Pub Date : 2019-04-26DOI: 10.1109/SIEDS.2019.8735619
Aman Srivastava, S. Sengupta, Sung-Jun Kang, K. Kant, Marium N. Khan, S. A. Ali, S. Moore, B. Amadi, P. Kelly, Sana Syed, Donald E. Brown
Machine learning and computer vision have found applications in medical science and, recently, pathology. In particular, deep learning methods for medical diagnostic imaging can reduce delays in diagnosis and give improved accuracy rates over other analysis techniques. This paper focuses on methods with applicability to automated diagnosis of images obtained from gastrointestinal biopsies. These deep learning techniques for biopsy images may help detect distinguishing features in tissues affected by enteropathies. Learning from different areas of an image, or looking for similar patterns in new images, allow for the development of potential classification or clustering models Techniques like these provide a cutting-edge solution to detecting anomalies. In this paper we explore state of the art deep learning architectures used for the visual recognition of natural images and assess their applicability in medical image analysis of digitized human gastrointestinal biopsy slides.
{"title":"Deep Learning for Detecting Diseases in Gastrointestinal Biopsy Images","authors":"Aman Srivastava, S. Sengupta, Sung-Jun Kang, K. Kant, Marium N. Khan, S. A. Ali, S. Moore, B. Amadi, P. Kelly, Sana Syed, Donald E. Brown","doi":"10.1109/SIEDS.2019.8735619","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735619","url":null,"abstract":"Machine learning and computer vision have found applications in medical science and, recently, pathology. In particular, deep learning methods for medical diagnostic imaging can reduce delays in diagnosis and give improved accuracy rates over other analysis techniques. This paper focuses on methods with applicability to automated diagnosis of images obtained from gastrointestinal biopsies. These deep learning techniques for biopsy images may help detect distinguishing features in tissues affected by enteropathies. Learning from different areas of an image, or looking for similar patterns in new images, allow for the development of potential classification or clustering models Techniques like these provide a cutting-edge solution to detecting anomalies. In this paper we explore state of the art deep learning architectures used for the visual recognition of natural images and assess their applicability in medical image analysis of digitized human gastrointestinal biopsy slides.","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":"121218897","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.2019.8735610
Jing Sun, Fang You, Bowei Sun, T. Hartka, Abigail A. Flower
Full body computed tomography (CT) is a widely used clinical evaluation method to detect hidden injury for victims of motor vehicle collisions (MVCs). However, full body CT scans are time consuming and expensive for both healthcare service providers and MVC victims. Injury risk prediction models that support CT scanning decisions are therefore highly desired. Existing studies have implemented logistic regression models to predict injury risk for victims' major body regions, including head, neck, chest, abdomen/pelvis, cervical spine, thoracic spine and lumbar spine. The work presented here involved the application of novel approaches to improve the prediction results. This study focused on examining patient information and crash data for front seat adult passengers using data from the National Automotive Sampling System - Crashworthiness Data System from 2000 to 2015. This dataset is imbued with a large amount of missingness and is highly imbalanced. Various imputation methods were employed in order to preserve the greatest amount of relevant historical data possible. The high imbalance in the data was resolved by the implementation of downsampling and synthetic minority over-sampling technique. Models that were applied in this study include logistic regression, random forests, support vector machines and gradient boosting. Autoencoders were also deployed to generate features of high importance to improve prediction results. The resulting models for all seven regions yielded sensitivities and specificities of at least 96% and 30%, respectively. Overall, these models were developed not to replace physicians' decisions, but to guide their CT scanning decisions.
