Pub Date : 2019-04-01DOI: 10.1109/SIEDS.2019.8735607
Jarett Cestaro, David Conklin, Douglas Ziman, Edmund Pan, Grant Anhorn, M. Cunningham, Nevan Schulte, Faraz Dadgostari, P. Beling
This research was driven by the need for a more efficient production scheduling system in a consumable liquid product division of a large consumer products company. The manufacturing process under inspection consists of continuous and discrete elements, on both production and packaging lines. The production lines are split into continuous production lines and batch production lines which produce the product in fixed batch amounts. Then there are several bottling lines, some of which package a particular bottle size and others that can package multiple bottle sizes. The main objective of this research was to reduce the amount of time it takes for the client to create production and bottling schedules. An optimization model was developed to automate this process and provide the client with the best possible schedule. The objective of the model is to minimize cost by minimizing the number of switches across the production and bottling lines, as well as minimizing the amount of overproduction. Inputs into the model include model parameters, like the number of shifts to schedule, and monthly demand numbers for each stock keeping unit (SKU). The variables being solved for are the amount of each flavor to be produced across the production lines during each shift, and the number of bottles of each SKU to be bottled across the bottling lines during each shift. Due to the unique constraints and resources of the client, a custom formulation using mixed integer programming was necessary to achieve these objectives. Overall, our model fell short in some areas but succeeded in others. Our analysis showed that the model had a 13% average decrease in production switches but an 87% average increase in bottling switches compared to the current manual scheduling system. However, the ability of our system to create a good enough initial schedule reduces the time it takes expert human schedulers to develop a final schedule by up to 85%. Runtime and computational constraints barred us from creating an optimal, cost-minimized solution for our client, and future work can be directed toward solving these issues.
{"title":"Optimization of Production and Packaging Schedules in a Mixed Discrete/Continuous Manufacturing Environment","authors":"Jarett Cestaro, David Conklin, Douglas Ziman, Edmund Pan, Grant Anhorn, M. Cunningham, Nevan Schulte, Faraz Dadgostari, P. Beling","doi":"10.1109/SIEDS.2019.8735607","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735607","url":null,"abstract":"This research was driven by the need for a more efficient production scheduling system in a consumable liquid product division of a large consumer products company. The manufacturing process under inspection consists of continuous and discrete elements, on both production and packaging lines. The production lines are split into continuous production lines and batch production lines which produce the product in fixed batch amounts. Then there are several bottling lines, some of which package a particular bottle size and others that can package multiple bottle sizes. The main objective of this research was to reduce the amount of time it takes for the client to create production and bottling schedules. An optimization model was developed to automate this process and provide the client with the best possible schedule. The objective of the model is to minimize cost by minimizing the number of switches across the production and bottling lines, as well as minimizing the amount of overproduction. Inputs into the model include model parameters, like the number of shifts to schedule, and monthly demand numbers for each stock keeping unit (SKU). The variables being solved for are the amount of each flavor to be produced across the production lines during each shift, and the number of bottles of each SKU to be bottled across the bottling lines during each shift. Due to the unique constraints and resources of the client, a custom formulation using mixed integer programming was necessary to achieve these objectives. Overall, our model fell short in some areas but succeeded in others. Our analysis showed that the model had a 13% average decrease in production switches but an 87% average increase in bottling switches compared to the current manual scheduling system. However, the ability of our system to create a good enough initial schedule reduces the time it takes expert human schedulers to develop a final schedule by up to 85%. Runtime and computational constraints barred us from creating an optimal, cost-minimized solution for our client, and future work can be directed toward solving these issues.","PeriodicalId":265421,"journal":{"name":"2019 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125122758","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 : 2019-04-01DOI: 10.1109/SIEDS.2019.8735600
Hayley Waleska, Caroline McNichols, Stefan Zachar, Torian Wright, Joshua Cauthen, Seshi Konu, M. DeDomenico, R. Bailey
Reservable student space is an essential resource for student organizations at universities. The ability to provide equitable access to spaces is a key role of the administration. The focus of this paper is a case study exploring mechanisms to improve both spaces and how students access them at the University of Virginia, taking a human-centered design approach to 1) analyzing the current system, 2) identifying, evaluating, and evolving recommendations to improve system performance, and 3) assessing impact of recommendations. Based on prior studies, usage data, surveys, interviews, and focus groups, we identified two driving questions: 1) Does the university have the needed spaces? 2) Are these spaces accessible by student groups? In response, the team developed a dual focus: Space Design and Utilization (SDU) to address the idea of “right spaces” and Reservation System Design (RSD) to address issues related to ease of access. SDU revealed issues with overly-strict policies and space design, a disparity in the spread of spaces across campus, and a shortage of spaces equipped to diverse student activity. To address these issues, we recommend the university audit its policies, focus future construction on creating hubs of space near student housing, and emphasize the ideal of multi-use space during new construction and renovations. RSD revealed a lack of procedural transparency leads to feelings of inequity between student groups, incorrect assumptions regarding users lead to dysfunctional interactions, and the system was not making optimal use of the limited spatial resources. To address issues, we recommend the university increase transparency through clear and consistent communication, refrain from making unjustified assumptions of users, and allocate spaces to proper events while allowing flexibility within spaces.
