Pub Date : 2022-06-22DOI: 10.1109/MeMeA54994.2022.9856558
Lili Zhu, P. Spachos, S. Gregori
Wearable technology is growing in popularity, and wearable devices, such as smartwatches, are used in many applications, from fitness tracking and activity recognition to health monitoring. As the affordability and popularity of such devices increase, so does the amount of personal and unique data that they provide. At the same time, advantages in microprocessor and memory technology enable multiple physiological signal sensors integrated into wearable devices to collect personal and unique data. After the data is extracted, machine learning classification algorithms can help investigate the insights of the data. In this work, we examine the performance of a real-time stress detection system based on physiological signals collected from wearable devices. Specifically, three physiological signals, electrodermal activity (EDA), electrocardiogram (ECG), and photoplethysmo-graph (PPG) that can be collected through smartwatches, are examined for stress classification. Six machine learning methods are used for the classification in a post-acquisition phase, at a computer, including Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest, Naive Bayes, Logistic Regression, and Stacking Ensemble Learning (SEL). Data from two publicly available datasets are used for training and testing. We examine the accuracy of each modality and the combination of all modalities. According to evaluation results, EDA has the best accuracy when SEL is used for classification. Also, the accuracy of EDA outperforms the other signals and combinations, in comparison with any of the other machine learning approaches, for both datasets. EDA collected from the wearable device has a great potential to be used for a real-time stress detection system.
{"title":"Multimodal Physiological Signals and Machine Learning for Stress Detection by Wearable Devices","authors":"Lili Zhu, P. Spachos, S. Gregori","doi":"10.1109/MeMeA54994.2022.9856558","DOIUrl":"https://doi.org/10.1109/MeMeA54994.2022.9856558","url":null,"abstract":"Wearable technology is growing in popularity, and wearable devices, such as smartwatches, are used in many applications, from fitness tracking and activity recognition to health monitoring. As the affordability and popularity of such devices increase, so does the amount of personal and unique data that they provide. At the same time, advantages in microprocessor and memory technology enable multiple physiological signal sensors integrated into wearable devices to collect personal and unique data. After the data is extracted, machine learning classification algorithms can help investigate the insights of the data. In this work, we examine the performance of a real-time stress detection system based on physiological signals collected from wearable devices. Specifically, three physiological signals, electrodermal activity (EDA), electrocardiogram (ECG), and photoplethysmo-graph (PPG) that can be collected through smartwatches, are examined for stress classification. Six machine learning methods are used for the classification in a post-acquisition phase, at a computer, including Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest, Naive Bayes, Logistic Regression, and Stacking Ensemble Learning (SEL). Data from two publicly available datasets are used for training and testing. We examine the accuracy of each modality and the combination of all modalities. According to evaluation results, EDA has the best accuracy when SEL is used for classification. Also, the accuracy of EDA outperforms the other signals and combinations, in comparison with any of the other machine learning approaches, for both datasets. EDA collected from the wearable device has a great potential to be used for a real-time stress detection system.","PeriodicalId":106228,"journal":{"name":"2022 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"27 Pt 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129761525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-22DOI: 10.1109/MeMeA54994.2022.9856451
E. D. Vita, Francesca De Tommasi, C. Altomare, Sofia Ialongo, C. Massaroni, D. Presti, E. Faiella, F. Andresciani, G. Pacella, Andrea Palermo, M. Carassiti, A. Iadicicco, R. Grasso, E. Schena, S. Campopiano
Traditional methods to treat thyroid nodules like thyroidectomy and radioiodine therapy can involve a multitude of risks, such as damages to parathyroid glands and aftercare hypothyroidism. Minimally invasive surgery (MIS) can represent an alternative solution, avoiding general anesthesia or radioactive substances. In the framework of MIS, thermal ablation therapies (TATs) are gaining momentum to treat both benign and malign tumors by inducing a significant temperature variation inside the treated tissue. Among TATs, microwave ablation (MWA) is a newly emerging technique which has proved to be an effective and safe method in treating tumors in different organs like liver and kidney, more recently including thyroid nodules. However, an experimental analysis of the temperature reached within the thyroid tissue during the treatment has not been performed yet. Temperature monitoring during TATs can be beneficial to ensure the complete tumor eradication, especially in case of new challenging organs like thyroid. In this regard, this work aims to assess the spatial and temporal distribution of the temperature increment during MWA by performing ex vivo tests on swine thyroid. Temperature variations have been recorded by means of different arrays of fiber optic Bragg grating sensors (FBGs), each of those embedding ten sensing points in parallel to the MW applicator inside the tissue. These trials could provide the first stage in the further investigation of thyroid MWA, towards a better understanding of the most suitable treatment settings for this kind of tumor to improve the treatment outcomes.
