The Experts below are selected from a list of 4473 Experts worldwide ranked by ideXlab platform
Niels Birbaumer - One of the best experts on this subject based on the ideXlab platform.
-
Electrooculogram based sleep stage classification using deep belief network
2015 International Joint Conference on Neural Networks (IJCNN), 2015Co-Authors: Qianyun Li, Jingyi Wang, Ujwal Chaudhary, Ander Ramos-murguialday, Niels BirbaumerAbstract:In this work, we used single Electrooculogram (EOG) signal to perform automatic sleep scoring. Deep belief network (DBN) and combination of DBN and Hidden Markov Models (HMM) are employed to discriminate sleep stages. Under the leave-one-out protocol, the average accuracy of DBN and DBN-HMM are 77.7% and 83.3% for all sleep stages, respectively. On the other hand, we found the EOG signal not only contribute to identify stages of Awake and rapid eye movement, also contribute to discriminate stage 2 and slow wave sleep stage.
-
IJCNN - Electrooculogram based sleep stage classification using deep belief network
2015 International Joint Conference on Neural Networks (IJCNN), 2015Co-Authors: Qianyun Li, Jingyi Wang, Ujwal Chaudhary, Ander Ramos-murguialday, Niels BirbaumerAbstract:In this work, we used single Electrooculogram (EOG) signal to perform automatic sleep scoring. Deep belief network (DBN) and combination of DBN and Hidden Markov Models (HMM) are employed to discriminate sleep stages. Under the leave-one-out protocol, the average accuracy of DBN and DBN-HMM are 77.7% and 83.3% for all sleep stages, respectively. On the other hand, we found the EOG signal not only contribute to identify stages of Awake and rapid eye movement, also contribute to discriminate stage 2 and slow wave sleep stage.
Anwesha Banerjee - One of the best experts on this subject based on the ideXlab platform.
-
effect of audio cue on Electrooculogram based eye movement analysis of visual memory recall
2015Co-Authors: Anwesha Banerjee, Shreyasi Datta, D N TibarewalaAbstract:Context aware ubiquitous computing systems are capable of assisting people by sensing human cognitive context. In this work, visual memory recall of human beings is identified by analysing their eye movements. Electrooculogram signals, potential difference produced in the surrounding region of eye socket for eye ball movement, are recorded to collect eye movement data. Electrooculogram signals while viewing ‘repeated’ and ‘non-repeated’ visual stimuli were classified for ‘with’ and ‘without’ audio cue sections. Adaptive autoregressive parameters, power spectral density, Hjorth parameters and wavelet coefficients are extracted from these signals as features. A combined feature space is formed comprising all four signal features. A maximum accuracy of 88.70 % is obtained on an average over five participating subjects using SVM-RBF classifier for ‘without audio’ visual memory recall. From this study, it is evident that this auditory effect leaves an impact on EOG signal patterns so that to make reduction in the recognition performance.
-
Electrooculogram based detection of visual memory recall process
2014 International Conference on Communication and Signal Processing, 2014Co-Authors: Anwesha Banerjee, Shreyasi Datta, Amit Konar, D N Tibarewala, R. JanarthananAbstract:Detection of visual memory recall finds applications in context aware ubiquitous computing systems capable of assisting people with memory oblivion. The present work is aimed at identification of visual memory recall of human beings from the analysis of their eye movements through Electrooculogram signals. These signals are represented through Adaptive Autoregressive Parameters, Power Spectral Density, Hjorth Parameters and Wavelet Coefficients as signal features. Classification of the obtained feature spaces is carried out using Support Vector Machine with Radial Basis Function Kernel, K-Nearest Neighbour and Naïve Bayes classifiers to distinctly identify previously seen and new images from a series of images presented as visual stimuli. Performance of classification is evaluated in terms of classification accuracy, sensitivity and specificity. A maximum accuracy of 89.50% is obtained on an average over ten participating subjects using SVM-RBF classifier on a combined feature space comprising all four signal features.
