Xiyuan Hou

EEG Based Stress Monitoring

Everyone experiences stress in life. Moderate stress can be beneficial to human, however, excessive stress is harmful to the health. To monitor stress, different methods can be used. In this work, an algorithm for stress level recognition from Electroencephalogram (EEG) is proposed. To validate the algorithm, an experiment is designed and carried out with 9 subjects. A Stroop colour-word test is used as a stressor to induce 4 levels of stress, and the EEG data are recorded during the experiment. Different feature combinations and classifiers are proposed and analyzed. By combining fractal dimension and statistical features and using Support Vector Machine (SVM) as the classifier, four levels of stress can be recognized with an average accuracy of 67.06%, three levels of stress can be recognized with an accuracy of 75.22%, and two levels of stress can be recognized with an accuracy of 85.71%. The algorithm is integrated into the system CogniMeter for stress state monitoring. Stress level of the user is visualized on the meter in real time. The system can be applied for stress monitoring of air traffic controllers, operators, etc.

CogniMeter: EEG-based Emotion, Mental Workload and Stress Visual Monitoring

Real-time EEG (Electroencephalogram)-based users emotion, mental workload and stress monitoring is a new direction in research and development of human-machine interfaces. It has attracted recently more attention from the research community and industry as wireless portable EEG devices became easily available on the market. EEG-based technology has been applied in anesthesiology, psychology, serious games or even in marketing. In this work, we describe available real-time algorithms of emotion recognition, mental workload, and stress recognition from EEG and propose a novel interface Cogni Meter for the users mental state visual monitoring. The system can be used in real time to assess human current emotions, levels of mental workload and stress. Currently, it is applied to monitor the users emotional state, mental workload and stress in simulation scenarios or used as a tool to assess the subjects mental state in human factor study experiments.

Six degree-of-freedom haptic rendering for biomolecular docking

Haptic device enable the user to manipulate the molecules and feel interactions during the docking process in virtual environment on the computer. Implementation of force-torque feedback allows the user to have more realistic experience during force simulation and find the optimum docking positions faster. In this paper, we propose a haptic rendering algorithm for biomolecular docking with force-torque feedback. It enables the user to experience six degree-of-freedom (DOF) haptic manipulation in molecular docking process. The linear smoothing method was proposed to improve stability of the haptic rendering during molecular docking. Collaborative docking with two devices was implemented.

Stable adaptive algorithm for Six Degrees-of-Freedom haptic rendering in a dynamic environment

Recently, physically-based simulations with haptics interaction attracted many researchers. In this paper, we propose an adaptive Six Degrees-of-Freedom (6-DOF) haptic rendering algorithm based on virtual coupling, which can automatically adjust virtual coupling parameters according to mass values of the simulated virtual tools. The algorithm can overcome the virtual tool displacement problem caused by the large mass values of the virtual tool and can provide stable force/torque display. The force/torque magnitude is saturated to the maximum force/torque values of the haptic device automatically. The implemented algorithm is tested on the simple and complex standard benchmarks. The experimental results confirm that the proposed adaptive 6-DOF haptic rendering algorithm displays good stability and accuracy for haptic rendering of dynamic virtual objects with mass values.

Haptic Rendering Algorithm for Biomolecular Docking with Torque Force

Haptic devices enable the user to manipulate the molecules and feel interactions during the docking process in virtual environment on the computer. Implementation of torque feedback allows the user to have more realistic experience during force simulation and find the optimum docking positions faster. In this paper, we propose a haptic rendering algorithm for biomolecular docking with torque force. It enables the user to experience six degree-of-freedom (DOF) haptic manipulation in docking process. The linear smoothing method was proposed to improve stability of the haptic rendering during molecular docking.

Emotion-enabled haptic-based serious game for post stroke rehabilitation

In this paper, we propose and develop a novel adaptive haptic- based serious game for post stroke rehabilitation. Real-time patients emotions monitoring based on the Electroencephalogram (EEG) is used as an additional game control. A subject-dependent algorithm recognizing negative and positive emotions from EEG is integrated. Force feedback is proposed and implemented in the game. The proposed EEG-enabled haptic-based serious game could help to promote rehabilitation of the patients with motor deficits after stroke. Such games could be used by the patients for post stroke rehabilitation even at home convenience without a nurse presence.