{"title":"Fiber Bragg Gratings for Temperature Monitoring during Thyroid Microwave Ablation: a Preliminary Analysis","authors":"E. D. Vita, Francesca De Tommasi, C. Altomare, Sofia Ialongo, C. Massaroni, D. Presti, E. Faiella, F. Andresciani, G. Pacella, Andrea Palermo, M. Carassiti, A. Iadicicco, R. Grasso, E. Schena, S. Campopiano","doi":"10.1109/MeMeA54994.2022.9856451","DOIUrl":"https://doi.org/10.1109/MeMeA54994.2022.9856451","url":null,"abstract":"Traditional methods to treat thyroid nodules like thyroidectomy and radioiodine therapy can involve a multitude of risks, such as damages to parathyroid glands and aftercare hypothyroidism. Minimally invasive surgery (MIS) can represent an alternative solution, avoiding general anesthesia or radioactive substances. In the framework of MIS, thermal ablation therapies (TATs) are gaining momentum to treat both benign and malign tumors by inducing a significant temperature variation inside the treated tissue. Among TATs, microwave ablation (MWA) is a newly emerging technique which has proved to be an effective and safe method in treating tumors in different organs like liver and kidney, more recently including thyroid nodules. However, an experimental analysis of the temperature reached within the thyroid tissue during the treatment has not been performed yet. Temperature monitoring during TATs can be beneficial to ensure the complete tumor eradication, especially in case of new challenging organs like thyroid. In this regard, this work aims to assess the spatial and temporal distribution of the temperature increment during MWA by performing ex vivo tests on swine thyroid. Temperature variations have been recorded by means of different arrays of fiber optic Bragg grating sensors (FBGs), each of those embedding ten sensing points in parallel to the MW applicator inside the tissue. These trials could provide the first stage in the further investigation of thyroid MWA, towards a better understanding of the most suitable treatment settings for this kind of tumor to improve the treatment outcomes.","PeriodicalId":106228,"journal":{"name":"2022 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125509897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-22DOI: 10.1109/MeMeA54994.2022.9856498
B. Koteska, Hristina Mitrova, A. Bogdanova, F. Lehocki
Continuous monitoring of blood oxygen saturation level (SpO2) during the second triage in the high casualty event and determining the hemostability of a patient/victim until arrival to a medical facility, is essential in emergency situations. Using a SmartPatch device attached to a victim's chest that contains a Photoplethysmogram Waveforms (PPG) sensor, one can obtain the SpO2 parameter. Our interest in the process of the SmartPatch prototype development is to investigate the monitoring of a blood oxygen saturation level by using the embedded PPG sensor. We explore acquiring the Sp02 by extracting the set of features from the PPG signal utilizing two Python toolkits, HeartPy and Neurokit, in order to model the Machine learning predictors, using multiple regressors. The PPG signal is preprocessed by various filtering techniques to remove low/high frequency noise. The model was trained and tested using the clinical data collected from 52 subjects with SpO2 levels varying from 83 – 100%. The best experimental results - MAE (1.45), MSE (3.85), RMSE (1.96) and RMSLE (0.02) scores are achieved with the Random Forest regressor in the experiment with 7 features extracted from the both toolkits.
