The Experts below are selected from a list of 46086 Experts worldwide ranked by ideXlab platform
Keumshik Hong - One of the best experts on this subject based on the ideXlab platform.
-
analysis of different classification techniques for two class Functional near infrared Spectroscopy based brain computer interface
Computational Intelligence and Neuroscience, 2016Co-Authors: Noman Naseer, Nauman Khalid Qureshi, Farzan Majeed Noori, Keumshik HongAbstract:We analyse and compare the classification accuracies of six different classifiers for a two-class mental task mental arithmetic and rest using Functional near-Infrared Spectroscopy fNIRS signals. The signals of the mental arithmetic and rest tasks from the prefrontal cortex region of the brain for seven healthy subjects were acquired using a multichannel continuous-wave imaging system. After removal of the physiological noises, six features were extracted from the oxygenated hemoglobin HbO signals. Two- and three-dimensional combinations of those features were used for classification of mental tasks. In the classification, six different modalities, linear discriminant analysis LDA, quadratic discriminant analysis QDA, k-nearest neighbour kNN, the Naive Bayes approach, support vector machine SVM, and artificial neural networks ANN, were utilized. With these classifiers, the average classification accuracies among the seven subjects for the 2- and 3-dimensional combinations of features were 71.6, 90.0, 69.7, 89.8, 89.5, and 91.4% and 79.6, 95.2, 64.5, 94.8, 95.2, and 96.3%, respectively. ANN showed the maximum classification accuracies: 91.4 and 96.3%. In order to validate the results, a statistical significance test was performed, which confirmed that the p values were statistically significant relative to all of the other classifiers p < 0.005 using HbO signals.
-
reduction of delay in detecting initial dips from Functional near infrared Spectroscopy signals using vector based phase analysis
International Journal of Neural Systems, 2016Co-Authors: Keumshik Hong, Noman NaseerAbstract:In this paper, we present a systematic method to reduce the time lag in detecting initial dips using a vector-based phase diagram and an autoregressive moving average with exogenous signals (ARMAX) model-based q-step-ahead prediction algorithm. With Functional near-Infrared Spectroscopy (fNIRS), signals related to mental arithmetic and right-hand clenching are acquired from the prefrontal and left primary motor cortices, respectively. The interrelationship between oxygenated hemoglobin, deoxygenated hemoglobin, total hemoglobin and cerebral oxygen exchange are related to initial dips. Specifically, a threshold value from the resting state hemodynamics is incorporated, as a decision criterion, into the vector-based phase diagram to determine the occurrence of initial dips. To further reduce the time lag, a [Formula: see text]-step-ahead prediction method is applied to predict the occurrence of the dips. A combination of the threshold criterion and the prediction method resulted in the delay time of about 0.9[Formula: see text]s. The results demonstrate that rapid detection of initial dip is possible and therefore can be used for real-time brain-computer interfacing.
-
online binary decision decoding using Functional near infrared Spectroscopy for the development of brain computer interface
Experimental Brain Research, 2014Co-Authors: Noman Naseer, Melissa Jiyoun Hong, Keumshik HongAbstract:In this paper, a Functional near-Infrared Spectroscopy (fNIRS)-based online binary decision decoding framework is developed. Fourteen healthy subjects are asked to mentally make “yes” or “no” decisions in answers to the given questions. For obtaining “yes” decoding, the subjects are asked to perform a mental task that causes a cognitive load on the prefrontal cortex, while for making “no” decoding, they are asked to relax. Signals from the prefrontal cortex are collected using continuous-wave near-Infrared Spectroscopy. It is observed and verified, using the linear discriminant analysis (LDA) and the support vector machine (SVM) classifications, that the cortical hemodynamic responses for making a “yes” decision are distinguishable from those for making a “no” decision. Using mean values of the changes in the concentration of hemoglobin as features, binary decisions are classified into two classes, “yes” and “no,” with an average classification accuracy of 74.28 % using LDA and 82.14 % using SVM. These results demonstrate and suggest the feasibility of fNIRS for a brain–computer interface.
