Pub Date : 2019-04-01DOI: 10.1109/SIEDS.2019.8735615
B. Potter, Gina Valentino, Laura Yates, T. Benzing, A. Salman
Embedded electronic devices and sensors are playing a major role in bridging the gap between the physical world and the virtual world. Billions of devices such as smartphones, smart watches, wearables, medical implants, and wireless sensor nodes are considered building blocks in making the Internet of Things a reality. Such devices often carry sensitive or proprietary data and are used in critical applications, such as the use of wireless sensor nodes to remotely capture atmospheric greenhouse gas emissions data. Additionally, some of the devices used to collect data are being deployed in remote areas where accessibility is not easy and transmission of data for processing is not available due to the lack of network connectivity. Additionally, the use of wireless sensor nodes has been proven to making data collection faster, less labor intensive, and more cost effective. In this paper, we present an efficient method to remotely collect data from three sensors in a wireless sensor node. The intended purpose of this project is to remotely monitor a tributary to the South Fork of the Shenandoah River. The system makes use of an unmanned aerial vehicle to collect data from a remote stream site. We detail the methodology in which a customized unmanned aerial vehicle flies within range of connectivity of a wireless sensor node, establishing a communication channel to upload and store the data for pending analysis. The methodology utilized is shown through an environmental case study which illustrates the advantages of implementing a wireless sensor node which includes accessing a remote location, continuous data collection, and reduction of labor and costs associated with field data collection methodologies. We show that our node is efficient in terms on its power and energy consumption.
{"title":"Environmental Monitoring Using a Drone-Enabled Wireless Sensor Network","authors":"B. Potter, Gina Valentino, Laura Yates, T. Benzing, A. Salman","doi":"10.1109/SIEDS.2019.8735615","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735615","url":null,"abstract":"Embedded electronic devices and sensors are playing a major role in bridging the gap between the physical world and the virtual world. Billions of devices such as smartphones, smart watches, wearables, medical implants, and wireless sensor nodes are considered building blocks in making the Internet of Things a reality. Such devices often carry sensitive or proprietary data and are used in critical applications, such as the use of wireless sensor nodes to remotely capture atmospheric greenhouse gas emissions data. Additionally, some of the devices used to collect data are being deployed in remote areas where accessibility is not easy and transmission of data for processing is not available due to the lack of network connectivity. Additionally, the use of wireless sensor nodes has been proven to making data collection faster, less labor intensive, and more cost effective. In this paper, we present an efficient method to remotely collect data from three sensors in a wireless sensor node. The intended purpose of this project is to remotely monitor a tributary to the South Fork of the Shenandoah River. The system makes use of an unmanned aerial vehicle to collect data from a remote stream site. We detail the methodology in which a customized unmanned aerial vehicle flies within range of connectivity of a wireless sensor node, establishing a communication channel to upload and store the data for pending analysis. The methodology utilized is shown through an environmental case study which illustrates the advantages of implementing a wireless sensor node which includes accessing a remote location, continuous data collection, and reduction of labor and costs associated with field data collection methodologies. We show that our node is efficient in terms on its power and energy consumption.","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":"126211923","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.2019.8735596
Andrew Khayyat, Claudia Sequera, Nathan Walk, Ehren Wong, J. Barbera, T. Mazzuchi, J. Santos
Congestive Heart Failure (CHF) is a condition where blood flow from the heart through the body is inadequate, causing congestion in the lungs and swelling in the body's tissues. An urban university teaching hospital is able to treat and assign post-discharge resources to patients diagnosed with CHF. Despite the current treatment methods and assignment of post-discharge resources, the rate of readmission for patients returning to the hospital within 30 days remains higher than the level expected by the Center for Medicare and Medicaid Services. This project proposes the development of a decision support tool to assist the hospital in reducing the readmission rate for patients diagnosed with CHF. The project initially analyzes medical comorbidities and social factors of patients to identify correlations with a patient's probability of readmission. A discriminant analysis baseline model constructed from an electronic health record database (September 2015 to December 2018) projects the readmission probability for a patient. Subsequently, a correlation study determines which post-discharge resources are associated with reducing the readmission probability in patients with specific combinations of medical comorbidities and social factors. Ultimately, the decision support tool analyzes a patient's unique combination of medical severity and social factors to project the patient's probability of readmission and provides a tailored list of suggested post-discharge resources to reduce the probability of readmission for that patient.
