Pub Date : 2018-11-01DOI: 10.1109/ICBME.2018.8703584
M. Nematollahi, S. Haghpanah, S. Taghvaei
Sit-to-stand motion is one of the most basic movements of each person throughout his life and is done repeatedly. This motion is prerequisite for other movements like running and climbing that in many people is easy to do, and in some people it may be hard to do or even not done at all. One way of helping the elderly and disabled people to do this motion is designing a device to facilitate this motion without need of assistance by others. To design such a device, it is necessary to obtain the dynamic equations of the body and then apply the appropriate control system on it. Activities in this field can be divided into two categories: obtaining experimental data for this motion involves the angles of body segments and forces, and then providing the torque values associated with each actuator in the device mechanism to optimize the motion, and second, provide nonlinear control methods to bring the current state of the device to a desired state such as adaptive and robust control methods. Also, due to the different conditions of each individual relative to the others, such as how to sit, body anatomy, age, etc., it is necessary that the proposed device and control system properly operate in a variety of conditions. The main purpose of this study is to design a suitable control system for devices that designed for helping people to stand and sit correctly. We propose inverse dynamic tracking for controlling the system. This control method has not been used to control this move yet. With such a control system, one can control the posture of assistive devices, such as lower limb three-link exoskeletons, and standing assistance systems to achieve natural motion.
{"title":"Inverse dynamic tracking control of sitting and standing movement","authors":"M. Nematollahi, S. Haghpanah, S. Taghvaei","doi":"10.1109/ICBME.2018.8703584","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703584","url":null,"abstract":"Sit-to-stand motion is one of the most basic movements of each person throughout his life and is done repeatedly. This motion is prerequisite for other movements like running and climbing that in many people is easy to do, and in some people it may be hard to do or even not done at all. One way of helping the elderly and disabled people to do this motion is designing a device to facilitate this motion without need of assistance by others. To design such a device, it is necessary to obtain the dynamic equations of the body and then apply the appropriate control system on it. Activities in this field can be divided into two categories: obtaining experimental data for this motion involves the angles of body segments and forces, and then providing the torque values associated with each actuator in the device mechanism to optimize the motion, and second, provide nonlinear control methods to bring the current state of the device to a desired state such as adaptive and robust control methods. Also, due to the different conditions of each individual relative to the others, such as how to sit, body anatomy, age, etc., it is necessary that the proposed device and control system properly operate in a variety of conditions. The main purpose of this study is to design a suitable control system for devices that designed for helping people to stand and sit correctly. We propose inverse dynamic tracking for controlling the system. This control method has not been used to control this move yet. With such a control system, one can control the posture of assistive devices, such as lower limb three-link exoskeletons, and standing assistance systems to achieve natural motion.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115805243","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 : 2018-11-01DOI: 10.1109/ICBME.2018.8703565
Saeed Sarbazi-Azad, M. S. Abadeh
Cancer detection is one of the major applications of clinical microarray data. High dimensionality is one of the important challenges in microarrays. Most of genes in microarrays have no importance or contribution on the class prediction and on the other side a lot of resources and memory are needed to processing this amount of genes. Thus the reduction in number of dimensions seems to be staple to predict cancer. In this paper a gene selection method using data complexity measures on microarray gene expression cancer data is presented. Two overlap measures as data complexity measure namely fisher discriminant ratio and attribute efficiency are applied to ranking the genes and afterward the high rank genes are considered as important ones to contribute in cancer diagnosis. Five well-known binary microarray cancer data are considered for evaluation and also the applied classifiers are Decision Tree (DT), naïve bayes (NB) and K-Nearest Neighbor (KNN). Two approaches that were considered are fisher-based and (attribute +fisher)-based gene selection. The results indicate that the model created by genes selected by fisher-based method can detect the cancerous samples with high accuracy.