-
reduction of trial to trial variability in Functional near infrared Spectroscopy signals by accounting for resting state Functional connectivity
Journal of Biomedical Optics, 2013Co-Authors: Xiaosu Hu, Keumshik Hong, Shuzhi Sam GeAbstract:The reduction of trial-to-trial variability (TTV) in task-evoked Functional near-Infrared Spectroscopy signals by considering the correlated low-frequency spontaneous fluctuations that account for the resting-state Functional connectivity in the brain is investigated. A resting-state session followed by a task-state session of a right hand finger-tapping task has been performed on five subjects. Significant ipsilateral and bilateral resting-state Functional connectivity has been detected at the subjects’ motor cortex using the seed correlation method. The correlation coefficients obtained during the resting-state are used to reduce the TTV in the signals measured during the task sessions. The results suggest that correlated spontaneous low-frequency fluctuations contribute significantly to the TTV in the task evoked fNIRS signals.
Martin Wolf - One of the best experts on this subject based on the ideXlab platform.
-
a review on continuous wave Functional near infrared Spectroscopy and imaging instrumentation and methodology
NeuroImage, 2014Co-Authors: Felix Scholkmann, Stefan Kleiser, Andreas Jaakko Metz, Raphael Zimmermann, Juan Mata Pavia, Ursula Wolf, Martin WolfAbstract:This year marks the 20th anniversary of Functional near-Infrared Spectroscopy and imaging (fNIRS/fNIRI). As the vast majority of commercial instruments developed until now are based on continuous wave technology, the aim of this publication is to review the current state of instrumentation and methodology of continuous wave fNIRI. For this purpose we provide an overview of the commercially available instruments and address instrumental aspects such as light sources, detectors and sensor arrangements. Methodological aspects, algorithms to calculate the concentrations of oxy- and deoxyhemoglobin and approaches for data analysis are also reviewed. From the single-location measurements of the early years, instrumentation has progressed to imaging initially in two dimensions (topography) and then three (tomography). The methods of analysis have also changed tremendously, from the simple modified Beer-Lambert law to sophisticated image reconstruction and data analysis methods used today. Due to these advances, fNIRI has become a modality that is widely used in neuroscience research and several manufacturers provide commercial instrumentation. It seems likely that fNIRI will become a clinical tool in the foreseeable future, which will enable diagnosis in single subjects.
-
single trial classification of motor imagery differing in task complexity a Functional near infrared Spectroscopy study
Journal of Neuroengineering and Rehabilitation, 2011Co-Authors: Lisa Holper, Martin WolfAbstract:Background For brain computer interfaces (BCIs), which may be valuable in neurorehabilitation, brain signals derived from mental activation can be monitored by non-invasive methods, such as Functional near-Infrared Spectroscopy (fNIRS). Single-trial classification is important for this purpose and this was the aim of the presented study. In particular, we aimed to investigate a combined approach: 1) offline single-trial classification of brain signals derived from a novel wireless fNIRS instrument; 2) to use motor imagery (MI) as mental task thereby discriminating between MI signals in response to different tasks complexities, i.e. simple and complex MI tasks.
-
single trial classification of motor imagery differing in task complexity a Functional near infrared Spectroscopy study
Journal of Neuroengineering and Rehabilitation, 2011Co-Authors: Lisa Holper, Martin WolfAbstract:For brain computer interfaces (BCIs), which may be valuable in neurorehabilitation, brain signals derived from mental activation can be monitored by non-invasive methods, such as Functional near-Infrared Spectroscopy (fNIRS). Single-trial classification is important for this purpose and this was the aim of the presented study. In particular, we aimed to investigate a combined approach: 1) offline single-trial classification of brain signals derived from a novel wireless fNIRS instrument; 2) to use motor imagery (MI) as mental task thereby discriminating between MI signals in response to different tasks complexities, i.e. simple and complex MI tasks. 12 subjects were asked to imagine either a simple finger-tapping task using their right thumb or a complex sequential finger-tapping task using all fingers of their right hand. fNIRS was recorded over secondary motor areas of the contralateral hemisphere. Using Fisher's linear discriminant analysis (FLDA) and cross validation, we selected for each subject a best-performing feature combination consisting of 1) one out of three channel, 2) an analysis time interval ranging from 5-15 s after stimulation onset and 3) up to four Δ[O2Hb] signal features (Δ[O2Hb] mean signal amplitudes, variance, skewness and kurtosis). The results of our single-trial classification showed that using the simple combination set of channels, time intervals and up to four Δ[O2Hb] signal features comprising Δ[O2Hb] mean signal amplitudes, variance, skewness and kurtosis, it was possible to discriminate single-trials of MI tasks differing in complexity, i.e. simple versus complex tasks (inter-task paired t-test p ≤ 0.001), over secondary motor areas with an average classification accuracy of 81%. Although the classification accuracies look promising they are nevertheless subject of considerable subject-to-subject variability. In the discussion we address each of these aspects, their limitations for future approaches in single-trial classification and their relevance for neurorehabilitation.
