Pub Date : 2021-12-08DOI: 10.1109/BioSMART54244.2021.9677664
W. Liu, Dandan Zhu, Zewei Xu, Yan Fu, Zhonglue Chen
There is a close relationship between Parkinson's disease (PD) and speech disorders in people with Parkinson's disease (PWP). Most of the previous studies focus on phonation analysis to extract features from speech signals. For Chinese language, though, articulation analysis can capture specific terms that better distinguish PWP from healthy people. In this paper, we put 28 phonation features and 448 articulation features into 10 kinds of classifiers. The results showed that: 1) The articulation features have better performance compared with phonation features; 2) The combination of 40 articulation features selected by LASSO and the Logistic Regression can achieve highest sensitivity at 82.44%.
{"title":"Suitability of Articulation Analysis for Extracting Speech Signals Features of Chinese Speaking Patients With Parkinson","authors":"W. Liu, Dandan Zhu, Zewei Xu, Yan Fu, Zhonglue Chen","doi":"10.1109/BioSMART54244.2021.9677664","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677664","url":null,"abstract":"There is a close relationship between Parkinson's disease (PD) and speech disorders in people with Parkinson's disease (PWP). Most of the previous studies focus on phonation analysis to extract features from speech signals. For Chinese language, though, articulation analysis can capture specific terms that better distinguish PWP from healthy people. In this paper, we put 28 phonation features and 448 articulation features into 10 kinds of classifiers. The results showed that: 1) The articulation features have better performance compared with phonation features; 2) The combination of 40 articulation features selected by LASSO and the Logistic Regression can achieve highest sensitivity at 82.44%.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133159781","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 : 2021-12-08DOI: 10.1109/BioSMART54244.2021.9677776
William D. Moscoso-Barrera, Iván S. Carreño-Pérez, Luis Mauricio Agudelo-Otalora, L. Giraldo-Cadavid, J. Burguete
Respiratory problems while sleeping cause several health effects, thus it becomes important to monitor respiratory signals to search the causes or moments when said health effects occur. This paper presents the design of an electronic system that first measures, then is instrumented and finally captures signals related to breathing: nasal flow and chest and abdomen respiratory effort. The designed device achieves the visualization of the previously mentioned signals through the Matlab software for its subsequent analysis, ensuring that the system can detect apnea and hypopnea events based solely on the respiratory signals.
{"title":"Design of an electronic device for the measurement of respiratory signals","authors":"William D. Moscoso-Barrera, Iván S. Carreño-Pérez, Luis Mauricio Agudelo-Otalora, L. Giraldo-Cadavid, J. Burguete","doi":"10.1109/BioSMART54244.2021.9677776","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677776","url":null,"abstract":"Respiratory problems while sleeping cause several health effects, thus it becomes important to monitor respiratory signals to search the causes or moments when said health effects occur. This paper presents the design of an electronic system that first measures, then is instrumented and finally captures signals related to breathing: nasal flow and chest and abdomen respiratory effort. The designed device achieves the visualization of the previously mentioned signals through the Matlab software for its subsequent analysis, ensuring that the system can detect apnea and hypopnea events based solely on the respiratory signals.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134051775","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 : 2021-12-08DOI: 10.1109/BioSMART54244.2021.9677856
Nazia Gillani, T. Arslan
People experiencing tremors, find it difficult to perform the activities of daily life. Simple yet essential everyday tasks such as eating, reaching out and grasping an object prove to be a challenge for them. Clinical assessment proves to be subjective and may not provide a true picture of how one's tremor changes throughout the day or varies from one activity to another. Hence, remote monitoring is vital. A few remote assessment approaches do exist in the literature, however, these are based on wearables. These solutions require the continuous wearing of the device, by the individual. This work presents a solution that can not only remotely and unobtrusively detect but also monitor tremors while individuals perform their daily life activities. A Frequency Modulated Continuous Wave (FMCW) radar sensor, designed for the automotive industry, has been configured to monitor these action tremors. Moreover, signal processing has been applied to convert temporal data acquired by the radar to time-frequency data. The results thus generated are used to extract useful clinical information regarding the peculiarities of tremor such as frequency, amplitude and time duration.
