Pub Date : 2015-12-07DOI: 10.1109/BioCAS.2015.7348420
Kohei Gamo, K. Niitsu, K. Nakazato
A noise-immune current-integration-based CMOS amperometric sensor platform with a bacteria-sized (1.2 μm × 2.05 μm) Au electroless-plated microelectrode array for robust bacteria counting is presented. For robust bacteria counting with sufficient signal-to-noise ratio (SNR), noise must be reduced because the bacteria-sized microelectrode surrounded by a wall can handle only small current (on the order of 100 pA). This is the first platform to employ a current integrator in conjunction with a bacteria-sized microelectrode array. As a result of the proposed current integration, noise associated with drift and the CMOS sensor array can be reduced. To verify the effectiveness of the proposed approach, a test chip was fabricated using 0.6 μm standard CMOS technology. Measurement results demonstrate successful high-sensitivity 2D direct counting of microbeads (1 μm diameter) with 27 dB SNR at 5-ms integration time.
{"title":"Noise-immune current-integration-based CMOS amperometric sensor platform with 1.2 μm × 2.05 μm electroless-plated microelectrode array for robust bacteria counting","authors":"Kohei Gamo, K. Niitsu, K. Nakazato","doi":"10.1109/BioCAS.2015.7348420","DOIUrl":"https://doi.org/10.1109/BioCAS.2015.7348420","url":null,"abstract":"A noise-immune current-integration-based CMOS amperometric sensor platform with a bacteria-sized (1.2 μm × 2.05 μm) Au electroless-plated microelectrode array for robust bacteria counting is presented. For robust bacteria counting with sufficient signal-to-noise ratio (SNR), noise must be reduced because the bacteria-sized microelectrode surrounded by a wall can handle only small current (on the order of 100 pA). This is the first platform to employ a current integrator in conjunction with a bacteria-sized microelectrode array. As a result of the proposed current integration, noise associated with drift and the CMOS sensor array can be reduced. To verify the effectiveness of the proposed approach, a test chip was fabricated using 0.6 μm standard CMOS technology. Measurement results demonstrate successful high-sensitivity 2D direct counting of microbeads (1 μm diameter) with 27 dB SNR at 5-ms integration time.","PeriodicalId":210391,"journal":{"name":"2015 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116946085","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 : 2015-12-07DOI: 10.1109/BioCAS.2015.7348381
Seunghyun Park, Soowon Kang, Hyeyoung Min, Sungroh Yoon
MicroRNAs (miRNAs) play an important role in the post-transcriptional regulation of gene expression by pairing target messenger RNAs (mRNAs). As the abnormal expression of miRNAs has been implicated in various diseases, there has been many studies on regulating the expression level of miRNA, including “miRNA sponges.” miRNA sponges, which are artificial miRNA decoys, contain complementary binding sites to a target miRNA and regulate the expression level of target miRNAs. As competitive endogenous RNAs (ceRNAs) have been found in a recent study, there have been many efforts to find natural miRNA sponges. However, there are no related studies about the computational approach using the pairwise interactions of numerous mRNA-miRNA pairs. In this study, a computational approach to find candidates of natural miRNA sponges is proposed. Whole miRNA binding sites with query miRNA and the secondary structures of reference mRNA are predicted, followed by calulating the adjusted minimum free energy (AMFE) as the total score. We can quantitatively compare the interactions between miRNAs and target mRNAs by using this proposed approach. Thirty viral miRNAs and about 300 of thousands of human mRNAs are used in this study. As a results, the top 20 natural miRNA sponge candidates are recorded. The results are expected to provide appropriate knowledge before in vivo experiments to validate the identification of miRNA sponges.
