Pub Date : 2019-12-01DOI: 10.1109/SPMB47826.2019.9037851
S. Rahman, M. Miranda, I. Obeid, J. Picone
The Neural Engineering Data Consortium at Temple University has been providing key data resources to support the development of deep learning technology for electroencephalography (EEG) applications [ 1 – 4 ] since 2012. We currently have over 1,700 subscribers to our resources and have been providing data, software and documentation from our web site [5] since 2012. In this poster, we introduce additions to our resources that have been developed within the past year to facilitate software development and big data machine learning research.
{"title":"Software and Data Resources to Advance Machine Learning Research in Electroencephalography","authors":"S. Rahman, M. Miranda, I. Obeid, J. Picone","doi":"10.1109/SPMB47826.2019.9037851","DOIUrl":"https://doi.org/10.1109/SPMB47826.2019.9037851","url":null,"abstract":"The Neural Engineering Data Consortium at Temple University has been providing key data resources to support the development of deep learning technology for electroencephalography (EEG) applications [ 1 – 4 ] since 2012. We currently have over 1,700 subscribers to our resources and have been providing data, software and documentation from our web site [5] since 2012. In this poster, we introduce additions to our resources that have been developed within the past year to facilitate software development and big data machine learning research.","PeriodicalId":143197,"journal":{"name":"2019 IEEE Signal Processing in Medicine and Biology Symposium (SPMB)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116248500","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 : 2019-12-01DOI: 10.1109/SPMB47826.2019.9037863
M. Usman, A. Gupta, W. Xue
Dry electrodes are gaining popularity in the area of electronic health for biosignal measurements due to their reusability and comfort as compared to traditional gel-based wet Ag/AgCl electrodes. This paper presents a performance comparison of dry and wet electrodes for medical devices, in particular, for bioelectrical impedance analysis (BIA). BIA is an emerging technology widely used for body composition analysis by computing the impedance of the human body. The designed system for BIA consists of a wearable silicone ring with four copper electrodes. The experiment is conducted on 40 healthy human subjects using both the ring and the Ag/AgCl electrodes. The linear regression demonstrates a high correlation between both electrodes (r = 0.96 for resistance and r = 0.93 for reactance). The measurement of root mean square noise is determined for both electrodes. The dry electrodes demonstrate a higher noise level (1.96 mV) as compared to the wet electrodes (0.282 mV), mainly due to the absence of conductive gel. Moreover, fast Fourier transform is performed to determine and filter out unwanted signals and to reduce the noise level in the dry electrodes. The results demonstrate that the designed ring electrodes have a comparable performance with commercial Ag/AgCl electrodes and can be used in mobile wearable medical devices.
{"title":"Analyzing Dry Electrodes for Wearable Bioelectrical Impedance Analyzers","authors":"M. Usman, A. Gupta, W. Xue","doi":"10.1109/SPMB47826.2019.9037863","DOIUrl":"https://doi.org/10.1109/SPMB47826.2019.9037863","url":null,"abstract":"Dry electrodes are gaining popularity in the area of electronic health for biosignal measurements due to their reusability and comfort as compared to traditional gel-based wet Ag/AgCl electrodes. This paper presents a performance comparison of dry and wet electrodes for medical devices, in particular, for bioelectrical impedance analysis (BIA). BIA is an emerging technology widely used for body composition analysis by computing the impedance of the human body. The designed system for BIA consists of a wearable silicone ring with four copper electrodes. The experiment is conducted on 40 healthy human subjects using both the ring and the Ag/AgCl electrodes. The linear regression demonstrates a high correlation between both electrodes (r = 0.96 for resistance and r = 0.93 for reactance). The measurement of root mean square noise is determined for both electrodes. The dry electrodes demonstrate a higher noise level (1.96 mV) as compared to the wet electrodes (0.282 mV), mainly due to the absence of conductive gel. Moreover, fast Fourier transform is performed to determine and filter out unwanted signals and to reduce the noise level in the dry electrodes. The results demonstrate that the designed ring electrodes have a comparable performance with commercial Ag/AgCl electrodes and can be used in mobile wearable medical devices.","PeriodicalId":143197,"journal":{"name":"2019 IEEE Signal Processing in Medicine and Biology Symposium (SPMB)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125006997","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 : 2019-12-01DOI: 10.1109/SPMB47826.2019.9037854
