Pub Date : 2020-10-02DOI: 10.1109/IETC47856.2020.9249225
T. R. Chaves, M. A. Izumida Martins, B. Pacheco
Overhead electricity distribution networks are exposed to several risks, which can cause great damage to the utility's operation. Many of these possible occurrences may be imperceptible to the present monitoring and control systems of the distributors. The monitoring device of the overhead transformer that will be described in this article aims to provide the utility more information about the main asset of the overhead distribution network, the transformer. With the data of electrical quantities on the low voltage side of the transformer and calculation of the hot spot temperature of the transformer, in order to avoid major damage to the distribution network and mitigate any errors not detected by the utility. The study was carried out in a region with a high concentration of load with a predominance of commercial consumers in the city of São Paulo - Vila Olímpia.
{"title":"MV/LV Overhead Transformer Monitoring and Hot Spot Temperature Estimation","authors":"T. R. Chaves, M. A. Izumida Martins, B. Pacheco","doi":"10.1109/IETC47856.2020.9249225","DOIUrl":"https://doi.org/10.1109/IETC47856.2020.9249225","url":null,"abstract":"Overhead electricity distribution networks are exposed to several risks, which can cause great damage to the utility's operation. Many of these possible occurrences may be imperceptible to the present monitoring and control systems of the distributors. The monitoring device of the overhead transformer that will be described in this article aims to provide the utility more information about the main asset of the overhead distribution network, the transformer. With the data of electrical quantities on the low voltage side of the transformer and calculation of the hot spot temperature of the transformer, in order to avoid major damage to the distribution network and mitigate any errors not detected by the utility. The study was carried out in a region with a high concentration of load with a predominance of commercial consumers in the city of São Paulo - Vila Olímpia.","PeriodicalId":186446,"journal":{"name":"2020 Intermountain Engineering, Technology and Computing (IETC)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130089797","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 : 2020-10-02DOI: 10.1109/IETC47856.2020.9249196
Kellie Wilson, M. Schoen
Being able to accurately model a complex machine is important in the design process. Jet engines are expensive and complex thermodynamic systems that require accurate modeling. Modeling allows testing and analysis to be performed before it is implemented. It also allows control schemes to be integrated to determine if it affects the functioning of the system. There are many different types of software available to model thermodynamic systems. T-MATS was released February 5, 2014. It is an open-source software that has the benefit of being fully incorporated with Matlab™ and Simulink™, which allows both modeling and control scheme integration. This paper discusses T-MATS compared to other software and different types of usage.
{"title":"Jet Engine Modeling and Control Using T-MATS","authors":"Kellie Wilson, M. Schoen","doi":"10.1109/IETC47856.2020.9249196","DOIUrl":"https://doi.org/10.1109/IETC47856.2020.9249196","url":null,"abstract":"Being able to accurately model a complex machine is important in the design process. Jet engines are expensive and complex thermodynamic systems that require accurate modeling. Modeling allows testing and analysis to be performed before it is implemented. It also allows control schemes to be integrated to determine if it affects the functioning of the system. There are many different types of software available to model thermodynamic systems. T-MATS was released February 5, 2014. It is an open-source software that has the benefit of being fully incorporated with Matlab™ and Simulink™, which allows both modeling and control scheme integration. This paper discusses T-MATS compared to other software and different types of usage.","PeriodicalId":186446,"journal":{"name":"2020 Intermountain Engineering, Technology and Computing (IETC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131511459","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 : 2020-10-02DOI: 10.1109/ietc47856.2020.9249112