{"title":"Decision Support Tool to Estimate and Reduce the Probability of Readmission for Congestive Heart Failure Patients","authors":"Andrew Khayyat, Claudia Sequera, Nathan Walk, Ehren Wong, J. Barbera, T. Mazzuchi, J. Santos","doi":"10.1109/SIEDS.2019.8735596","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735596","url":null,"abstract":"Congestive Heart Failure (CHF) is a condition where blood flow from the heart through the body is inadequate, causing congestion in the lungs and swelling in the body's tissues. An urban university teaching hospital is able to treat and assign post-discharge resources to patients diagnosed with CHF. Despite the current treatment methods and assignment of post-discharge resources, the rate of readmission for patients returning to the hospital within 30 days remains higher than the level expected by the Center for Medicare and Medicaid Services. This project proposes the development of a decision support tool to assist the hospital in reducing the readmission rate for patients diagnosed with CHF. The project initially analyzes medical comorbidities and social factors of patients to identify correlations with a patient's probability of readmission. A discriminant analysis baseline model constructed from an electronic health record database (September 2015 to December 2018) projects the readmission probability for a patient. Subsequently, a correlation study determines which post-discharge resources are associated with reducing the readmission probability in patients with specific combinations of medical comorbidities and social factors. Ultimately, the decision support tool analyzes a patient's unique combination of medical severity and social factors to project the patient's probability of readmission and provides a tailored list of suggested post-discharge resources to reduce the probability of readmission for that patient.","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":"123781206","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.2019.8735593
A. Fabbri, Franciny Medeiros Barreto, Joslaine Cristina Jeske de Freitas
Enterprise Architecture (EA) is a way for organizing the operations and structure of a business. It is also defined as a set of artifacts that describe the objects of an organization or an enterprise that include IT (Information Technology) alignment documentation, organizational models, reusable components, architectural patterns, and guiding principles of the design and evolution of its objects. In order to introduce technological advances and help companies to define a corporate strategy for maintaining their capacity, this article presents a model for EA using a non-preemptive multiprocessing system. Colored Petri nets (NPCs) make it possible to model very large and complex systems because they can represent data types and different levels of abstraction. The complex color sets, like arrays of records, are applied in the models of scheduling used in this paper (one and two processors) to simplify the model and increase the abstraction capability compared to models that do not used complex systems. The proposed models automatically execute processes with input times, service times and the name of a single non-preemptive method. Beside this, they calculate the waiting and turnaround time of processes further idle times of the one or two processors. Thus, all necessary details related to scheduling and running processes are obtained for processing. In addition, the results of the comparison between models with one or two processors show that there is a significant decrease in the final execution time for the models with two processors.
