Pub Date : 2021-12-08DOI: 10.1109/BioSMART54244.2021.9677744
S. Said, Z. Albarakeh, T. Beyrouthy, S. Alkork, A. Nait-Ali
Recently, wearable technologies have several bio-engineering applications. In this paper, a Multi-channel surface electromyography (sEMG) wearable armband has been used for an access control system in biometrics applications. A set of experiments have been conducted to explore the ability of sEMG signal to be used for user's identification system. Features are extracted from EMG signals in both frequency and time domains. Three classifiers have been used, namely: K-nearest Neighbors (KNN), Linear Discernment Analysis (LDA), and Ensemble of Classifiers. Results show that the KNN classifier allows performance of 86.01 % in the user's identification system.
{"title":"Machine-Learning based Wearable Multi-Channel sEMG Biometrics Modality for User's Identification","authors":"S. Said, Z. Albarakeh, T. Beyrouthy, S. Alkork, A. Nait-Ali","doi":"10.1109/BioSMART54244.2021.9677744","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677744","url":null,"abstract":"Recently, wearable technologies have several bio-engineering applications. In this paper, a Multi-channel surface electromyography (sEMG) wearable armband has been used for an access control system in biometrics applications. A set of experiments have been conducted to explore the ability of sEMG signal to be used for user's identification system. Features are extracted from EMG signals in both frequency and time domains. Three classifiers have been used, namely: K-nearest Neighbors (KNN), Linear Discernment Analysis (LDA), and Ensemble of Classifiers. Results show that the KNN classifier allows performance of 86.01 % in the user's identification system.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"1 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":"131387135","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/BioSMART54244.2021.9677566
Audace B. K. Didavi, R. Agbokpanzo, M. Agbomahena
In this paper, we make a comparative study of the performance of three methods for predicting the power output of a photovoltaic installation: Decision Tree, Random Forest and XGBoost. We performed these predictions in Python using as input meteorological data such as wind speed, sun position, temperature, direct irradiation, diffuse irradiation and reflected irradiation and as output data the power output of a 1000Wp panel. These data were downloaded from the PVGIS database for the city of Natitingou (Benin) and for a period of 12 years (from January 1st 2005 to December 31st 2016). We obtained as Mean Square Errors 2.195026, 3.058383 and 5.544319 respectively for the XGBoost, Random Forest and Decision Tree and for Regression Values 0.9999999194, 0.9999797366 and 0.9997013968 respectively for the XGBoost, Random Forest and Decision Tree. We conclude that all three models are effective for the forecasting task performed but that the XGBoost is the best performing model with Mean Square Error and Regression Value of 2.195026 and 0.9999999194 respectively.
{"title":"Comparative study of Decision Tree, Random Forest and XGBoost performance in forecasting the power output of a photovoltaic system","authors":"Audace B. K. Didavi, R. Agbokpanzo, M. Agbomahena","doi":"10.1109/BioSMART54244.2021.9677566","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677566","url":null,"abstract":"In this paper, we make a comparative study of the performance of three methods for predicting the power output of a photovoltaic installation: Decision Tree, Random Forest and XGBoost. We performed these predictions in Python using as input meteorological data such as wind speed, sun position, temperature, direct irradiation, diffuse irradiation and reflected irradiation and as output data the power output of a 1000Wp panel. These data were downloaded from the PVGIS database for the city of Natitingou (Benin) and for a period of 12 years (from January 1st 2005 to December 31st 2016). We obtained as Mean Square Errors 2.195026, 3.058383 and 5.544319 respectively for the XGBoost, Random Forest and Decision Tree and for Regression Values 0.9999999194, 0.9999797366 and 0.9997013968 respectively for the XGBoost, Random Forest and Decision Tree. We conclude that all three models are effective for the forecasting task performed but that the XGBoost is the best performing model with Mean Square Error and Regression Value of 2.195026 and 0.9999999194 respectively.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"26 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":"126659947","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/BioSMART54244.2021.9677819
Samar Shaabeth, Zahraa Abdeljaleel
Mesh quality is considered a verification step in the validation procedure for computational modelling. In this paper, the element meshing size was studied using computational mesh quality check method for two dimensional computed tomographic image of the human thorax. Three cases of healthy adults (aged 60, 45 and 36) were scanned and two layers for each set of images were segmented and modelled with two pinpoint mechanical loading (CPR and Kick). Segmentation was done using SOLIDWORKS software while meshing and simulation were performed using ANSYS. The meshing method was performed in the modelling simulation software and five-element sizes were tested for the geometry (3, 2, 1, 0.7, and 0.5 mm). In each case, simulation was run with recording the strain and total deformation for comparing the strain range change while changing the element size. Additional parameters for the simulation software were measured to record the mesh quality before each simulation ensuring the convergence each time. In conclusion, meshing element size was found to be a significant factor even for two-dimensional finite element model and element size reduction can be limited to 0.7mm without the need for further reduction for lower computational time and effort.
