Lanlan Chen

A framework on wavelet-based nonlinear features and extreme learning machine for epileptic seizure detection

Abstract Background Many investigations based on nonlinear methods have been carried out for the research of seizure detection. However, some of these nonlinear measures cannot achieve satisfying performance without considering the basic rhythms of epileptic EEGs. New method To overcome the defects, this paper proposed a framework on wavelet-based nonlinear features and extreme learning machine (ELM) for the seizure detection. Three nonlinear methods, i.e., approximate entropy (ApEn), sample entropy (SampEn) and recurrence quantification analysis (RQA) were computed from orignal EEG signals and corresponding wavelet decomposed sub-bands separately. The wavelet-based energy was measured as the comparative. Then the combination of sub-band features was fed to ELM and SVM classifier respectively. Results The decomposed sub-band signals show significant discrimination between interictal and ictal states and the union of sub-band features helps to achieve better detection. All the three nonlinear methods show higher sensitivity than the wavelet-based energy analysis using the proposed framework. The wavelet-based SampEn-ELM detector reaches the best performance with a sensitivity of 92.6% and a false detection rate (FDR) of 0.078. Compared with SVM, the ELM detector is better in terms of detection accuracy and learning efficiency. Comparison with existing method(s) The decomposition of original signals into sub-bands leads to better identification of seizure events compared with that of the existing nonlinear methods without considering the time–frequency decomposition. Conclusions The proposed framework achieves not only a high detection accuracy but also a very fast learning speed, which makes it feasible for the further development of the automatic seizure detection system.

A new quantitative evaluation method of Parkinson's disease based on free spiral drawing

Parkinsons disease is a common disease of central nervous system among the elderly, and its complex symptoms bring some difficulties for the clinical diagnosis. In this study, a new method based on free spiral drawing was proposed to for quantitative evaluation of hand movement of patients with Parkinsons disease. According to the characteristics of hand movement in free spiral drawing, a set of parameters were defined and calculated. Experimental results showed that this method of evaluation was consistent with the clinical diagnosis. The proposed method based on free spiral drawing is effective in clinical diagnosis, and it provides a basis for quantitative evaluating the effectiveness of surgery and treatment.

Systematic Evaluation of Relaxation Circumstances Based on Bio-neurological Signals

The widespread use of relaxation technique amongst medicine community and sustained work environments makes a more complete understanding of its physiological effects. This research proposes a systematic evaluation for relaxation circumstances, which consists of subjective evidence and objective evidence. Innovative feature of this evaluation system is adding bio-neurological signals to support previous findings about relaxation circumstances. A work-rest schedule containing mental calculation and music relaxation is specially designed to reflect effect of prolonged cognitive work and relaxation in mental work environments. The results indicate that short period of music relaxation in sustained mental work is effective to counteract the accumulation of mental fatigue and improve work efficiency. This systematic evaluation method can be widely applicable, in medical fields, working environments and daily life for the purpose of prediction, detection and evaluation of human states.

Comfortable environments for mental work by suitable work-rest schedule: Mental fatigue and relaxation

Sustained mental work easily causes mental fatigue. Comfortable environments are necessary to be introduced into mental work. It is very practical research to explore the characteristics under progressive mental fatigue and make a suitable work-rest schedule. In this research, a work-rest schedule containing mental calculation task and music relaxation is specially designed to reflect effect of prolonged cognitive work and relaxation factors in mental work environments. An integrated design and evaluation system for human fatigue-relaxation research is proposed, which consisted of subjective evidence (visual analogue scale) and objective evidence (calculation performance and bio-neurological signals especially EEG signals). The results from subjective evidence and objective evidence indicate that a short break of music relaxation (e.g. 15 minutes) in sustained mental work can successfully counteract the accumulation of mental fatigue and improve work efficiency. EEG analysis supports the music function from bio-neurological point of view. Suitable work-rest schedule has widespread application in boarder population and various situations to alleviate the impact of every life and improve life satisfaction.

EEG Feature Extraction During Mental Fatigue and Relaxation by Principal Component Analysis

EEG is one of the most predictive and reliable measurements for mental fatigue and relaxation evaluation. The aim of this study is to transform a number of EEG spectrum variables into few principal components using PCA method. After transformation, EEG multivariate dataset can be visualized in a lower-dimensional space where different mental states are clearly discriminated from each other.

Recognition of Epileptic EEG Using Support Vector Machines

A new approach based on support vector machine (SVM) is presented for the recognition of epileptic EEG. Firstly, the original signals of normal and epileptic EEG are decomposed with multi-resolution wavelet analysis. Secondly, their approximate entropy (ApEn) is estimated to extract features from raw EEG data. Finally, a SVM classifier with a Gaussian kernel function of SVM is used for the classification. Simulation results demonstrated that the SVM combined with wavelet transform and ApEn achieves high recognition accuracies.

Automatic recognition of epileptic discharges based on shape similarity in time-domain

Abstract Background Epilepsy is a common neurological disease, and electroencephalogram (EEG) contains massive epilepsy information. Automatic recognition of epileptic discharges has great significance in diagnosis of epilepsy. New method This paper proposes a novel automatic recognition of epileptic waves method in EEG signals based on shape similarity in time-series sequence directly. Merger of the increasing and decreasing sequences (MIDS) was used to improve the recognition accuracy and reduce the computation cost. Then shape templates were designed, and the modified Hausdorff distance was employed to measure the shape similarity of waveforms in template matching part. This approach imitates human visual cognitive process to analyze EEG and employs image recognition method into one-dimensional signals, which is a direct, original and effective method. Results 373 epileptic discharge fragments marked by clinicians from 20 patients’ EEG recordings were selected. By fusing significance rules, 98.39% of them were recognized, with the false recognition rate 1.1%. Comparison with existing methods Experimental results indicate that the proposed approach yielded better performance for interictal epileptiform discharges (IEDS) recognition compared with the previous methods. Conclusions The proposed approach has good performance and high stability in automatic recognition of epileptic discharges both in ictal and interictal period, which could support the diagnosis of epilepsy greatly.

Investigation of Mental Fatigue Induced by a Continuous Mental Arithmetic Task Based on EEG Coherence Analysis

In the present study, twelve volunteers were participated in a 2 h continuous mental arithmetic task without any break, which was designed to induce mental fatigue. The negative influence was investigated through EEG coherence, which was used as a measure of synchronization of different underlying brain regions. It was observed that the sustained mental task led to increased EEG coherence, which did not result in more efficient performance. The change of EEG coherence was widespread not limited to specific brain regions or frequency bands. The variation of EEG coherence combined with behavior performance validated the impact of mental fatigue caused by a continuous mental task.

A New Support Vector Machine Algorithm with Scalable Penalty Coefficients for Training Samples

In this paper, a new method to determine the penalty coefficients for different samples for the support vector machine (SVM) algorithm was proposed. Sequential minimal optimization (SMO) was then used to solve the SVM problem. Simulation results from applying the proposed method to binary classification problems show that the generalization error of the proposed method was smaller than standard SVM algorithm in the cases that the sizes of binary sample training sets (1) were selected in proportion; (2) were the same; (3) were quite different.

Effect Evaluation of Relaxation Training Based on Nonlinear Parameters of Electroencephalogram Waves

The purpose of this study is to evaluate the effect of music relaxation and to explore the relationship among visual analog scales, behavior performance and electroencephalogram (EEG) analysis. In the experiments, subjects did mental arithmetic until felt fatigued and then relaxed by listening to classical music. In order to analyze EEG signals, two nonlinear parameters L-Z complexity and approximate entropy were calculated. It was found that different brain states had different nonlinear characteristics.