Pub Date : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478748
J. Cordeiro, O. Postolache
The paper presents preliminary results to the length-of-stay (LOS) analysis on neonatal intensive care units, taking as base a 10 year dataset that encompasses data from all neonatal Portuguese units. Unlike conventional studies based on statistical analysis, this investigation uses data science techniques, including machine learning hyperparameters optimization automatization and explainable artificial intelligence (XAI) tools, to understand the relevance of factors and their impact on LOS. In this work was designed and implemented an accurate LOS prediction model which results have been included in the paper. Through XAI techniques application, it was already possible to confirm insights claimed by state-of-the-art studies, namely about the importance of birth weight and gestational age for LOS as well as the importance of hospital-acquired infections. The work presents as novelty the weights (quantification) of these factors as well as the introduction of two new factors, which were not considered until now. The study makes part of ongoing work and will continue to provide better insights for better investment LOS in neonatal care units.
{"title":"Length of Stay Analysis at Neonatal Care Units with Data Science - Preliminary Results","authors":"J. Cordeiro, O. Postolache","doi":"10.1109/MeMeA52024.2021.9478748","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478748","url":null,"abstract":"The paper presents preliminary results to the length-of-stay (LOS) analysis on neonatal intensive care units, taking as base a 10 year dataset that encompasses data from all neonatal Portuguese units. Unlike conventional studies based on statistical analysis, this investigation uses data science techniques, including machine learning hyperparameters optimization automatization and explainable artificial intelligence (XAI) tools, to understand the relevance of factors and their impact on LOS. In this work was designed and implemented an accurate LOS prediction model which results have been included in the paper. Through XAI techniques application, it was already possible to confirm insights claimed by state-of-the-art studies, namely about the importance of birth weight and gestational age for LOS as well as the importance of hospital-acquired infections. The work presents as novelty the weights (quantification) of these factors as well as the introduction of two new factors, which were not considered until now. The study makes part of ongoing work and will continue to provide better insights for better investment LOS in neonatal care units.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124842378","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478679
F. Darwaish, S. Redpath, K. Greenwood, C. Aubertin, A. Ibey, A. Chan, J. Green, R. Langlois
Vibration and noise exposure during emergency neonatal ground and air transport are recognized as hazards for the neonate; however, no standardized test environment exists to reliably quantify such exposure with high repeatability. An on-road test was performed to provide a quantitative measurement of on-road vibrations to be used in the development of the standardized test environment. This paper details the ambulance on-road test instrumentation, analysis, and results. On-road findings indicate that neonates experience vibrations that exceed adult standards; that the power spectral density of the acceleration at the neonate contains peaks (at 2 Hz and 9 Hz) in the frequency range humans are most sensitive (1-20 Hz); and that the damped natural frequency of the patient transport system considered is 9.5 Hz.
{"title":"Characterizing On-Road Vibrations in Ontario’s Neonatal Patient Transport","authors":"F. Darwaish, S. Redpath, K. Greenwood, C. Aubertin, A. Ibey, A. Chan, J. Green, R. Langlois","doi":"10.1109/MeMeA52024.2021.9478679","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478679","url":null,"abstract":"Vibration and noise exposure during emergency neonatal ground and air transport are recognized as hazards for the neonate; however, no standardized test environment exists to reliably quantify such exposure with high repeatability. An on-road test was performed to provide a quantitative measurement of on-road vibrations to be used in the development of the standardized test environment. This paper details the ambulance on-road test instrumentation, analysis, and results. On-road findings indicate that neonates experience vibrations that exceed adult standards; that the power spectral density of the acceleration at the neonate contains peaks (at 2 Hz and 9 Hz) in the frequency range humans are most sensitive (1-20 Hz); and that the damped natural frequency of the patient transport system considered is 9.5 Hz.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128496203","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478686
Giorgia Fiori, Fabio Fuiano, A. Scorza, M. Schmid, J. Galo, S. Conforto, S. Sciuto
In recent years, the scientific community highlighted how the combination of the progressive evolution of the Ultrasound (US) technologies and the difficulties in retrieving a fixed number of Quality Control (QC) parameters to assess US equipment performance represents a burden in the definition of a shared worldwide standard. Consequently, this preliminary study introduces and investigates a novel parameter for Pulsed Wave (PW) Doppler QC, namely the Average Maximum Velocity Sensitivity (AMVS). The mathematical expression of the parameter hereby presented has a differential nature that prevents AMVS from being dependent on the insonification angle, which is a commonly accepted systematic error source for the accuracy in the PW Doppler maximum velocity estimation. Data have been acquired from three US systems of intermediate technology level, each one equipped with a phased array US probe. Tests have been performed with two different US system settings and two constant flow rate regimes set on a Doppler flow phantom. Despite the limitations encountered, from the results AMVS emerged as a promising parameter for the assessment of US sensitivity. Therefore, further studies are going to be conducted with different Doppler phantom models, on a higher number of US diagnostic systems and probes.