{"title":"2D Mesh Study of Simulated Mechanical Loading on Thoracic Cross-Sectional Image","authors":"Samar Shaabeth, Zahraa Abdeljaleel","doi":"10.1109/BioSMART54244.2021.9677819","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677819","url":null,"abstract":"Mesh quality is considered a verification step in the validation procedure for computational modelling. In this paper, the element meshing size was studied using computational mesh quality check method for two dimensional computed tomographic image of the human thorax. Three cases of healthy adults (aged 60, 45 and 36) were scanned and two layers for each set of images were segmented and modelled with two pinpoint mechanical loading (CPR and Kick). Segmentation was done using SOLIDWORKS software while meshing and simulation were performed using ANSYS. The meshing method was performed in the modelling simulation software and five-element sizes were tested for the geometry (3, 2, 1, 0.7, and 0.5 mm). In each case, simulation was run with recording the strain and total deformation for comparing the strain range change while changing the element size. Additional parameters for the simulation software were measured to record the mesh quality before each simulation ensuring the convergence each time. In conclusion, meshing element size was found to be a significant factor even for two-dimensional finite element model and element size reduction can be limited to 0.7mm without the need for further reduction for lower computational time and effort.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"58 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":"123226897","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/BioSMART54244.2021.9677850
Sarah Mroz, N. Baddour, Connor McGuirk, P. Juneau, Albert Tu, Kevin Cheung, E. Lemaire
Human pose estimation is a computer vision task that predicts the position of person's body landmarks within a given image or video. This technology could help provide virtual motion assessments by analyzing videos captured when the patient is outside a clinical setting. In this study, a newer pose estimation model that can run on a smartphone (BlazePose) was compared to a well-accepted solution (OpenPose) to determine if these models can provide clinically viable body keypoints for virtual motion assessment. Using ten videos of clinically relevant movements (recorded by physicians), keypoint coordinates were generated from each model. Using OpenPose as a baseline, Pearson correlation and root mean square error were calculated between the BlazePose and OpenPose keypoint trajectories. BlazePose had more instances where keypoints deviated from anatomical joint centres, compared to OpenPose, indicating the BlazePose was not yet viable for clinically relevant assessments. However, BlazePose runtime was much faster than OpenPose and returned metrics that could be incorporated into a smartphone solution. Future designs of a smartphone-based system for conducting virtual motion assessments should utilize OpenPose for pose estimation; however, BlazePose could be used for other design aspects such as movement pre-screening or activity classification.