Robert W. Lucas, Patrick Spackman, Ivann Velasco, Peter R. Nyholm
Signal/Image Processing A Speech Emotion Recognition Solution Based on Support Vector Machine for Children with Autism Spectrum Disorder to Help Identify Human Emotions Rezwan Matin (Texas State University, USA), Damian Valles (Texas State University, USA) 1 Research Paper Classification Using Supervised Machine Learning Techniques Shovan Chowdhury (Idaho State University, USA), Marco P Schoen (Idaho State University, USA) 7 Machine Learning Pipeline for Shift-Invariant Detection of Volcanoes on Venus Trey Scofield (Montana State University, USA), Bradley M Whitaker (Montana State University, USA) 13 Software Architecture for Machine Learning in Personal Financial Planning Qianwen Bi (Utah Valley University, USA), Jingpeng Tang (Utah Valley University, USA), Bradley Van Fleet (Utah Valley University, USA), Jason Nelson (Utah Valley University, USA), Ian Beal (Utah Valley University, USA), Candra Ray (Utah Valley University, USA), Andrew Ossola (Alumni & Contributing AuthorFinance and Economics, USA) 19
基于支持向量机的自闭症谱系障碍儿童语音情绪识别解决方案Rezwan Matin (Texas State University, USA)， Damian Valles (Texas State University, USA) 1研究论文:基于监督机器学习技术的分类Shovan Chowdhury (Idaho State University, USA)， Marco P Schoen (Idaho State University, USA)13个人理财规划中的机器学习软件架构毕倩文(美国犹他谷大学)、唐景鹏(美国犹他谷大学)、Bradley Van Fleet(美国犹他谷大学)、Jason Nelson(美国犹他谷大学)、Ian Beal(美国犹他谷大学)、Candra Ray(美国犹他谷大学)，Andrew Ossola(校友及特约作者，美国财经
{"title":"Program2020 Intermountain Engineering, Technology and Computing (IETC)","authors":"Robert W. Lucas, Patrick Spackman, Ivann Velasco, Peter R. Nyholm","doi":"10.1109/ietc47856.2020.9249112","DOIUrl":"https://doi.org/10.1109/ietc47856.2020.9249112","url":null,"abstract":"Signal/Image Processing A Speech Emotion Recognition Solution Based on Support Vector Machine for Children with Autism Spectrum Disorder to Help Identify Human Emotions Rezwan Matin (Texas State University, USA), Damian Valles (Texas State University, USA) 1 Research Paper Classification Using Supervised Machine Learning Techniques Shovan Chowdhury (Idaho State University, USA), Marco P Schoen (Idaho State University, USA) 7 Machine Learning Pipeline for Shift-Invariant Detection of Volcanoes on Venus Trey Scofield (Montana State University, USA), Bradley M Whitaker (Montana State University, USA) 13 Software Architecture for Machine Learning in Personal Financial Planning Qianwen Bi (Utah Valley University, USA), Jingpeng Tang (Utah Valley University, USA), Bradley Van Fleet (Utah Valley University, USA), Jason Nelson (Utah Valley University, USA), Ian Beal (Utah Valley University, USA), Candra Ray (Utah Valley University, USA), Andrew Ossola (Alumni & Contributing AuthorFinance and Economics, USA) 19","PeriodicalId":186446,"journal":{"name":"2020 Intermountain Engineering, Technology and Computing (IETC)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133319489","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 : 2020-10-02DOI: 10.1109/IETC47856.2020.9249066
Kevin Escobar, D. Parker, Jonathan Jacobs, Tara Spafford, Alex Orange, Timothy Hahn, D. Detienne, Jon Davies, Angela Rasmussen
This paper demonstrates geolocation on the University of Utah's National Science Foundation Salt Lake 5G Platform for Open Wireless Data-driven Experimental Research testbed. A 5G Cloud Radio Access Network system based on Orthogonal Frequency-division Multiplexing modulation scheme was implemented to transmit data. Timing synchronization and Time Difference of Arrival calculations were performed between four receivers and one transmitter. Possible locations of the transmitting user equipment relative to the receiving base stations are displayed on a map overlay.