-
testing the potential of a virtual reality neurorehabilitation system during performance of observation imagery and imitation of motor actions recorded by wireless Functional near infrared Spectroscopy fnirs
Journal of Neuroengineering and Rehabilitation, 2010Co-Authors: Lisa Holper, Thomas Muehlemann, Felix Scholkmann, Kynan Eng, Daniel C Kiper, Martin WolfAbstract:Background Several neurorehabilitation strategies have been introduced over the last decade based on the so-called simulation hypothesis. This hypothesis states that a neural network located in primary and secondary motor areas is activated not only during overt motor execution, but also during observation or imagery of the same motor action. Based on this hypothesis, we investigated the combination of a virtual reality (VR) based neurorehabilitation system together with a wireless Functional near infrared Spectroscopy (fNIRS) instrument. This combination is particularly appealing from a rehabilitation perspective as it may allow minimally constrained monitoring during neurorehabilitative training.
Noman Naseer - One of the best experts on this subject based on the ideXlab platform.
-
enhancing classification performance of Functional near infrared Spectroscopy brain computer interface using adaptive estimation of general linear model coefficients
Frontiers in Neurorobotics, 2017Co-Authors: Nauman Khalid Qureshi, Noman Naseer, Farzan Majeed Noori, Hammad Nazeer, Rayyan Azam Khan, Sajid SaleemAbstract:In this paper, a novel methodology for enhanced classification of Functional near-Infrared Spectroscopy (fNIRS) signals utilizable in a two-class (motor imagery and rest; mental rotation and rest) brain-computer interface (BCI) is presented. First, fNIRS signals corresponding to motor imagery and mental rotation are acquired from the motor and prefrontal cortex respectively afterwards, filtered to remove physiological noises. Then, the signals are modelled using the general linear model (GLM), the coefficients of which are adaptively estimated using the least squares technique. Subsequently, multiple feature combinations of estimated coefficients were used for classification. The best classification accuracies achieved for five subjects, for motor imagery versus rest are 79.5, 83.7, 82.6, 81.4, and 84.1% whereas those for mental rotation versus rest are 85.5, 85.2, 87.8, 83.7, and 84.8%, respectively, using support vector machine (SVM). These results are compared with the best classification accuracies obtained using the conventional hemodynamic response. By means of the proposed methodology, the average classification accuracy obtained was significantly higher (p < 0.05). These results serve to demonstrate the feasibility of developing a high-classification-performance fNIRS-BCI.
-
analysis of different classification techniques for two class Functional near infrared Spectroscopy based brain computer interface
Computational Intelligence and Neuroscience, 2016Co-Authors: Noman Naseer, Nauman Khalid Qureshi, Farzan Majeed Noori, Keumshik HongAbstract:We analyse and compare the classification accuracies of six different classifiers for a two-class mental task mental arithmetic and rest using Functional near-Infrared Spectroscopy fNIRS signals. The signals of the mental arithmetic and rest tasks from the prefrontal cortex region of the brain for seven healthy subjects were acquired using a multichannel continuous-wave imaging system. After removal of the physiological noises, six features were extracted from the oxygenated hemoglobin HbO signals. Two- and three-dimensional combinations of those features were used for classification of mental tasks. In the classification, six different modalities, linear discriminant analysis LDA, quadratic discriminant analysis QDA, k-nearest neighbour kNN, the Naive Bayes approach, support vector machine SVM, and artificial neural networks ANN, were utilized. With these classifiers, the average classification accuracies among the seven subjects for the 2- and 3-dimensional combinations of features were 71.6, 90.0, 69.7, 89.8, 89.5, and 91.4% and 79.6, 95.2, 64.5, 94.8, 95.2, and 96.3%, respectively. ANN showed the maximum classification accuracies: 91.4 and 96.3%. In order to validate the results, a statistical significance test was performed, which confirmed that the p values were statistically significant relative to all of the other classifiers p < 0.005 using HbO signals.