{"title":"Modeling and Simulating Enterprise Architecture Activities Using a Non Preemptive Multiprocessor System","authors":"A. Fabbri, Franciny Medeiros Barreto, Joslaine Cristina Jeske de Freitas","doi":"10.1109/SIEDS.2019.8735593","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735593","url":null,"abstract":"Enterprise Architecture (EA) is a way for organizing the operations and structure of a business. It is also defined as a set of artifacts that describe the objects of an organization or an enterprise that include IT (Information Technology) alignment documentation, organizational models, reusable components, architectural patterns, and guiding principles of the design and evolution of its objects. In order to introduce technological advances and help companies to define a corporate strategy for maintaining their capacity, this article presents a model for EA using a non-preemptive multiprocessing system. Colored Petri nets (NPCs) make it possible to model very large and complex systems because they can represent data types and different levels of abstraction. The complex color sets, like arrays of records, are applied in the models of scheduling used in this paper (one and two processors) to simplify the model and increase the abstraction capability compared to models that do not used complex systems. The proposed models automatically execute processes with input times, service times and the name of a single non-preemptive method. Beside this, they calculate the waiting and turnaround time of processes further idle times of the one or two processors. Thus, all necessary details related to scheduling and running processes are obtained for processing. In addition, the results of the comparison between models with one or two processors show that there is a significant decrease in the final execution time for the models with two processors.","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":"121937981","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.2019.8735601
E. Argudo, Julia Grehan, Luke Leidy, Jeong-su Alice Park, Morgan Patterson, Suhani Sanghavi, Devon Smith, S. Guerlain
The healthcare sector sees one of the highest rates of work-related musculoskeletal disorders (WMSDs) of all private sector industries. Many of these job-related injuries stem from poor ergonomics: examples include holding static positions for prolonged periods of time, standing or sitting in awkward postures, performing repetitive motions throughout the course of a procedure, and working in environments with poor ergonomic design. The goal of this project is to increase awareness of safe ergonomic practices in hospitals through an online educational program for healthcare employees. The program informs users of risky ergonomic behaviors and provides recommendations for improvements. The topics covered in the program include: 1.An Introduction to Ergonomics, Healthcare Ergonomics, and Musculoskeletal Disorders 2.Postures In and Out of the Workplace 3.Measurement Techniques for Quantifying Postures 4.Environmental Factors Influencing Ergonomics 5.Recommendation: Microbreaks 6.Recommendation: Exercise Programs To date, beta testing of the course has taken place. The program was designed to be effective, coherent, and efficient and of suitable quality and engagement to become accredited for Continuing Medical Education credits to help motivate healthcare professionals to complete the course. Intervention effectiveness is measured using pre- and post-module question scores and a survey of opinions. The program was deemed fairly effective and very efficient but needs improvement in terms of engagement. Several issues are also identified regarding the limitations of Coursera, the online educational learning platform being used to develop, evaluate, and deliver the content.
{"title":"Development and Evaluation of an Online Ergonomics Educational Program for Healthcare Professionals","authors":"E. Argudo, Julia Grehan, Luke Leidy, Jeong-su Alice Park, Morgan Patterson, Suhani Sanghavi, Devon Smith, S. Guerlain","doi":"10.1109/SIEDS.2019.8735601","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735601","url":null,"abstract":"The healthcare sector sees one of the highest rates of work-related musculoskeletal disorders (WMSDs) of all private sector industries. Many of these job-related injuries stem from poor ergonomics: examples include holding static positions for prolonged periods of time, standing or sitting in awkward postures, performing repetitive motions throughout the course of a procedure, and working in environments with poor ergonomic design. The goal of this project is to increase awareness of safe ergonomic practices in hospitals through an online educational program for healthcare employees. The program informs users of risky ergonomic behaviors and provides recommendations for improvements. The topics covered in the program include: 1.An Introduction to Ergonomics, Healthcare Ergonomics, and Musculoskeletal Disorders 2.Postures In and Out of the Workplace 3.Measurement Techniques for Quantifying Postures 4.Environmental Factors Influencing Ergonomics 5.Recommendation: Microbreaks 6.Recommendation: Exercise Programs To date, beta testing of the course has taken place. The program was designed to be effective, coherent, and efficient and of suitable quality and engagement to become accredited for Continuing Medical Education credits to help motivate healthcare professionals to complete the course. Intervention effectiveness is measured using pre- and post-module question scores and a survey of opinions. The program was deemed fairly effective and very efficient but needs improvement in terms of engagement. Several issues are also identified regarding the limitations of Coursera, the online educational learning platform being used to develop, evaluate, and deliver the content.","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":"127592970","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.2019.8735635
Mengyao Zhang, N. Han, Benjamin J. Lobo
Despite the efforts of governmental and nonprofit agencies to increase seatbelt usage in the state of Virginia, drivers continue to drive while unrestrained. A better understanding of drivers' seatbelt usage would allow government officials and nonprofit agencies to more effectively target the right locations and populations with enforcement activities and education programs aimed at reducing unrestrained crashes. Recent literature has focused on identifying factors (such as sociodemographic characteristics of drivers) that correlate with seatbelt usage. This work aims to discover additional characteristics of unrestrained crashes and to predict the occurrence of unrestrained crashes in Virginia. To achieve these objectives, inferential analysis and predictive modeling were performed on Virginia crash data collected during the 2015 through 2017 time period and the seatbelt conviction data for these drivers. For the inferential part, hypothesis testing methods were used to uncover significant relationships between variables. Kernel density estimation (KDE) was used to identify spatial and temporal differences in restrained versus unrestrained crashes. For the predictive part, predictive machine learning models such as logistic regression and random forests were built to predict whether a crash was restrained or unrestrained. Results from this study will aid governmental and other agencies to develop occupant protection programs, increase public awareness, and target education and enforcement activities.