{"title":"Unobtrusive Detection and Monitoring of Tremors using Non-Contact Radar Sensor","authors":"Nazia Gillani, T. Arslan","doi":"10.1109/BioSMART54244.2021.9677856","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677856","url":null,"abstract":"People experiencing tremors, find it difficult to perform the activities of daily life. Simple yet essential everyday tasks such as eating, reaching out and grasping an object prove to be a challenge for them. Clinical assessment proves to be subjective and may not provide a true picture of how one's tremor changes throughout the day or varies from one activity to another. Hence, remote monitoring is vital. A few remote assessment approaches do exist in the literature, however, these are based on wearables. These solutions require the continuous wearing of the device, by the individual. This work presents a solution that can not only remotely and unobtrusively detect but also monitor tremors while individuals perform their daily life activities. A Frequency Modulated Continuous Wave (FMCW) radar sensor, designed for the automotive industry, has been configured to monitor these action tremors. Moreover, signal processing has been applied to convert temporal data acquired by the radar to time-frequency data. The results thus generated are used to extract useful clinical information regarding the peculiarities of tremor such as frequency, amplitude and time duration.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132397908","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 : 2021-12-08DOI: 10.1109/BioSMART54244.2021.9677807
Evgenii Rudakov, Loufrani Laurent, Valentin Cousin, Ahmed Roshdi, R. Fournier, A. Nait-Ali, T. Beyrouthy, S. A. Kork
Emotion identification plays a vital role in human interactions. For this purpose, Computer-vision methods for automatic emotion recognition is nowadays a widely studied topic. One of the most studied approaches for automatic emotion recognition is processing multi-channel Electroencephalogram signals (EEG). This paper presents a new model for emotion recognition using brain maps as input and providing emotion states in terms of arousal and valence as output. Brain maps are a spatial representation of features extracted from EEG signals. The proposed model, called Multi-Task Convolutional Neural Network (MT-CNN), is fed with stacked brain maps of four different waves of different frequency bands: alpha, beta, gamma and theta, using differential entropy and power spectra density and considering observation windows of 0.5s. This model is trained and tested on the DEAP dataset, a well-known dataset for comparison purposes. This work shows that the MT-CNN nerforms better than other methods.
{"title":"Multi-Task CNN model for emotion recognition from EEG Brain maps","authors":"Evgenii Rudakov, Loufrani Laurent, Valentin Cousin, Ahmed Roshdi, R. Fournier, A. Nait-Ali, T. Beyrouthy, S. A. Kork","doi":"10.1109/BioSMART54244.2021.9677807","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677807","url":null,"abstract":"Emotion identification plays a vital role in human interactions. For this purpose, Computer-vision methods for automatic emotion recognition is nowadays a widely studied topic. One of the most studied approaches for automatic emotion recognition is processing multi-channel Electroencephalogram signals (EEG). This paper presents a new model for emotion recognition using brain maps as input and providing emotion states in terms of arousal and valence as output. Brain maps are a spatial representation of features extracted from EEG signals. The proposed model, called Multi-Task Convolutional Neural Network (MT-CNN), is fed with stacked brain maps of four different waves of different frequency bands: alpha, beta, gamma and theta, using differential entropy and power spectra density and considering observation windows of 0.5s. This model is trained and tested on the DEAP dataset, a well-known dataset for comparison purposes. This work shows that the MT-CNN nerforms better than other methods.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127196700","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 : 2021-12-08DOI: 10.1109/BioSMART54244.2021.9677763
Wail Sabbani, B. Orsal, L. P. Bidel, L. Urban, C. Jay-Allemand, Fanny Rolet
The photopolymerization of caffeic acid (3,4-Dihydroxy-trans-cinnamate) was triggered using pulses of UV-C light at 278 nm during which the fluorescence of caffeic acid was measured and can be considered as an indicator for this pho-topolymerization process. We present a technological approach and evaluate the fluorescence signal of caffeic acid excited by pulses of UV-C radiation using a silicon photomultiplier SiPM in Geiger mode. Furthermore, liquid chromatography - mass spectrometry (LC-MS) analysis showed that a dimer of caffeic acid was successfully photodimerized.