-
reduction of delay in detecting initial dips from Functional near infrared Spectroscopy signals using vector based phase analysis
International Journal of Neural Systems, 2016Co-Authors: Keumshik Hong, Noman NaseerAbstract:In this paper, we present a systematic method to reduce the time lag in detecting initial dips using a vector-based phase diagram and an autoregressive moving average with exogenous signals (ARMAX) model-based q-step-ahead prediction algorithm. With Functional near-Infrared Spectroscopy (fNIRS), signals related to mental arithmetic and right-hand clenching are acquired from the prefrontal and left primary motor cortices, respectively. The interrelationship between oxygenated hemoglobin, deoxygenated hemoglobin, total hemoglobin and cerebral oxygen exchange are related to initial dips. Specifically, a threshold value from the resting state hemodynamics is incorporated, as a decision criterion, into the vector-based phase diagram to determine the occurrence of initial dips. To further reduce the time lag, a [Formula: see text]-step-ahead prediction method is applied to predict the occurrence of the dips. A combination of the threshold criterion and the prediction method resulted in the delay time of about 0.9[Formula: see text]s. The results demonstrate that rapid detection of initial dip is possible and therefore can be used for real-time brain-computer interfacing.
-
online binary decision decoding using Functional near infrared Spectroscopy for the development of brain computer interface
Experimental Brain Research, 2014Co-Authors: Noman Naseer, Melissa Jiyoun Hong, Keumshik HongAbstract:In this paper, a Functional near-Infrared Spectroscopy (fNIRS)-based online binary decision decoding framework is developed. Fourteen healthy subjects are asked to mentally make “yes” or “no” decisions in answers to the given questions. For obtaining “yes” decoding, the subjects are asked to perform a mental task that causes a cognitive load on the prefrontal cortex, while for making “no” decoding, they are asked to relax. Signals from the prefrontal cortex are collected using continuous-wave near-Infrared Spectroscopy. It is observed and verified, using the linear discriminant analysis (LDA) and the support vector machine (SVM) classifications, that the cortical hemodynamic responses for making a “yes” decision are distinguishable from those for making a “no” decision. Using mean values of the changes in the concentration of hemoglobin as features, binary decisions are classified into two classes, “yes” and “no,” with an average classification accuracy of 74.28 % using LDA and 82.14 % using SVM. These results demonstrate and suggest the feasibility of fNIRS for a brain–computer interface.
David A Boas - One of the best experts on this subject based on the ideXlab platform.
-
Functional near infrared Spectroscopy enabling routine Functional brain imaging
Current Opinion in Biomedical Engineering, 2017Co-Authors: Meryem A. Yücel, Maria Angela Franceschini, David A Boas, Theodore J Huppert, Juliette SelbAbstract:Functional near-Infrared Spectroscopy (fNIRS) maps human brain function by measuring and imaging local changes in hemoglobin concentrations in the brain that arise from the modulation of cerebral blood flow and oxygen metabolism by neural activity. Since its advent over 20 years ago, researchers have exploited and continuously advanced the ability of near infrared light to penetrate through the scalp and skull in order to non-invasively monitor changes in cerebral hemoglobin concentrations that reflect brain activity. We review recent advances in signal processing and hardware that significantly improve the capabilities of fNIRS by reducing the impact of confounding signals to improve statistical robustness of the brain signals and by enhancing the density, spatial coverage, and wearability of measuring devices respectively. We then summarize the application areas that are experiencing rapid growth as fNIRS begins to enable routine Functional brain imaging.
-
using prerecorded hemodynamic response functions in detecting prefrontal pain response a Functional near infrared Spectroscopy study
Neurophotonics, 2017Co-Authors: Ke Peng, David A Boas, Christopher M. Aasted, Meryem A. Yücel, David Borsook, Sarah C Steele, Lino BecerraAbstract:Currently, there is no method for providing a nonverbal objective assessment of pain. Recent work using Functional near-Infrared Spectroscopy (fNIRS) has revealed its potential for objective measures. We conducted two fNIRS scans separated by 30 min and measured the hemodynamic response to the electrical noxious and innocuous stimuli over the anterior prefrontal cortex (aPFC) in 14 subjects. Based on the estimated hemodynamic response functions (HRFs), we first evaluated the test–retest reliability of using fNIRS in measuring the pain response over the aPFC. We then proposed a general linear model (GLM)-based detection model that employs the subject-specific HRFs from the first scan to detect the pain response in the second scan. Our results indicate that fNIRS has a reasonable reliability in detecting the hemodynamic changes associated with noxious events, especially in the medial portion of the aPFC. Compared with a standard HRF with a fixed shape, including the subject-specific HRFs in the GLM allows for a significant improvement in the detection sensitivity of aPFC pain response. This study supports the potential application of individualized analysis in using fNIRS and provides a robust model to perform objective determination of pain perception.