{"title":"Computational prediction of competitive endogenous RNA","authors":"Seunghyun Park, Soowon Kang, Hyeyoung Min, Sungroh Yoon","doi":"10.1109/BioCAS.2015.7348381","DOIUrl":"https://doi.org/10.1109/BioCAS.2015.7348381","url":null,"abstract":"MicroRNAs (miRNAs) play an important role in the post-transcriptional regulation of gene expression by pairing target messenger RNAs (mRNAs). As the abnormal expression of miRNAs has been implicated in various diseases, there has been many studies on regulating the expression level of miRNA, including “miRNA sponges.” miRNA sponges, which are artificial miRNA decoys, contain complementary binding sites to a target miRNA and regulate the expression level of target miRNAs. As competitive endogenous RNAs (ceRNAs) have been found in a recent study, there have been many efforts to find natural miRNA sponges. However, there are no related studies about the computational approach using the pairwise interactions of numerous mRNA-miRNA pairs. In this study, a computational approach to find candidates of natural miRNA sponges is proposed. Whole miRNA binding sites with query miRNA and the secondary structures of reference mRNA are predicted, followed by calulating the adjusted minimum free energy (AMFE) as the total score. We can quantitatively compare the interactions between miRNAs and target mRNAs by using this proposed approach. Thirty viral miRNAs and about 300 of thousands of human mRNAs are used in this study. As a results, the top 20 natural miRNA sponge candidates are recorded. The results are expected to provide appropriate knowledge before in vivo experiments to validate the identification of miRNA sponges.","PeriodicalId":210391,"journal":{"name":"2015 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117053727","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 : 2015-12-07DOI: 10.1109/BioCAS.2015.7348398
C. Baj-Rossi, A. Cavallini, T. R. Jost, M. Proietti, F. Grassi, G. Micheli, S. Carrara
This paper compares three different biocompatible packaging covers suitable to support full implantation of multi-panel sensors for remote monitoring of metabolism. The three covers have been designed, realized and implanted in mice for 30 days. ATP and neutrophil concentrations have been measured at the implant site after the device was explanted, to assess the level of biocompatibility of the device.
{"title":"Biocompatible packagings for fully implantable multi-panel devices for remote monitoring of metabolism","authors":"C. Baj-Rossi, A. Cavallini, T. R. Jost, M. Proietti, F. Grassi, G. Micheli, S. Carrara","doi":"10.1109/BioCAS.2015.7348398","DOIUrl":"https://doi.org/10.1109/BioCAS.2015.7348398","url":null,"abstract":"This paper compares three different biocompatible packaging covers suitable to support full implantation of multi-panel sensors for remote monitoring of metabolism. The three covers have been designed, realized and implanted in mice for 30 days. ATP and neutrophil concentrations have been measured at the implant site after the device was explanted, to assess the level of biocompatibility of the device.","PeriodicalId":210391,"journal":{"name":"2015 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127173453","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 : 2015-12-07DOI: 10.1109/BioCAS.2015.7348373
C. Patti, S. Shahrbabaki, Chamila Dissanayaka, D. Cvetkovic
Sleep spindle detection using supervised learning methods such as Artificial Neural Networks and Support Vector Machines had been researched in the past. Supervised learning methods such as the above are prone to overfitting problems. In this research paper, we explore the detection of sleep spindles using the Random Forest classifier which is known to over fit data to a much lower extent when compared to other supervised classifiers. The classifier was developed using data from 3 subjects and it was tested on data from 12 subjects from the MASS database. A sensitivity of 71.2% and a specificity of 96.73% was achieved using the random forest classifier.