{"title":"Gene Selection for Cancer Classification from Microarray Data Using Data Overlap Measure","authors":"Saeed Sarbazi-Azad, M. S. Abadeh","doi":"10.1109/ICBME.2018.8703565","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703565","url":null,"abstract":"Cancer detection is one of the major applications of clinical microarray data. High dimensionality is one of the important challenges in microarrays. Most of genes in microarrays have no importance or contribution on the class prediction and on the other side a lot of resources and memory are needed to processing this amount of genes. Thus the reduction in number of dimensions seems to be staple to predict cancer. In this paper a gene selection method using data complexity measures on microarray gene expression cancer data is presented. Two overlap measures as data complexity measure namely fisher discriminant ratio and attribute efficiency are applied to ranking the genes and afterward the high rank genes are considered as important ones to contribute in cancer diagnosis. Five well-known binary microarray cancer data are considered for evaluation and also the applied classifiers are Decision Tree (DT), naïve bayes (NB) and K-Nearest Neighbor (KNN). Two approaches that were considered are fisher-based and (attribute +fisher)-based gene selection. The results indicate that the model created by genes selected by fisher-based method can detect the cancerous samples with high accuracy.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125328112","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 : 2018-11-01DOI: 10.1109/ICBME.2018.8703570
Siavash Sohangir, A. Mojra
The purpose of this article is to construct a real model of the knee joint to determine fluid’s behavior inside it, based on the computed tomography (CT) scan images of a patient. The meniscus and cartilage are considered as porous media and are modeled as poroelastic materials. The main output is the velocity profile in the knee joint. Results show that the fluid content velocity is maximum through the lateral surfaces. Moreover, effect of aging is studied by varying the permeability of the meniscus. It is observed that the permeability has direct correlation with the fluid flow velocity inside the knee joint.
{"title":"A Numerical Study on Fluid Flow inside the Knee Joint through a Porous Media Approach","authors":"Siavash Sohangir, A. Mojra","doi":"10.1109/ICBME.2018.8703570","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703570","url":null,"abstract":"The purpose of this article is to construct a real model of the knee joint to determine fluid’s behavior inside it, based on the computed tomography (CT) scan images of a patient. The meniscus and cartilage are considered as porous media and are modeled as poroelastic materials. The main output is the velocity profile in the knee joint. Results show that the fluid content velocity is maximum through the lateral surfaces. Moreover, effect of aging is studied by varying the permeability of the meniscus. It is observed that the permeability has direct correlation with the fluid flow velocity inside the knee joint.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126841353","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 : 2018-11-01DOI: 10.1109/icbme.2018.8703547
{"title":"ICBME 2018 Cover Page","authors":"","doi":"10.1109/icbme.2018.8703547","DOIUrl":"https://doi.org/10.1109/icbme.2018.8703547","url":null,"abstract":"","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126243169","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 : 2018-11-01DOI: 10.1109/ICBME.2018.8703528
Abazar Arabameri, D. Asemani, J. Hajati
To understand complex immunological mechanisms alongside avoiding huge experimentation costs, mathematical modelling has been used in the development of anticancer drugs. In this paper, a mathematical model is proposed to describe the roles of hypoxia-inducible factors (HIFs) (transcription factors released by tumors in response to a decrease in available oxygen), in the interactions between the tumor and the immune system. For this purpose, a previously published model of immunotherapy with dendritic cells (DCs) is extended so as to incorporate the treatment with an HIF inhibitor drug. Based on the experimental data, this extended model is calibrated for the model parameters leading to an acceptable level of the mean absolute percentage error in the validation phase. The proposed model is capable of determining the most effective immunosuppressive mechanism by which the HIF effects, and the effect of HIF on DCs and inflammatory factors of the immune system has been found to be of great importance.