-
Electrooculogram based cognitive context recognition
International Conference on Electronics Communication and Instrumentation (ICECI), 2014Co-Authors: Shreyasi Datta, Anwesha Banerjee, Amit Konar, D N TibarewalaAbstract:Recognition of cognitive context is an important aspect of context aware pervasive computing systems. The present work is aimed at identification of cognitive contexts of human beings from the analysis of their eye movements by acquiring Electrooculogram signals. These signals are represented through Adaptive Autoregressive Parameters, Hjorth Parameters and Wavelet Coefficients as signal features. Classification of the obtained feature spaces is carried out using Support Vector Machine with Radial Basis Function Kernel to distinctly identify a particular class of activity defining a person's cognitive context, achieving an average recognition accuracy of 91.825% for eight types of cognitive activities.
-
cognitive activity recognition based on Electrooculogram analysis
2014Co-Authors: Anwesha Banerjee, Shreyasi Datta, Amit Konar, D N Tibarewala, Janarthanan RamadossAbstract:This work is aimed at identification of human cognitive activities from the analysis of their eye movements using Electrooculogram signals. These signals are represented through Adaptive Autoregressive Parameters, Wavelet Coefficients, Power Spectral Density and Hjorth Parameters as signal features. To distinctly identify a particular class of cognitive activity, the obtained feature spaces are classified using Support Vector Machine with Radial Basis Function Kernel. An average accuracy of 90.39% for recognition of eight types of cognitive activities has been achieved in a one-versus-all classification approach.
-
classifying Electrooculogram to detect directional eye movements
Procedia Technology, 2013Co-Authors: Anwesha Banerjee, Shreyasi Datta, Amit Konar, D N Tibarewala, R JanarthananAbstract:Human computer interfaces that can be controlled by eye movements may be used as intelligent rehabilitation aids. Electrooculogram (EOG), the bio-potential produced around eyes due to eye ball motion can be used to track eye movements. This paper presents a comparative study of different methods for Electrooculogram classification to utilize it to control rehabilitation aids. Electrooculogram is acquired with a designed data acquisition system and different signal features are extracted. Those features are used to classify the movements of the eyeball in horizontal and vertical direction. Based on these classified signals control commands can be generated for human computer interface.
D N Tibarewala - One of the best experts on this subject based on the ideXlab platform.
-
effect of audio cue on Electrooculogram based eye movement analysis of visual memory recall
2015Co-Authors: Anwesha Banerjee, Shreyasi Datta, D N TibarewalaAbstract:Context aware ubiquitous computing systems are capable of assisting people by sensing human cognitive context. In this work, visual memory recall of human beings is identified by analysing their eye movements. Electrooculogram signals, potential difference produced in the surrounding region of eye socket for eye ball movement, are recorded to collect eye movement data. Electrooculogram signals while viewing ‘repeated’ and ‘non-repeated’ visual stimuli were classified for ‘with’ and ‘without’ audio cue sections. Adaptive autoregressive parameters, power spectral density, Hjorth parameters and wavelet coefficients are extracted from these signals as features. A combined feature space is formed comprising all four signal features. A maximum accuracy of 88.70 % is obtained on an average over five participating subjects using SVM-RBF classifier for ‘without audio’ visual memory recall. From this study, it is evident that this auditory effect leaves an impact on EOG signal patterns so that to make reduction in the recognition performance.
-
Electrooculogram based detection of visual memory recall process
2014 International Conference on Communication and Signal Processing, 2014Co-Authors: Anwesha Banerjee, Shreyasi Datta, Amit Konar, D N Tibarewala, R. JanarthananAbstract:Detection of visual memory recall finds applications in context aware ubiquitous computing systems capable of assisting people with memory oblivion. The present work is aimed at identification of visual memory recall of human beings from the analysis of their eye movements through Electrooculogram signals. These signals are represented through Adaptive Autoregressive Parameters, Power Spectral Density, Hjorth Parameters and Wavelet Coefficients as signal features. Classification of the obtained feature spaces is carried out using Support Vector Machine with Radial Basis Function Kernel, K-Nearest Neighbour and Naïve Bayes classifiers to distinctly identify previously seen and new images from a series of images presented as visual stimuli. Performance of classification is evaluated in terms of classification accuracy, sensitivity and specificity. A maximum accuracy of 89.50% is obtained on an average over ten participating subjects using SVM-RBF classifier on a combined feature space comprising all four signal features.