{"title":"Application of random forest classifier for automatic sleep spindle detection","authors":"C. Patti, S. Shahrbabaki, Chamila Dissanayaka, D. Cvetkovic","doi":"10.1109/BioCAS.2015.7348373","DOIUrl":"https://doi.org/10.1109/BioCAS.2015.7348373","url":null,"abstract":"Sleep spindle detection using supervised learning methods such as Artificial Neural Networks and Support Vector Machines had been researched in the past. Supervised learning methods such as the above are prone to overfitting problems. In this research paper, we explore the detection of sleep spindles using the Random Forest classifier which is known to over fit data to a much lower extent when compared to other supervised classifiers. The classifier was developed using data from 3 subjects and it was tested on data from 12 subjects from the MASS database. A sensitivity of 71.2% and a specificity of 96.73% was achieved using the random forest classifier.","PeriodicalId":210391,"journal":{"name":"2015 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123748447","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 : 2015-12-07DOI: 10.1109/BioCAS.2015.7348331
Y. Jia, Zheyuan Wang, S. Mirbozorgi, Maysam Ghovanloo
In this live demonstration, we present a smart homecage system, called the Enercage-HC, with closed-loop wireless power transmission, wireless communication, and automated tracking and behavior recognition capabilities. Wireless power is delivered in near-field at 13.56 MHz in the FCC-approved ISM-band through an array of coils designed to provide the entire homecage with homogeneous magnetic field. Bidirectional data transmission is accomplished at 2.4 GHz via Bluetooth Low Energy (BLE) for communication with sensors and stimulators attached to or implanted in the animal body. A dual-mode 2D/3D imaging system based on Microsoft Kinect® is used for animal subject tracking and behavioral analysis.
{"title":"Live demonstration: A smart homecage system with behavior analysis and closed-loop optogenetic stimulation capacibilities","authors":"Y. Jia, Zheyuan Wang, S. Mirbozorgi, Maysam Ghovanloo","doi":"10.1109/BioCAS.2015.7348331","DOIUrl":"https://doi.org/10.1109/BioCAS.2015.7348331","url":null,"abstract":"In this live demonstration, we present a smart homecage system, called the Enercage-HC, with closed-loop wireless power transmission, wireless communication, and automated tracking and behavior recognition capabilities. Wireless power is delivered in near-field at 13.56 MHz in the FCC-approved ISM-band through an array of coils designed to provide the entire homecage with homogeneous magnetic field. Bidirectional data transmission is accomplished at 2.4 GHz via Bluetooth Low Energy (BLE) for communication with sensors and stimulators attached to or implanted in the animal body. A dual-mode 2D/3D imaging system based on Microsoft Kinect® is used for animal subject tracking and behavioral analysis.","PeriodicalId":210391,"journal":{"name":"2015 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116030200","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 : 2015-12-07DOI: 10.1109/BioCAS.2015.7348382
G. Bianchi, Fabiola Casasopra, Gianluca Durelli, M. Santambrogio
At the basis of proteins identification we have a string matching algorithm, which has a computational complexity that scales with the length of both the searched and the reference string. This complexity, as well as the fact that to match a single protein we need multiple search of different string in the whole database, makes the protein identification a computational intensive task taking tens of seconds to complete. When performing this task with General Purpose Processors (GPPs), as it might be in a large scale installation (such as medical or research centers), this long execution time translates into a high energy requirement which greatly impacts the scalability and maintenance cost of the system. This paper illustrates a possible way to exploit Field Programmable Gate Arrays (FPGAs) to implement a string matching algorithm with an higher energy efficiency, up to 6 times better, than a standard GPP; such solution can be a building block for large-scale installations aimed at improving protein identification.
{"title":"A hardware approach to protein identification","authors":"G. Bianchi, Fabiola Casasopra, Gianluca Durelli, M. Santambrogio","doi":"10.1109/BioCAS.2015.7348382","DOIUrl":"https://doi.org/10.1109/BioCAS.2015.7348382","url":null,"abstract":"At the basis of proteins identification we have a string matching algorithm, which has a computational complexity that scales with the length of both the searched and the reference string. This complexity, as well as the fact that to match a single protein we need multiple search of different string in the whole database, makes the protein identification a computational intensive task taking tens of seconds to complete. When performing this task with General Purpose Processors (GPPs), as it might be in a large scale installation (such as medical or research centers), this long execution time translates into a high energy requirement which greatly impacts the scalability and maintenance cost of the system. This paper illustrates a possible way to exploit Field Programmable Gate Arrays (FPGAs) to implement a string matching algorithm with an higher energy efficiency, up to 6 times better, than a standard GPP; such solution can be a building block for large-scale installations aimed at improving protein identification.","PeriodicalId":210391,"journal":{"name":"2015 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116521970","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 : 2015-12-07DOI: 10.1109/BioCAS.2015.7348383
Shaojie Su, J. Gao, Zhe Cao, Hong Chen, Zhihua Wang
To minimize the risk of prosthetic impingement after total hip replacement (THR), a novel smart trial is proposed for intraoperative estimation of hip range of motion (ROM) in THR surgery. The smart trial is used to examine the stability, range of motions and risk of dislocation during the surgery, relocate hip implants, and finally will be replaced by real implant prosthesis. The smart trial is composed of a customized femoral head trial with a camera and an inertial measurement unit (IMU) inside, and a customized acetabular cup trial with reference patterns printed on the internal surface. A depth estimation algorithm based on images taken by the camera is designed for the detection of critical regions where impingement or dislocation is about to happen, and an extended Kalman filter is designed for the fusion of the data from IMU to acquire better orientation estimation accuracy. This paper is proof of concept with limited validation through an experimental setup. Simulation results show that the root mean square error (RMSE) of the depth estimation is 1mm and that of the orientation estimation is less than 0.05 degree. The hip ROM is displayed in 3-D mode in real time.