{"title":"Lost in Space: A Case Study on Optimizing Student Spaces at the University of Virginia","authors":"Hayley Waleska, Caroline McNichols, Stefan Zachar, Torian Wright, Joshua Cauthen, Seshi Konu, M. DeDomenico, R. Bailey","doi":"10.1109/SIEDS.2019.8735600","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735600","url":null,"abstract":"Reservable student space is an essential resource for student organizations at universities. The ability to provide equitable access to spaces is a key role of the administration. The focus of this paper is a case study exploring mechanisms to improve both spaces and how students access them at the University of Virginia, taking a human-centered design approach to 1) analyzing the current system, 2) identifying, evaluating, and evolving recommendations to improve system performance, and 3) assessing impact of recommendations. Based on prior studies, usage data, surveys, interviews, and focus groups, we identified two driving questions: 1) Does the university have the needed spaces? 2) Are these spaces accessible by student groups? In response, the team developed a dual focus: Space Design and Utilization (SDU) to address the idea of “right spaces” and Reservation System Design (RSD) to address issues related to ease of access. SDU revealed issues with overly-strict policies and space design, a disparity in the spread of spaces across campus, and a shortage of spaces equipped to diverse student activity. To address these issues, we recommend the university audit its policies, focus future construction on creating hubs of space near student housing, and emphasize the ideal of multi-use space during new construction and renovations. RSD revealed a lack of procedural transparency leads to feelings of inequity between student groups, incorrect assumptions regarding users lead to dysfunctional interactions, and the system was not making optimal use of the limited spatial resources. To address issues, we recommend the university increase transparency through clear and consistent communication, refrain from making unjustified assumptions of users, and allocate spaces to proper events while allowing flexibility within spaces.","PeriodicalId":265421,"journal":{"name":"2019 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132258146","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 : 2019-04-01DOI: 10.1109/SIEDS.2019.8735624
Annie Hatcher, Stephen Jung, Holden Keegan, Todd Le, Henry C Quach, C. Ward, Justin L. Weisberg, G. Louis
Hurricane Maria destroyed most of the agricultural sector on the island of Dominica and left the inhabitants with no locally grown produce for months. As climate change brings more frequent and extreme weather events, the Caribbean region becomes increasingly vulnerable to their adverse effects. Agriculture is a large component of Dominica's economy, and the country seeks to adapt its agricultural practices to accommodate the changing environmental conditions. A Charlottesville, VA startup company, Babylon Micro-Farms (BMF), received a grant to adapt their current hydroponic crop cultivation system to create a prototype for humanitarian food assistance. This prototype “fold-out farm” (FoF) would be solar-powered and transportable to Dominica for testing as a reliable source of fresh produce for families. The produce grown using the FoF could also provide extra income for these families. In order to assess the feasibility of implementing the FoF in Dominica, our project team is developing a Capacity Factor Analysis (CFA). CFA assesses a community's capability to successfully acquire and independently sustain a technology using the following factors: Institutional, Human Resources, Technical, Economic, Environmental, Energy, Socio-Cultural, and Service. By analyzing these individual factors, we hope to identify issues likely to affect the successful deployment of the FoF in Dominica. The results of this CFA lead to suggestions for improvements to the FoF technology and its implementation in Dominica. The development of this CFA will continue to be useful to BMF in the future while implementing their technology in other communities.