Julien Boussard, Mykel J. Kochenderfer, J. Zeitzer
Our goal is to predict subjective sleep quality (SSQ) from objective sleep data and identify the causes and markers of the variances within “normal” sleep. Such information would increase our understanding of the causes of variation in SSQ and potentially improve our ability to improve SSQ. Previous approaches rely on human annotation of the electroencephalographic (EEG) brain signals, to deal with the noisy, high dimensional nature of the EEGs. We aim to use recurrent neural networks to directly analyze and extract useful information from EEG brain signals. We analyze population-based overnight sleep polysomnography data obtained from 4885 community-dwelling adults. We use convolutional and recurrent neural networks to process the EEGs and combine them with information related to health and lifestyle to predict subjective depth and restfulness of sleep. We compare the coefficient of determination to the ones obtained with regression methods and technician annotations of the EEGs in previous studies. Predicting SSQ from our data set of community-dwelling adults using RNNs to analyze the whole EEG signals appear to be less accurate than previous approaches predictions. It might be necessary to acquire more data, possibly with new variables that might be better correlated with SSQ. RNNs are, however, able to extract variables correlated with SSQ from EEG signals. Our results provide insights into how RNNs can be used to extract information from brain signals and how methods such as hierarchical clustering analysis can help neural networks predict subjective variables from polysomnography data.
{"title":"Predicting Subjective Sleep Quality Using Recurrent Neural Networks","authors":"Julien Boussard, Mykel J. Kochenderfer, J. Zeitzer","doi":"10.1109/SPMB47826.2019.9037854","DOIUrl":"https://doi.org/10.1109/SPMB47826.2019.9037854","url":null,"abstract":"Our goal is to predict subjective sleep quality (SSQ) from objective sleep data and identify the causes and markers of the variances within “normal” sleep. Such information would increase our understanding of the causes of variation in SSQ and potentially improve our ability to improve SSQ. Previous approaches rely on human annotation of the electroencephalographic (EEG) brain signals, to deal with the noisy, high dimensional nature of the EEGs. We aim to use recurrent neural networks to directly analyze and extract useful information from EEG brain signals. We analyze population-based overnight sleep polysomnography data obtained from 4885 community-dwelling adults. We use convolutional and recurrent neural networks to process the EEGs and combine them with information related to health and lifestyle to predict subjective depth and restfulness of sleep. We compare the coefficient of determination to the ones obtained with regression methods and technician annotations of the EEGs in previous studies. Predicting SSQ from our data set of community-dwelling adults using RNNs to analyze the whole EEG signals appear to be less accurate than previous approaches predictions. It might be necessary to acquire more data, possibly with new variables that might be better correlated with SSQ. RNNs are, however, able to extract variables correlated with SSQ from EEG signals. Our results provide insights into how RNNs can be used to extract information from brain signals and how methods such as hierarchical clustering analysis can help neural networks predict subjective variables from polysomnography data.","PeriodicalId":143197,"journal":{"name":"2019 IEEE Signal Processing in Medicine and Biology Symposium (SPMB)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114631822","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 : 2019-12-01DOI: 10.1109/spmb47826.2019.9037850