{"title":"A novel Sensitivity Index from the Flow Velocity Variation in Quality Control for PW Doppler: a preliminary study","authors":"Giorgia Fiori, Fabio Fuiano, A. Scorza, M. Schmid, J. Galo, S. Conforto, S. Sciuto","doi":"10.1109/MeMeA52024.2021.9478686","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478686","url":null,"abstract":"In recent years, the scientific community highlighted how the combination of the progressive evolution of the Ultrasound (US) technologies and the difficulties in retrieving a fixed number of Quality Control (QC) parameters to assess US equipment performance represents a burden in the definition of a shared worldwide standard. Consequently, this preliminary study introduces and investigates a novel parameter for Pulsed Wave (PW) Doppler QC, namely the Average Maximum Velocity Sensitivity (AMVS). The mathematical expression of the parameter hereby presented has a differential nature that prevents AMVS from being dependent on the insonification angle, which is a commonly accepted systematic error source for the accuracy in the PW Doppler maximum velocity estimation. Data have been acquired from three US systems of intermediate technology level, each one equipped with a phased array US probe. Tests have been performed with two different US system settings and two constant flow rate regimes set on a Doppler flow phantom. Despite the limitations encountered, from the results AMVS emerged as a promising parameter for the assessment of US sensitivity. Therefore, further studies are going to be conducted with different Doppler phantom models, on a higher number of US diagnostic systems and probes.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127220642","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478599
Riccardo Sabbadini, J. D. Tocco, C. Massaroni, E. Schena, M. Carassiti
In recent years, the market dedicated to wearable devices has undergone a strong expansion due to the increasingly development of innovative and personalized technologies for monitoring vital parameters. The COVID-19 pandemic has led the change in daily habits through the introduction of personal protective equipment (e.g., face mask) into everyday routine. The use of an instrumented face mask to monitor heart rate (HR) and respiratory rate (RR) of workers in occupational settings may be useful to better understand the physiological conditions and the presence of environmental and physical stressors.Among many methods used to estimate these two vital signs, photoplethysmography has gained broad acceptance in the scientific community. Several sites have been used to place the photoplethysmographic sensor (e.g., ear lobe and finger-tip) to estimate the above-mentioned physiological parameters. In this paper, we proposed a smart face mask (SFM) instrumented by a photoplethysmographic sensor. This configuration is particularly adequate to be used in those occupational settings which require the use of common input peripherals (e.g., mouse and keyboard) which prompt to fast movement of hands and fingers, limiting the performance of common measurement systems (e.g., smartwatches) due to motion artifacts. The proof of concept of SFM has been conducted by mimicking conditions close to the mentioned occupational settings through the use of a low computational power algorithm. The proposed system showed promising results by returning values in agreement with the reference system mimicking RR in a wide range of values.