{"title":"Machine learning based SpO2 prediction from PPG signal's characteristics features","authors":"B. Koteska, Hristina Mitrova, A. Bogdanova, F. Lehocki","doi":"10.1109/MeMeA54994.2022.9856498","DOIUrl":"https://doi.org/10.1109/MeMeA54994.2022.9856498","url":null,"abstract":"Continuous monitoring of blood oxygen saturation level (SpO2) during the second triage in the high casualty event and determining the hemostability of a patient/victim until arrival to a medical facility, is essential in emergency situations. Using a SmartPatch device attached to a victim's chest that contains a Photoplethysmogram Waveforms (PPG) sensor, one can obtain the SpO2 parameter. Our interest in the process of the SmartPatch prototype development is to investigate the monitoring of a blood oxygen saturation level by using the embedded PPG sensor. We explore acquiring the Sp02 by extracting the set of features from the PPG signal utilizing two Python toolkits, HeartPy and Neurokit, in order to model the Machine learning predictors, using multiple regressors. The PPG signal is preprocessed by various filtering techniques to remove low/high frequency noise. The model was trained and tested using the clinical data collected from 52 subjects with SpO2 levels varying from 83 – 100%. The best experimental results - MAE (1.45), MSE (3.85), RMSE (1.96) and RMSLE (0.02) scores are achieved with the Random Forest regressor in the experiment with 7 features extracted from the both toolkits.","PeriodicalId":106228,"journal":{"name":"2022 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"86 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128860816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-22DOI: 10.1109/MeMeA54994.2022.9856407
Ardiana Carlucci, Marco Morisco, Francesco Dell’Olio
In recent years, the medical sector has made use of innovative and advanced electronic and robotic systems that offer enormous potential, allowing research, diagnosis, and treatments that had been considered unbelievable until today. In particular, medical robotics contributes to expanding and improving the possibilities of intervention in various sectors of medicine through the development of complex platforms integrating sensors, actuators, processing hardware, and software. The paper reports on the development, at prototype level, of an electronic device for vital sign detection. The device is integrated with Aphel, an artificial intelligence (AI) platform that includes humanoid robots, supporting patients and healthcare professionals in hospitals. The achieved results highlight the advantages of the convergence between electronic devices and robotic entities in a wide range of healthcare applications.
{"title":"Human Vital Sign Detection by a Microcontroller-Based Device Integrated into a Social Humanoid Robot","authors":"Ardiana Carlucci, Marco Morisco, Francesco Dell’Olio","doi":"10.1109/MeMeA54994.2022.9856407","DOIUrl":"https://doi.org/10.1109/MeMeA54994.2022.9856407","url":null,"abstract":"In recent years, the medical sector has made use of innovative and advanced electronic and robotic systems that offer enormous potential, allowing research, diagnosis, and treatments that had been considered unbelievable until today. In particular, medical robotics contributes to expanding and improving the possibilities of intervention in various sectors of medicine through the development of complex platforms integrating sensors, actuators, processing hardware, and software. The paper reports on the development, at prototype level, of an electronic device for vital sign detection. The device is integrated with Aphel, an artificial intelligence (AI) platform that includes humanoid robots, supporting patients and healthcare professionals in hospitals. The achieved results highlight the advantages of the convergence between electronic devices and robotic entities in a wide range of healthcare applications.","PeriodicalId":106228,"journal":{"name":"2022 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127693523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-22DOI: 10.1109/MeMeA54994.2022.9856550
G. Bandini, A. Landi, F. Santini, A. Basolo, M. Marracci, P. Piaggi
Whole-room indirect calorimeters (WRIC) are accurate tools to precisely measure energy metabolism in humans via calculation of oxygen consumption and carbon dioxide production. Yet, overall accuracy of metabolic measurements relies on the validity of the theoretical model for gas exchange inside the WRIC volume in addition to experimental and environmental conditions that contribute to the uncertainty of WRIC outcome variables. The aim of this study was to quantitatively study the static sensitivity of a WRIC operated in a push configuration and located at the laboratories of the University Hospital of Pisa with the goal to identify the experimental conditions required to reach the best degree of accuracy for outcome metabolic measurements. Herein we demonstrate that achieving a fractional concentration of carbon dioxide inside the $text{WRIC} > 0.2{%}$ at the steady state conditions allows to obtain a relative uncertainty <5% for the outcome metabolic measurements.