{"title":"[Copyright notice]","authors":"","doi":"10.1109/spmb47826.2019.9037850","DOIUrl":"https://doi.org/10.1109/spmb47826.2019.9037850","url":null,"abstract":"","PeriodicalId":143197,"journal":{"name":"2019 IEEE Signal Processing in Medicine and Biology Symposium (SPMB)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132892369","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 : 2019-12-01DOI: 10.1109/SPMB47826.2019.9037844
T. Hassan, L. McKinney, R. Sandler, A. Kassab, C. Price, F. Moslehy, H. Mansy
Sound transmission in the human body can be affected by the tissue composition along the sound path and surrounding structures. Therefore, acoustic transmission may correlate with pathologies involving structural changes. Previous studies utilized sound transmission to detect a variety of pulmonary, gastrointestinal, vascular, cardiac conditions, and developmental dysplasia of the hip (DDH) [1] [2] [3] [4] [5] [6] . The objective of this study is to design and test a reliable system capable of providing adequate acoustic stimulus, and simultaneously measure transmitted signals at multiple skin surface locations. The study objectives include determining: (1) the static load needed to reach a target SNR (>20 dB) at the measurement points and a target coherence (>0.8) between excitation and measurement points; (2) the exciter sensitivity to static load changes; and (3) the exciter input maximum power and corresponding acceleration. These results will help guide the choice of optimal exciter that: (1) can withstand sufficient static load (~500g), which would provide coupling to the bone to reach a target SNR and coherence; (2) has low sensitivity to load (low variability for a load change ~100 gm); (3) can provide sufficient acoustic excitation energy to maintain the target SNR and coherence; (4) be available at a reasonable cost (~<$500); (5) ensures patient comfort (with no subject discomfort reported for a contact area of ~ 2 cm 2 ).
声在人体内的传播受声路沿线的组织组成和周围结构的影响。因此，声传输可能与涉及结构改变的病理有关。先前的研究利用声音传播来检测各种肺部、胃肠道、血管、心脏疾病和髋关节发育不良(DDH)[1][2][3][4][5][6]。本研究的目的是设计和测试一个可靠的系统，能够提供足够的声刺激，并同时测量多个皮肤表面位置的传输信号。研究目标包括确定:(1)在测点处达到目标信噪比(>20 dB)和激励点与测点之间达到目标相干度(>0.8)所需的静态负载;(2)励磁器对静负载变化的灵敏度;(3)励磁器输入最大功率及相应加速度。这些结果将有助于指导最佳激励器的选择:(1)能够承受足够的静载荷(~500g)，这将提供与骨骼的耦合以达到目标信噪比和相干性;(2)对负荷的敏感性低(负荷变化的可变性低~100克);(3)能够提供足够的声激发能量，维持目标信噪比和相干性;(4)以合理的成本(~< 500美元)提供;(5)确保患者舒适(接触面积约2 cm 2无受试者不适报告)。
{"title":"A System for Measuring Sound Transmission Through Joints","authors":"T. Hassan, L. McKinney, R. Sandler, A. Kassab, C. Price, F. Moslehy, H. Mansy","doi":"10.1109/SPMB47826.2019.9037844","DOIUrl":"https://doi.org/10.1109/SPMB47826.2019.9037844","url":null,"abstract":"Sound transmission in the human body can be affected by the tissue composition along the sound path and surrounding structures. Therefore, acoustic transmission may correlate with pathologies involving structural changes. Previous studies utilized sound transmission to detect a variety of pulmonary, gastrointestinal, vascular, cardiac conditions, and developmental dysplasia of the hip (DDH) [1] [2] [3] [4] [5] [6] . The objective of this study is to design and test a reliable system capable of providing adequate acoustic stimulus, and simultaneously measure transmitted signals at multiple skin surface locations. The study objectives include determining: (1) the static load needed to reach a target SNR (>20 dB) at the measurement points and a target coherence (>0.8) between excitation and measurement points; (2) the exciter sensitivity to static load changes; and (3) the exciter input maximum power and corresponding acceleration. These results will help guide the choice of optimal exciter that: (1) can withstand sufficient static load (~500g), which would provide coupling to the bone to reach a target SNR and coherence; (2) has low sensitivity to load (low variability for a load change ~100 gm); (3) can provide sufficient acoustic excitation energy to maintain the target SNR and coherence; (4) be available at a reasonable cost (~<$500); (5) ensures patient comfort (with no subject discomfort reported for a contact area of ~ 2 cm 2 ).","PeriodicalId":143197,"journal":{"name":"2019 IEEE Signal Processing in Medicine and Biology Symposium (SPMB)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132948112","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 : 2019-12-01DOI: 10.1109/SPMB47826.2019.9037858