{"title":"Injury Risk Prediction for Body Regions after Motor Vehicle Collisions to Guide CT Scanning Decisions","authors":"Jing Sun, Fang You, Bowei Sun, T. Hartka, Abigail A. Flower","doi":"10.1109/SIEDS.2019.8735610","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735610","url":null,"abstract":"Full body computed tomography (CT) is a widely used clinical evaluation method to detect hidden injury for victims of motor vehicle collisions (MVCs). However, full body CT scans are time consuming and expensive for both healthcare service providers and MVC victims. Injury risk prediction models that support CT scanning decisions are therefore highly desired. Existing studies have implemented logistic regression models to predict injury risk for victims' major body regions, including head, neck, chest, abdomen/pelvis, cervical spine, thoracic spine and lumbar spine. The work presented here involved the application of novel approaches to improve the prediction results. This study focused on examining patient information and crash data for front seat adult passengers using data from the National Automotive Sampling System - Crashworthiness Data System from 2000 to 2015. This dataset is imbued with a large amount of missingness and is highly imbalanced. Various imputation methods were employed in order to preserve the greatest amount of relevant historical data possible. The high imbalance in the data was resolved by the implementation of downsampling and synthetic minority over-sampling technique. Models that were applied in this study include logistic regression, random forests, support vector machines and gradient boosting. Autoencoders were also deployed to generate features of high importance to improve prediction results. The resulting models for all seven regions yielded sensitivities and specificities of at least 96% and 30%, respectively. Overall, these models were developed not to replace physicians' decisions, but to guide their CT scanning decisions.","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":"133708353","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.2019.8735626
Rohan M. Karanth, Matthew S. Guyer, Natalie L. Twilley, Mary Boyd Crosier, S. C. Monroe, Alex J. McQuain, Lynn T. Kha, M. Boukhechba, M. Gerber, Laura E. Barnes
Recent advances in sensing technology have made it possible to monitor how behavioral systems unfold in people's natural settings by leveraging sensors embedded in personal smartphones and other smart devices. This paper provides a framework for how smartphone sensor data can be collected, cleaned, and modeled to predict relevant disease contexts such as location. These variables can then be used in context-sensitive models to understand how a user's behavior and contexts might differ from typical patterns when impacted by illness. To develop rich contextual models, we first conducted a 2-week smartphone monitoring study where sensor data and corresponding location contexts were tagged for 7 users. Next, we demonstrated how multimodal sensor data can be used to predict location context by modeling the tagged dataset and analyzing differences in sensors to find indicators for each location. The results of this effort include 1) identification of ground truth data for contexts of interest to be used in future modeling, 2) establishment of a process to collect, clean, and visualize smartphone data generated by both iOS and Android systems, and 3) creation of models to predict a participant's location and context using raw smartphone data. This context identification process could be used in future research to perform analyses that leverage past patterns of user behavior to recognize disease indicators.
{"title":"Modeling User Context from Smartphone Data for Recognition of Health Status","authors":"Rohan M. Karanth, Matthew S. Guyer, Natalie L. Twilley, Mary Boyd Crosier, S. C. Monroe, Alex J. McQuain, Lynn T. Kha, M. Boukhechba, M. Gerber, Laura E. Barnes","doi":"10.1109/SIEDS.2019.8735626","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735626","url":null,"abstract":"Recent advances in sensing technology have made it possible to monitor how behavioral systems unfold in people's natural settings by leveraging sensors embedded in personal smartphones and other smart devices. This paper provides a framework for how smartphone sensor data can be collected, cleaned, and modeled to predict relevant disease contexts such as location. These variables can then be used in context-sensitive models to understand how a user's behavior and contexts might differ from typical patterns when impacted by illness. To develop rich contextual models, we first conducted a 2-week smartphone monitoring study where sensor data and corresponding location contexts were tagged for 7 users. Next, we demonstrated how multimodal sensor data can be used to predict location context by modeling the tagged dataset and analyzing differences in sensors to find indicators for each location. The results of this effort include 1) identification of ground truth data for contexts of interest to be used in future modeling, 2) establishment of a process to collect, clean, and visualize smartphone data generated by both iOS and Android systems, and 3) creation of models to predict a participant's location and context using raw smartphone data. This context identification process could be used in future research to perform analyses that leverage past patterns of user behavior to recognize disease indicators.","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":"115400129","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.2019.8735639
Jingnan Yang, Justin Ward, Erfaneh Gharavi, Jennifer Dawson, Raf Alvarado
Readily available, trustworthy, and usable medical information is vital to promoting global health. Cochrane is a non-profit medical organization that conducts and publishes systematic reviews of medical research findings. Over 3000 Cochrane Reviews are presently used as evidence in Wikipedia articles. Currently, Cochrane's researchers manually search Wikipedia pages related to medicine in order to identify Wikipedia articles that can be improved with Cochrane evidence. Our aim is to streamline this process by applying existing document similarity and information retrieval methods to automatically link Wikipedia articles and Cochrane Reviews. Potential challenges to this project include document length and the specificity of the corpora. These challenges distinguish this problem from ordinary document representation and retrieval problems. For our methodology, we worked with data from 7400 Cochrane Reviews, ranging from one to several pages in length, and 33,000 Wikipedia articles categorized as medical. We explored different methods of document vectorization including TFIDF, LDA, LSA, word2Vec, and doc2Vec. For every document in both corpora, their similarity to each document in the opposing set was calculated using established vector similarity metrics such as cosine similarity and KL-divergence. Labeled data for this unsupervised task was not available. Models were evaluated by comparing the results to two standards: (1) Cochrane Reviews currently cited in Wikipedia articles and (2) a data set provided by a medical expert that indicates which Cochrane Reviews could be considered for specific Wikipedia articles. Our system performs best using TFIDF document representation and cosine similarity.