{"title":"Smart trail with camera and inertial measurement unit for intraoperative estimation of hip range of motion in total hip replacement surgery","authors":"Shaojie Su, J. Gao, Zhe Cao, Hong Chen, Zhihua Wang","doi":"10.1109/BioCAS.2015.7348383","DOIUrl":"https://doi.org/10.1109/BioCAS.2015.7348383","url":null,"abstract":"To minimize the risk of prosthetic impingement after total hip replacement (THR), a novel smart trial is proposed for intraoperative estimation of hip range of motion (ROM) in THR surgery. The smart trial is used to examine the stability, range of motions and risk of dislocation during the surgery, relocate hip implants, and finally will be replaced by real implant prosthesis. The smart trial is composed of a customized femoral head trial with a camera and an inertial measurement unit (IMU) inside, and a customized acetabular cup trial with reference patterns printed on the internal surface. A depth estimation algorithm based on images taken by the camera is designed for the detection of critical regions where impingement or dislocation is about to happen, and an extended Kalman filter is designed for the fusion of the data from IMU to acquire better orientation estimation accuracy. This paper is proof of concept with limited validation through an experimental setup. Simulation results show that the root mean square error (RMSE) of the depth estimation is 1mm and that of the orientation estimation is less than 0.05 degree. The hip ROM is displayed in 3-D mode in real time.","PeriodicalId":210391,"journal":{"name":"2015 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122874457","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 : 2015-12-07DOI: 10.1109/BioCAS.2015.7348347
J. B. Romaine, M. Delgado-Restituto
This paper reports a mathematically simple, hardware efficient algorithm for use in the detection of epileptic seizures via an approximation of synchronization between two neural EEG signals. The algorithm assumes that the signals are pre-filtered into a desired narrow band, spanning only several 10's of Hz. Using this narrow band it is possible to collect the discrete time stamps, which are represented as the number of samples between two consecutive minimum within a given signal. The difference between a discrete time stamp in one signal and in another, at a given period in time gives an indication as to the amount of frequency difference between the two signals. Once these differences are accumulated, it provides an estimate as to when large increases and decrease in frequency happen in the two signals, with respect to one another.