{"title":"A smart face mask based on photoplethysmography for cardiorespiratory monitoring in occupational settings","authors":"Riccardo Sabbadini, J. D. Tocco, C. Massaroni, E. Schena, M. Carassiti","doi":"10.1109/MeMeA52024.2021.9478599","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478599","url":null,"abstract":"In recent years, the market dedicated to wearable devices has undergone a strong expansion due to the increasingly development of innovative and personalized technologies for monitoring vital parameters. The COVID-19 pandemic has led the change in daily habits through the introduction of personal protective equipment (e.g., face mask) into everyday routine. The use of an instrumented face mask to monitor heart rate (HR) and respiratory rate (RR) of workers in occupational settings may be useful to better understand the physiological conditions and the presence of environmental and physical stressors.Among many methods used to estimate these two vital signs, photoplethysmography has gained broad acceptance in the scientific community. Several sites have been used to place the photoplethysmographic sensor (e.g., ear lobe and finger-tip) to estimate the above-mentioned physiological parameters. In this paper, we proposed a smart face mask (SFM) instrumented by a photoplethysmographic sensor. This configuration is particularly adequate to be used in those occupational settings which require the use of common input peripherals (e.g., mouse and keyboard) which prompt to fast movement of hands and fingers, limiting the performance of common measurement systems (e.g., smartwatches) due to motion artifacts. The proof of concept of SFM has been conducted by mimicking conditions close to the mentioned occupational settings through the use of a low computational power algorithm. The proposed system showed promising results by returning values in agreement with the reference system mimicking RR in a wide range of values.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122351853","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478709
P. Toledo, H. Klimach, S. Bampi, P. Crovetti
This paper presents a power-efficient Ultra Low Voltage (ULV) Fully-Differential (FD) Digital-Based Operational Transconductance Amplifier for Biomedical signal processing (BioDIGOTA), which digitally processes biological analog signals using CMOS standard-cells. Post-layout simulations, including parasitic effects in 180nm CMOS technology, show that BioDIG- OTA consumes only 144 nW at 300 mV of supply voltage while driving a 20 pF capacitive load, with a power efficiency factor (PEF) lower than 1. The layout occupies 0.03 mm2 total silicon area, excluding I/0 pads. The proposed BioDIGOTA proves that digital-based analog design can be adopted in biomedical signal amplifiers, lowering the total silicon area by 2.3X times compared to the current state of the art landscape while keeping reasonable power and system performance.
{"title":"A 300mV-Supply, 144nW-Power, 0.03mm2-Area, 0.2-PEF Digital-Based Biomedical Signal Amplifier in 180nm CMOS","authors":"P. Toledo, H. Klimach, S. Bampi, P. Crovetti","doi":"10.1109/MeMeA52024.2021.9478709","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478709","url":null,"abstract":"This paper presents a power-efficient Ultra Low Voltage (ULV) Fully-Differential (FD) Digital-Based Operational Transconductance Amplifier for Biomedical signal processing (BioDIGOTA), which digitally processes biological analog signals using CMOS standard-cells. Post-layout simulations, including parasitic effects in 180nm CMOS technology, show that BioDIG- OTA consumes only 144 nW at 300 mV of supply voltage while driving a 20 pF capacitive load, with a power efficiency factor (PEF) lower than 1. The layout occupies 0.03 mm2 total silicon area, excluding I/0 pads. The proposed BioDIGOTA proves that digital-based analog design can be adopted in biomedical signal amplifiers, lowering the total silicon area by 2.3X times compared to the current state of the art landscape while keeping reasonable power and system performance.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130542076","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478721
A. A. Raj, Vaishali Balakarthikeyan, Deepak Vagish, S. Vijayarangan, S. Preejith, M. Sivaprakasam
An oral presentation is a key stressor in a work environment. High levels of stress might abruptly decrease the quality and quantity of information that needs to be delivered to the audience. So it is important to analyze the person’s stress levels and regulate their stress condition for a better result in their delivery of a speech. Heart Rate Variability (HRV) derived from Electrocardiogram (ECG) is a well-established measure for stress analysis of an individual. To analyse stress, ECG data were collected during an oral presentation from 44 subjects. Frequency domain spectral analysis was done to classify the stress regions. The ratio of the Low Frequency to High Frequency (LF/HF) parameter, a widely accepted method of HRV analysis, was calculated every 5 minutes throughout the entire data. The ECG data were collected for 8 hours during the day. The primary statistical analysis was done to understand the patterns and changes that gets reflected due to this activity. 4:30 to 5:30 PM was the time in which the oral presentation was made each ranging from 15 to 25 minutes. Statistical analysis was done for comparison between the oral presentation period and the other time periods. An increase in the LF/HF ratio was observed during the oral presentation. Variations in the median and standard deviation were observed in both data sets. Analysis of variance was done to understand the variation in the subgroup of the data. A comparison box and whisker plot representation is done to show the distribution, its central value and variability between male and female subjects. The distribution was found to be wider for male subjects compared to female subjects. The standard deviation of LF/HF ratio during the oral presentation was significantly higher than during normal working hours. Also, subjects were requested to answer a short questionnaire to understand the cause of mental stress and the results were discussed.