{"title":"Static sensitivity of whole-room indirect calorimeters","authors":"G. Bandini, A. Landi, F. Santini, A. Basolo, M. Marracci, P. Piaggi","doi":"10.1109/MeMeA54994.2022.9856550","DOIUrl":"https://doi.org/10.1109/MeMeA54994.2022.9856550","url":null,"abstract":"Whole-room indirect calorimeters (WRIC) are accurate tools to precisely measure energy metabolism in humans via calculation of oxygen consumption and carbon dioxide production. Yet, overall accuracy of metabolic measurements relies on the validity of the theoretical model for gas exchange inside the WRIC volume in addition to experimental and environmental conditions that contribute to the uncertainty of WRIC outcome variables. The aim of this study was to quantitatively study the static sensitivity of a WRIC operated in a push configuration and located at the laboratories of the University Hospital of Pisa with the goal to identify the experimental conditions required to reach the best degree of accuracy for outcome metabolic measurements. Herein we demonstrate that achieving a fractional concentration of carbon dioxide inside the $text{WRIC} > 0.2{%}$ at the steady state conditions allows to obtain a relative uncertainty <5% for the outcome metabolic measurements.","PeriodicalId":106228,"journal":{"name":"2022 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122849047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-22DOI: 10.1109/MeMeA54994.2022.9856465
F. Nardo, Martina Morano, S. Fioretti
The present study involves Continuous Wavelet Transform (CWT) for the analysis of surface electromyographic (sEM G) signals, with the aim of assessing muscle co-contraction during early stance of healthy-subj ect walking. CWT approach allows computing the coscalogram function, a localized statistical assessment of cross-energy density between two signals. In this study, CWT coscalogram function between two sEMG signals from antagonist muscles is used to quantify muscular co-contraction activity. Daubechies of order 4 (factorization in 6 levels) is adopted as mother wavelet. Noise reduction in the sEMG signals is performed applying CWT denoising. Co-contractions between gastrocnemius lateralis and tibialis anterior are assessed on a set of experimental sEM G signals acquired in 15 able-bodied subjects during walking. Results show as the present CWT approach can provide a reliable assessment of co-contraction in early-stance phase of walking, highlighting that this co-contraction is short (< 1 0 ms) and very frequent. A large variability in the occurrence of the co-contraction is also detected, suggesting that each subject adopts her/his own modality of co-contraction. However, the same physiological purpose is maintained for all subj ects, i.e., to control shock absorption and improve weight-bearing stability during the first phase of human walking. Physiological reliability of experimental results suggests the appropriateness of the present method in clinical applications.
{"title":"Quantification of ankle muscle co-contraction during early stance by wavelet-based analysis of surface electromyographic signals","authors":"F. Nardo, Martina Morano, S. Fioretti","doi":"10.1109/MeMeA54994.2022.9856465","DOIUrl":"https://doi.org/10.1109/MeMeA54994.2022.9856465","url":null,"abstract":"The present study involves Continuous Wavelet Transform (CWT) for the analysis of surface electromyographic (sEM G) signals, with the aim of assessing muscle co-contraction during early stance of healthy-subj ect walking. CWT approach allows computing the coscalogram function, a localized statistical assessment of cross-energy density between two signals. In this study, CWT coscalogram function between two sEMG signals from antagonist muscles is used to quantify muscular co-contraction activity. Daubechies of order 4 (factorization in 6 levels) is adopted as mother wavelet. Noise reduction in the sEMG signals is performed applying CWT denoising. Co-contractions between gastrocnemius lateralis and tibialis anterior are assessed on a set of experimental sEM G signals acquired in 15 able-bodied subjects during walking. Results show as the present CWT approach can provide a reliable assessment of co-contraction in early-stance phase of walking, highlighting that this co-contraction is short (< 1 0 ms) and very frequent. A large variability in the occurrence of the co-contraction is also detected, suggesting that each subject adopts her/his own modality of co-contraction. However, the same physiological purpose is maintained for all subj ects, i.e., to control shock absorption and improve weight-bearing stability during the first phase of human walking. Physiological reliability of experimental results suggests the appropriateness of the present method in clinical applications.","PeriodicalId":106228,"journal":{"name":"2022 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126334062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-22DOI: 10.1109/MeMeA54994.2022.9856565
Vaishali Balakarthikeyan, S. Vijayarangan, S. Preejith, M. Sivaprakasam