{"title":"Assessing the Viability of a Fold-Out Hydroponic Farm for Humanitarian Relief Efforts in Dominica","authors":"Annie Hatcher, Stephen Jung, Holden Keegan, Todd Le, Henry C Quach, C. Ward, Justin L. Weisberg, G. Louis","doi":"10.1109/SIEDS.2019.8735624","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735624","url":null,"abstract":"Hurricane Maria destroyed most of the agricultural sector on the island of Dominica and left the inhabitants with no locally grown produce for months. As climate change brings more frequent and extreme weather events, the Caribbean region becomes increasingly vulnerable to their adverse effects. Agriculture is a large component of Dominica's economy, and the country seeks to adapt its agricultural practices to accommodate the changing environmental conditions. A Charlottesville, VA startup company, Babylon Micro-Farms (BMF), received a grant to adapt their current hydroponic crop cultivation system to create a prototype for humanitarian food assistance. This prototype “fold-out farm” (FoF) would be solar-powered and transportable to Dominica for testing as a reliable source of fresh produce for families. The produce grown using the FoF could also provide extra income for these families. In order to assess the feasibility of implementing the FoF in Dominica, our project team is developing a Capacity Factor Analysis (CFA). CFA assesses a community's capability to successfully acquire and independently sustain a technology using the following factors: Institutional, Human Resources, Technical, Economic, Environmental, Energy, Socio-Cultural, and Service. By analyzing these individual factors, we hope to identify issues likely to affect the successful deployment of the FoF in Dominica. The results of this CFA lead to suggestions for improvements to the FoF technology and its implementation in Dominica. The development of this CFA will continue to be useful to BMF in the future while implementing their technology in other communities.","PeriodicalId":265421,"journal":{"name":"2019 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116327112","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 : 2019-04-01DOI: 10.1109/SIEDS.2019.8735621
Vaibhav Sharma, Benjamin Shpringer, S. Yang, M. Bolger, Sodiq Adewole, D. Brown, Erfaneh Gharavi
Most past research in the area of serious games for simulation has focused on games with constrained multiple-choice based dialogue systems. Recent advancements in natural language processing research make free-input text classification-based dialogue systems more feasible, but an effective framework for collecting training data for such systems has not yet been developed. This paper presents methods for collecting and generating data for training a free-input classification-based system. Various data crowdsourcing prompt types are presented. A binary category system, which increases the fidelity of the labeling to make free-input classification more effective, is presented. Finally, a data generation algorithm based on the binary data labeling system is presented. Future work will use the data crowdsourcing and generation methods presented here to implement a free-input dialogue system in a virtual reality (VR) simulation designed for cultural competency training.
{"title":"Data Collection Methods for Building a Free Response Training Simulation","authors":"Vaibhav Sharma, Benjamin Shpringer, S. Yang, M. Bolger, Sodiq Adewole, D. Brown, Erfaneh Gharavi","doi":"10.1109/SIEDS.2019.8735621","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735621","url":null,"abstract":"Most past research in the area of serious games for simulation has focused on games with constrained multiple-choice based dialogue systems. Recent advancements in natural language processing research make free-input text classification-based dialogue systems more feasible, but an effective framework for collecting training data for such systems has not yet been developed. This paper presents methods for collecting and generating data for training a free-input classification-based system. Various data crowdsourcing prompt types are presented. A binary category system, which increases the fidelity of the labeling to make free-input classification more effective, is presented. Finally, a data generation algorithm based on the binary data labeling system is presented. Future work will use the data crowdsourcing and generation methods presented here to implement a free-input dialogue system in a virtual reality (VR) simulation designed for cultural competency training.","PeriodicalId":265421,"journal":{"name":"2019 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126448807","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 : 2019-04-01DOI: 10.1109/SIEDS.2019.8735613
J. Peterson, Chase Cohen, P. Harrison, Jonathan Novak, Chad C. Tossell, Elizabeth Phillips
The battlefield of the future will look very different than the battlefields of the past. Automated technologies are finding themselves more and more integrated into every aspect of the fight. As technology continues to advance, the United States Military must consider what a human-machine team will look like and how an optimal relationship between the two assets can be formed, especially under the stressful conditions that often characterize military contexts. For a human-machine team in a military context to work at maximum efficiency, an ideal level of empathy towards an automated teammate must be obtained. The goal of this study is to determine the effect stress can have on an individual's empathetic reaction toward a Pepper robot. Twenty-eight participants interacted with a Pepper robot either under stress or not. Empathy toward the robot was measured through subjective assessments as well as by participant decisions to continue interacting with Pepper even though doing so would harm the robot. Although not conclusive, the results suggest an interaction between participant gender and stress on empathy toward the Pepper robot. Women showed more empathy toward Pepper under higher levels of stress than lower levels of stress. However, the opposite was true for men. Men showed less empathy toward Pepper under higher levels of stress. The results of this study could help to inform military training and robot design.