{"title":"Mathematical Model of Cancer Immunotherapy by Dendritic Cells Combined with Tumor Hypoxia Treatment","authors":"Abazar Arabameri, D. Asemani, J. Hajati","doi":"10.1109/ICBME.2018.8703528","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703528","url":null,"abstract":"To understand complex immunological mechanisms alongside avoiding huge experimentation costs, mathematical modelling has been used in the development of anticancer drugs. In this paper, a mathematical model is proposed to describe the roles of hypoxia-inducible factors (HIFs) (transcription factors released by tumors in response to a decrease in available oxygen), in the interactions between the tumor and the immune system. For this purpose, a previously published model of immunotherapy with dendritic cells (DCs) is extended so as to incorporate the treatment with an HIF inhibitor drug. Based on the experimental data, this extended model is calibrated for the model parameters leading to an acceptable level of the mean absolute percentage error in the validation phase. The proposed model is capable of determining the most effective immunosuppressive mechanism by which the HIF effects, and the effect of HIF on DCs and inflammatory factors of the immune system has been found to be of great importance.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131122509","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 : 2018-11-01DOI: 10.1109/ICBME.2018.8703602
H. Barnamehei, M. Razaghi, Shabnam Panahi, Mahmoud Modabberibejandi, Masoud Lashgari, M. Safaei, A. Rezaei
The main goal of this study is to determine the neuromuscular coordination and synergies during roundhouse kick executed by elite taekwondo players. Muscles synergy (coordination) is a tactics of CNS (Central Nervous System) to consider a lower dimensional parameters of motor coordination commands from the central nervous system (CNS) of human body or animals. Fifteen elite players from Iran taekwondo national team participated in current study. Neuromuscular coordination (synergies) were extracted from six taekwondo specific muscles. Studies on athletics performance featured how factors such as the lowest number of motor coordination determination for most of the data variance correlate with impairments and motor task. Neuromuscular coordination (synergies) and their separate synergy activation curves were determined from six lower extremity muscles via a NNMF (Non Negative Matrix Factorization) theory. Three muscle synergies were capable to express 90% of the variance in electromyography signals across all players. The scalar product similarity of the neuromuscular synergies among the athletics is found to be 0.81±0.17.
{"title":"Identification and quantification of modular control during Roundhouse kick executed by elite Taekwondo players","authors":"H. Barnamehei, M. Razaghi, Shabnam Panahi, Mahmoud Modabberibejandi, Masoud Lashgari, M. Safaei, A. Rezaei","doi":"10.1109/ICBME.2018.8703602","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703602","url":null,"abstract":"The main goal of this study is to determine the neuromuscular coordination and synergies during roundhouse kick executed by elite taekwondo players. Muscles synergy (coordination) is a tactics of CNS (Central Nervous System) to consider a lower dimensional parameters of motor coordination commands from the central nervous system (CNS) of human body or animals. Fifteen elite players from Iran taekwondo national team participated in current study. Neuromuscular coordination (synergies) were extracted from six taekwondo specific muscles. Studies on athletics performance featured how factors such as the lowest number of motor coordination determination for most of the data variance correlate with impairments and motor task. Neuromuscular coordination (synergies) and their separate synergy activation curves were determined from six lower extremity muscles via a NNMF (Non Negative Matrix Factorization) theory. Three muscle synergies were capable to express 90% of the variance in electromyography signals across all players. The scalar product similarity of the neuromuscular synergies among the athletics is found to be 0.81±0.17.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"583 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134460172","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 : 2018-11-01DOI: 10.1109/ICBME.2018.8703568
A. Javadi, V. Nekoukar, Marzieh Ebrahimi
Cancer is an important lethal disease. Therefore, many studies have focused on the drug delivery in the cancer treatment in order to obtain a better survival rate. In recent years, personalized medicine for the cancer treatment has been considered by researchers. One of the methods for implementing the personalized medicine is to apply mathematical models of tumor growth and to study the dynamic behavior of the tumor response to drugs. One of the main important factors of the model is drug resistance that may lead to failure of the treatment. In this study, a mathematical model of tumor growth of melanoma cancer is proposed for mouse models. In the presented model, drug sensitivity and drug resistance are considered. Parameters of the model are estimated using experimental data measured of mouse models. The mice were treated with a signaling pathway inhibitor (Notch inhibitor) of cancer stem cells.