A. Alivar, C. Carlson, A. Suliman, S. Warren, P. Prakash, D. Thompson, B. Natarajan
Sleep problems are a common concern for parents and caregivers in children with autism spectrum disorder (ASD). One of the main challenges in sleep studies with these individuals is the difficulty in monitoring sleep quality without sensors and wires attached to the subject’s body. Additionally, there is limited knowledge of how their sleep quality is related to their daytime behaviors. In this study, we evaluate an unobtrusive and inexpensive smart bed system for in-home, long-term sleep quality monitoring using ballistocardiogram (BCG) signals. By extracting different sleep quality indicators using BCG signals, we build bi-directional predictive models for daytime behaviors and nighttime sleep quality using two classifiers as support vector machine (SVM) and artificial neural network (ANN). For all daytime behaviors of interest, we achieve more than 78% average accuracy using previous nights sleep quality. Additionally, night time sleep qualities are predicted with more than 78% average accuracy using previous day and night features.
{"title":"A Pilot Study on Predicting Daytime Behavior & Sleep Quality in Children With ASD","authors":"A. Alivar, C. Carlson, A. Suliman, S. Warren, P. Prakash, D. Thompson, B. Natarajan","doi":"10.1109/SPMB47826.2019.9037858","DOIUrl":"https://doi.org/10.1109/SPMB47826.2019.9037858","url":null,"abstract":"Sleep problems are a common concern for parents and caregivers in children with autism spectrum disorder (ASD). One of the main challenges in sleep studies with these individuals is the difficulty in monitoring sleep quality without sensors and wires attached to the subject’s body. Additionally, there is limited knowledge of how their sleep quality is related to their daytime behaviors. In this study, we evaluate an unobtrusive and inexpensive smart bed system for in-home, long-term sleep quality monitoring using ballistocardiogram (BCG) signals. By extracting different sleep quality indicators using BCG signals, we build bi-directional predictive models for daytime behaviors and nighttime sleep quality using two classifiers as support vector machine (SVM) and artificial neural network (ANN). For all daytime behaviors of interest, we achieve more than 78% average accuracy using previous nights sleep quality. Additionally, night time sleep qualities are predicted with more than 78% average accuracy using previous day and night features.","PeriodicalId":143197,"journal":{"name":"2019 IEEE Signal Processing in Medicine and Biology Symposium (SPMB)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131090065","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 : 2019-12-01DOI: 10.1109/SPMB47826.2019.9037842
P. Gamage, M. K. Azad, R. Sandler, H. Mansy
Seismocardiography (SCG) is the measurement of the chest surface accelerations that are primarily produced by a combination of mechanical activities of the heart, such as valve closures and openings, blood momentum changes and myocardial movements [ 1 – 3 ]. The complex nature of these processes has made it challenging to relate the morphology of the SCG signal to its genesis. Certain studies have used medical imaging to identify several feature points of the SCG signal by correlating their occurrence time with the corresponding cardiac events seen in imaging [4 , 5] . However, these findings remain inconclusive [6] . The localized movements (i.e. valve openings and closures, ventricular contractions, blood flow accelerations etc.) may superimpose causing complex movements where original movements may amplify or nullify as they reach the chest surface and affect SCG morphology. Hence, SCG signal can also be described as the propagated vibrations generated by individual sources (i.e., valve closures and openings, blood flow accelerations). These vibrations displace their more immediate boundaries (e.g., pericardium, Aorta wall) and surrounding tissues (e.g. lung tissue, ribs, chest wall muscle and skin) before they are detected at the chest surface. Hence, modeling the propagation of overall cardiac wall motion to the chest surface may help enhance our understanding of SCG genesis.