{"title":"Geolocation on the University of Utah POWDER 5G Testbed","authors":"Kevin Escobar, D. Parker, Jonathan Jacobs, Tara Spafford, Alex Orange, Timothy Hahn, D. Detienne, Jon Davies, Angela Rasmussen","doi":"10.1109/IETC47856.2020.9249066","DOIUrl":"https://doi.org/10.1109/IETC47856.2020.9249066","url":null,"abstract":"This paper demonstrates geolocation on the University of Utah's National Science Foundation Salt Lake 5G Platform for Open Wireless Data-driven Experimental Research testbed. A 5G Cloud Radio Access Network system based on Orthogonal Frequency-division Multiplexing modulation scheme was implemented to transmit data. Timing synchronization and Time Difference of Arrival calculations were performed between four receivers and one transmitter. Possible locations of the transmitting user equipment relative to the receiving base stations are displayed on a map overlay.","PeriodicalId":186446,"journal":{"name":"2020 Intermountain Engineering, Technology and Computing (IETC)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133140776","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 : 2020-10-02DOI: 10.1109/IETC47856.2020.9249197
Mohammad Shekaramiz, T. Moon
The sparse signal recovery problem from a set of compressively sensed noisy measurements using sparse Bayesian learning (SBL) modeling and variational Bayesian (VB) inference technique is considered. In the context of SBL, two main approaches are considered here. In the first approach, each component of the sparse signal is modeled via a Gaussian prior with a Gamma/inverse-Gamma hyper prior on its variance/precision. In the second model, each component of the sparse signal is modeled via a Gaussian prior combined with a Bernoulli prior along with a Gamma/inverse-Gamma hyper prior on its variance/precision. In this work, we consider such modeling and derive the update rules for the latent variables and parameters of each modeling in detail. We believe that such rigorous details on these two modeling and inferences provide sufficient intuition for better understanding the inference using variational Bayes, which can also serve as basic models when incorporating any further structures on the sparse/compressible signal.
{"title":"Compressive Sensing via Variational Bayesian Inference","authors":"Mohammad Shekaramiz, T. Moon","doi":"10.1109/IETC47856.2020.9249197","DOIUrl":"https://doi.org/10.1109/IETC47856.2020.9249197","url":null,"abstract":"The sparse signal recovery problem from a set of compressively sensed noisy measurements using sparse Bayesian learning (SBL) modeling and variational Bayesian (VB) inference technique is considered. In the context of SBL, two main approaches are considered here. In the first approach, each component of the sparse signal is modeled via a Gaussian prior with a Gamma/inverse-Gamma hyper prior on its variance/precision. In the second model, each component of the sparse signal is modeled via a Gaussian prior combined with a Bernoulli prior along with a Gamma/inverse-Gamma hyper prior on its variance/precision. In this work, we consider such modeling and derive the update rules for the latent variables and parameters of each modeling in detail. We believe that such rigorous details on these two modeling and inferences provide sufficient intuition for better understanding the inference using variational Bayes, which can also serve as basic models when incorporating any further structures on the sparse/compressible signal.","PeriodicalId":186446,"journal":{"name":"2020 Intermountain Engineering, Technology and Computing (IETC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131304643","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 : 2020-10-02DOI: 10.1109/IETC47856.2020.9249200
H. Nieto-Chaupis
Once constellation of satellites are working in a collaborative manner, the security of their messages would have to be highly secure from all angles of scenarios by which the praxis of eavesdropping constitutes a constant thread for the instability of the different tasks and missions. In this paper we employ the Bennet-Brassard commonly known as the BB84 protocol in conjunction to the technique of Cognitive Radio applied to the Internet of Space Things to build a prospective technology to guarantee the communications among geocentric orbital satellites. The simulations have yielded that for a constellation of 5 satellites, the probability of successful of completion the communication might be of order of 75% ±5%.