{"title":"Modeling of Therapy-Induced Tumor Growth in Presence of Drug Resistance for Melanoma Cancer","authors":"A. Javadi, V. Nekoukar, Marzieh Ebrahimi","doi":"10.1109/ICBME.2018.8703568","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703568","url":null,"abstract":"Cancer is an important lethal disease. Therefore, many studies have focused on the drug delivery in the cancer treatment in order to obtain a better survival rate. In recent years, personalized medicine for the cancer treatment has been considered by researchers. One of the methods for implementing the personalized medicine is to apply mathematical models of tumor growth and to study the dynamic behavior of the tumor response to drugs. One of the main important factors of the model is drug resistance that may lead to failure of the treatment. In this study, a mathematical model of tumor growth of melanoma cancer is proposed for mouse models. In the presented model, drug sensitivity and drug resistance are considered. Parameters of the model are estimated using experimental data measured of mouse models. The mice were treated with a signaling pathway inhibitor (Notch inhibitor) of cancer stem cells.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127595752","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 : 2018-11-01DOI: 10.1109/ICBME.2018.8703543
S. Hemati, G. Hossein-Zadeh
Many behavioral and neuroimaging studies have shown that the human brain represents, recall and learn concrete words more accurately and easier than abstract words. This phenomenon is defined as the concreteness effect. Dual coding theory is one of the main important theories which is often used to justify the concreteness effect. Several neuroimaging studies tried to localize and compare activated areas during concrete and abstract word processing, but brain connectivity was not studied in the above tasks. In a fMRI experiment, we acquired fMRI data from 11 healthy volunteers in the visual mental imagery of concrete and abstract characteristics. In a novel work, we then used inter-hemispheric connectivity to compare the brain hemispheres integration between concrete and abstract word processing. Twelve important brain regions reported in previous studies of abstract or concrete concept processing were selected. Then the correlations of BOLD activity of each region with its corresponding contralateral region were calculated and compared for the time intervals of concrete and abstract word processing. Results revealed that the inter-hemispheric connectivity during concrete word imagery was significantly different compared to abstract word imagery (FDR correction, q = 0.05) in three contrasting regions which were middle occipital gyrus, inferior occipital gyrus and temporal pole (superior temporal gyrus). Notably, in all of these three areas, the inter-hemispheric functional connectivity was significantly stronger during concrete word imagery to that of abstract. These results imply that the synchronization between brain hemispheres within visual and language processing areas is significantly stronger for imagery of concrete words (more imageable words) than that of abstract words (less imageable words).
{"title":"Increased inter-hemispheric functional connectivity for concrete word imagery compared to abstract word imagery","authors":"S. Hemati, G. Hossein-Zadeh","doi":"10.1109/ICBME.2018.8703543","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703543","url":null,"abstract":"Many behavioral and neuroimaging studies have shown that the human brain represents, recall and learn concrete words more accurately and easier than abstract words. This phenomenon is defined as the concreteness effect. Dual coding theory is one of the main important theories which is often used to justify the concreteness effect. Several neuroimaging studies tried to localize and compare activated areas during concrete and abstract word processing, but brain connectivity was not studied in the above tasks. In a fMRI experiment, we acquired fMRI data from 11 healthy volunteers in the visual mental imagery of concrete and abstract characteristics. In a novel work, we then used inter-hemispheric connectivity to compare the brain hemispheres integration between concrete and abstract word processing. Twelve important brain regions reported in previous studies of abstract or concrete concept processing were selected. Then the correlations of BOLD activity of each region with its corresponding contralateral region were calculated and compared for the time intervals of concrete and abstract word processing. Results revealed that the inter-hemispheric connectivity during concrete word imagery was significantly different compared to abstract word imagery (FDR correction, q = 0.05) in three contrasting regions which were middle occipital gyrus, inferior occipital gyrus and temporal pole (superior temporal gyrus). Notably, in all of these three areas, the inter-hemispheric functional connectivity was significantly stronger during concrete word imagery to that of abstract. These results imply that the synchronization between brain hemispheres within visual and language processing areas is significantly stronger for imagery of concrete words (more imageable words) than that of abstract words (less imageable words).","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128453514","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 : 2018-11-01DOI: 10.1109/ICBME.2018.8703555
Mojtaba Zarei, Kimia Javadi, A. Kalhor
This paper aims at the estimation of the Domain of Attraction (DoA) of the free tumor equilibrium point of perturbed tumor immunotherapy model via the Arc-Length Function (ALF). The ALFs are categorized among the maximal Lyapunov functions which are able to provide a more accurate estimation of the DoA in comparison to their other counterparts such as Rational Lyapunov Functions (RLFs), Sum Of Square (SOS) polynomial Lyapunov functions, and Optimal Quadratic Lyapunov Functions (OQLFs). There is no analytical method to construct the ALFs, however, some numerical methods have been proposed in the literature. Based on the existing method, one can approximate the ALF with a certain degree of a polynomial function. That the system under study has a polynomial structure was the main basis of the previously proposed method to estimate the DoA via the ALFs. However, the intended model in this paper describing the tumor-immune system competition dynamics contains non-polynomial terms. To cope with the aforementioned problem, the Taylor expansion of the non-polynomial terms are considered and by solving an optimization problem, one can calculate the corresponding lower boundary of the level set with the approximated ALF as an estimation of the DoA. In order to represent the performance of the employed method, the obtained result is compared with the reported result in the literature.