Fractal dimension based neurofeedback training to improve cognitive abilities

Currently, neurofeedback training can be used not only to treat the patients with attention deficit hyperactivity disorder, learning difficulties, etc. but also to improve cognitive abilities of healthy people. Training protocols based on alpha, theta, or theta/beta power calculated from Electroencephalogram (EEG) are commonly used in the neurofeedback training. However, when the standard neurofeedback protocols are used, the EEG recording is required before the training to obtain the training threshold for each subject. In this paper, we propose a fractal dimension (FD)-based neurofeedback training protocol with adaptive algorithm, which does not need any before-training recording. The algorithm is integrated in the Shooting game. The efficiency of the FD-based neurofeedback training in comparison with traditional individual theta/beta based neurofeedback training is assessed using Psychology Experiment Building Language (PEBL) tests such as matrix rotation (for spatial ability), change detection (for focused attention), math processing (for cognitive abilities) and test of attentional vigilance (for attention of vigilance). 40 subjects participated in the study. They were divided randomly into FD-based neurofeedback training group and theta/beta ratio-based training group. The results show that after neurofeedback training participants from FD-based training group has similar or better test performance than the one from ratio-based group.

EEG-Based Human Factors Evaluation of Conflict Resolution Aid and Tactile User Interface in Future Air Traffic Control Systems

Currently, Air Traffic Control (ATC) systems are reliable with automation supports, however, the increased traffic density and complex air traffic situations bring new challenges to ATC systems and air-traffic controllers (ATCOs). We conduct an experiment to evaluate the current ATC system and test conflict resolution automation and tactile user interface to be the inputs of the future ATC system. We propose an Electroencephalogram (EEG)-based system to monitor and analyze human factors measurements of ATCOs in ATC systems to apply it in our experiment. The EEG-based tools are used to monitor and record the brain states of ATCOs during the experiment. Real-time EEG-based human factors evaluation of an ATC system allows researchers to analyze the changes of ATCOs’ brain states during the performance of various ATC tasks. Based on the analyses of the objective real time data together with the subjective feedback from ATCOs, we are able to reliably evaluate current ATC systems and refine new concepts of future ATC system.

Visual Haptic-based Collaborative Molecular Docking

In this paper, we propose a novel approach to search for protein-protein complementary pairs in collaborative virtual environment. This method employs visual and force feedback tools to search for the optimal interaction between proteins. The search is manual with force feedback consisting of a repulsion or attraction force. We developed a prototype system that allows real-time interactive visualization and manipulation of molecules with force feedback in virtual collaborative environment. In our system, we implemented haptic interface to facilitate the exploration and analysis of molecular docking. Haptic device enables both users to manipulate the molecules and feel its interaction during the docking process in collaborative virtual experiment on computer. In future, these techniques could help the user to understand molecular interactions, and could be used both in research and e-learning.

CogniMeter: EEG-Based Brain States Monitoring

Electroencephalogram EEG techniques are traditionally used in the medical field. Recent research work focuses on applying these techniques to daily life with wireless and relatively low-price EEG devices available in the market. As a result, applications such as neurofeedback training, neuromarketing, emotion, stress, mental workload recognition, etc. using EEG techniques on healthy adults have been developed. Since the EEG measures and records electrical activity in the brain, it is possible for it to reflect a persons brain states. In this paper, we describe a novel brain computer interface called CogniMeter integrated with proposed real-time emotion, mental workload, and stress recognition algorithms. With this system, we can assess human emotions, mental workload, and stress in real time. This work can be applied as a human study tool in many fields. For example, the wellbeing of users within a system or workers in industry can be monitored to improve their protection from overly stressful workload conditions. In research, brain state monitoring can be applied in simulation scenarios during human factor study experiments. In marketing, a persons emotional response toward products or advertisements can be studied using EEG-based brain states monitoring.