{"title":"Statistical Analysis of Mental Stress During Oral Presentation","authors":"A. A. Raj, Vaishali Balakarthikeyan, Deepak Vagish, S. Vijayarangan, S. Preejith, M. Sivaprakasam","doi":"10.1109/MeMeA52024.2021.9478721","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478721","url":null,"abstract":"An oral presentation is a key stressor in a work environment. High levels of stress might abruptly decrease the quality and quantity of information that needs to be delivered to the audience. So it is important to analyze the person’s stress levels and regulate their stress condition for a better result in their delivery of a speech. Heart Rate Variability (HRV) derived from Electrocardiogram (ECG) is a well-established measure for stress analysis of an individual. To analyse stress, ECG data were collected during an oral presentation from 44 subjects. Frequency domain spectral analysis was done to classify the stress regions. The ratio of the Low Frequency to High Frequency (LF/HF) parameter, a widely accepted method of HRV analysis, was calculated every 5 minutes throughout the entire data. The ECG data were collected for 8 hours during the day. The primary statistical analysis was done to understand the patterns and changes that gets reflected due to this activity. 4:30 to 5:30 PM was the time in which the oral presentation was made each ranging from 15 to 25 minutes. Statistical analysis was done for comparison between the oral presentation period and the other time periods. An increase in the LF/HF ratio was observed during the oral presentation. Variations in the median and standard deviation were observed in both data sets. Analysis of variance was done to understand the variation in the subgroup of the data. A comparison box and whisker plot representation is done to show the distribution, its central value and variability between male and female subjects. The distribution was found to be wider for male subjects compared to female subjects. The standard deviation of LF/HF ratio during the oral presentation was significantly higher than during normal working hours. Also, subjects were requested to answer a short questionnaire to understand the cause of mental stress and the results were discussed.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130649723","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478669
A. Gullino, S. Grassini, G. Gugliandolo, K. Moulaee, N. Donato, M. Parvis, L. Lombardo
Hydrogen is a target gas in the assessment of gut health. Several are the approaches to estimate the concentration of this gas, endogenously present in the gut and, of course, in the blood and the exhaled breath. In this paper, development and characterization of a resistive gas sensor for hydrogen monitoring is reported. The sensing material is based on Nb2O5 Pt thin films, obtained by depositing a niobium oxide layer and a platinum one on a tiny alumina substrate, by means of a lab-scale plasma sputtering reactor. The deposited layers were treated with a thermal process at 600 °C for 30 min. The developed devices were characterized in a hydrogen concentration range of 2000 ppm to 80000 ppm, showing promising results.
{"title":"Hydrogen chemoresistive sensor for the analysis of gut health","authors":"A. Gullino, S. Grassini, G. Gugliandolo, K. Moulaee, N. Donato, M. Parvis, L. Lombardo","doi":"10.1109/MeMeA52024.2021.9478669","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478669","url":null,"abstract":"Hydrogen is a target gas in the assessment of gut health. Several are the approaches to estimate the concentration of this gas, endogenously present in the gut and, of course, in the blood and the exhaled breath. In this paper, development and characterization of a resistive gas sensor for hydrogen monitoring is reported. The sensing material is based on Nb2O5 Pt thin films, obtained by depositing a niobium oxide layer and a platinum one on a tiny alumina substrate, by means of a lab-scale plasma sputtering reactor. The deposited layers were treated with a thermal process at 600 °C for 30 min. The developed devices were characterized in a hydrogen concentration range of 2000 ppm to 80000 ppm, showing promising results.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131293401","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478778
I. O. Joudeh, Ana-Maria Creţu, R. B. Wallace, R. Goubran, M. Allegue-Martínez, F. Knoefel
The recognition of human activities in real-time remains an important challenge to enable supportive residential well-being assessments. In this paper, we measure and assess patterns associated with dynamic human activities, such as the actions of sitting-down and standing-up, by analyzing Wi-Fi channel state information. Two Wi-Fi sensors are used to capture information about a person’s activities within a limited space. The effect of sensor location and activity location within the space are assessed to study the independence of the proposed solution with respect to these factors. From the acquired data, feature vectors of 168 variables of kurtosis, maximum, maximum peak, mean, minimum, skew, standard deviation, and variance values are calculated. Traditional classifiers are evaluated for the prediction of dynamic sitting and standing activities. Results obtained demonstrate a classification accuracy of 98.5% using a medium Gaussian support vector machine. Deep learning using a bidirectional long short-term memory network is also tested for sequence-to-label and sequence-to-sequence classification from time series of statistical measures. These models achieved accuracies of 90.7% and 85.1%, respectively. The proposed feature extraction and applied classification demonstrate the ability of our solution to not only differentiate between static and motion activities, but also distinguish between the similar motions of standing-up and sitting-down. Therefore, this work goes beyond the state-of-the-art that generally focuses on detecting motion, not distinguishing between similar movements by subjects.