{"title":"Hyper Secure Cognitive Radio Communications in an Internet of Space Things Network Based on the BB84 Protocol","authors":"H. Nieto-Chaupis","doi":"10.1109/IETC47856.2020.9249200","DOIUrl":"https://doi.org/10.1109/IETC47856.2020.9249200","url":null,"abstract":"Once constellation of satellites are working in a collaborative manner, the security of their messages would have to be highly secure from all angles of scenarios by which the praxis of eavesdropping constitutes a constant thread for the instability of the different tasks and missions. In this paper we employ the Bennet-Brassard commonly known as the BB84 protocol in conjunction to the technique of Cognitive Radio applied to the Internet of Space Things to build a prospective technology to guarantee the communications among geocentric orbital satellites. The simulations have yielded that for a constellation of 5 satellites, the probability of successful of completion the communication might be of order of 75% ±5%.","PeriodicalId":186446,"journal":{"name":"2020 Intermountain Engineering, Technology and Computing (IETC)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115798453","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 : 2020-10-02DOI: 10.1109/IETC47856.2020.9249124
Waseem Sheikh, Nadeem Sheikh
Around 466 million people worldwide (over 5% of the world's population) have disabling hearing loss, and out of these 34 million are children. Estimates suggest that by 2050, over 900 million people worldwide will have disabling hearing loss. The annual global cost of unaddressed hearing loss amounts to US$ 750 billion. Early detection of hearing loss can reduce its impact on an individual's life in addition to saving a huge cost. This paper, the first in a series of three papers, presents the design and features of an open-source application framework for hearing impairment diagnosis. The framework is built using the Model-View-ViewModel (MVVM) pattern which separates the development of graphical user interface (GUI) from the development of business and back-end logic. Some of the benefits of the MVVM pattern include reusable components, independent development of GUI and business or back-end logic, flexibility to modify GUI without having to change business or back-end logic, ease of unit testing, and reduced maintenance overhead. The proposed framework along with the open-source code makes it possible to easily extend the application functionality thus enabling other researchers and practitioners to develop their own versions of hearing loss diagnosis applications. The proposed software was evaluated by an otolaryngologist and found to be very beneficial in assisting a clinician to reach a hearing impairment diagnosis conclusion more methodically, swiftly and accurately.
{"title":"A Model-View-ViewModel (MVVM) Application Framework for Hearing Impairment Diagnosis - Design and Features","authors":"Waseem Sheikh, Nadeem Sheikh","doi":"10.1109/IETC47856.2020.9249124","DOIUrl":"https://doi.org/10.1109/IETC47856.2020.9249124","url":null,"abstract":"Around 466 million people worldwide (over 5% of the world's population) have disabling hearing loss, and out of these 34 million are children. Estimates suggest that by 2050, over 900 million people worldwide will have disabling hearing loss. The annual global cost of unaddressed hearing loss amounts to US$ 750 billion. Early detection of hearing loss can reduce its impact on an individual's life in addition to saving a huge cost. This paper, the first in a series of three papers, presents the design and features of an open-source application framework for hearing impairment diagnosis. The framework is built using the Model-View-ViewModel (MVVM) pattern which separates the development of graphical user interface (GUI) from the development of business and back-end logic. Some of the benefits of the MVVM pattern include reusable components, independent development of GUI and business or back-end logic, flexibility to modify GUI without having to change business or back-end logic, ease of unit testing, and reduced maintenance overhead. The proposed framework along with the open-source code makes it possible to easily extend the application functionality thus enabling other researchers and practitioners to develop their own versions of hearing loss diagnosis applications. The proposed software was evaluated by an otolaryngologist and found to be very beneficial in assisting a clinician to reach a hearing impairment diagnosis conclusion more methodically, swiftly and accurately.","PeriodicalId":186446,"journal":{"name":"2020 Intermountain Engineering, Technology and Computing (IETC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123911868","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 : 2020-10-02DOI: 10.1109/IETC47856.2020.9249157
Porter Glines, Brandon Biggs, P. Bodily
There is growing interest in the ability to generate natural and meaningful sequences (e.g., in domains such as language or music). Many existing sequence generation models, including Markov and neural algorithms, capture local coherence, but have no mechanism for applying the structural constraints that are so often essential for the development of meaning. We describe a novel solution to this problem which combines hidden Markov models with constraints, allowing sequences which obey user-defined constraints to be generated according to data-driven probability distributions. Compared to other constrained probabilistic solutions, our Constrained Hidden Markov Process (CHiMP) has significantly greater expressivity, allowing the user to generate constrained sequences that are longer and which have more numerous structural constraints.