{"title":"Comparing the Quality of Human Pose Estimation with BlazePose or OpenPose","authors":"Sarah Mroz, N. Baddour, Connor McGuirk, P. Juneau, Albert Tu, Kevin Cheung, E. Lemaire","doi":"10.1109/BioSMART54244.2021.9677850","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677850","url":null,"abstract":"Human pose estimation is a computer vision task that predicts the position of person's body landmarks within a given image or video. This technology could help provide virtual motion assessments by analyzing videos captured when the patient is outside a clinical setting. In this study, a newer pose estimation model that can run on a smartphone (BlazePose) was compared to a well-accepted solution (OpenPose) to determine if these models can provide clinically viable body keypoints for virtual motion assessment. Using ten videos of clinically relevant movements (recorded by physicians), keypoint coordinates were generated from each model. Using OpenPose as a baseline, Pearson correlation and root mean square error were calculated between the BlazePose and OpenPose keypoint trajectories. BlazePose had more instances where keypoints deviated from anatomical joint centres, compared to OpenPose, indicating the BlazePose was not yet viable for clinically relevant assessments. However, BlazePose runtime was much faster than OpenPose and returned metrics that could be incorporated into a smartphone solution. Future designs of a smartphone-based system for conducting virtual motion assessments should utilize OpenPose for pose estimation; however, BlazePose could be used for other design aspects such as movement pre-screening or activity classification.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"76 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":"129939871","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/BioSMART54244.2021.9677891
Widya Dwi Ariyati, A. Arifin, Siti Halimah Baki, Muhammad Hilman Fatoni
Stroke is a disease that arises due to disturbances in the Central Nervous System (CNS). Stroke sufferers can experience paralysis in the upper limbs caused by a decrease in muscle mass and muscle ability to carry out activities. Cyclic movement is a movement that utilizes the motor control system in the body that is carried out repeatedly. Stroke patients with upper-body motor paralysis cause limitations in carrying out daily activities. A person with a stroke requires rehabilitation to restore the function of the affected muscle. Rehabilitation with the help of Functional Electrical Stimulation (FES) has been commonly used in stroke patients. This study combines cyclic movement exercises with Functional Electrical Stimulation (FES) which is used to activate impaired muscles in a person with central nervous system disorders through the general restoration of motor control. Exercises with cyclic movements are used in the form of pedaling movements on the hands. By combining hand pedaling and FES, it can provide a structured exercise pattern for the muscles of stroke sufferers while providing variation in the post-stroke rehabilitation process. This study developed an upper-limb FES cycling device that can be used to assist the rehabilitation of a person with hemiparesis, especially in the hands by combining hand strokes and Functional Electrical Stimulation (FES) with a Fuzzy Logic Controller (FLC). The combined hand stroke and FES system can work continuously and provide a final error value of -1.09735 then the output of the Fuzzy Logic Controller (FLC) which is used as input to the FES produces a pulse width error value difference of 0.178216 μs. In further research, it could be done by reducing the error value of the output of the controller and adding monitoring parameters to optimize system performance.
{"title":"Upper Limb Function Restoration using Arm Cycling Functional Electrical Stimulation with Fuzzy Logic Controller","authors":"Widya Dwi Ariyati, A. Arifin, Siti Halimah Baki, Muhammad Hilman Fatoni","doi":"10.1109/BioSMART54244.2021.9677891","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677891","url":null,"abstract":"Stroke is a disease that arises due to disturbances in the Central Nervous System (CNS). Stroke sufferers can experience paralysis in the upper limbs caused by a decrease in muscle mass and muscle ability to carry out activities. Cyclic movement is a movement that utilizes the motor control system in the body that is carried out repeatedly. Stroke patients with upper-body motor paralysis cause limitations in carrying out daily activities. A person with a stroke requires rehabilitation to restore the function of the affected muscle. Rehabilitation with the help of Functional Electrical Stimulation (FES) has been commonly used in stroke patients. This study combines cyclic movement exercises with Functional Electrical Stimulation (FES) which is used to activate