{"title":"Perturbed Tumor Immunotherapy Domain of Attraction Estimation via the Arc-Length Function","authors":"Mojtaba Zarei, Kimia Javadi, A. Kalhor","doi":"10.1109/ICBME.2018.8703555","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703555","url":null,"abstract":"This paper aims at the estimation of the Domain of Attraction (DoA) of the free tumor equilibrium point of perturbed tumor immunotherapy model via the Arc-Length Function (ALF). The ALFs are categorized among the maximal Lyapunov functions which are able to provide a more accurate estimation of the DoA in comparison to their other counterparts such as Rational Lyapunov Functions (RLFs), Sum Of Square (SOS) polynomial Lyapunov functions, and Optimal Quadratic Lyapunov Functions (OQLFs). There is no analytical method to construct the ALFs, however, some numerical methods have been proposed in the literature. Based on the existing method, one can approximate the ALF with a certain degree of a polynomial function. That the system under study has a polynomial structure was the main basis of the previously proposed method to estimate the DoA via the ALFs. However, the intended model in this paper describing the tumor-immune system competition dynamics contains non-polynomial terms. To cope with the aforementioned problem, the Taylor expansion of the non-polynomial terms are considered and by solving an optimization problem, one can calculate the corresponding lower boundary of the level set with the approximated ALF as an estimation of the DoA. In order to represent the performance of the employed method, the obtained result is compared with the reported result in the literature.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127010540","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 : 2018-11-01DOI: 10.1109/ICBME.2018.8703534
Amirhossein Safari, M. Mohebbi
In this paper, we present a false alarm reduction algorithm for Ventricular Tachycardia (VT) arrhythmias in intensive care unit (ICU) using multivariate statistical process control (MSPC) and frequency analysis of electrocardiogram (ECG) signal. First, we decompose the ECG signal into three different frequency bands. The ECG beats are detected, and VT beats are labeled. In the next step, several features consist of time domain features, bispectrum features, and Poincaré plot features are extracted from ECG Signal The extracted feature vector of each ECG beat is monitored using MSPC for detecting anomalies. The performance of the proposed method is evaluated using the Ventricular Tachycardia cases of 2015 Physionet challenge database. This dataset consists of 2 ECG channel, arterial blood pressure (ABP) and/or photoplethysmograph (PPG) signal, and an alarm annotation for each record. The obtained sensitivity and specificity were 86.5%, and 80.7% respectively. We have also investigated the advantage of using ABP signal in improving the results of false alarm reduction. For this purpose, some biological features are extracted from ABP and used as an extra feature vector. Results show that using ABP signal can improve the performance of the algorithm.
{"title":"Reduction of Ventricular Tachycardia False Alarms Using Multivariate Statistical Process Control and Frequency Analysis","authors":"Amirhossein Safari, M. Mohebbi","doi":"10.1109/ICBME.2018.8703534","DOIUrl":"https://doi.org/10.1109/ICBME.2018.8703534","url":null,"abstract":"In this paper, we present a false alarm reduction algorithm for Ventricular Tachycardia (VT) arrhythmias in intensive care unit (ICU) using multivariate statistical process control (MSPC) and frequency analysis of electrocardiogram (ECG) signal. First, we decompose the ECG signal into three different frequency bands. The ECG beats are detected, and VT beats are labeled. In the next step, several features consist of time domain features, bispectrum features, and Poincaré plot features are extracted from ECG Signal The extracted feature vector of each ECG beat is monitored using MSPC for detecting anomalies. The performance of the proposed method is evaluated using the Ventricular Tachycardia cases of 2015 Physionet challenge database. This dataset consists of 2 ECG channel, arterial blood pressure (ABP) and/or photoplethysmograph (PPG) signal, and an alarm annotation for each record. The obtained sensitivity and specificity were 86.5%, and 80.7% respectively. We have also investigated the advantage of using ABP signal in improving the results of false alarm reduction. For this purpose, some biological features are extracted from ABP and used as an extra feature vector. Results show that using ABP signal can improve the performance of the algorithm.","PeriodicalId":338286,"journal":{"name":"2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126668913","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：