Yohei Tomita

A design of the preference acquisition detection system using the EEG

Estimation of emotional states has been multi-disciplinary research interests. Among them, although there are many ways of the estimation such as subjective evaluations and behavioral taxonomy, direct evaluation from the human brain is more reliable. Especially, electroencephalographic (EEG) signal analysis is widely used because of its simplicity and convenience. In our research, emotional states are investigated with a simple electroencephalography which has only one electrode. This device is lighter and cheaper than existing devices. However, its feasibility has yet been proven.

EEG frequency analysis for dozing detection system

It is important to estimate the driver dozing practically. In the conventional study, the electroencephalogram (EEG) has been a promising indicator to driver dozing. Furthermore, it is known that frequency of the EEG is highly related to the sleep and the wake conditions. Therefore, we extract frequency components of the EEG from the whole cerebral cortex, by using the rhythmic component extraction (RCE), proposed by Tanaka et al. RCE extracts a component by combining multi-channel signals with weights that are optimally sought for such that the extracted component maximally contains the power in the frequency range of interest and suppresses that in unnecessary frequencies. As a result, we confirmed the interested frequency power is emphasized. These results imply that this method is available for analyzing the sleeping.

Proposal of ride comfort evaluation method using the EEG

In this study, we propose the ride comfort evaluation method by using the electroencephalography (EEG). Recently, the subjective evaluation method that is questionnaire survey etc. is used for introducing the human sensibility. However, it is not established because of the difficulty of obtaining the human sensibility. Moreover, the objective evaluation method is hoped because the subjective evaluation method has ambiguous criterion by individual, and difference of sensitivity. Therefore, we propose the evaluation method by using the EEG that objective evaluation is possible. In this study, we investigate a ride comfort of car driving. We use the general car and we investigate the ride comfort according to the difference of the tire. The EEG is measured in driving condition. Moreover, the ride comfort subjective evaluation is surveyed by semantic differential method (SD method). The feature of the EEG during the driving and feature of the subjective evaluation is extracted by the factor analysis (FA). From the result, the EEG feature and subjective evaluation feature has correlation. Thus, the effectiveness of the proposed method as an objective evaluation method was shown.

Time-Series Models of the EEG Wearing Overcorrected Glasses

Most people do not notice the overcorrected glasses in daily life. The overcorrected glasses have harmful effects on the eye. Then, these effects are thought to have harmful effects on the brain, too. Therefore, to reveal the effects on the brain by the overcorrection, we analyze electroencephalogram (EEG). At the experiment, the subject played the PC game for 30 minutes (techno-stress) with overcorrected glasses. As the results for time-series analysis and average-variance analysis, the differences of the EEG feature between the correction and the overcorrection are confirmed.

The EEG analysis method for obtaining the feeling

The electroencephalogram (EEG), the brain activity of neurons in the brain, is used to record brain activity for many purposes. It also changes depends on mental conditions because mental conditions are generated in the brain. In this study, we try to estimate the mental conditions by observing the EEG patterns. The EEG data caused by mental changes is obtained as giving the subjects animal assisted therapy. The method for estimation is AdaBoosting as the neural network. We set the input vector as EEG changes and output vector is set as mental changes. Subjects are 25 people: 19 males and 6 females (age: 21-24 years old). Previous study reveals the correlation between the EEG and the activeness, and between the EEG and the tiredness. Therefore, in this paper, we try to estimate these mental parameters by the EEG at the first step.

Dimension reduction of RCE signal by PCA and LPP for estimation of the sleeping

Irregular hour and suffering from stress cause driver doze and falling asleep during important situations. Therefore, it is necessary to know the mechanism of the sleeping. In this study, we distinct the sleep conditions by the rhythmic component extraction (RCE). By using this method, a particular EEG component is extracted as the weighted sum of multi-channel signals. This component concentrates the energy in a certain frequency range. Furthermore, when the weight of a specific channel is high, this channel is thought to be significant for extracting a focused frequency range. Therefore, the sleep conditions are analyzed by the power and the weight of RCE. As for weight analysis, the principal component analysis (PCA) and the locality preserving projection (LPP) are used to reduce the dimension. In the experiment, we measure the EEG in two conditions (before and during the sleeping). Comparing these EEGs by the RCE, the power of the alpha wave component decreased during the sleeping and the theta power increased. The weight distributions under two conditions did not significantly differ. It is to be solved in the further study.

Discrimination of the Sleeping EEG by the Adaptive Rhythmic Component Extraction

It is crucial to practically estimate the driver dozing. For this purpose, the analysis of the frequency components of the electroencephalogram (EEG) is accepted as the most favorable. Therefore, we propose to extract the frequency components of the EEG, by using the rhythmic component extraction (RCE), proposed by Tanaka et al. First of all, we analyze differences of power spectrum among the channels. As this result, the recognition accuracy between the sleeping and the waking when the frontal lobe is used is 76.9%. In addition, we distinct the EEG data by using weight features of the RCE. As results, the accuracy is up to 94.1%. It is shown the effectiveness of the weight analysis. Therefore, there is possibility that we can extract effective electrodes by the RCE weights.

Riding condition extraction system by the EEG analysis

In this paper, we propose the electroencephalography (EEG) feature extraction method of the change in riding comfort according to the difference of the tire. It is a proposal of the objective evaluation technique. The feature of the EEG during the driving is extracted by the factor analysis. Moreover, the correlation between the subjective evaluation and the detected features of EEG is calculated. Then, the effectiveness of the proposed method as a objective evaluation technique was shown from the result.

The classification system with the evolutionary computation

The purpose of this paper is to obtain the object. In particular, we focus on the face detection. By using the proposed method, we recognize faces with a near-infrared (NIR) camera. The face detection that used images from the NIR camera is comparatively difficult to be done, because they are gray scale images. In this paper, the filter by using the GA is designed for the purpose of getting the faces. The method of detecting faces and the position from the NIR images is proposed in the on-line image. It is demonstrated that our approach is effective for vehicle driver monitoring. Finally, it was confirmed that the proposed method works well.

Analysis of the EEG during the sleeping by the rhythmic component extraction

In this experiment, we record the EEG data during the sleeping and the awakening for the drowsiness cognition. As is well known, analyzing the frequency components of the EEG is important for the sleeping. There are many studies to analyze the EEG frequency data for recognizing the sleeping quality, and so on. However, there is no established method for the analysis of the sleeping EEG. From these reason, we are going to apply the rhythmic component extraction (RCE), proposed by Tanaka et al., to extract the rhythmic component in the brain. RCE finds a component extracted by using a weighted sum of observed channel signals. The weights are optimized by maximizing the power in a certain frequency range of interest. In the experiment, the subjects lie back, relax in a chair, and sleep. We take the EEG recording at 30 channels. From the results, the EEG features, such as the alpha and the theta wave, are different between the sleeping and the waking. These rhythmic components are extracted by the Fourier transform and the RCE. By using the RCE, we confirmed the alpha wave and the theta wave when they are not extracted in a single channel signal. Furthermore, we confirmed the effective measurement locations by analyzing the RCE weights.