{"title":"Bi-directional Relevance Matching between Medical Corpora","authors":"Jingnan Yang, Justin Ward, Erfaneh Gharavi, Jennifer Dawson, Raf Alvarado","doi":"10.1109/SIEDS.2019.8735639","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735639","url":null,"abstract":"Readily available, trustworthy, and usable medical information is vital to promoting global health. Cochrane is a non-profit medical organization that conducts and publishes systematic reviews of medical research findings. Over 3000 Cochrane Reviews are presently used as evidence in Wikipedia articles. Currently, Cochrane's researchers manually search Wikipedia pages related to medicine in order to identify Wikipedia articles that can be improved with Cochrane evidence. Our aim is to streamline this process by applying existing document similarity and information retrieval methods to automatically link Wikipedia articles and Cochrane Reviews. Potential challenges to this project include document length and the specificity of the corpora. These challenges distinguish this problem from ordinary document representation and retrieval problems. For our methodology, we worked with data from 7400 Cochrane Reviews, ranging from one to several pages in length, and 33,000 Wikipedia articles categorized as medical. We explored different methods of document vectorization including TFIDF, LDA, LSA, word2Vec, and doc2Vec. For every document in both corpora, their similarity to each document in the opposing set was calculated using established vector similarity metrics such as cosine similarity and KL-divergence. Labeled data for this unsupervised task was not available. Models were evaluated by comparing the results to two standards: (1) Cochrane Reviews currently cited in Wikipedia articles and (2) a data set provided by a medical expert that indicates which Cochrane Reviews could be considered for specific Wikipedia articles. Our system performs best using TFIDF document representation and cosine similarity.","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":"121998219","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.2019.8735627
T. A. Malapane
This research paper explores the in-depth application of Data Mining in the Fourth Industrial Revolution (4IR) in South Africa. The Industrial Revolution concept has fundamentally changed our society and economy. In South Africa, data mining phenomena has not been fully realized in the age of the 4IR. In the age of information and 4IR data is viewed as a strategic assert that companies should invest in. Results in this study shows that the concept of data mining in South African business landscape is not fully executed and applied to business development and management as a practice. Statistical observations also indicate that baselines, historical data and intelligence if used properly can benefit businesses to grow and develop. This study attempted to discover hidden valuable knowledge by analyzing data using statistical data mining techniques during which a new data mining technique to analyze data, interpret it and present it was discovered. This research tested the new approach referred to as Alex Malapane Data Mining Technique (AMDMT) using test questions which were explored as per the objective of this study.