impaired muscles in a person with central nervous system disorders through the general restoration of motor control. Exercises with cyclic movements are used in the form of pedaling movements on the hands. By combining hand pedaling and FES, it can provide a structured exercise pattern for the muscles of stroke sufferers while providing variation in the post-stroke rehabilitation process. This study developed an upper-limb FES cycling device that can be used to assist the rehabilitation of a person with hemiparesis, especially in the hands by combining hand strokes and Functional Electrical Stimulation (FES) with a Fuzzy Logic Controller (FLC). The combined hand stroke and FES system can work continuously and provide a final error value of -1.09735 then the output of the Fuzzy Logic Controller (FLC) which is used as input to the FES produces a pulse width error value difference of 0.178216 μs. In further research, it could be done by reducing the error value of the output of the controller and adding monitoring parameters to optimize system performance.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"12 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":"126673111","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/BioSMART54244.2021.9677733
G. L. K. Reddy, M. Manikandan, N. V. L Narasimha Murty
Nowadays, wearable sensors or portable devices have great potentials for real-time monitoring of health and fitness of an individual but they are constrained with limited battery power. Therefore, exploring lightweight signal processing technique is highly demanded for accurately measuring the pulse rate (PR) and respiration rate (RR) from the photoplethysmo-gram (PPG) signal in addition to the data compression in order to reduce or even eliminate the need for frequent charging of devices and replacement of batteries. In this paper, we present a lightweight unified predictive coding framework for achieving simultaneous data compression, PR and RR extraction from the PPG signal. Evaluation results demonstrate that the proposed unified framework can achieve compression ratio of 4:1 with energy saving of 52.38 %. For PR estimation, the method had mean absolute error (MAE) of 1.20 (bpm), Pearson coefficient of 0.9829 and Bland Altman ratio of 5.37. The RR estimation had promising MAE results of 3.1 (1.5-5.6 for 25th-75th percentiles) and outperforms the existing methods.
{"title":"Predictive Coding with Simultaneous Extraction of Pulse and Respiration Rates from PPG Signal for Energy Constrained Wearable Devices","authors":"G. L. K. Reddy, M. Manikandan, N. V. L Narasimha Murty","doi":"10.1109/BioSMART54244.2021.9677733","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677733","url":null,"abstract":"Nowadays, wearable sensors or portable devices have great potentials for real-time monitoring of health and fitness of an individual but they are constrained with limited battery power. Therefore, exploring lightweight signal processing technique is highly demanded for accurately measuring the pulse rate (PR) and respiration rate (RR) from the photoplethysmo-gram (PPG) signal in addition to the data compression in order to reduce or even eliminate the need for frequent charging of devices and replacement of batteries. In this paper, we present a lightweight unified predictive coding framework for achieving simultaneous data compression, PR and RR extraction from the PPG signal. Evaluation results demonstrate that the proposed unified framework can achieve compression ratio of 4:1 with energy saving of 52.38 %. For PR estimation, the method had mean absolute error (MAE) of 1.20 (bpm), Pearson coefficient of 0.9829 and Bland Altman ratio of 5.37. The RR estimation had promising MAE results of 3.1 (1.5-5.6 for 25th-75th percentiles) and outperforms the existing methods.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"13 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":"127191831","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/BioSMART54244.2021.9677745
R. Shahbaz, C. Hannachi, F. Deshours, G. Alquié, H. Kokabi, I. Brocheriou, G. Lenaour, F. Koskas, J. Davaine
This paper presents a Complementary Split-Ring Resonator (CSRR) model for the non-destructive characterisation of carotid plaques. The proposed sensor model is corroborated through histopathological examination of the carotid plaques of three different patients, in addition to their ex-vivo S-parameter measurements and system co-simulation using Advanced Design System (ADS) software. The performance of the implemented model is then investigated to identify the conversion loss level of each studied carotid-plaque sample. The results demonstrate that a stable plaque with mainly fibrotic and calcified tissue has a higher conversion loss level. In contrast, a lower level of conversion loss characterises a plaque that has mostly necrotic tissue.
