Yanbing Qi

Removal of Ocular Artifacts in EEG—An Improved Approach Combining DWT and ANC for Portable Applications

A new model to remove ocular artifacts (OA) from electroencephalograms (EEGs) is presented. The model is based on discrete wavelet transformation (DWT) and adaptive noise cancellation (ANC). Using simulated and measured data, the accuracy of the model is compared with the accuracy of other existing methods based on stationary wavelet transforms and our previous work based on wavelet packet transform and independent component analysis. A particularly novel feature of the new model is the use of DWTs to construct an OA reference signal, using the three lowest frequency wavelet coefficients of the EEGs. The results show that the new model demonstrates an improved performance with respect to the recovery of true EEG signals and also has a better tracking performance. Because the new model requires only single channel sources, it is well suited for use in portable environments where constraints with respect to acceptable wearable sensor attachments usually dictate single channel devices. The model is also applied and evaluated against data recorded within the EUFP 7 Project-Online Predictive Tools for Intervention in Mental Illness (OPTIMI). The results show that the proposed model is effective in removing OAs and meets the requirements of portable systems used for patient monitoring as typified by the OPTIMI project.

Improving individual identification in security check with an EEG based biometric solution

Security issue is always challenging to the real world applications. Many biometric approaches, such as fingerprint, iris and retina, have been proposed to improve recognizing accuracy or practical facility in individual identification in security. However, there is little research on individual identification using EEG methodology mainly because of the complexity of EEG signal collection and analysis in practice. In this paper, we present an EEG based unobtrusive and non-replicable solution to achieve more practical and accurate in individual identification, and our experiment involving 10 subjects has been conducted to verify this method. The accuracy of 10 subjects can reach at 96.77%. The high-level accuracy result has validated the utility of our solution in the real world. Besides, subject combinations were randomly selected, and the recognizing performance from 3 subjects to 10 subjects can still keep equivalent, which has proven the extendibility of the solution.

A Real-Time Electroencephalogram (EEG) Based Individual Identification Interface for Mobile Security in Ubiquitous Environment

With the booms of mobile communication, especially mobile smart phone, technologies to identify individuals for mobile security calls for some more strict requirements in user-friendly, real-time and ubiquitous aspects. In addition to traditional approaches (for example, password check), some advanced biometric methodologies have been applied in practice, such as fingerprint and iris based solutions, however, these solutions generally lack a true ubiquitous nature for mobile security. In this paper, we present a real time EEG based individual identification interface to support ubiquitous applications. The EEG signals are collected through a mono-polar single channel in real time via a mobile EEG device. An experiment involving about 20 subjects has been conducted to evaluate the interface. The experiment comprises three types of tests: accuracy test, time dimension test and capacity dimension test. The results of these experiments demonstrate that our approach is highly suitable to the demands of mobile security in ubiquitous environment. In addition, we integrate this interface into scenarios of ubiquitous application - Online Predictive Tools for Intervention in Mental Illness (OPTIMI).

AN EEG BASED NONLINEARITY ANALYSIS METHOD FOR SCHIZOPHRENIA DIAGNOSIS

In this paper, the complexity and chaos of EEG (electroencephalogram) signals exhibited in schizophrenic patients are analyzed using four nonlinear features: C0-complexity, Kolmogorov entropy together with an estimation of the correlation dimension and Lempel-Ziv complexity. The first two of these being novel applications of these measures. EEGs from 31 schizophrenic patients (18 males, 13 females, mean age 25.9 ±3.6 years) and 31 age/sex matched control subjects were recorded using 12 electrodes. In a t-test, it was found that all four nonlinear features had a significant variance between the schizophrenics and the control set (p ≤ 0.05). A classification accuracy of 91.7% was obtained by Back Propagation Neural Networks. Our results show that the discrimination of schizophrenic behavior is possible with respect to a control set using nonlinear analysis of EEG signals. We also assert that these methods may be the basis for a valuable tool set of EEG methods that could be used by psychiatrists when diagnosing schizophrenic patients.

Towards an efficient and accurate EEG data analysis in EEG-based individual identification

Individual identification plays an important role in privacy protection and information security. Especially, with the development of brain science, individual identification based on Electroencephalograph (EEG) may be applicable. The key to realize EEG-based identification is to find the signal features with unique individual characteristics in spite of numerous signal processing algorithms and techniques. In this paper, EEG signals of 10 subjects stay in calm were collected from Cz point with eyes closed. Then EEG signal features were extracted by spectrum estimation (linear analysis) and nonlinear dynamics methods and further classified by k-Nearest-Neighbor classifier to identify each subject. Classification successful rate has reached 97.29% with linear features, while it is only 44.14% with nonlinear dynamics features. The experiment result indicates that the linear features of EEG, such as center frequency, max power, power ratio, average peak-to-peak value and coefficients of AR model may have better performance than the nonlinear dynamics parameters of EEG in individual identification.