-
Electrooculogram based cognitive context recognition
International Conference on Electronics Communication and Instrumentation (ICECI), 2014Co-Authors: Shreyasi Datta, Anwesha Banerjee, Amit Konar, D N TibarewalaAbstract:Recognition of cognitive context is an important aspect of context aware pervasive computing systems. The present work is aimed at identification of cognitive contexts of human beings from the analysis of their eye movements by acquiring Electrooculogram signals. These signals are represented through Adaptive Autoregressive Parameters, Hjorth Parameters and Wavelet Coefficients as signal features. Classification of the obtained feature spaces is carried out using Support Vector Machine with Radial Basis Function Kernel to distinctly identify a particular class of activity defining a person's cognitive context, achieving an average recognition accuracy of 91.825% for eight types of cognitive activities.
-
cognitive activity recognition based on Electrooculogram analysis
2014Co-Authors: Anwesha Banerjee, Shreyasi Datta, Amit Konar, D N Tibarewala, Janarthanan RamadossAbstract:This work is aimed at identification of human cognitive activities from the analysis of their eye movements using Electrooculogram signals. These signals are represented through Adaptive Autoregressive Parameters, Wavelet Coefficients, Power Spectral Density and Hjorth Parameters as signal features. To distinctly identify a particular class of cognitive activity, the obtained feature spaces are classified using Support Vector Machine with Radial Basis Function Kernel. An average accuracy of 90.39% for recognition of eight types of cognitive activities has been achieved in a one-versus-all classification approach.
-
classifying Electrooculogram to detect directional eye movements
Procedia Technology, 2013Co-Authors: Anwesha Banerjee, Shreyasi Datta, Amit Konar, D N Tibarewala, R JanarthananAbstract:Human computer interfaces that can be controlled by eye movements may be used as intelligent rehabilitation aids. Electrooculogram (EOG), the bio-potential produced around eyes due to eye ball motion can be used to track eye movements. This paper presents a comparative study of different methods for Electrooculogram classification to utilize it to control rehabilitation aids. Electrooculogram is acquired with a designed data acquisition system and different signal features are extracted. Those features are used to classify the movements of the eyeball in horizontal and vertical direction. Based on these classified signals control commands can be generated for human computer interface.
Koichi Tanno - One of the best experts on this subject based on the ideXlab platform.
-
gaze estimation method using analysis of Electrooculogram signals and kinect sensor
Computational Intelligence and Neuroscience, 2017Co-Authors: Keiko Sakurai, Koichi Tanno, Hiroki TamuraAbstract:A gaze estimation system is one of the communication methods for severely disabled people who cannot perform gestures and speech. We previously developed an eye tracking method using a compact and light Electrooculogram (EOG) signal, but its accuracy is not very high. In the present study, we conducted experiments to investigate the EOG component strongly correlated with the change of eye movements. The experiments in this study are of two types: experiments to see objects only by eye movements and experiments to see objects by face and eye movements. The experimental results show the possibility of an eye tracking method using EOG signals and a Kinect sensor.
-
A study on gaze estimation system using the direction of eyes and face
2016 World Automation Congress (WAC), 2016Co-Authors: Keiko Sakurai, Hiroki Tamura, Koichi TannoAbstract:The aim of this study is to present Electrooculogram signals and Kinect sensor (RGB-D sensor) that can be used as a human interface efficiently. The gaze estimation using eyes and face is also important in study for preventing traffic accidents. In this paper, we introduce eye movement tracking system using cross-channels Electrooculogram signals and RGB-D sensor for face tracking. Thus, gaze estimation system can be established by both eye movement and face tracking. In order to confirm the effectiveness of our proposal system, we tried the experiments in an environment in which the experimental subjects can move freely eyes and head. As the results of the experiments, angle of 30°, 60°,-30°,-60° gaze estimation is recognized with high accuracy in our system. In addition, the identification rate of each angle is also high accuracy.