-
mayer waves reduce the accuracy of estimated hemodynamic response functions in Functional near infrared Spectroscopy
Biomedical Optics Express, 2016Co-Authors: Meryem A. Yücel, Christopher M. Aasted, Lino Becerra, David Borsook, Juliette Selb, Peiyi Lin, David A BoasAbstract:Analysis of cerebral hemodynamics reveals a wide spectrum of oscillations ranging from 0.0095 to 2 Hz. While most of these oscillations can be filtered out during analysis of Functional near-Infrared Spectroscopy (fNIRS) signals when estimating stimulus evoked hemodynamic responses, oscillations around 0.1 Hz are an exception. This is due to the fact that they share a common spectral range with typical stimulus evoked hemodynamic responses from the brain. Here we investigate the effect of hemodynamic oscillations around 0.1 Hz on the estimation of hemodynamic response functions from fNIRS data. Our results show that for an expected response of ~1 µM in oxygenated hemoglobin concentration (HbO), Mayer wave oscillations with an amplitude > ~1 µM at 0.1 Hz reduce the accuracy of the estimated response as quantified by a 3 fold increase in the mean squared error and decrease in correlation (R2 below 0.78) when compared to the true HRF. These results indicate that the amplitude of oscillations at 0.1 Hz can serve as an objective metric of the expected HRF estimation accuracy. In addition, we investigated the effect of short separation regression on the recovered HRF, and found that this improves the recovered HRF when large amplitude 0.1 Hz oscillations are present in fNIRS data. We suspect that the development of other filtering strategies may provide even further improvement.
-
Anatomical guidance for Functional near-Infrared Spectroscopy: AtlasViewer tutorial
Neurophotonics, 2015Co-Authors: Christopher M. Aasted, Meryem A. Yücel, Robert J. Cooper, Jay Dubb, Daisuke Tsuzuki, Lino Becerra, Mike P. Petkov, David Borsook, Ippeita Dan, David A BoasAbstract:Functional near-Infrared Spectroscopy (fNIRS) is an optical imaging method that is used to noninvasively measure cerebral hemoglobin concentration changes induced by brain activation. Using structural guidance in fNIRS research enhances interpretation of results and facilitates making comparisons between studies. AtlasViewer is an open-source software package we have developed that incorporates multiple spatial registration tools to enable structural guidance in the interpretation of fNIRS studies. We introduce the reader to the layout of the AtlasViewer graphical user interface, the folder structure, and user files required in the creation of fNIRS probes containing sources and detectors registered to desired locations on the head, evaluating probe fabrication error and intersubject probe placement variability, and different procedures for estimating measurement sensitivity to different brain regions as well as image reconstruction performance. Further, we detail how AtlasViewer provides a generic head atlas for guiding interpretation of fNIRS results, but also permits users to provide subject-specific head anatomies to interpret their results. We anticipate that AtlasViewer will be a valuable tool in improving the anatomical interpretation of fNIRS studies.
Shuzhi Sam Ge - One of the best experts on this subject based on the ideXlab platform.
-
reduction of trial to trial variability in Functional near infrared Spectroscopy signals by accounting for resting state Functional connectivity
Journal of Biomedical Optics, 2013Co-Authors: Xiaosu Hu, Keumshik Hong, Shuzhi Sam GeAbstract:The reduction of trial-to-trial variability (TTV) in task-evoked Functional near-Infrared Spectroscopy signals by considering the correlated low-frequency spontaneous fluctuations that account for the resting-state Functional connectivity in the brain is investigated. A resting-state session followed by a task-state session of a right hand finger-tapping task has been performed on five subjects. Significant ipsilateral and bilateral resting-state Functional connectivity has been detected at the subjects’ motor cortex using the seed correlation method. The correlation coefficients obtained during the resting-state are used to reduce the TTV in the signals measured during the task sessions. The results suggest that correlated spontaneous low-frequency fluctuations contribute significantly to the TTV in the task evoked fNIRS signals.