{"title":"An Application of Data Mining in the Fourth Industrial Revolution - A Case of South Africa","authors":"T. A. Malapane","doi":"10.1109/SIEDS.2019.8735627","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735627","url":null,"abstract":"This research paper explores the in-depth application of Data Mining in the Fourth Industrial Revolution (4IR) in South Africa. The Industrial Revolution concept has fundamentally changed our society and economy. In South Africa, data mining phenomena has not been fully realized in the age of the 4IR. In the age of information and 4IR data is viewed as a strategic assert that companies should invest in. Results in this study shows that the concept of data mining in South African business landscape is not fully executed and applied to business development and management as a practice. Statistical observations also indicate that baselines, historical data and intelligence if used properly can benefit businesses to grow and develop. This study attempted to discover hidden valuable knowledge by analyzing data using statistical data mining techniques during which a new data mining technique to analyze data, interpret it and present it was discovered. This research tested the new approach referred to as Alex Malapane Data Mining Technique (AMDMT) using test questions which were explored as per the objective of this 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":"133892206","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.2019.8735651
Sean S Baggott, J. Santos
The purpose of this article is to introduce a risk analysis framework to enhance the cyber security of and to protect the critical infrastructure of the electric power grid of the United States. Building on the fundamental questions of risk assessment and management, this framework aims to advance the current risk analysis discussions pertaining to the electric power grid. Most of the previous risk-related studies on the electric power grid focus mainly on the recovery of the network from hurricanes and other natural disasters. In contrast, a disproportionately small number of studies explicitly investigate the vulnerability of the electric power grid to cyber-attack scenarios, and how they could be prevented or mitigated. Such a limited approach leaves the United States vulnerable to foreign and domestic threats (both state-sponsored and “lone wolf”) to infiltrate a network that lacks a comprehensive security environment or coordinated government response. By conducting a review of the literature and presenting a risk-based framework, this article underscores the need for a coordinated United States cyber security effort toward formulating strategies and responses conducive to protecting the nation against attacks on the electric power grid.
{"title":"Risk Analysis Framework for Cyber Security and Critical Infrastructure Protection of the US Electric Power Grid","authors":"Sean S Baggott, J. Santos","doi":"10.1109/SIEDS.2019.8735651","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735651","url":null,"abstract":"The purpose of this article is to introduce a risk analysis framework to enhance the cyber security of and to protect the critical infrastructure of the electric power grid of the United States. Building on the fundamental questions of risk assessment and management, this framework aims to advance the current risk analysis discussions pertaining to the electric power grid. Most of the previous risk-related studies on the electric power grid focus mainly on the recovery of the network from hurricanes and other natural disasters. In contrast, a disproportionately small number of studies explicitly investigate the vulnerability of the electric power grid to cyber-attack scenarios, and how they could be prevented or mitigated. Such a limited approach leaves the United States vulnerable to foreign and domestic threats (both state-sponsored and “lone wolf”) to infiltrate a network that lacks a comprehensive security environment or coordinated government response. By conducting a review of the literature and presenting a risk-based framework, this article underscores the need for a coordinated United States cyber security effort toward formulating strategies and responses conducive to protecting the nation against attacks on the electric power grid.","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":"131979831","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.2019.8735653
L. Beane, Elena Gillis, Raf Alvarado, C. Wylie
To improve democratic engagement between the people and the government, the city of Charlottesville put forward a proposition to construct an online portal that would contain data from the city departments that is considered public by nature. This move was intended to promote the ease of access to data pertinent to ongoing policy debates in the city and incentivize the public to contribute to the policy-making process with informed participation. Such efforts, while successful at their start, have gradually stagnated, and the end objective of the portal has not been reached. In this paper we identify possible reasons for this stagnation – inconsistent formatting of the datasets, variables that are not meant for human legibility, and limited data with disproportional representation from the city departments. We then propose a data pipeline that serves as a tool to extract utility from the data. It does so by converting the datasets into a consistent format, merges the datasets, and allows for creation of simple visualizations. The pipeline acts as a link between the raw data published by the government units and the city by increasing its interpretability and legibility and outputting results that are easily relatable to the policy issues at hand. We demonstrate this by analyzing datasets for crime and real estate and relating our findings to the affordable housing debate.