-
A study on human interface system using the direction of eyes and face
Artificial Life and Robotics, 2015Co-Authors: Keiko Sakurai, Hiroki Tamura, Kazuhiko Inami, Koichi TannoAbstract:Establishing an efficient alternative channel for communication without overt speech and hand movements is important for increasing the quality of life for patients lacking correct limb and facial muscular responses. This paper presents the eye movement tracking system using cross-channel Electrooculogram signals. In addition, we used Kinect sensor (RGB-D sensor) for face tracking. Thus, gaze estimation system can be established by both eye movement and face tracking. Simulation experiments were designed in order to confirm the effectiveness of the proposed system. As a result of simulation experiments, gaze position estimation is recognized under high accuracy in our system.
-
ICGEC (2) - A Study on Human Interface for Communication Using Electrooculogram Signals
Advances in Intelligent Systems and Computing, 2015Co-Authors: Kazuya Gondou, Hiroki Tamura, Koichi TannoAbstract:Human interface using eyes for a person with disabilities has been researched. Almost ALS (Amyotrophic Lateral Sclerosis) patient can move facial muscle and eyeball. Therefore, human interface using eyes is the communication tool for a person with disabilities. Human interface is very important when aiming at improvement of quality of life. There are various gaze recognition methods. For example, camera [1] and search coil method [2] are general techniques. In this paper, we propose a human interface for communication using Electrooculogram method by 4 electrodes. From the simulation results, our system has high accuracy of eyes pattern classification.
-
development of mouse cursor control system using dc and ac elements of Electrooculogram signals and its applications
International Journal of Intelligent Computing in Medical Sciences & Image Processing, 2013Co-Authors: Hiroki Tamura, Koichi Tanno, Masaki Miyashita, Takao Manabe, Yasufumi FuseAbstract:The aim of this study is to present Electrooculogram signals that can be used for human computer interface efficiently. Establishing an efficient alternative channel for communication without overt speech and hand movements is important to increase the quality of life for patients suffering from Amyotrophic Lateral Sclerosis or other illnesses that prevent correct limb and facial muscular responses. Using Electrooculogram signals, it is possible to improve the communication abilities of those patients who can move their eyes. In this paper, we introduce the mouse cursor control system for Amyotrophic Lateral Sclerosis patients using Electrooculogram signals. We propose the algorithm using alternating current and direct current of Electrooculogram signals corresponding to the baseline drift problem. The focus of our proposal system was laid on noise, baseline drift and eye blink artifact removal. In order to test the effectiveness of our proposal system, we tried the experiments of the Alphabet sentence in...
Qianyun Li - One of the best experts on this subject based on the ideXlab platform.
-
Electrooculogram based sleep stage classification using deep belief network
2015 International Joint Conference on Neural Networks (IJCNN), 2015Co-Authors: Qianyun Li, Jingyi Wang, Ujwal Chaudhary, Ander Ramos-murguialday, Niels BirbaumerAbstract:In this work, we used single Electrooculogram (EOG) signal to perform automatic sleep scoring. Deep belief network (DBN) and combination of DBN and Hidden Markov Models (HMM) are employed to discriminate sleep stages. Under the leave-one-out protocol, the average accuracy of DBN and DBN-HMM are 77.7% and 83.3% for all sleep stages, respectively. On the other hand, we found the EOG signal not only contribute to identify stages of Awake and rapid eye movement, also contribute to discriminate stage 2 and slow wave sleep stage.
-
IJCNN - Electrooculogram based sleep stage classification using deep belief network
2015 International Joint Conference on Neural Networks (IJCNN), 2015Co-Authors: Qianyun Li, Jingyi Wang, Ujwal Chaudhary, Ander Ramos-murguialday, Niels BirbaumerAbstract:In this work, we used single Electrooculogram (EOG) signal to perform automatic sleep scoring. Deep belief network (DBN) and combination of DBN and Hidden Markov Models (HMM) are employed to discriminate sleep stages. Under the leave-one-out protocol, the average accuracy of DBN and DBN-HMM are 77.7% and 83.3% for all sleep stages, respectively. On the other hand, we found the EOG signal not only contribute to identify stages of Awake and rapid eye movement, also contribute to discriminate stage 2 and slow wave sleep stage.