Pub Date : 2022-11-03DOI: 10.1109/MetroCon56047.2022.9971141
Garrett I. Cayce, Arthur C. Depoian, Colleen P. Bailey, P. Guturu
This work investigates an evolution of verified recent advances to machine learning applied to electrocardiogram (ECG) data. The successful inference of heartbeat arrhythmia has long been a goal yet achieved, the techniques presented advance the worthy endeavor. The mutation of the training data through amplitude and time inversion creates artificial information leading to a more robust and accurate model in comparison to the current state of the art. Over a 5% reduction in accuracy error is reached with the proposed techniques in comparison to that of the base model.
{"title":"Improved Neural Network Arrhythmia Classification Through Integrated Data Augmentation","authors":"Garrett I. Cayce, Arthur C. Depoian, Colleen P. Bailey, P. Guturu","doi":"10.1109/MetroCon56047.2022.9971141","DOIUrl":"https://doi.org/10.1109/MetroCon56047.2022.9971141","url":null,"abstract":"This work investigates an evolution of verified recent advances to machine learning applied to electrocardiogram (ECG) data. The successful inference of heartbeat arrhythmia has long been a goal yet achieved, the techniques presented advance the worthy endeavor. The mutation of the training data through amplitude and time inversion creates artificial information leading to a more robust and accurate model in comparison to the current state of the art. Over a 5% reduction in accuracy error is reached with the proposed techniques in comparison to that of the base model.","PeriodicalId":292881,"journal":{"name":"2022 IEEE MetroCon","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124576541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroCon56047.2022.9971137
N. I. Hossain, Shawana Tabassum
This work reports a kirigami-shaped sensor interfaced with an internet-of-things platform for strain insensitive and real-time temperature detection. The performance of the sensor was characterized under different stretching and twisting deformations, along with humidity variations. Excellent agreement was observed between the experimental and simulation results. The kirigami architecture shielded the sensor from motion artifacts, thereby demonstrating its promise in long-term wearable applications.
{"title":"Performance Analysis of a Kirigami-shaped Temperature Sensor","authors":"N. I. Hossain, Shawana Tabassum","doi":"10.1109/MetroCon56047.2022.9971137","DOIUrl":"https://doi.org/10.1109/MetroCon56047.2022.9971137","url":null,"abstract":"This work reports a kirigami-shaped sensor interfaced with an internet-of-things platform for strain insensitive and real-time temperature detection. The performance of the sensor was characterized under different stretching and twisting deformations, along with humidity variations. Excellent agreement was observed between the experimental and simulation results. The kirigami architecture shielded the sensor from motion artifacts, thereby demonstrating its promise in long-term wearable applications.","PeriodicalId":292881,"journal":{"name":"2022 IEEE MetroCon","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128502846","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroCon56047.2022.9971131
Jared Riley, S. Williams, Corey Reyna, Ethan R. Adams, Arthur C. Depoian, Colleen P. Bailey, P. Guturu
One of the most challenging and significant objectives of NASA over the coming years is to successfully send humans to Mars. The past six decades of safety concerns addressed for satellite and rover missions, become an even more important consideration with human passengers. Atmospheric and surface conditions of Mars can change abruptly, leading to communication breaks, equipment failures, and potential safety threats. The sudden onset of a dust storm, or a more common dust devil, can interfere with atmospheric entry, ground mechanical equipment, solar charging systems, and much more. By combining traditional signal processing techniques and with an efficient machine learning algorithm, this paper proposes to classify atmospheric disturbances on the red planet with a high level of accuracy.
{"title":"Classifying the Devil in the Dust: Edge AI","authors":"Jared Riley, S. Williams, Corey Reyna, Ethan R. Adams, Arthur C. Depoian, Colleen P. Bailey, P. Guturu","doi":"10.1109/MetroCon56047.2022.9971131","DOIUrl":"https://doi.org/10.1109/MetroCon56047.2022.9971131","url":null,"abstract":"One of the most challenging and significant objectives of NASA over the coming years is to successfully send humans to Mars. The past six decades of safety concerns addressed for satellite and rover missions, become an even more important consideration with human passengers. Atmospheric and surface conditions of Mars can change abruptly, leading to communication breaks, equipment failures, and potential safety threats. The sudden onset of a dust storm, or a more common dust devil, can interfere with atmospheric entry, ground mechanical equipment, solar charging systems, and much more. By combining traditional signal processing techniques and with an efficient machine learning algorithm, this paper proposes to classify atmospheric disturbances on the red planet with a high level of accuracy.","PeriodicalId":292881,"journal":{"name":"2022 IEEE MetroCon","volume":"163 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131563358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroCon56047.2022.9971138
Steven Lincoln
Agile development is all about delivering value frequently, but how do you know if you are achieving your Agile objectives. Are you delivering value? Are you delivering frequently? Both terms can be subjective, and they can have varying meanings dependent on your industry, business model, your customer’s expectations, and your leadership. What if there were a way to measure value and frequency objectively as it pertains to your business? It would let you know whether you are succeeding in your Agile journey and whether over time you are improving, stagnating, or regressing. This paper will evaluate what drives value and how an organization can tailor those drivers to establish a measurement to evaluate how successful they are in delivering value frequently.