{"title":"Developing a data pipeline to improve accessibility and utilization of Charlottesville's Open Data Portal","authors":"L. Beane, Elena Gillis, Raf Alvarado, C. Wylie","doi":"10.1109/SIEDS.2019.8735653","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735653","url":null,"abstract":"To improve democratic engagement between the people and the government, the city of Charlottesville put forward a proposition to construct an online portal that would contain data from the city departments that is considered public by nature. This move was intended to promote the ease of access to data pertinent to ongoing policy debates in the city and incentivize the public to contribute to the policy-making process with informed participation. Such efforts, while successful at their start, have gradually stagnated, and the end objective of the portal has not been reached. In this paper we identify possible reasons for this stagnation – inconsistent formatting of the datasets, variables that are not meant for human legibility, and limited data with disproportional representation from the city departments. We then propose a data pipeline that serves as a tool to extract utility from the data. It does so by converting the datasets into a consistent format, merges the datasets, and allows for creation of simple visualizations. The pipeline acts as a link between the raw data published by the government units and the city by increasing its interpretability and legibility and outputting results that are easily relatable to the policy issues at hand. We demonstrate this by analyzing datasets for crime and real estate and relating our findings to the affordable housing debate.","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":"115499233","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.2019.8735637
David J. Culver, Alexander B. Colon, Deanna R. Washington, Maurice G. Appleton, A. Strang, A. Alizadeh, A. Burns, M. Poliks, Chad C. Tossell
Wearable sweat sensors will soon launch in the commercial sector. Many of these sensors focus on hydration monitoring, which is critical for optimizing performance and ensuring safety; particularly as it relates to individuals participating in extremely demanding physical activities. For these reasons, we tested the, durability, and comfort of a prototype sweat sensor in a mock special operations field event. Data were collected at the U.S. Air Force Academy to include measures of hydration levels (e.g., Urine Specific Gravity) and fluid loss (e.g., body weight) across a series of five strenuous physical activities. We evaluated the prototype design in terms of comfort and intrusiveness. Observations and survey data revealed the participants did not perceive the technologies as intrusive. All of the requisite activities were completed and the technologies did not hinder performance. General Electric, the developers of the particular sensor evaluated, received important design-related information for future iterations. With this technology the U.S. military hopes to see a decrease in the number of heat and hydration related incidents by enhancing the safety of its personnel. Moreover, the future design of this system is critical as part of a physiological dashboard used by special operations forces. A combination of optimizing human performance and safety could create the next iteration of the world's most powerful ground forces.
{"title":"Field Test of Wearable Sensors for Hydration Monitoring","authors":"David J. Culver, Alexander B. Colon, Deanna R. Washington, Maurice G. Appleton, A. Strang, A. Alizadeh, A. Burns, M. Poliks, Chad C. Tossell","doi":"10.1109/SIEDS.2019.8735637","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735637","url":null,"abstract":"Wearable sweat sensors will soon launch in the commercial sector. Many of these sensors focus on hydration monitoring, which is critical for optimizing performance and ensuring safety; particularly as it relates to individuals participating in extremely demanding physical activities. For these reasons, we tested the, durability, and comfort of a prototype sweat sensor in a mock special operations field event. Data were collected at the U.S. Air Force Academy to include measures of hydration levels (e.g., Urine Specific Gravity) and fluid loss (e.g., body weight) across a series of five strenuous physical activities. We evaluated the prototype design in terms of comfort and intrusiveness. Observations and survey data revealed the participants did not perceive the technologies as intrusive. All of the requisite activities were completed and the technologies did not hinder performance. General Electric, the developers of the particular sensor evaluated, received important design-related information for future iterations. With this technology the U.S. military hopes to see a decrease in the number of heat and hydration related incidents by enhancing the safety of its personnel. Moreover, the future design of this system is critical as part of a physiological dashboard used by special operations forces. A combination of optimizing human performance and safety could create the next iteration of the world's most powerful ground forces.","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":"130603802","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.2019.8735598
Haley Finegan, Seth Jaffe, Angela Leon, Kim Lytle, Edward Morgan, Charlotte Greene, Anne Meyer, B. Brinkman, S. D. De Wekker, H. Yochum, N. Bezzo, G. Lewin
Soil respiration (SR), the carbon dioxide flux produced by organisms in soil, is not well quantified and understood compared to other soil characteristics. Currently, environmental scientists collect SR data either by manually taking measurements in the field, which is time intensive, or by receiving information from permanently placed sensors, which limits the locations where data is collected. This project aims to provide an efficient means of collecting spatially diverse data for environmental research and agricultural monitoring by designing and constructing an autonomous ground vehicle that can navigate to specific points of interest, collect SR and other ambient atmospheric measurements, and transmit the data remotely to a base station. To do so, the robot relies on a variety of subsystems including the robot's frame, differential steering, a mechanical arm that deploys an array of ground sensors, a radio network, and on-board temperature, pressure, humidity, wind speed, and GPS ambient atmospheric sensors. The vehicle will use the Robot Operating System (ROS) along with GPS, motion planning, and LIDAR to navigate between user-specified sampling locations while avoiding obstacles, which will minimize the need for human labor and allow more areas to be visited for data collection as compared to permanently placed sensors. The proposed autonomous system will help environmental scientists and agricultural managers collect and analyze soil data in the field.