本文提出了一种用于颈动脉斑块非破坏性表征的互补裂环谐振器(CSRR)模型。通过对三名不同患者的颈动脉斑块进行组织病理学检查，以及他们的离体s参数测量和使用Advanced Design system (ADS)软件进行系统联合模拟，证实了所提出的传感器模型。然后研究实现模型的性能，以确定每个研究的颈动脉斑块样本的转换损失水平。结果表明，以纤维化和钙化组织为主的稳定斑块具有较高的转化损失水平。相反，低水平的转化损失表明斑块主要是坏死组织。
{"title":"Conversion Loss Analysis in CSRR-Based Microwave Sensors for Carotid Plaques Characterization","authors":"R. Shahbaz, C. Hannachi, F. Deshours, G. Alquié, H. Kokabi, I. Brocheriou, G. Lenaour, F. Koskas, J. Davaine","doi":"10.1109/BioSMART54244.2021.9677745","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677745","url":null,"abstract":"This paper presents a Complementary Split-Ring Resonator (CSRR) model for the non-destructive characterisation of carotid plaques. The proposed sensor model is corroborated through histopathological examination of the carotid plaques of three different patients, in addition to their ex-vivo S-parameter measurements and system co-simulation using Advanced Design System (ADS) software. The performance of the implemented model is then investigated to identify the conversion loss level of each studied carotid-plaque sample. The results demonstrate that a stable plaque with mainly fibrotic and calcified tissue has a higher conversion loss level. In contrast, a lower level of conversion loss characterises a plaque that has mostly necrotic tissue.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"1 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":"126023092","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/BioSMART54244.2021.9677671
Debora Bettiga, Marco Mandolfo, Riccardo Lolatto, L. Lamberti
The present study was aimed at exploring how different combinations of price tag colours can influence consumer approach, arousal, and price visibility. An experimental investigation was set out to compare individual responses to two different hues conveying different degrees of perceived sophistication, excitement, and visual salience. Specifically, cortical responses were processed to calculate an index of individual approach-withdrawal. Cardiac responses were tracked to assess sympathetic activations. Behavioural measures were related to instinctive nonverbal responses and included ocular behaviours, through eye-tracking, used as a measure of visual salience. Cortical activations showed how black labels affected positively the observer. Sophisticated price displays were connected to positive initial impressions towards the visual stimulus. Orange hues tended to elicit higher physiological arousal and visual salience, pointing to a signaling role effective to generate a sense of alertness.
{"title":"Investigating the effect of price tag colours on cortical, cardiac and ocular responses","authors":"Debora Bettiga, Marco Mandolfo, Riccardo Lolatto, L. Lamberti","doi":"10.1109/BioSMART54244.2021.9677671","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677671","url":null,"abstract":"The present study was aimed at exploring how different combinations of price tag colours can influence consumer approach, arousal, and price visibility. An experimental investigation was set out to compare individual responses to two different hues conveying different degrees of perceived sophistication, excitement, and visual salience. Specifically, cortical responses were processed to calculate an index of individual approach-withdrawal. Cardiac responses were tracked to assess sympathetic activations. Behavioural measures were related to instinctive nonverbal responses and included ocular behaviours, through eye-tracking, used as a measure of visual salience. Cortical activations showed how black labels affected positively the observer. Sophisticated price displays were connected to positive initial impressions towards the visual stimulus. Orange hues tended to elicit higher physiological arousal and visual salience, pointing to a signaling role effective to generate a sense of alertness.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"1 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":"129780589","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/BioSMART54244.2021.9677649
Yazan Jian, Michel Pasquier, A. Sagahyroon, F. Aloul
Diabetes Mellitus (DM) is a chronic disease that is considered to be life threatening. It can affect any part of the body over time, resulting in more serious complications such as Dyslipidemia, Neuropathy and Retinopathy. In this work, different supervised classification algorithms were applied to build several models to predict and diagnose eight diabetes complications. The complications include: Metabolic Syndrome, Dyslipidemia, Neuropathy, Nephropathy, Diabetic Foot, Hypertension, Obesity, and Retinopathy. For this study, a dataset collected by the Rashid Centre for Diabetes and Research (RCDR) located in Ajman, UAE, was utilized. The dataset contains 884 records with 79 features. Some essential preprocessing steps were applied to handle the missing values and unbalanced data problems. Multiple solutions were tested and evaluated.