Heart Rate Variability (HRV) is a widely accepted technique used to measure the stress level of individuals. The state of the art HRV features namely Hilbert spectral and Detrended Fluctuation Analysis (DFA) estimates have opened ways to measure mental state of the individual. The HRV spectral estimates Instantaneous Amplitude of Low Frequency band (LFiA) & Instantaneous Amplitude of High Frequency band (H FiA) derived from Hilbert Transform provides better categorization of mental stress states than conventional frequency parameters due to joint 2-D representation of the low and High frequency HRV bands. Another HRV based approach DFA, which is robust against non-linearity and non-stationarity of cardiac time series caused by complex interactions, helps in providing reliable HRV interpretation. Based on the research evidences for both Hilbert and DFA estimates, it was observed that the use of Hilbert spectral estimates in stress assessment was not validated under free living condition and the application of DFA for mental stress assessment of individuals was not studied. In this work the utility of Hilbert Transform and DFA in HRV based stress assessment was studied under two different settings (confined and free living). The first objective was to determine whether DFA can be used to delineate between two mental states (baseline and stress), under both confined and free living conditions, and to quantify its discriminatory power in the context of mental stress detection. The second objective was to examine the utility of Hilbert estimates in determining mental state under free living conditions. The third objective was to compare the discriminatory power of DFA and Hilbert Transform in stress state detection. From this study, it was observed that both Hilbert and DFA methods can be used to delineate between two mental states under both confined and free living conditions. From the comparative analysis, it was observed that Hilbert estimates showed better discriminatory power than DFA under both the settings.
{"title":"A Comparative Study of Heart Rate Variability Methods for Stress Detection","authors":"Vaishali Balakarthikeyan, S. Vijayarangan, S. Preejith, M. Sivaprakasam","doi":"10.1109/MeMeA54994.2022.9856565","DOIUrl":"https://doi.org/10.1109/MeMeA54994.2022.9856565","url":null,"abstract":"Heart Rate Variability (HRV) is a widely accepted technique used to measure the stress level of individuals. The state of the art HRV features namely Hilbert spectral and Detrended Fluctuation Analysis (DFA) estimates have opened ways to measure mental state of the individual. The HRV spectral estimates Instantaneous Amplitude of Low Frequency band (LFiA) & Instantaneous Amplitude of High Frequency band (H FiA) derived from Hilbert Transform provides better categorization of mental stress states than conventional frequency parameters due to joint 2-D representation of the low and High frequency HRV bands. Another HRV based approach DFA, which is robust against non-linearity and non-stationarity of cardiac time series caused by complex interactions, helps in providing reliable HRV interpretation. Based on the research evidences for both Hilbert and DFA estimates, it was observed that the use of Hilbert spectral estimates in stress assessment was not validated under free living condition and the application of DFA for mental stress assessment of individuals was not studied. In this work the utility of Hilbert Transform and DFA in HRV based stress assessment was studied under two different settings (confined and free living). The first objective was to determine whether DFA can be used to delineate between two mental states (baseline and stress), under both confined and free living conditions, and to quantify its discriminatory power in the context of mental stress detection. The second objective was to examine the utility of Hilbert estimates in determining mental state under free living conditions. The third objective was to compare the discriminatory power of DFA and Hilbert Transform in stress state detection. From this study, it was observed that both Hilbert and DFA methods can be used to delineate between two mental states under both confined and free living conditions. From the comparative analysis, it was observed that Hilbert estimates showed better discriminatory power than DFA under both the settings.","PeriodicalId":106228,"journal":{"name":"2022 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126538340","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-22DOI: 10.1109/MeMeA54994.2022.9856564
Andrei Krivošei, M. Min, P. Annus, Olev Märtens, M. Metshein, Kristina Lotamõis, M. Rist
In the paper we proposed a new method for the cardiac pulse wave base lines and peak lines estimation and correction. The proposed method is mainly directed, but not limited, to the Electrical Bio-Impedance (EBI) and Central Aortic Pressure (CAP) signals. However, the method can be extended to other signal kinds and application fields. Definitely, the proposed method can be applied to the PPG signals and blood pressure waveforms measured from different body locations, not only central aortic pressure. The base line correction approach, instead of filtering, is selected due to the physiological peculiarities of the cardiac cycle. The minimum value of a cardiac signal, which is the diastolic blood pressure (minimum pressure in the cardiac cycle), varies much less than the systolic peak value. Thus, in our research work we use the base line correction (subtraction) instead of mean value subtraction (filtering) to get cardiac signal's component. The proposed method is based on combination of the mathematical morphology and on the Hankel matrix. The method does not need separate estimates of peaks and valleys of the waveforms. Moreover, for correctly estimated signal frequency, the proposed method estimates the base line and the peak line as a piecewise lines between signal's minima or maxima. The result is a corrected cardiac signal that does not need additional processing, based on piecewise estimates of the base and peak lines.