{"title":"Hardware friendly algorithm for the calculation of phase synchronization between neural signals","authors":"J. B. Romaine, M. Delgado-Restituto","doi":"10.1109/BioCAS.2015.7348347","DOIUrl":"https://doi.org/10.1109/BioCAS.2015.7348347","url":null,"abstract":"This paper reports a mathematically simple, hardware efficient algorithm for use in the detection of epileptic seizures via an approximation of synchronization between two neural EEG signals. The algorithm assumes that the signals are pre-filtered into a desired narrow band, spanning only several 10's of Hz. Using this narrow band it is possible to collect the discrete time stamps, which are represented as the number of samples between two consecutive minimum within a given signal. The difference between a discrete time stamp in one signal and in another, at a given period in time gives an indication as to the amount of frequency difference between the two signals. Once these differences are accumulated, it provides an estimate as to when large increases and decrease in frequency happen in the two signals, with respect to one another.","PeriodicalId":210391,"journal":{"name":"2015 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"897 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114424097","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 : 2015-12-07DOI: 10.1109/BioCAS.2015.7348449
Amir Mirbeik, Negar Tavassolian
This article numerically verifies ultra-high-resolution confocal millimeter-wave imaging for biomedical applications for the first time. A system with an ultra-wide bandwidth of more than 85 GHz is proposed to provide the ultra-high resolutions required for biomedical imaging applications. The feasibility of detecting early-stage tumors in three dimensions is shown using realistic numerical phantoms. A suitable image formation algorithm is developed and applied to the data. Successful resolution of spherical tumors is achieved in the obtained images both axially and laterally.
{"title":"Ultra-high resolution millimeter-wave imaging for biomedical applications: Feasibility study","authors":"Amir Mirbeik, Negar Tavassolian","doi":"10.1109/BioCAS.2015.7348449","DOIUrl":"https://doi.org/10.1109/BioCAS.2015.7348449","url":null,"abstract":"This article numerically verifies ultra-high-resolution confocal millimeter-wave imaging for biomedical applications for the first time. A system with an ultra-wide bandwidth of more than 85 GHz is proposed to provide the ultra-high resolutions required for biomedical imaging applications. The feasibility of detecting early-stage tumors in three dimensions is shown using realistic numerical phantoms. A suitable image formation algorithm is developed and applied to the data. Successful resolution of spherical tumors is achieved in the obtained images both axially and laterally.","PeriodicalId":210391,"journal":{"name":"2015 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122191223","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 : 2015-12-07DOI: 10.1109/BioCAS.2015.7348368
H. Rajaei, M. Cabrerizo, S. Sargolzaei, Alberto Pinzon-Ardila, S. Gonzalez-Arias, M. Adjouadi
This study proposes a nonlinear data-driven method to delineate Electroencephalogram (EEG) recordings as either coming from controls or patients with epilepsy. This method uses the probability of recurrence and the correlation between electrodes to extract the phase synchronization and the functional connectivity maps of the brain from interictal EEG data recordings. This newly proposed algorithm utilizes probabilistic clustering by extracting graph theoretical features from the calculated functional connectivity matrices. Results reveal that brain connectivity networks of epileptic and control populations show statistically significant differences (t (340) = -37.4771, p<;0.01) between them. Performance results show an accuracy of 92.8% with a sensitivity of 85.7% and a specificity of 100%, when tested on 14 subjects. These preliminary results confirm that this method can be used to enhance and validate diagnosis of epileptic patients from controls using non-invasive scalp EEG signals.
{"title":"Pediatric epilepsy: Clustering by functional connectivity using phase synchronization","authors":"H. Rajaei, M. Cabrerizo, S. Sargolzaei, Alberto Pinzon-Ardila, S. Gonzalez-Arias, M. Adjouadi","doi":"10.1109/BioCAS.2015.7348368","DOIUrl":"https://doi.org/10.1109/BioCAS.2015.7348368","url":null,"abstract":"This study proposes a nonlinear data-driven method to delineate Electroencephalogram (EEG) recordings as either coming from controls or patients with epilepsy. This method uses the probability of recurrence and the correlation between electrodes to extract the phase synchronization and the functional connectivity maps of the brain from interictal EEG data recordings. This newly proposed algorithm utilizes probabilistic clustering by extracting graph theoretical features from the calculated functional connectivity matrices. Results reveal that brain connectivity networks of epileptic and control populations show statistically significant differences (t (340) = -37.4771, p<;0.01) between them. Performance results show an accuracy of 92.8% with a sensitivity of 85.7% and a specificity of 100%, when tested on 14 subjects. These preliminary results confirm that this method can be used to enhance and validate diagnosis of epileptic patients from controls using non-invasive scalp EEG signals.","PeriodicalId":210391,"journal":{"name":"2015 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130327607","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：