Shang-Lin Wu

Controlling a Human–Computer Interface System With a Novel Classification Method that Uses Electrooculography Signals

Electrooculography (EOG) signals can be used to control human-computer interface (HCI) systems, if properly classified. The ability to measure and process these signals may help HCI users to overcome many of the physical limitations and inconveniences in daily life. However, there are currently no effective multidirectional classification methods for monitoring eye movements. Here, we describe a classification method used in a wireless EOG-based HCI device for detecting eye movements in eight directions. This device includes wireless EOG signal acquisition components, wet electrodes and an EOG signal classification algorithm. The EOG classification algorithm is based on extracting features from the electrical signals corresponding to eight directions of eye movement (up, down, left, right, up-left, down-left, up-right, and down-right) and blinking. The recognition and processing of these eight different features were achieved in real-life conditions, demonstrating that this device can reliably measure the features of EOG signals. This system and its classification procedure provide an effective method for identifying eye movements. Additionally, it may be applied to study eye functions in real-life conditions in the near future.

A Novel 16-Channel Wireless System for Electroencephalography Measurements With Dry Spring-Loaded Sensors

Understanding brain function using electroencephalography (EEG) is an important issue for cerebral nervous system diseases, especially for epilepsy and Alzheimers disease. Many EEG measurement systems are used reliably to study these diseases, but their bulky size and the use of wet sensors make them uncomfortable and inconvenient for users. To overcome the limitations of conventional EEG measurement systems, a wireless and wearable multichannel EEG measurement system is proposed in this paper. This system includes a wireless data acquisition device, dry spring-loaded sensors, and a size-adjustable soft cap. We compared the performance of the proposed system using dry versus conventional wet sensors. A significant positive correlation between readings from wet and dry sensors was achieved, thus demonstrating the performance of the system. Moreover, four different features of EEG signals (i.e., normal, eye-blinking, closed-eyes, and teeth-clenching signals) were measured by 16 dry sensors to ensure that they could be detected in real-life cognitive neuroscience applications. Thus, we have shown that it is possible to reliably measure EEG signals using the proposed system. This paper presents novel insights into the field of cognitive neuroscience, showing the possibility of studying brain function under real-life conditions.

Brain Dynamics in Predicting Driving Fatigue Using a Recurrent Self-Evolving Fuzzy Neural Network

This paper proposes a generalized prediction system called a recurrent self-evolving fuzzy neural network (RSEFNN) that employs an on-line gradient descent learning rule to address the electroencephalography (EEG) regression problem in brain dynamics for driving fatigue. The cognitive states of drivers significantly affect driving safety; in particular, fatigue driving, or drowsy driving, endangers both the individual and the public. For this reason, the development of brain-computer interfaces (BCIs) that can identify drowsy driving states is a crucial and urgent topic of study. Many EEG-based BCIs have been developed as artificial auxiliary systems for use in various practical applications because of the benefits of measuring EEG signals. In the literature, the efficacy of EEG-based BCIs in recognition tasks has been limited by low resolutions. The system proposed in this paper represents the first attempt to use the recurrent fuzzy neural network (RFNN) architecture to increase adaptability in realistic EEG applications to overcome this bottleneck. This paper further analyzes brain dynamics in a simulated car driving task in a virtual-reality environment. The proposed RSEFNN model is evaluated using the generalized cross-subject approach, and the results indicate that the RSEFNN is superior to competing models regardless of the use of recurrent or nonrecurrent structures.

An Interval Type-2 Neural Fuzzy System for Online System Identification and Feature Elimination

We propose an integrated mechanism for discarding derogatory features and extraction of fuzzy rules based on an interval type-2 neural fuzzy system (NFS)-in fact, it is a more general scheme that can discard bad features, irrelevant antecedent clauses, and even irrelevant rules. High-dimensional input variable and a large number of rules not only enhance the computational complexity of NFSs but also reduce their interpretability. Therefore, a mechanism for simultaneous extraction of fuzzy rules and reducing the impact of (or eliminating) the inferior features is necessary. The proposed approach, namely an interval type-2 Neural Fuzzy System for online System Identification and Feature Elimination (IT2NFS-SIFE), uses type-2 fuzzy sets to model uncertainties associated with information and data in designing the knowledge base. The consequent part of the IT2NFS-SIFE is of Takagi-Sugeno-Kang type with interval weights. The IT2NFS-SIFE possesses a self-evolving property that can automatically generate fuzzy rules. The poor features can be discarded through the concept of a membership modulator. The antecedent and modulator weights are learned using a gradient descent algorithm. The consequent part weights are tuned via the rule-ordered Kalman filter algorithm to enhance learning effectiveness. Simulation results show that IT2NFS-SIFE not only simplifies the system architecture by eliminating derogatory/irrelevant antecedent clauses, rules, and features but also maintains excellent performance.