{"title":"Using Machine Learning to Predict Diabetes Complications","authors":"Yazan Jian, Michel Pasquier, A. Sagahyroon, F. Aloul","doi":"10.1109/BioSMART54244.2021.9677649","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677649","url":null,"abstract":"Diabetes Mellitus (DM) is a chronic disease that is considered to be life threatening. It can affect any part of the body over time, resulting in more serious complications such as Dyslipidemia, Neuropathy and Retinopathy. In this work, different supervised classification algorithms were applied to build several models to predict and diagnose eight diabetes complications. The complications include: Metabolic Syndrome, Dyslipidemia, Neuropathy, Nephropathy, Diabetic Foot, Hypertension, Obesity, and Retinopathy. For this study, a dataset collected by the Rashid Centre for Diabetes and Research (RCDR) located in Ajman, UAE, was utilized. The dataset contains 884 records with 79 features. Some essential preprocessing steps were applied to handle the missing values and unbalanced data problems. Multiple solutions were tested and evaluated.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"37 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":"126957164","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/BioSMART54244.2021.9677721
Bryce Chalfant, A. Ridgel, Kwangtaek Kim
The Virtual Button Clicking Simulation (VBCS), a multifaceted haptic reaching task simulation, was developed for rehabilitation of Parkinson's disease (PD). The VBCS was designed to provide personalized haptic feedback so that the users can practice reaching and touching 3D virtual buttons using a stylus haptic device (Geomagic Touch). The simulation system provides user preferred settings to change button design, size, arrangement with force feedback, and hand motion tracking. To evaluate the VBCS system, two user studies were conducted with ten healthy subjects and three PD patients. Each participant was trained to reach and touch a series of highlighted buttons using the haptic device and then provided a rating of the system usability using a NASA TLX sheet. The results suggest that the VBCS has a good usability in both healthy and PD participants and that the VBCS provides information regarding the timing and quality of the reaching movements. This data suggests that VBCS could be a helpful tool for upper extremity movement evaluation and motor rehabilitation in individuals with PD.
{"title":"An Initial Study of Virtual Button Pressing with Haptic Feedback for the Rehabilitation of Parkinson's Disease","authors":"Bryce Chalfant, A. Ridgel, Kwangtaek Kim","doi":"10.1109/BioSMART54244.2021.9677721","DOIUrl":"https://doi.org/10.1109/BioSMART54244.2021.9677721","url":null,"abstract":"The Virtual Button Clicking Simulation (VBCS), a multifaceted haptic reaching task simulation, was developed for rehabilitation of Parkinson's disease (PD). The VBCS was designed to provide personalized haptic feedback so that the users can practice reaching and touching 3D virtual buttons using a stylus haptic device (Geomagic Touch). The simulation system provides user preferred settings to change button design, size, arrangement with force feedback, and hand motion tracking. To evaluate the VBCS system, two user studies were conducted with ten healthy subjects and three PD patients. Each participant was trained to reach and touch a series of highlighted buttons using the haptic device and then provided a rating of the system usability using a NASA TLX sheet. The results suggest that the VBCS has a good usability in both healthy and PD participants and that the VBCS provides information regarding the timing and quality of the reaching movements. This data suggests that VBCS could be a helpful tool for upper extremity movement evaluation and motor rehabilitation in individuals with PD.","PeriodicalId":286026,"journal":{"name":"2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART)","volume":"76 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":"124501559","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：