{"title":"Monitoring photopolymerization of caffeic acid using a UV-C pulsed light generator and silicon photomultiplier","authors":"Wail Sabbani, B. Orsal, L. P. Bidel, L. Urban, C. Jay-Allemand, Fanny Rolet","doi":"10.1109/BioSMART54244.2021.9677763","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677763","url":null,"abstract":"The photopolymerization of caffeic acid (3,4-Dihydroxy-trans-cinnamate) was triggered using pulses of UV-C light at 278 nm during which the fluorescence of caffeic acid was measured and can be considered as an indicator for this pho-topolymerization process. We present a technological approach and evaluate the fluorescence signal of caffeic acid excited by pulses of UV-C radiation using a silicon photomultiplier SiPM in Geiger mode. Furthermore, liquid chromatography - mass spectrometry (LC-MS) analysis showed that a dimer of caffeic acid was successfully photodimerized.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115704442","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 : 2021-12-08DOI: 10.1109/BioSMART54244.2021.9677686
Sagila K. Gangadharan, A. Vinod
Drowsiness, leading to traffic and workplace accidents has been a persistent safety concern over years. Most of the electroencephalogram (EEG)-based drowsiness detection methods in literature use pre-trained classifier models. However, due to the non-stationarity of EEG signals, the patterns associated with drowsiness vary from subject to subject (inter-subject variability) and from session to session for each individual subject (intra-subject variability), necessitating an adaptive drowsiness detection algorithm. In this paper, an electroencephalogram (EEG) based drowsiness detection algorithm, that can adapt to the inter-subject and intra-subject variabilities is proposed. Drowsiness detection is performed based on a simple thresholding algorithm in which, session dependent thresholds are predicted adaptively using a regression model. The proposed drowsiness detection is done using a consumer grade wearable headband ensuring user comfort and the algorithm yields a better detection accuracy of 85.01 % compared to conventional classifier-based approach (83.15%). The proposed adaptive thresholding algorithm can effectively be used for drowsiness detection and is suitable for real time drowsiness detection since the thresholds are determined adaptively.
{"title":"A Nonlinear Penalty Driven Adaptive Thresholding Algorithm for Drowsiness Detection using EEG","authors":"Sagila K. Gangadharan, A. Vinod","doi":"10.1109/BioSMART54244.2021.9677686","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677686","url":null,"abstract":"Drowsiness, leading to traffic and workplace accidents has been a persistent safety concern over years. Most of the electroencephalogram (EEG)-based drowsiness detection methods in literature use pre-trained classifier models. However, due to the non-stationarity of EEG signals, the patterns associated with drowsiness vary from subject to subject (inter-subject variability) and from session to session for each individual subject (intra-subject variability), necessitating an adaptive drowsiness detection algorithm. In this paper, an electroencephalogram (EEG) based drowsiness detection algorithm, that can adapt to the inter-subject and intra-subject variabilities is proposed. Drowsiness detection is performed based on a simple thresholding algorithm in which, session dependent thresholds are predicted adaptively using a regression model. The proposed drowsiness detection is done using a consumer grade wearable headband ensuring user comfort and the algorithm yields a better detection accuracy of 85.01 % compared to conventional classifier-based approach (83.15%). The proposed adaptive thresholding algorithm can effectively be used for drowsiness detection and is suitable for real time drowsiness detection since the thresholds are determined adaptively.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117050920","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 : 2021-12-08DOI: 10.1109/BioSMART54244.2021.9677782
Hessa Albawardi, Aljohara Almoaibed, Noor Al Abbas, Sarah Alsayed, Tarfa Almaghlouth, Saleh I. Alzahrani
Many patients suffer from neuromuscular diseases that prevent them from controlling their muscles. This motion limitation makes them fully reliable on others. This work presents a design of a low-cost brain-computer interface (BCI) system with which an electrical wheelchair is controlled directly by the patient's electroencephalogram (EEG). The design of the system is based on steady state visually evoked potentials (SSVEPs). Four groups of flickering stimuli are used in a graphical interface. To navigate the wheelchair, the user focusses his sight in the desired direction on the graphical interface to produce the corresponding SSVEP signal. The signal is acquired from the user's brain and processed using a proposed SSVEP detection algorithm. Based on the output of the algorithm, a command (forward, backward, left, or right) is translated to control the wheelchair. For the offline analysis, a comparison between O1 and O2 positions was done. Based on the obtained results, O2 gave the highest amplitude for 60% of the subjects. An additional experiment was done to choose the optimal stimulus colour. It was found that green/black is the best option that was both comfortable and provided a strong signal. For the real-time analysis, Neuromore software was used to develop the detection algorithm used for controlling the wheelchair prototype.