{"title":"Development of an Autonomous Agricultural Vehicle to Measure Soil Respiration","authors":"Haley Finegan, Seth Jaffe, Angela Leon, Kim Lytle, Edward Morgan, Charlotte Greene, Anne Meyer, B. Brinkman, S. D. De Wekker, H. Yochum, N. Bezzo, G. Lewin","doi":"10.1109/SIEDS.2019.8735598","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735598","url":null,"abstract":"Soil respiration (SR), the carbon dioxide flux produced by organisms in soil, is not well quantified and understood compared to other soil characteristics. Currently, environmental scientists collect SR data either by manually taking measurements in the field, which is time intensive, or by receiving information from permanently placed sensors, which limits the locations where data is collected. This project aims to provide an efficient means of collecting spatially diverse data for environmental research and agricultural monitoring by designing and constructing an autonomous ground vehicle that can navigate to specific points of interest, collect SR and other ambient atmospheric measurements, and transmit the data remotely to a base station. To do so, the robot relies on a variety of subsystems including the robot's frame, differential steering, a mechanical arm that deploys an array of ground sensors, a radio network, and on-board temperature, pressure, humidity, wind speed, and GPS ambient atmospheric sensors. The vehicle will use the Robot Operating System (ROS) along with GPS, motion planning, and LIDAR to navigate between user-specified sampling locations while avoiding obstacles, which will minimize the need for human labor and allow more areas to be visited for data collection as compared to permanently placed sensors. The proposed autonomous system will help environmental scientists and agricultural managers collect and analyze soil data in the field.","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":"121540680","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.2019.8735595
D. Bernheimer, Tala Feda, C. Pallaria, Ashley Schnarrs
Drinking water is vital for the functioning of society; hence, municipalities are tasked with providing and exploring sources for adequate potable water. Increasing population and changes in climate have strained water supplies around the world, leaving more communities to explore alternative means of supplying potable water beyond the traditional sources. One of these alternatives is Direct Potable Reuse, or DPR, which is a closed system, recycling wastewater from homes and its community, cleaning the water, and reintroducing it back into the potable water supply. Since DPR systems are new, it is important to ensure that a DPR system is capable to perform with a high level of reliability. This project analyzes DPR advanced water treatment systems to check the mechanical reliability of the system and its components. Several types of methodologies are used to model and predict the system's risk behavior, such as Expert Judgement, Failure Modes and Effects Analysis, and Event Trees Analysis. Through analysis of the advanced water treatment process, the more vulnerable or higher liability components and processes can be identified. The purpose of this analysis is to reduce risk in future iterations of water treatment facilities, coupled with suggested risk mitigation strategies developed through the detailing and analysis of the treatment processes. The information provided by this project may be useful to decision makers when designing and implementing new DPR systems, and when maintaining and improving existing DPR systems.
{"title":"Direct Potable Reuse Systems Risk Analysis","authors":"D. Bernheimer, Tala Feda, C. Pallaria, Ashley Schnarrs","doi":"10.1109/SIEDS.2019.8735595","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735595","url":null,"abstract":"Drinking water is vital for the functioning of society; hence, municipalities are tasked with providing and exploring sources for adequate potable water. Increasing population and changes in climate have strained water supplies around the world, leaving more communities to explore alternative means of supplying potable water beyond the traditional sources. One of these alternatives is Direct Potable Reuse, or DPR, which is a closed system, recycling wastewater from homes and its community, cleaning the water, and reintroducing it back into the potable water supply. Since DPR systems are new, it is important to ensure that a DPR system is capable to perform with a high level of reliability. This project analyzes DPR advanced water treatment systems to check the mechanical reliability of the system and its components. Several types of methodologies are used to model and predict the system's risk behavior, such as Expert Judgement, Failure Modes and Effects Analysis, and Event Trees Analysis. Through analysis of the advanced water treatment process, the more vulnerable or higher liability components and processes can be identified. The purpose of this analysis is to reduce risk in future iterations of water treatment facilities, coupled with suggested risk mitigation strategies developed through the detailing and analysis of the treatment processes. The information provided by this project may be useful to decision makers when designing and implementing new DPR systems, and when maintaining and improving existing DPR systems.","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":"122950673","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：