{"title":"Hankel Matrix Based Algorithm for Cardiac Pulse Wave Base and Peak Lines Correction","authors":"Andrei Krivošei, M. Min, P. Annus, Olev Märtens, M. Metshein, Kristina Lotamõis, M. Rist","doi":"10.1109/MeMeA54994.2022.9856564","DOIUrl":"https://doi.org/10.1109/MeMeA54994.2022.9856564","url":null,"abstract":"In the paper we proposed a new method for the cardiac pulse wave base lines and peak lines estimation and correction. The proposed method is mainly directed, but not limited, to the Electrical Bio-Impedance (EBI) and Central Aortic Pressure (CAP) signals. However, the method can be extended to other signal kinds and application fields. Definitely, the proposed method can be applied to the PPG signals and blood pressure waveforms measured from different body locations, not only central aortic pressure. The base line correction approach, instead of filtering, is selected due to the physiological peculiarities of the cardiac cycle. The minimum value of a cardiac signal, which is the diastolic blood pressure (minimum pressure in the cardiac cycle), varies much less than the systolic peak value. Thus, in our research work we use the base line correction (subtraction) instead of mean value subtraction (filtering) to get cardiac signal's component. The proposed method is based on combination of the mathematical morphology and on the Hankel matrix. The method does not need separate estimates of peaks and valleys of the waveforms. Moreover, for correctly estimated signal frequency, the proposed method estimates the base line and the peak line as a piecewise lines between signal's minima or maxima. The result is a corrected cardiac signal that does not need additional processing, based on piecewise estimates of the base and peak lines.","PeriodicalId":106228,"journal":{"name":"2022 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126852427","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-22DOI: 10.1109/MeMeA54994.2022.9856461
D. Borzelli, A. d’Avella, S. Gurgone, L. Gastaldi
EMG-driven robotic devices require the estimation of the forces exerted by the human operator from muscle activity. Approximating the relation between EMG and force with a linear mapping may be accurate enough for numerous real-time applications, such as controlling exoskeletons or prostheses. However, while a linear mapping from the EMG activity to endpoint force may be identified by minimizing the error without any constraint, introducing some constraints may be helpful to determine a mapping which is more anatomically accurate. The presence of noise and the muscle redundancy may introduce errors in the estimation achieved by the unconstrained optimization. Contrarily, anatomical constraints, estimated from an accurate musculoskeletal model, would limit the effect of noise, but they would increase the algorithm complexity and its computational costs. This study compares the two algorithms (unconstrained and constrained) for the estimation of the forces exerted by a human participant from the EMG activity of several upper limb muscles. The two algorithms were tested on data collected during an isometric force generation task performed during multiple sessions spanning two days. Accuracy and consistency across sessions of the reconstructed forces were assessed. Data showed that the unconstrained algorithm allowed for a better reconstruction of the exerted forces, but the constrained mapping is more robust across sessions. Further studies will investigate which of the two algorithms reconstruct a mapping perceived by the participants as more natural during EMG-driven control.