{"title":"Measuring Value","authors":"Steven Lincoln","doi":"10.1109/MetroCon56047.2022.9971138","DOIUrl":"https://doi.org/10.1109/MetroCon56047.2022.9971138","url":null,"abstract":"Agile development is all about delivering value frequently, but how do you know if you are achieving your Agile objectives. Are you delivering value? Are you delivering frequently? Both terms can be subjective, and they can have varying meanings dependent on your industry, business model, your customer’s expectations, and your leadership. What if there were a way to measure value and frequency objectively as it pertains to your business? It would let you know whether you are succeeding in your Agile journey and whether over time you are improving, stagnating, or regressing. This paper will evaluate what drives value and how an organization can tailor those drivers to establish a measurement to evaluate how successful they are in delivering value frequently.","PeriodicalId":292881,"journal":{"name":"2022 IEEE MetroCon","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131827980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroCon56047.2022.9971133
Hirak Mazumdar, M. P. Murphy, Shilpa Bhatkande, H. Emerson, D. Kaplan, Hardik A. Gohel
The use of physical models to predict groundwater contaminant movement remains technically challenging due to the complexity of the phenomena, the heterogeneity of key parameters in nature, and the presence of poorly defined interactive and feedback processes. New approaches to address these challenges are needed. In this study, we evaluate various Artificial Intelligence (AI)-based approaches to understand hexavalent chromium (Cr(VI)) plumes located on the U.S. Department of Energy’s (DOE) Hanford Site in Richland, WA. The groundwater monitoring dataset used in this study included data from the 100 Area along the Columbia River and included data collected between 2010 to 2019. This study investigates the most prominent contaminant, Cr(VI), with the Extreme Gradient Boosting (XGBoost) machine learning model. The XGBoost model was compared with an optimized version using an Empirical Bayes Search Cross-Validation technique for better prediction. The optimized XGBoost model yielded an R2 value of 0.99 on the training set and 0.85 on the testing set, whereas X G B Boost without optimization yielded a value of 0.83 on the training set and 0.73 on the testing set. This paper provides an overview of a computational method for groundwater contamination modeling that shows promise for improving current remediation efforts.
{"title":"Optimized Machine Learning Model for Predicting Groundwater Contamination","authors":"Hirak Mazumdar, M. P. Murphy, Shilpa Bhatkande, H. Emerson, D. Kaplan, Hardik A. Gohel","doi":"10.1109/MetroCon56047.2022.9971133","DOIUrl":"https://doi.org/10.1109/MetroCon56047.2022.9971133","url":null,"abstract":"The use of physical models to predict groundwater contaminant movement remains technically challenging due to the complexity of the phenomena, the heterogeneity of key parameters in nature, and the presence of poorly defined interactive and feedback processes. New approaches to address these challenges are needed. In this study, we evaluate various Artificial Intelligence (AI)-based approaches to understand hexavalent chromium (Cr(VI)) plumes located on the U.S. Department of Energy’s (DOE) Hanford Site in Richland, WA. The groundwater monitoring dataset used in this study included data from the 100 Area along the Columbia River and included data collected between 2010 to 2019. This study investigates the most prominent contaminant, Cr(VI), with the Extreme Gradient Boosting (XGBoost) machine learning model. The XGBoost model was compared with an optimized version using an Empirical Bayes Search Cross-Validation technique for better prediction. The optimized XGBoost model yielded an R2 value of 0.99 on the training set and 0.85 on the testing set, whereas X G B Boost without optimization yielded a value of 0.83 on the training set and 0.73 on the testing set. This paper provides an overview of a computational method for groundwater contamination modeling that shows promise for improving current remediation efforts.","PeriodicalId":292881,"journal":{"name":"2022 IEEE MetroCon","volume":"41 20","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113934029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroCon56047.2022.9971142
Awele I. Anyanhun
Black box descriptions created using a model-based systems engineering approach provide an excellent way to communicate a complex system concept. Furthermore, it enables the early analysis of the system’s desired emergent behavior before embarking on a detailed system design. In this paper, an exemplar executable Black box system model is developed for the “Provide Full Duplex Data Relay Service” Use Case for a communication subsystem used for intersatellite communication. Behavioral and parametric diagrams are created and used to analyze the black box system model behavior and properties. The resulting model portrays that the utility and efficacy of an executable black box model goes beyond being just an abstract representation of a System of Interest to demonstrating how it fosters the development of a complete and more robust requirement baseline.