{"title":"Understanding and Predicting Drivers' Seatbelt Usage in Crashes in Virginia","authors":"Mengyao Zhang, N. Han, Benjamin J. Lobo","doi":"10.1109/SIEDS.2019.8735635","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735635","url":null,"abstract":"Despite the efforts of governmental and nonprofit agencies to increase seatbelt usage in the state of Virginia, drivers continue to drive while unrestrained. A better understanding of drivers' seatbelt usage would allow government officials and nonprofit agencies to more effectively target the right locations and populations with enforcement activities and education programs aimed at reducing unrestrained crashes. Recent literature has focused on identifying factors (such as sociodemographic characteristics of drivers) that correlate with seatbelt usage. This work aims to discover additional characteristics of unrestrained crashes and to predict the occurrence of unrestrained crashes in Virginia. To achieve these objectives, inferential analysis and predictive modeling were performed on Virginia crash data collected during the 2015 through 2017 time period and the seatbelt conviction data for these drivers. For the inferential part, hypothesis testing methods were used to uncover significant relationships between variables. Kernel density estimation (KDE) was used to identify spatial and temporal differences in restrained versus unrestrained crashes. For the predictive part, predictive machine learning models such as logistic regression and random forests were built to predict whether a crash was restrained or unrestrained. Results from this study will aid governmental and other agencies to develop occupant protection programs, increase public awareness, and target education and enforcement activities.","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":"129170266","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.2019.8735599
M. Ramakrishnan, Sakshi Jawarani, V. Sriram, Raf Alvarado
The Collective Biographies of Women Project (CBW) seeks to annotate a large corpus of nineteenth and twentieth century British and American biographical texts about women. These annotations, applied at the paragraph level, draw from a controlled vocabulary known as BESS, Biographical Elements and Structure Schema. The BESS vocabulary terms are grouped into five major categories – Stage Of life, Persona, Event, Topos, Discourse. The corpus is drawn from 1,270 known books, comprising around 13,000 chapters of about 8,000 women. Because manual annotation is painstaking, time-consuming, and error-prone, there is a need to automate the annotation process for the entire corpus. Using the BESS vocabulary as labels and the currently annotated paragraphs as a training set, we developed a supervised machine learning classifier to aid in this process. Employing several methods, including Logistic Regression, Random Forest and Language models, we achieved an accuracy of ∼87%. In addition to aiding in the work of annotation, we have made recommendations about further developing the BESS vocabulary.