{"title":"Unconstrained and constrained estimation of a linear EMG-to-force mapping during isometric force generation","authors":"D. Borzelli, A. d’Avella, S. Gurgone, L. Gastaldi","doi":"10.1109/MeMeA54994.2022.9856461","DOIUrl":"https://doi.org/10.1109/MeMeA54994.2022.9856461","url":null,"abstract":"EMG-driven robotic devices require the estimation of the forces exerted by the human operator from muscle activity. Approximating the relation between EMG and force with a linear mapping may be accurate enough for numerous real-time applications, such as controlling exoskeletons or prostheses. However, while a linear mapping from the EMG activity to endpoint force may be identified by minimizing the error without any constraint, introducing some constraints may be helpful to determine a mapping which is more anatomically accurate. The presence of noise and the muscle redundancy may introduce errors in the estimation achieved by the unconstrained optimization. Contrarily, anatomical constraints, estimated from an accurate musculoskeletal model, would limit the effect of noise, but they would increase the algorithm complexity and its computational costs. This study compares the two algorithms (unconstrained and constrained) for the estimation of the forces exerted by a human participant from the EMG activity of several upper limb muscles. The two algorithms were tested on data collected during an isometric force generation task performed during multiple sessions spanning two days. Accuracy and consistency across sessions of the reconstructed forces were assessed. Data showed that the unconstrained algorithm allowed for a better reconstruction of the exerted forces, but the constrained mapping is more robust across sessions. Further studies will investigate which of the two algorithms reconstruct a mapping perceived by the participants as more natural during EMG-driven control.","PeriodicalId":106228,"journal":{"name":"2022 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127847278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-06-22DOI: 10.1109/MeMeA54994.2022.9856442
S. Grassini, L. E. Sebar, A. Baldi, A. Comba, E. Angelini, E. Berutti
The paper deals with a measuring approach based on Raman Spectroscopy and micro-CT imaging for correlating the degree of conversion of bulk-fill composites to the contraction shrinkage and consequently to the internal gap formation in high c-factor dental cavities. The developed study was performed on extracted molars in which a first-class cavity was prepared. A micro-CT scan was performed before and after composite lightcuring to tridimensionally measure the interfacial gap between the composite material and the cavity walls. After the complete polymerization of the composite, each sample was sectioned vertically to expose the lateral surface of the restorative material. Raman Spectroscopy measurements were performed along the cross-section of the cavity filled with the restorative material, every 0.5 mm from the occlusal surface. The obtained results showed a minimal gap opening after light-curing and a degree of conversion which was not affected by the bulk-fill composite thickness. Thanks to the 3D rendering, it should be observed that gaps were mostly concentrated at the cavity floor and despite the reduction in the degree of conversion detected in the deeper portions of the restoration, a three-dimensional opening of an interfacial gap was not observed. Therefore, it is possible to assume the presence of a correlation between the degree of conversion and the volumetric interfacial gap could. Further studies are actually in progress to compare these preliminary results with those obtained on other dental composite materials.
{"title":"Measurements for restorative dentistry: shrinkage and conversion degree of bulk-fill composites","authors":"S. Grassini, L. E. Sebar, A. Baldi, A. Comba, E. Angelini, E. Berutti","doi":"10.1109/MeMeA54994.2022.9856442","DOIUrl":"https://doi.org/10.1109/MeMeA54994.2022.9856442","url":null,"abstract":"The paper deals with a measuring approach based on Raman Spectroscopy and micro-CT imaging for correlating the degree of conversion of bulk-fill composites to the contraction shrinkage and consequently to the internal gap formation in high c-factor dental cavities. The developed study was performed on extracted molars in which a first-class cavity was prepared. A micro-CT scan was performed before and after composite lightcuring to tridimensionally measure the interfacial gap between the composite material and the cavity walls. After the complete polymerization of the composite, each sample was sectioned vertically to expose the lateral surface of the restorative material. Raman Spectroscopy measurements were performed along the cross-section of the cavity filled with the restorative material, every 0.5 mm from the occlusal surface. The obtained results showed a minimal gap opening after light-curing and a degree of conversion which was not affected by the bulk-fill composite thickness. Thanks to the 3D rendering, it should be observed that gaps were mostly concentrated at the cavity floor and despite the reduction in the degree of conversion detected in the deeper portions of the restoration, a three-dimensional opening of an interfacial gap was not observed. Therefore, it is possible to assume the presence of a correlation between the degree of conversion and the volumetric interfacial gap could. Further studies are actually in progress to compare these preliminary results with those obtained on other dental composite materials.","PeriodicalId":106228,"journal":{"name":"2022 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123930559","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：