{"title":"Design of Low-Cost Steady State Visually Evoked Potential-Based Brain Computer Interface Using OpenBCI and Neuromore","authors":"Hessa Albawardi, Aljohara Almoaibed, Noor Al Abbas, Sarah Alsayed, Tarfa Almaghlouth, Saleh I. Alzahrani","doi":"10.1109/BioSMART54244.2021.9677782","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677782","url":null,"abstract":"Many patients suffer from neuromuscular diseases that prevent them from controlling their muscles. This motion limitation makes them fully reliable on others. This work presents a design of a low-cost brain-computer interface (BCI) system with which an electrical wheelchair is controlled directly by the patient's electroencephalogram (EEG). The design of the system is based on steady state visually evoked potentials (SSVEPs). Four groups of flickering stimuli are used in a graphical interface. To navigate the wheelchair, the user focusses his sight in the desired direction on the graphical interface to produce the corresponding SSVEP signal. The signal is acquired from the user's brain and processed using a proposed SSVEP detection algorithm. Based on the output of the algorithm, a command (forward, backward, left, or right) is translated to control the wheelchair. For the offline analysis, a comparison between O1 and O2 positions was done. Based on the obtained results, O2 gave the highest amplitude for 60% of the subjects. An additional experiment was done to choose the optimal stimulus colour. It was found that green/black is the best option that was both comfortable and provided a strong signal. For the real-time analysis, Neuromore software was used to develop the detection algorithm used for controlling the wheelchair prototype.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"21 24","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132737945","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 : 2021-12-08DOI: 10.1109/BioSMART54244.2021.9677812
Filip Cuckov, Sean Spencer, P. Górczynski, Lucas Lomba, Garry Ingles, Preston Watson, Michael Kearns, Joseph Harling, Eric Yeh, Shakir Khan, Tayyaba Hasan, J. Celli
This paper presents a cyber-physical framework with software and hardware tools and supporting infrastructure aimed at accelerating the development and field deployment of scalable next-generation smart medical devices. We validate the framework by rapidly developing a reconfigurable embedded system platform and software framework for the realization of a next-generation photo-dynamic therapy smart medical device, thus reducing the time-to-market for clinical testing and commercialization ventures. The re-configurable platform is power-efficient, robust, and composed of using four modular components: a main microcontroller module, a power management module, a user interface management module, and a laser or high-power light emitting diode driver module with a slave microcontroller hosted on an interchangeable daughter board; ensuring its reliability and repairability in resource limited settings. The design allows for future hardware expansion and reconfiguration within its circuitry, making it compact and portable. Results include the manufactured hardware of the embedded system and the implementation of the model-view-controller software stack that enables our next-generation photo-dynamic therapy smart medical device.
{"title":"Towards a Reconfigurable Cyber-Physical Systems Framework for Rapid Development of Scalable Next-Generation Smart Medical Devices","authors":"Filip Cuckov, Sean Spencer, P. Górczynski, Lucas Lomba, Garry Ingles, Preston Watson, Michael Kearns, Joseph Harling, Eric Yeh, Shakir Khan, Tayyaba Hasan, J. Celli","doi":"10.1109/BioSMART54244.2021.9677812","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677812","url":null,"abstract":"This paper presents a cyber-physical framework with software and hardware tools and supporting infrastructure aimed at accelerating the development and field deployment of scalable next-generation smart medical devices. We validate the framework by rapidly developing a reconfigurable embedded system platform and software framework for the realization of a next-generation photo-dynamic therapy smart medical device, thus reducing the time-to-market for clinical testing and commercialization ventures. The re-configurable platform is power-efficient, robust, and composed of using four modular components: a main microcontroller module, a power management module, a user interface management module, and a laser or high-power light emitting diode driver module with a slave microcontroller hosted on an interchangeable daughter board; ensuring its reliability and repairability in resource limited settings. The design allows for future hardware expansion and reconfiguration within its circuitry, making it compact and portable. Results include the manufactured hardware of the embedded system and the implementation of the model-view-controller software stack that enables our next-generation photo-dynamic therapy smart medical device.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134255644","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 : 2021-12-08DOI: 10.1109/BioSMART54244.2021.9677750
Anubha Gupta, Deepankar Kansal, V. Gupta, M. Shetty, M. Girish, M. Gupta
COVID-19 pandemic erupted in December 2019, spreading extremely fast and stretching the healthcare infras-tructure of most countries beyond their capacities. This impacted the healthcare workers (HCW) adversely because 1) they were pressured to work almost round the clock without a break; 2) they were in close contact with the COVID-19 patients and hence, were at high risk; and 3) they suffered from the fear of spreading COVID to their families. Hence, many HCWs were stressed and burnout. It is known that stress directly affects the heart and can lead to serious cardiovascular problems. Currently, stress is measured subjectively via self-declared questionnaires. Objective markers of stress are required to ascertain the quantitative impact of stress on the heart. Thus, this paper aims to detect stress contributing factors in HCWs and determine the changes in the ECG of stressed HCWs. We collected data from multiple hospitals in Northern India and developed a deep learning model, namely X-ECGNet, to detect stress. We also tried to add interpretability to the model using the recent method of SHAP analysis. Deployment of such models can help the government and hospital administrations timely detect stress in HCWs and make informed decisions to save systems from collapse during such calamities.