妇女集体传记项目(CBW)试图注释19世纪和20世纪英国和美国关于妇女的传记文本的大量语料库。这些注释应用于段落级别，从称为BESS (Biographical Elements and Structure Schema)的受控词汇表中提取。BESS词汇术语分为五大类:人生阶段、人物角色、事件、话题、话语。该语料库取自1270本已知的书籍，包括大约8000名女性的13000章。由于手工注释费时费力，而且容易出错，因此需要对整个语料库的注释过程进行自动化。使用BESS词汇表作为标签，当前注释的段落作为训练集，我们开发了一个有监督的机器学习分类器来帮助这个过程。采用多种方法，包括逻辑回归、随机森林和语言模型，我们实现了~ 87%的准确率。除了帮助注释工作之外，我们还提出了进一步开发BESS词汇表的建议。
{"title":"Collective Biographies of Women: A Machine Learning Approach to Paragraph Annotation","authors":"M. Ramakrishnan, Sakshi Jawarani, V. Sriram, Raf Alvarado","doi":"10.1109/SIEDS.2019.8735599","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735599","url":null,"abstract":"The Collective Biographies of Women Project (CBW) seeks to annotate a large corpus of nineteenth and twentieth century British and American biographical texts about women. These annotations, applied at the paragraph level, draw from a controlled vocabulary known as BESS, Biographical Elements and Structure Schema. The BESS vocabulary terms are grouped into five major categories – Stage Of life, Persona, Event, Topos, Discourse. The corpus is drawn from 1,270 known books, comprising around 13,000 chapters of about 8,000 women. Because manual annotation is painstaking, time-consuming, and error-prone, there is a need to automate the annotation process for the entire corpus. Using the BESS vocabulary as labels and the currently annotated paragraphs as a training set, we developed a supervised machine learning classifier to aid in this process. Employing several methods, including Logistic Regression, Random Forest and Language models, we achieved an accuracy of ∼87%. In addition to aiding in the work of annotation, we have made recommendations about further developing the BESS vocabulary.","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":"131200694","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.2019.8735631
Ab Boxley, Marcelo Costa de Sousa, Ashish Singh
In a competitive industry like corrugated packaging, companies are constantly looking for opportunities to increase the efficiency of operations while maintaining high standards of customer service. This paper presents a multi-faceted approach to a large player in this industry, incorporating demand trends for different packaging specifications to optimize raw material and tooling dimensions, and rebalance production costs and wastage at the conversion facility. Given the market dynamics, a value-creating solution needs to be able to capture fluctuations in demand including unexpected orders from key customers requiring individual treatment. We propose a process-driven solution incorporating both a supply chain communications methodology and a simulation-based tool that managers can rely on to guide the selection of tooled SKUs to be maintained in the production line. To provide the user with realistic optionality, both assumptions and sensitivities are employed surrounding parameters such as service level, lead time, and cost variances. The resultant suite combines a series of optimization algorithms that are aligned with inventory management best practices and produce an application that is relevant, applicable, and flexible enough for business managers to make decisions on the fly and reach an optimal solution given the restrictions imposed by the operation.
{"title":"Optimizing Stock Keeping Units (SKUs) in the Packaging Industry Managing for Indefinite Constraints and Forecasting Uncertainty","authors":"Ab Boxley, Marcelo Costa de Sousa, Ashish Singh","doi":"10.1109/SIEDS.2019.8735631","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735631","url":null,"abstract":"In a competitive industry like corrugated packaging, companies are constantly looking for opportunities to increase the efficiency of operations while maintaining high standards of customer service. This paper presents a multi-faceted approach to a large player in this industry, incorporating demand trends for different packaging specifications to optimize raw material and tooling dimensions, and rebalance production costs and wastage at the conversion facility. Given the market dynamics, a value-creating solution needs to be able to capture fluctuations in demand including unexpected orders from key customers requiring individual treatment. We propose a process-driven solution incorporating both a supply chain communications methodology and a simulation-based tool that managers can rely on to guide the selection of tooled SKUs to be maintained in the production line. To provide the user with realistic optionality, both assumptions and sensitivities are employed surrounding parameters such as service level, lead time, and cost variances. The resultant suite combines a series of optimization algorithms that are aligned with inventory management best practices and produce an application that is relevant, applicable, and flexible enough for business managers to make decisions on the fly and reach an optimal solution given the restrictions imposed by the operation.","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":"134550416","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.2019.8735650
Cooper Grever, Debora Kropp, Joshua Smith, Tori Monteleone
The Federal Republic of Nigeria has extensive natural resources and significant economic potential, but portions of the population suffer from poverty and lack of access to essential supplies, such as food and vaccines, due to geographic isolation. Railways offer a stable, practical method to transport resources over large distances. Railway infrastructure has also been shown to increase welfare of isolated communities and while the current railway network is limited in structure and technology, renewed government interest provides an opportunity to expand the current Nigerian railway. This paper describes the construction of a data-driven railway development map to increase coverage for the resource of interest, vaccines, to remote areas of Nigeria. A dataset of hundreds of potential city-hubs was evaluated and minimized based on coverage radius. Multiple railway networks were modeled to maximize coverage through both a minimum spanning tree and traveling salesman method while constrained by minimal distance. These models were then refined by applying nominal scoring to the city-hubs. To calculate scores, the significant factors for vaccination coverage were determined on a state-by-state basis by a stepwise regression. The coefficient values of the normalized significant factors were applied to city-hubs through nominal scoring based on their state and population. The expanded network and selected city-hubs were implemented into a geospatial map of Nigeria to provide a data-driven display for recommended railway expansions. The networks were further constrained by topographic obstacles and a forecasting model was developed based on population growth and the expanded railway. The methodology established in this project can be adapted to assist other developing countries facing similar challenges.
