically studied due to the highly technical nature of compiling and wrangling these data. This research project partners with the Cultural Resilience Informatics and Analysis (CURIA) Lab to design a robust data pipeline that collects, processes, and stores data from eBay to quantify and analyze the network mobility of illicit cultural property. The data pipeline consists of a template for accessing eBay's API, understanding API documentation, and collecting necessary features for network analysis. This process represents the first data pipeline architecture to our knowledge that collects data from listings across categories of interest, and stores features in a SQLite database through an automated, recursive script for social science research. The metadata for building and maintaining the data pipeline is recorded in an in-depth guide. The result of this data pipeline framework is a replicable blueprint for interacting with an online marketplace's API environment. This project will act as a precursor to begin research regarding the global trade of illicit cultural property through subsequent network and spatial analysis.
{"title":"Investigating the Illicit Trade of Cultural Property with an Automated Data Pipeline Architecture","authors":"Nicholas Landi, Elizabeth Lee, Karolina Naranjo-Velasco, Felipe Barraza","doi":"10.1109/sieds55548.2022.9799367","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799367","url":null,"abstract":"The scale of global art crime has been difficult to quantify due to the vast number of transactions and varying methods of trade. Although online marketplace platforms such as eBay offer promising data to study and track this illicit market, this relationship has not been systematically studied due to the highly technical nature of compiling and wrangling these data. This research project partners with the Cultural Resilience Informatics and Analysis (CURIA) Lab to design a robust data pipeline that collects, processes, and stores data from eBay to quantify and analyze the network mobility of illicit cultural property. The data pipeline consists of a template for accessing eBay's API, understanding API documentation, and collecting necessary features for network analysis. This process represents the first data pipeline architecture to our knowledge that collects data from listings across categories of interest, and stores features in a SQLite database through an automated, recursive script for social science research. The metadata for building and maintaining the data pipeline is recorded in an in-depth guide. The result of this data pipeline framework is a replicable blueprint for interacting with an online marketplace's API environment. This project will act as a precursor to begin research regarding the global trade of illicit cultural property through subsequent network and spatial analysis.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114200787","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 : 2022-04-28DOI: 10.1109/sieds55548.2022.9799386
Emma Graham
To survive in our unpredictable, evolving world, cognitive beings learn to make decisions with the limited knowledge of the world they process. Reflective of an individual's view of the world, a cognitive decision-making model is explored in a partially observable, stochastic environment. The cognitive model uses the Partially Observable Markov Decision Process problem formulation, which is a framework for neurological models and considered implementable in neural circuitry [26] [16]. To structure a planning model comparable to that of DeepMind's MuZero in a partially observable environment, a belief function will translate the observations to a vector of belief states that will be discretized so as to be used as the observations of a MuZero-based machine learning algorithm [29]. The belief states are computed recursively from the previous belief state using Bayesian inference. Bayes rule is thought to capture the neurological and cognitive levels of reasoning [26]. Components of the planning, training, and action methods of the cognitive model will follow those of MuZero. The model could then be trained and act, in way parallel to that of MuZero, in a partially observable environment. Cognitive insights from a model structured in this form and additional considerations are discussed.
{"title":"A Working Theory of a Learned Model in a Partially Observable Environment for Cognitive Decision-Making","authors":"Emma Graham","doi":"10.1109/sieds55548.2022.9799386","DOIUrl":"https://doi.org/10.1109/sieds55548.2022.9799386","url":null,"abstract":"To survive in our unpredictable, evolving world, cognitive beings learn to make decisions with the limited knowledge of the world they process. Reflective of an individual's view of the world, a cognitive decision-making model is explored in a partially observable, stochastic environment. The cognitive model uses the Partially Observable Markov Decision Process problem formulation, which is a framework for neurological models and considered implementable in neural circuitry [26] [16]. To structure a planning model comparable to that of DeepMind's MuZero in a partially observable environment, a belief function will translate the observations to a vector of belief states that will be discretized so as to be used as the observations of a MuZero-based machine learning algorithm [29]. The belief states are computed recursively from the previous belief state using Bayesian inference. Bayes rule is thought to capture the neurological and cognitive levels of reasoning [26]. Components of the planning, training, and action methods of the cognitive model will follow those of MuZero. The model could then be trained and act, in way parallel to that of MuZero, in a partially observable environment. Cognitive insights from a model structured in this form and additional considerations are discussed.","PeriodicalId":286724,"journal":{"name":"2022 Systems and Information Engineering Design Symposium (SIEDS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115827556","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：