{"title":"Ideal Warrior and Robot Relations: Stress and Empathy's Role in Human-Robot Teaming","authors":"J. Peterson, Chase Cohen, P. Harrison, Jonathan Novak, Chad C. Tossell, Elizabeth Phillips","doi":"10.1109/SIEDS.2019.8735613","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735613","url":null,"abstract":"The battlefield of the future will look very different than the battlefields of the past. Automated technologies are finding themselves more and more integrated into every aspect of the fight. As technology continues to advance, the United States Military must consider what a human-machine team will look like and how an optimal relationship between the two assets can be formed, especially under the stressful conditions that often characterize military contexts. For a human-machine team in a military context to work at maximum efficiency, an ideal level of empathy towards an automated teammate must be obtained. The goal of this study is to determine the effect stress can have on an individual's empathetic reaction toward a Pepper robot. Twenty-eight participants interacted with a Pepper robot either under stress or not. Empathy toward the robot was measured through subjective assessments as well as by participant decisions to continue interacting with Pepper even though doing so would harm the robot. Although not conclusive, the results suggest an interaction between participant gender and stress on empathy toward the Pepper robot. Women showed more empathy toward Pepper under higher levels of stress than lower levels of stress. However, the opposite was true for men. Men showed less empathy toward Pepper under higher levels of stress. The results of this study could help to inform military training and robot design.","PeriodicalId":265421,"journal":{"name":"2019 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115066108","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 : 2019-04-01DOI: 10.1109/SIEDS.2019.8735640
Catherine Beazley, Karan Gadiya, Ravi K U Rakesh, D. Roden, Boda Ye, Brendan Abraham, Donald E. Brown, M. Veeraraghavan
Exploratory data analysis is invaluable for understanding data, choosing correct models, and interpreting, validating, and applying results. It often leads to the discovery of patterns that can answer a number of research questions. In this paper, we perform exploratory data analysis on cybersecurity data in the NetFlow Dataset from “The Unified Host and Network Dataset”. “The Unified Host and Network Dataset” is a large, open source dataset collected on the Los Alamos National Laboratory (LANL) enterprise network that was published to encourage new research in cybersecurity. The NetFlow Dataset is a compilation of flow logs from routers within the LANL network that are aggregated to a relational format using network stitching. Our exploratory data analysis shows distinct patterns and clusters within a day of data. Specifically, scatter plots of the number of packets sent by the destination device versus the number of packets sent by the source device show three distinct, no-intercept linear relationships between the variables. The relationships suggest three common patterns for how the source device and destination device interactively send packets to each other. Our analysis also shows that byte and packet distributions of connections on rare ports and connections on common ports are statistically different, suggesting these differences can be used to discriminate between normal and abnormal network behavior. Our findings may be useful for research into classification problems with a Unified Host and Network Dataset and for furthering cluster analysis in cybersecurity research.
{"title":"Exploratory Data Analysis of a Unified Host and Network Dataset","authors":"Catherine Beazley, Karan Gadiya, Ravi K U Rakesh, D. Roden, Boda Ye, Brendan Abraham, Donald E. Brown, M. Veeraraghavan","doi":"10.1109/SIEDS.2019.8735640","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735640","url":null,"abstract":"Exploratory data analysis is invaluable for understanding data, choosing correct models, and interpreting, validating, and applying results. It often leads to the discovery of patterns that can answer a number of research questions. In this paper, we perform exploratory data analysis on cybersecurity data in the NetFlow Dataset from “The Unified Host and Network Dataset”. “The Unified Host and Network Dataset” is a large, open source dataset collected on the Los Alamos National Laboratory (LANL) enterprise network that was published to encourage new research in cybersecurity. The NetFlow Dataset is a compilation of flow logs from routers within the LANL network that are aggregated to a relational format using network stitching. Our exploratory data analysis shows distinct patterns and clusters within a day of data. Specifically, scatter plots of the number of packets sent by the destination device versus the number of packets sent by the source device show three distinct, no-intercept linear relationships between the variables. The relationships suggest three common patterns for how the source device and destination device interactively send packets to each other. Our analysis also shows that byte and packet distributions of connections on rare ports and connections on common ports are statistically different, suggesting these differences can be used to discriminate between normal and abnormal network behavior. Our findings may be useful for research into classification problems with a Unified Host and Network Dataset and for furthering cluster analysis in cybersecurity research.","PeriodicalId":265421,"journal":{"name":"2019 Systems and Information Engineering Design Symposium (SIEDS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132950327","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：