{"title":"Railway Transportation Expansion and Resource Coverage Analysis in Nigeria","authors":"Cooper Grever, Debora Kropp, Joshua Smith, Tori Monteleone","doi":"10.1109/SIEDS.2019.8735650","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735650","url":null,"abstract":"The Federal Republic of Nigeria has extensive natural resources and significant economic potential, but portions of the population suffer from poverty and lack of access to essential supplies, such as food and vaccines, due to geographic isolation. Railways offer a stable, practical method to transport resources over large distances. Railway infrastructure has also been shown to increase welfare of isolated communities and while the current railway network is limited in structure and technology, renewed government interest provides an opportunity to expand the current Nigerian railway. This paper describes the construction of a data-driven railway development map to increase coverage for the resource of interest, vaccines, to remote areas of Nigeria. A dataset of hundreds of potential city-hubs was evaluated and minimized based on coverage radius. Multiple railway networks were modeled to maximize coverage through both a minimum spanning tree and traveling salesman method while constrained by minimal distance. These models were then refined by applying nominal scoring to the city-hubs. To calculate scores, the significant factors for vaccination coverage were determined on a state-by-state basis by a stepwise regression. The coefficient values of the normalized significant factors were applied to city-hubs through nominal scoring based on their state and population. The expanded network and selected city-hubs were implemented into a geospatial map of Nigeria to provide a data-driven display for recommended railway expansions. The networks were further constrained by topographic obstacles and a forecasting model was developed based on population growth and the expanded railway. The methodology established in this project can be adapted to assist other developing countries facing similar challenges.","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":"128686215","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.2019.8735632
Jennavive Benko, William Clark, Candace R. Craig, Grace Culver, Patrick Mahan, Ajay Patel, D. Voce, N. Bezzo, G. Lewin
This project identifies methods for improving the security and resilience of autonomous vehicles in coordinated networks. Specifically, we developed a trust algorithm that quantifies the reliability of agents within the network. The algorithm takes advantage of the historic reliability of an agent, defined as reputation, and the tendency towards increasing or decreasing error, defined as trend. The trust algorithm is cyclic; trust measurements help detect anomalies within the network and anomalies are used to update trust measurements. This paper outlines the trust algorithm and results from its application in both simulation in MATLAB and a hardware demonstration on TurtleBot 2 robots. This paper represents a work in progress. Preliminary results have been gathered from simulation and further results will be gathered from the hardware demonstration after integration is complete.