{"title":"Location Independence in Machine Learning Classification of Sitting-Down and Standing-Up Actions using Wi-Fi Sensors","authors":"I. O. Joudeh, Ana-Maria Creţu, R. B. Wallace, R. Goubran, M. Allegue-Martínez, F. Knoefel","doi":"10.1109/MeMeA52024.2021.9478778","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478778","url":null,"abstract":"The recognition of human activities in real-time remains an important challenge to enable supportive residential well-being assessments. In this paper, we measure and assess patterns associated with dynamic human activities, such as the actions of sitting-down and standing-up, by analyzing Wi-Fi channel state information. Two Wi-Fi sensors are used to capture information about a person’s activities within a limited space. The effect of sensor location and activity location within the space are assessed to study the independence of the proposed solution with respect to these factors. From the acquired data, feature vectors of 168 variables of kurtosis, maximum, maximum peak, mean, minimum, skew, standard deviation, and variance values are calculated. Traditional classifiers are evaluated for the prediction of dynamic sitting and standing activities. Results obtained demonstrate a classification accuracy of 98.5% using a medium Gaussian support vector machine. Deep learning using a bidirectional long short-term memory network is also tested for sequence-to-label and sequence-to-sequence classification from time series of statistical measures. These models achieved accuracies of 90.7% and 85.1%, respectively. The proposed feature extraction and applied classification demonstrate the ability of our solution to not only differentiate between static and motion activities, but also distinguish between the similar motions of standing-up and sitting-down. Therefore, this work goes beyond the state-of-the-art that generally focuses on detecting motion, not distinguishing between similar movements by subjects.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125399616","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478592
Xiao Sha, PuYang Zheng, Yasha Karimi, M. Stanaćević
Establishing communication between free floating brain implants is critical in applications that require a population of implants to operate in an organized manner or in a real-time feedback loop. We present a feasibility study of a data transmission link between mm-sized free floating brain implants through capacitive coupling. The proposed capacitive link utilizes metal plates integrated on a bottom and a sidewall of the implant. We demonstrate that the minimum required input power for establishing the data link is 31 nW at the operating frequency of 915 MHz. We demonstrate the feasibility of the data link up to a distance of 2 mm between the implants.