{"title":"Modeling Seismocardiographic Signal using Finite Element Modeling and Medical Image Processing","authors":"P. Gamage, M. K. Azad, R. Sandler, H. Mansy","doi":"10.1109/SPMB47826.2019.9037842","DOIUrl":"https://doi.org/10.1109/SPMB47826.2019.9037842","url":null,"abstract":"Seismocardiography (SCG) is the measurement of the chest surface accelerations that are primarily produced by a combination of mechanical activities of the heart, such as valve closures and openings, blood momentum changes and myocardial movements [ 1 – 3 ]. The complex nature of these processes has made it challenging to relate the morphology of the SCG signal to its genesis. Certain studies have used medical imaging to identify several feature points of the SCG signal by correlating their occurrence time with the corresponding cardiac events seen in imaging [4 , 5] . However, these findings remain inconclusive [6] . The localized movements (i.e. valve openings and closures, ventricular contractions, blood flow accelerations etc.) may superimpose causing complex movements where original movements may amplify or nullify as they reach the chest surface and affect SCG morphology. Hence, SCG signal can also be described as the propagated vibrations generated by individual sources (i.e., valve closures and openings, blood flow accelerations). These vibrations displace their more immediate boundaries (e.g., pericardium, Aorta wall) and surrounding tissues (e.g. lung tissue, ribs, chest wall muscle and skin) before they are detected at the chest surface. Hence, modeling the propagation of overall cardiac wall motion to the chest surface may help enhance our understanding of SCG genesis.","PeriodicalId":143197,"journal":{"name":"2019 IEEE Signal Processing in Medicine and Biology Symposium (SPMB)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132374565","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 : 2019-12-01DOI: 10.1109/SPMB47826.2019.9037836
N. Capp, V. Fauveau, Y. Au, P. Glasser, T. Muqeem, G. Hassen, A. Cardenas
Patients with respiratory diseases are often rushed to the emergency room with acute decompensation. If not managed properly, chronic respiratory disease prolongs the episode of care or leads to hospital readmissions that are costly and burdensome to the patient. The current standard of care, in an inpatient setting, relies on labor-intensive, eSpisodic clinical assessments to detect signs of worsening disease progression. In the outpatient setting, disease monitoring relies solely on self-reporting by patients. Occasionally, patients have the aid of an instrument, such as a peak flow meter, but these aids are prone to user error and cannot always accurately report critical data 0. Additionally, patients with COPD (Chronic Obstructive Pulmonary Disease) and asthma often receive inadequate treatment due to poor communication between the patient and clinician [2] – [3] , poor disease status assessment by the clinician, inconsistent use of medication [4] – [5] , or the unreliability of peak flow measurements 0. A system capable of continuously and remotely monitoring a patient’s respiratory health could address this disconnect in patient care. Utilizing an intelligent patient monitoring system could improve patient care triage, reduce the length of hospital stay, lower the healthcare costs incurred by expensive pulmonary complications, and standardize the objective assessment of a patient’s respiratory health.