{"title":"Security and Resiliency of Coordinated Autonomous Vehicles","authors":"Jennavive Benko, William Clark, Candace R. Craig, Grace Culver, Patrick Mahan, Ajay Patel, D. Voce, N. Bezzo, G. Lewin","doi":"10.1109/SIEDS.2019.8735632","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735632","url":null,"abstract":"This project identifies methods for improving the security and resilience of autonomous vehicles in coordinated networks. Specifically, we developed a trust algorithm that quantifies the reliability of agents within the network. The algorithm takes advantage of the historic reliability of an agent, defined as reputation, and the tendency towards increasing or decreasing error, defined as trend. The trust algorithm is cyclic; trust measurements help detect anomalies within the network and anomalies are used to update trust measurements. This paper outlines the trust algorithm and results from its application in both simulation in MATLAB and a hardware demonstration on TurtleBot 2 robots. This paper represents a work in progress. Preliminary results have been gathered from simulation and further results will be gathered from the hardware demonstration after integration is complete.","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":"116863560","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.2019.8735646
Sean Mullane, Ruoyan Chen, Sridhar Vemulapalli, Eli J. Draizen, Ke Wang, C. Mura, P. Bourne
The biological function of a protein stems from its 3-dimensional structure, which is thermodynamically determined by the energetics of interatomic forces between its amino acid building blocks (the order of amino acids, known as the sequence, defines a protein). Given the costs (time, money, human resources) of determining protein structures via experimental means like X-ray crystallography, can we better describe and compare protein 3D structures in a robust and efficient manner, so as to gain meaningful biological insights? We begin by considering a relatively simple problem, limiting ourselves to just protein secondary structural elements. Historically, many computational methods have been devised to classify amino acid residues in a protein chain into one of several discrete “secondary structures”, of which the most well-characterized are the geometrically regular $mathbf{a}$-helix and $boldsymbol{beta}$-sheet; irregular structural patterns, such as ‘turns’ and ‘loops’, are less understood. Here, we present a study of Deep Learning techniques to classify the loop-like end cap structures which delimit a-helices. Previous work used highly empirical and heuristic methods to manually classify helix capping motifs. Instead, we use structural data directly—including (i) backbone torsion angles computed from 3D structures, (ii) macromolecular feature sets (e.g., physicochemical properties), and (iii) helix cap classification data (from CAPS-DB)—as the ground truth to train a bidirectional long short–term memory (BiLSTM) model to classify helix cap residues. We tried different network architectures and scanned hyperparameters in order to train and assess several models; we also trained a Support Vector Classifier (SVC) to use as a baseline. Ultimately, we achieved 85% class-balanced accuracy with a deep BiLSTM model.
{"title":"Machine Learning for Classification of Protein Helix Capping Motifs","authors":"Sean Mullane, Ruoyan Chen, Sridhar Vemulapalli, Eli J. Draizen, Ke Wang, C. Mura, P. Bourne","doi":"10.1109/SIEDS.2019.8735646","DOIUrl":"https://doi.org/10.1109/SIEDS.2019.8735646","url":null,"abstract":"The biological function of a protein stems from its 3-dimensional structure, which is thermodynamically determined by the energetics of interatomic forces between its amino acid building blocks (the order of amino acids, known as the sequence, defines a protein). Given the costs (time, money, human resources) of determining protein structures via experimental means like X-ray crystallography, can we better describe and compare protein 3D structures in a robust and efficient manner, so as to gain meaningful biological insights? We begin by considering a relatively simple problem, limiting ourselves to just protein secondary structural elements. Historically, many computational methods have been devised to classify amino acid residues in a protein chain into one of several discrete “secondary structures”, of which the most well-characterized are the geometrically regular $mathbf{a}$-helix and $boldsymbol{beta}$-sheet; irregular structural patterns, such as ‘turns’ and ‘loops’, are less understood. Here, we present a study of Deep Learning techniques to classify the loop-like end cap structures which delimit a-helices. Previous work used highly empirical and heuristic methods to manually classify helix capping motifs. Instead, we use structural data directly—including (i) backbone torsion angles computed from 3D structures, (ii) macromolecular feature sets (e.g., physicochemical properties), and (iii) helix cap classification data (from CAPS-DB)—as the ground truth to train a bidirectional long short–term memory (BiLSTM) model to classify helix cap residues. We tried different network architectures and scanned hyperparameters in order to train and assess several models; we also trained a Support Vector Classifier (SVC) to use as a baseline. Ultimately, we achieved 85% class-balanced accuracy with a deep BiLSTM model.","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":"115225866","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：