{"title":"X-ECGNet: An Interpretable DL model for Stress Detection using ECG in COVID-19 Healthcare Workers","authors":"Anubha Gupta, Deepankar Kansal, V. Gupta, M. Shetty, M. Girish, M. Gupta","doi":"10.1109/BioSMART54244.2021.9677750","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677750","url":null,"abstract":"COVID-19 pandemic erupted in December 2019, spreading extremely fast and stretching the healthcare infras-tructure of most countries beyond their capacities. This impacted the healthcare workers (HCW) adversely because 1) they were pressured to work almost round the clock without a break; 2) they were in close contact with the COVID-19 patients and hence, were at high risk; and 3) they suffered from the fear of spreading COVID to their families. Hence, many HCWs were stressed and burnout. It is known that stress directly affects the heart and can lead to serious cardiovascular problems. Currently, stress is measured subjectively via self-declared questionnaires. Objective markers of stress are required to ascertain the quantitative impact of stress on the heart. Thus, this paper aims to detect stress contributing factors in HCWs and determine the changes in the ECG of stressed HCWs. We collected data from multiple hospitals in Northern India and developed a deep learning model, namely X-ECGNet, to detect stress. We also tried to add interpretability to the model using the recent method of SHAP analysis. Deployment of such models can help the government and hospital administrations timely detect stress in HCWs and make informed decisions to save systems from collapse during such calamities.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131508498","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 : 2021-12-08DOI: 10.1109/BioSMART54244.2021.9677643
M. Harastani, S. Jonić
Cryogenic electron tomography (cryo-ET) allows studying biological macromolecular complexes in cells by three-dimensional (3D) data analysis. The complexes continuously change their shapes (conformations) to achieve biological functions. The shape heterogeneity in cryo-ET is a bottleneck for comprehending biological mechanisms and developing drugs. Cryo-ET data suffer from a low signal-to-noise ratio and spatial anisotropies (missing wedge artefacts), making it particularly challenging for resolving the shape variability. Other shape variability analysis techniques simplify the problem by consid-ering discrete rather than continuous conformational changes of complexes. Recently, HEMNMA-3D was introduced for cryo-ET continuous shape variability analysis, based on elastic and rigid-body 3D registration between simulated shapes and cryo-ET data using normal mode analysis and fast rotational matching with missing wedge compensation. HEMNMA-3D provides a visual insight into molecular dynamics by grouping and aver-aging subtomograms of similar shapes and by animating movies of registered motions. This article reviews HEMNMA-3D and compares it with existing literature on a simulated dataset for nucleosome shape variability.
{"title":"Comparison between HEMNMA-3D and Traditional Classification Techniques for Analyzing Biomolecular Continuous Shape Variability in Cryo Electron Subtomograms","authors":"M. Harastani, S. Jonić","doi":"10.1109/BioSMART54244.2021.9677643","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677643","url":null,"abstract":"Cryogenic electron tomography (cryo-ET) allows studying biological macromolecular complexes in cells by three-dimensional (3D) data analysis. The complexes continuously change their shapes (conformations) to achieve biological functions. The shape heterogeneity in cryo-ET is a bottleneck for comprehending biological mechanisms and developing drugs. Cryo-ET data suffer from a low signal-to-noise ratio and spatial anisotropies (missing wedge artefacts), making it particularly challenging for resolving the shape variability. Other shape variability analysis techniques simplify the problem by consid-ering discrete rather than continuous conformational changes of complexes. Recently, HEMNMA-3D was introduced for cryo-ET continuous shape variability analysis, based on elastic and rigid-body 3D registration between simulated shapes and cryo-ET data using normal mode analysis and fast rotational matching with missing wedge compensation. HEMNMA-3D provides a visual insight into molecular dynamics by grouping and aver-aging subtomograms of similar shapes and by animating movies of registered motions. This article reviews HEMNMA-3D and compares it with existing literature on a simulated dataset for nucleosome shape variability.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"2015 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127658831","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：