Common spatial pattern and linear discriminant analysis for motor imagery classification

A Brain-Computer Interface (BCI) system provides a convenient way of communication for healthy subjects and subjects who suffer from severe diseases such as amyotrophic lateral sclerosis (ALS). Motor imagery (MI) is one of the popular ways of designing BCI systems. The architecture of many BCI system is quite complex and they involve time consuming processing. The electroencephalography (EEG) signal is the most commonly used inputs for BCI applications but EEG is often contaminated with noise. To overcome such drawbacks, in this paper we use the common spatial pattern (CSP) for feature extraction from EEG and the linear discriminant analysis (LDA) for motor imagery classification. In this study, CSP and LDA have been used to reduce the artifact and classify MI-based EEG signal. We have used two-level cross validation scheme to determine the subject specific best time window and number of CSP features. We have compared the performance of our system with BCI competition results. We have also experimented with MI data generated in our lab. The proposed system is found to produce good results. In particular, using our EEG data for MI movements, we have obtained an average classification accuracy of 80% for two subjects using only 9 channels, without any feature selection. This proposed MI-based BCI system may be used in real life applications.

Fuzzy Integral with Particle Swarm Optimization for a Motor-Imagery-Based Brain-Computer Interface

A brain–computer interface (BCI) system using electroencephalography signals provides a convenient means of communication between the human brain and a computer. Motor imagery (MI), in which motor actions are mentally rehearsed without engaging in actual physical execution, has been widely used as a major BCI approach. One robust algorithm that can successfully cope with the individual differences in MI-related rhythmic patterns is to create diverse ensemble classifiers using the subband common spatial pattern (SBCSP) method. To aggregate outputs of ensemble members, this study uses fuzzy integral with particle swarm optimization (PSO), which can regulate subject-specific parameters for the assignment of optimal confidence levels for classifiers. The proposed system combining SBCSP, fuzzy integral, and PSO exhibits robust performance for offline single-trial classification of MI and real-time control of a robotic arm using MI. This paper represents the first attempt to utilize fuzzy fusion technique to attack the individual differences problem of MI applications in real-world noisy environments. The results of this study demonstrate the practical feasibility of implementing the proposed method for real-world applications.

A hybrid of cuckoo search and simplex method for fuzzy neural network training

In this paper, a new hybrid algorithm mixing the simplex method of Nelder and Mead (NM) and the cuckoo search (CS), abbreviated as NM-CS, is proposed for the training of the Fuzzy Neural Networks (FNNs). In standard CS, cuckoo birds engage the obligate brood parasitism by laying their own eggs to other host birds. If a host bird discovers the alien eggs, they will either throw these eggs away or abandon its nest and build a new nest elsewhere. In the proposed hybrid algorithm, instead of using the probability to discover an alien egg for the CS, we use the concept of a simplex which is used in the NM algorithm to abandon and generate the new nests. Our proposed method puts more emphasis on exploration of the search space and enhances the ability to avoid local optimum. Some simulation problems will be provided to compare the performances of the proposed method and other methods in training an FNN. In these simulations, it is observed that the proposed method outperforms other methods.

Design of the multi-channel electroencephalography-based brain-computer interface with novel dry sensors

The traditional brain-computer interface (BCI) system measures the electroencephalography (EEG) signals by the wet sensors with the conductive gel and skin preparation processes. To overcome the limitations of traditional BCI system with conventional wet sensors, a wireless and wearable multi-channel EEG-based BCI system is proposed in this study, including the wireless EEG data acquisition device, dry spring-loaded sensors, a size-adjustable soft cap. The dry spring-loaded sensors are made of metal conductors, which can measure the EEG signals without skin preparation and conductive gel. In addition, the proposed system provides a size-adjustable soft cap that can be used to fit users head properly. Indeed, the results are shown that the proposed system can properly and effectively measure the EEG signals with the developed cap and sensors, even under movement. In words, the developed wireless and wearable BCI system is able to be used in cognitive neuroscience applications.

A Novel Mechanism to Fuse Various Sub-Aspect Brain-Computer Interface (BCI) Systems with PSO for Motor Imagery Task

In this study, we develop a novel multi-fusion brain-computer interface (BCI) system based on a fuzzy neural network (FNN) and information fusion approaches to cope with a classification task for identifying right/left hand motor imagery. In the proposed system, we utilize a filter bank and sub-band common spatial pattern (SBCSP) to extract features from raw EEG data. A self-organizing neural fuzzy inference network (SONFIN) is then applied for a recognition task. In order to improve the classification performance, we form a committee of networks and employ fuzzy integral (FI) to attain a joint decision. To further optimize the fusion approaches, a particle swarm optimization (PSO) algorithm is exploited to globally update parameters used in the fusion stage. In consequence, our experimental result shows that the proposed fuzzy fusion system possesses superior performance compared to other comparative models.

A wireless Electrooculography-based human-computer interface for baseball game

Gaming control becomes popular based on the development of human-computer interface (HCI). Among many kinds of physiological signals, Electrooculography (EOG) signal is more stable which can be used to control HCI systems based on eye movement detection and signal processing methods. However, there are currently no effective multi-directional classification methods for monitoring eye movements. In addition, many EOG-based HCI systems have been developed with traditional wet electrodes. Those traditional electrodes require conductive gel and skin preparation on some users. Here, we describe a signal processing method used in a wireless EOG-based HCI system with dry electrodes for detecting eye movements to have 9 options. This system includes wireless EOG signal acquisition device, dry electrodes and an EOG signal processing algorithm. The EOG signal processing algorithm is based on 9 options of eye movement and blink signals. The results demonstrated an application of baseball game control using the proposed wireless HCI system. This system provides an effective and convenient method for eye movement detection.