{"title":"Probabilistic Generation of Sequences Under Constraints","authors":"Porter Glines, Brandon Biggs, P. Bodily","doi":"10.1109/IETC47856.2020.9249157","DOIUrl":"https://doi.org/10.1109/IETC47856.2020.9249157","url":null,"abstract":"There is growing interest in the ability to generate natural and meaningful sequences (e.g., in domains such as language or music). Many existing sequence generation models, including Markov and neural algorithms, capture local coherence, but have no mechanism for applying the structural constraints that are so often essential for the development of meaning. We describe a novel solution to this problem which combines hidden Markov models with constraints, allowing sequences which obey user-defined constraints to be generated according to data-driven probability distributions. Compared to other constrained probabilistic solutions, our Constrained Hidden Markov Process (CHiMP) has significantly greater expressivity, allowing the user to generate constrained sequences that are longer and which have more numerous structural constraints.","PeriodicalId":186446,"journal":{"name":"2020 Intermountain Engineering, Technology and Computing (IETC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123724856","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 : 2020-10-02DOI: 10.1109/IETC47856.2020.9249172
K. A. Stone, Shane Dittrich, M. Luna, Omid Heidari, A. Perez-Gracia, M. Schoen
The emerging technology of Augmented Reality can be applied to create novel developer tools in industrial robotics. This paper details the development of an app to interface with ABB robot controller using Microsoft HoloLens. RAPID code from the controller is parsed and converted to mirrored objects which can be displayed in the real world, on top and around the actual robot. This enables the user to interact with the robot in an augmented reality environment. The goal is to improve the human-robot communication by interpreting robot language and converting it to an interactive and intuitive interface.
{"title":"`1Augmented Reality Interface For Industrial Robot Controllers","authors":"K. A. Stone, Shane Dittrich, M. Luna, Omid Heidari, A. Perez-Gracia, M. Schoen","doi":"10.1109/IETC47856.2020.9249172","DOIUrl":"https://doi.org/10.1109/IETC47856.2020.9249172","url":null,"abstract":"The emerging technology of Augmented Reality can be applied to create novel developer tools in industrial robotics. This paper details the development of an app to interface with ABB robot controller using Microsoft HoloLens. RAPID code from the controller is parsed and converted to mirrored objects which can be displayed in the real world, on top and around the actual robot. This enables the user to interact with the robot in an augmented reality environment. The goal is to improve the human-robot communication by interpreting robot language and converting it to an interactive and intuitive interface.","PeriodicalId":186446,"journal":{"name":"2020 Intermountain Engineering, Technology and Computing (IETC)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127134410","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 : 2020-10-02DOI: 10.1109/IETC47856.2020.9249126
A. Zahin, L. Tan, R. Hu
In this paper, we propose a novel framework for the smart healthcare system, where we employ the compressed sensing (CS) and the combination of the state-of-the-art machine learning based denoiser as well as the alternating direction of method of multipliers (ADMM) structure. This integration significantly simplifies the software implementation for the low-complexity encoder, thanks to the modular structure of ADMM. Furthermore, we focus on detecting fall down actions from image streams. Thus, the primary purpose of this study is to reconstruct the image as visibly clear as possible and hence it helps the detection step at the trained classifier. For this efficient smart health monitoring framework, we employ the trained binary convolutional neural network (CNN) classifier for the fall-action classifier, because this scheme is a part of surveillance scenario. In this scenario, we deal with the fall-images, thus, we compress, transmit and reconstruct the fall-images. Experimental results demonstrate the impacts of network parameters and the significant performance gain of the proposal compared to traditional methods.
{"title":"A Machine Learning Based Framework for the Smart Healthcare System","authors":"A. Zahin, L. Tan, R. Hu","doi":"10.1109/IETC47856.2020.9249126","DOIUrl":"https://doi.org/10.1109/IETC47856.2020.9249126","url":null,"abstract":"In this paper, we propose a novel framework for the smart healthcare system, where we employ the compressed sensing (CS) and the combination of the state-of-the-art machine learning based denoiser as well as the alternating direction of method of multipliers (ADMM) structure. This integration significantly simplifies the software implementation for the low-complexity encoder, thanks to the modular structure of ADMM. Furthermore, we focus on detecting fall down actions from image streams. Thus, the primary purpose of this study is to reconstruct the image as visibly clear as possible and hence it helps the detection step at the trained classifier. For this efficient smart health monitoring framework, we employ the trained binary convolutional neural network (CNN) classifier for the fall-action classifier, because this scheme is a part of surveillance scenario. In this scenario, we deal with the fall-images, thus, we compress, transmit and reconstruct the fall-images. Experimental results demonstrate the impacts of network parameters and the significant performance gain of the proposal compared to traditional methods.","PeriodicalId":186446,"journal":{"name":"2020 Intermountain Engineering, Technology and Computing (IETC)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129118322","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：