{"title":"The Niftiness of Executable MBSE Black Box Models: A Satellite Subsystem Exemplar","authors":"Awele I. Anyanhun","doi":"10.1109/MetroCon56047.2022.9971142","DOIUrl":"https://doi.org/10.1109/MetroCon56047.2022.9971142","url":null,"abstract":"Black box descriptions created using a model-based systems engineering approach provide an excellent way to communicate a complex system concept. Furthermore, it enables the early analysis of the system’s desired emergent behavior before embarking on a detailed system design. In this paper, an exemplar executable Black box system model is developed for the “Provide Full Duplex Data Relay Service” Use Case for a communication subsystem used for intersatellite communication. Behavioral and parametric diagrams are created and used to analyze the black box system model behavior and properties. The resulting model portrays that the utility and efficacy of an executable black box model goes beyond being just an abstract representation of a System of Interest to demonstrating how it fosters the development of a complete and more robust requirement baseline.","PeriodicalId":292881,"journal":{"name":"2022 IEEE MetroCon","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114083203","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroCon56047.2022.9971140
Colleen P. Bailey, Arthur C. Depoian, Ethan R. Adams
Recent years have seen a growing trend towards massive deep learning neural network algorithms. This movement is further perpetuated by the rapid growth in available computation. While these giant models attain remarkable performance, the required computational cost is proportionally huge. There is a resulting necessity for efficient and intelligent algorithm design that can achieve similar high performance to current state-of the-art.
{"title":"Edge AI: Addressing the Efficiency Paradigm","authors":"Colleen P. Bailey, Arthur C. Depoian, Ethan R. Adams","doi":"10.1109/MetroCon56047.2022.9971140","DOIUrl":"https://doi.org/10.1109/MetroCon56047.2022.9971140","url":null,"abstract":"Recent years have seen a growing trend towards massive deep learning neural network algorithms. This movement is further perpetuated by the rapid growth in available computation. While these giant models attain remarkable performance, the required computational cost is proportionally huge. There is a resulting necessity for efficient and intelligent algorithm design that can achieve similar high performance to current state-of the-art.","PeriodicalId":292881,"journal":{"name":"2022 IEEE MetroCon","volume":"191 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133487178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroCon56047.2022.9971136
Aidan G. Kurz, Ethan R. Adams, Arthur C. Depoian, Colleen P. Bailey, P. Guturu
The constant production and lack of efficient waste management procedure has created a need for automated classification of trash as it comes into facilities. This paper proposes a new algorithm for efficiently classifying objects found in solid waste processing by utilizing a combination of vision transformers (ViT) and convolutional neural networks (CNNs) to create a Multi-Head block for parallel processing of multiple transformers. This method identifies five unique classes of the most common material found in waste with peak test accuracy of 94.27% using 35492 total parameters, a reduction of 99.74% when compared to current state of the art methods, allowing for lower power operations and easier deployment.
{"title":"WMC-ViT: Waste Multi-class Classification Using a Modified Vision Transformer","authors":"Aidan G. Kurz, Ethan R. Adams, Arthur C. Depoian, Colleen P. Bailey, P. Guturu","doi":"10.1109/MetroCon56047.2022.9971136","DOIUrl":"https://doi.org/10.1109/MetroCon56047.2022.9971136","url":null,"abstract":"The constant production and lack of efficient waste management procedure has created a need for automated classification of trash as it comes into facilities. This paper proposes a new algorithm for efficiently classifying objects found in solid waste processing by utilizing a combination of vision transformers (ViT) and convolutional neural networks (CNNs) to create a Multi-Head block for parallel processing of multiple transformers. This method identifies five unique classes of the most common material found in waste with peak test accuracy of 94.27% using 35492 total parameters, a reduction of 99.74% when compared to current state of the art methods, allowing for lower power operations and easier deployment.","PeriodicalId":292881,"journal":{"name":"2022 IEEE MetroCon","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130374718","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-03DOI: 10.1109/MetroCon56047.2022.9971134
Arthur C. Depoian, Ethan R. Adams, Aidan G. Kurz, Colleen P. Bailey, P. Guturu, K. Namuduri
The future of image compression is abundant with the opportunities recently developed through the application of advanced neural network algorithms configured to take into account multiple image parameters. This progress has spurred on further progression into more complex architectures to extract the feature of the image for optimal compression. Of the many models available, this work tracks an evolution of end to end image compression by first analyzing BLS2017 and its successors, BMSHJ2018 and MS2020.
{"title":"Recent Advances in Entropy Based Image Compression","authors":"Arthur C. Depoian, Ethan R. Adams, Aidan G. Kurz, Colleen P. Bailey, P. Guturu, K. Namuduri","doi":"10.1109/MetroCon56047.2022.9971134","DOIUrl":"https://doi.org/10.1109/MetroCon56047.2022.9971134","url":null,"abstract":"The future of image compression is abundant with the opportunities recently developed through the application of advanced neural network algorithms configured to take into account multiple image parameters. This progress has spurred on further progression into more complex architectures to extract the feature of the image for optimal compression. Of the many models available, this work tracks an evolution of end to end image compression by first analyzing BLS2017 and its successors, BMSHJ2018 and MS2020.","PeriodicalId":292881,"journal":{"name":"2022 IEEE MetroCon","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125515788","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：