{"title":"Strados Labs: An Efficient Process to Acquire and Characterize Clinically Validated Respiratory System Information Using a Non-Invasive Bio-Sensor","authors":"N. Capp, V. Fauveau, Y. Au, P. Glasser, T. Muqeem, G. Hassen, A. Cardenas","doi":"10.1109/SPMB47826.2019.9037836","DOIUrl":"https://doi.org/10.1109/SPMB47826.2019.9037836","url":null,"abstract":"Patients with respiratory diseases are often rushed to the emergency room with acute decompensation. If not managed properly, chronic respiratory disease prolongs the episode of care or leads to hospital readmissions that are costly and burdensome to the patient. The current standard of care, in an inpatient setting, relies on labor-intensive, eSpisodic clinical assessments to detect signs of worsening disease progression. In the outpatient setting, disease monitoring relies solely on self-reporting by patients. Occasionally, patients have the aid of an instrument, such as a peak flow meter, but these aids are prone to user error and cannot always accurately report critical data 0. Additionally, patients with COPD (Chronic Obstructive Pulmonary Disease) and asthma often receive inadequate treatment due to poor communication between the patient and clinician [2] – [3] , poor disease status assessment by the clinician, inconsistent use of medication [4] – [5] , or the unreliability of peak flow measurements 0. A system capable of continuously and remotely monitoring a patient’s respiratory health could address this disconnect in patient care. Utilizing an intelligent patient monitoring system could improve patient care triage, reduce the length of hospital stay, lower the healthcare costs incurred by expensive pulmonary complications, and standardize the objective assessment of a patient’s respiratory health.","PeriodicalId":143197,"journal":{"name":"2019 IEEE Signal Processing in Medicine and Biology Symposium (SPMB)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132210527","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 : 2019-12-01DOI: 10.1109/SPMB47826.2019.9037855
Michael W. Stanford, V. Stanford
We discuss selected emerging technologies in physiological signal processing, low-cost pervasive sensors, diagnostic pattern recognition, and some research issues they entail. Serious practical issues remain for signal acquisition from users in their own environments using these commodity sensors. To illustrate the technical issues, we describe a novel robust processing algorithm for mobile ECG sensors (i.e. non-contact capacitive sensors with low signal-to-noise ratios). We describe the detection techniques designed to function effectively with such noisy ECG data.
{"title":"Commodity Sensors, Physiological Signals, Research Opportunities, and Practical Issues","authors":"Michael W. Stanford, V. Stanford","doi":"10.1109/SPMB47826.2019.9037855","DOIUrl":"https://doi.org/10.1109/SPMB47826.2019.9037855","url":null,"abstract":"We discuss selected emerging technologies in physiological signal processing, low-cost pervasive sensors, diagnostic pattern recognition, and some research issues they entail. Serious practical issues remain for signal acquisition from users in their own environments using these commodity sensors. To illustrate the technical issues, we describe a novel robust processing algorithm for mobile ECG sensors (i.e. non-contact capacitive sensors with low signal-to-noise ratios). We describe the detection techniques designed to function effectively with such noisy ECG data.","PeriodicalId":143197,"journal":{"name":"2019 IEEE Signal Processing in Medicine and Biology Symposium (SPMB)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133704394","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 : 2019-12-01DOI: 10.1109/SPMB47826.2019.9037835
Z. Zhu, J. Li, C. Dai, C. Martinez-Luna, B. McDonald, T. Farrell, X. Huang, E. Clancy
The surface electromyogram (EMG) is used as a control source for limb prostheses. When developing hand-wrist prostheses control schemes with able-bodied subjects, it is common to relate forearm EMG to hand-wrist forces/moments using supervised models. However, subjects with unilateral limb absence cannot produce such forces. Thus, we contrasted use of “output” alternatives from the force generated by the sound side in “mirror” movements [ 1 – 2 ], or directly using a target followed with their limb-absent side [ 3 – 4 ].
{"title":"Comparison of EMG-Force Calibration Protocols for Myoelectric Control of Prostheses","authors":"Z. Zhu, J. Li, C. Dai, C. Martinez-Luna, B. McDonald, T. Farrell, X. Huang, E. Clancy","doi":"10.1109/SPMB47826.2019.9037835","DOIUrl":"https://doi.org/10.1109/SPMB47826.2019.9037835","url":null,"abstract":"The surface electromyogram (EMG) is used as a control source for limb prostheses. When developing hand-wrist prostheses control schemes with able-bodied subjects, it is common to relate forearm EMG to hand-wrist forces/moments using supervised models. However, subjects with unilateral limb absence cannot produce such forces. Thus, we contrasted use of “output” alternatives from the force generated by the sound side in “mirror” movements [ 1 – 2 ], or directly using a target followed with their limb-absent side [ 3 – 4 ].","PeriodicalId":143197,"journal":{"name":"2019 IEEE Signal Processing in Medicine and Biology Symposium (SPMB)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128815429","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：