{"title":"Capacitive Link for Data Communication Between Free Floating mm-sized Brain Implants","authors":"Xiao Sha, PuYang Zheng, Yasha Karimi, M. Stanaćević","doi":"10.1109/MeMeA52024.2021.9478592","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478592","url":null,"abstract":"Establishing communication between free floating brain implants is critical in applications that require a population of implants to operate in an organized manner or in a real-time feedback loop. We present a feasibility study of a data transmission link between mm-sized free floating brain implants through capacitive coupling. The proposed capacitive link utilizes metal plates integrated on a bottom and a sidewall of the implant. We demonstrate that the minimum required input power for establishing the data link is 31 nW at the operating frequency of 915 MHz. We demonstrate the feasibility of the data link up to a distance of 2 mm between the implants.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116662232","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478698
Agnese Piersanti, Francesco Giurato, L. Burattini, A. Tura, M. Morettini
The use of Continuous Glucose Monitoring (CGM) systems in the management of diabetes is rapidly growing and represents an eligible technology to overcome the limitations of self-monitoring of blood glucose. However, not complete standardization of the CGM data analyses methodologies is limiting the potential of these devices. In the last few years, different software solutions have been proposed to find a common pattern for making CGM data analysis results more interpretable and reproducible. The aim of this study was to compare two of the newest open-source software packages available for CGM data analysis, GLU and iglu. To perform the comparison, CGM data of 9 subjects with type 1 diabetes coming from the open D1NAMO dataset have been analyzed with both software. Metrics available both in GLU and iglu have been compared, namely: Area Under the Curve (AUC), Time Above Range (TAR), Time Below Range (TBR), Time in Range (TIR) and Mean Absolute Deviation (MAD). Mean values for GLU and iglu were: AUC (170 ± 23 vs. 165 ± 27 mg•dl-1); TAR (40 ± 17 vs. 38 ± 21 %); TBR (6 ± 7 % in both); TIR (54 ± 18 vs. 60 ± 21 %), MAD (43 ± 20 vs. 67 ± 28 mg•dl-1). Only MAD was found statistically different between GLU and iglu. In conclusion, this comparison provided an overview of the graphical and computational aspects in CGM analysis provided by GLU and iglu software packages, which could be useful to researchers and clinicians to find a transparent and consistent way of interpreting CGM data.
连续血糖监测(CGM)系统在糖尿病管理中的应用正在迅速增长，它代表了一种克服自我血糖监测局限性的合适技术。然而，CGM数据分析方法的不完全标准化限制了这些设备的潜力。在过去几年中，已经提出了不同的软件解决方案，以找到一种通用模式，使CGM数据分析结果更具可解释性和可重复性。本研究的目的是比较两种最新的开源软件包，GLU和iglu可用于CGM数据分析。为了进行比较，我们使用两种软件对来自D1NAMO开放数据集的9例1型糖尿病患者的CGM数据进行分析。GLU和iglu可用的指标进行了比较，即:曲线下面积(AUC)，范围以上时间(TAR)，范围以下时间(TBR)，范围内时间(TIR)和平均绝对偏差(MAD)。GLU和iglu的平均值分别为AUC(170±23 vs 165±27 mg•dl-1);TAR(40±17% vs. 38±21%);TBR(6±7%);TIR(54±18比60±21%)，MAD(43±20比67±28 mg•dl-1)。GLU和iglu之间只有MAD有统计学差异。总之，这一比较提供了GLU和iglu软件包提供的CGM分析的图形和计算方面的概述，这可能有助于研究人员和临床医生找到一种透明和一致的方法来解释CGM数据。
{"title":"Comparison of Software Packages for the Analysis of Continuous Glucose Monitoring Data","authors":"Agnese Piersanti, Francesco Giurato, L. Burattini, A. Tura, M. Morettini","doi":"10.1109/MeMeA52024.2021.9478698","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478698","url":null,"abstract":"The use of Continuous Glucose Monitoring (CGM) systems in the management of diabetes is rapidly growing and represents an eligible technology to overcome the limitations of self-monitoring of blood glucose. However, not complete standardization of the CGM data analyses methodologies is limiting the potential of these devices. In the last few years, different software solutions have been proposed to find a common pattern for making CGM data analysis results more interpretable and reproducible. The aim of this study was to compare two of the newest open-source software packages available for CGM data analysis, GLU and iglu. To perform the comparison, CGM data of 9 subjects with type 1 diabetes coming from the open D1NAMO dataset have been analyzed with both software. Metrics available both in GLU and iglu have been compared, namely: Area Under the Curve (AUC), Time Above Range (TAR), Time Below Range (TBR), Time in Range (TIR) and Mean Absolute Deviation (MAD). Mean values for GLU and iglu were: AUC (170 ± 23 vs. 165 ± 27 mg•dl-1); TAR (40 ± 17 vs. 38 ± 21 %); TBR (6 ± 7 % in both); TIR (54 ± 18 vs. 60 ± 21 %), MAD (43 ± 20 vs. 67 ± 28 mg•dl-1). Only MAD was found statistically different between GLU and iglu. In conclusion, this comparison provided an overview of the graphical and computational aspects in CGM analysis provided by GLU and iglu software packages, which could be useful to researchers and clinicians to find a transparent and consistent way of interpreting CGM data.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125126489","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：