Sungho Jo

Quantitative Evaluation of a Low-Cost Noninvasive Hybrid Interface Based on EEG and Eye Movement

This paper describes a low-cost noninvasive brain-computer interface (BCI) hybridized with eye tracking. It also discusses its feasibility through a Fitts law-based quantitative evaluation method. Noninvasive BCI has recently received a lot of attention. To bring the BCI applications into real life, user-friendly and easily portable devices need to be provided. In this work, as an approach to realize a real-world BCI, electroencephalograph (EEG)-based BCI combined with eye tracking is investigated. The two interfaces can be complementary to attain improved performance. Especially to consider public availability, a low-cost interface device is intentionally used for test. A low-cost commercial EEG recording device is integrated with an inexpensive custom-built eye tracker. The developed hybrid interface is evaluated through target pointing and selection experiments. Eye movement is interpreted as cursor movement and noninvasive BCI selects a cursor point with two selection confirmation schemes. Using Fitts law, the proposed interface scheme is compared with other interface schemes such as mouse, eye tracking with dwell time, and eye tracking with keyboard. In addition, the proposed hybrid BCI system is discussed with respect to a practical interface scheme. Although further advancement is required, the proposed hybrid BCI system has the potential to be practically useful in a natural and intuitive manner.

Brain-actuated humanoid robot navigation control using asynchronous Brain-Computer Interface

Brain-actuated robotic systems have been proposed as a new control interface to translate different human intentions into appropriate motion commands for robotic applications. This study proposes a brain-actuated humanoid robot navigation system that uses an EEG-BCI. The experimental procedures consisted of offline training sessions, online feedback test sessions, and real-time control sessions. During the offline training sessions, amplitude features from the EEGs were extracted using band power analysis, and the informative feature components were selected using the Fisher ratio and the linear discriminant analysis (LDA) distance metric. The Intentional Activity Classifier (IAC) and the Motor Direction Classifier (MDC) were hierarchically structured and trained to build an asynchronous BCI system. During the navigation experiments, the subject controlled the humanoid robot in an indoor maze using the BCI system with real-time images from the camera on the robots head. The results showed that three subjects successfully navigated the indoor maze using the proposed brain-actuated humanoid robot navigation system.

Design and control of thermal SMA based small crawling robot mimicking C. elegans

This paper presents a design of a thermal SMA based simple small-sized and low-weight crawling robot, mimicking the crawling motion mechanism of Caenorhabditis elegans (C. elegans). Properties of the thermal SMA are similar to those of C. elegans muscle, which enables us to generate biologically relevant undulating motions. Each of 12 body segments composed of a pair of actuators is designed to be serially connected via a link that includes a motion control unit. Microcontroller is used to implement a simple sequential mode-based motion control scheme. Computer simulation and experimental results with a four segment prototype demonstrate the feasibility of the proposed robot design and control mechanism.

Non-invasive brain signal interface for a wheelchair navigation

This work presents that, only using non-invasively captured brain signals, a person can navigate an electric wheelchair with no serious training for a long term. Only two electrodes are set on the scalp non-invasively to detect a P300 EEG signal and a reference signal. A simple signal processing interprets the measured signals to decide a movement direction of the wheelchair. The whole devices are loaded on the wheelchair. No external system is required. The experimental results demonstrate the feasibility of the simple BCI processing to achieve reasonable performance.

Human gait-based bipedal walking robot design in progress

This work presents the mechanical human gait-based 3D bipedal walking robot. The robot mimics human walking through the push-off mechanism at the ankle, the passive knee bending mechanism, and the simple lateral balance control. To generate walking, it uses simple waveforms which are derived from human gait data. The preliminary experiment demonstrates that the robot walks stably.

Noninvasive Brain-Computer Interface-based control of humanoid navigation

This study proposes an asynchronous noninvasive Brain Computer Interface (BCI) -based navigation system for a humanoid robot, which can behave similarly to a human. In the experimental procedure, each subject is asked to undertake three different sessions: offline training, an online feedback test, and real-time control of a humanoid robot in an indoor maze. During the offline training session, amplitude features from the EEG are extracted using auto-regressive frequency analysis with a Laplacian filter. The optimal feature components are selected by using the Fisher ratio and the linear discriminant analysis (LDA) distance metric. Two classifiers are hierarchically set to build the asynchronous BCI system. During the online test session, the trained BCI system translates a subjects ongoing EEG into four mental states: rest, left-hand imagery, right-hand imagery, and foot imagery. Event-by-event analysis is applied to evaluate the performance of the BCI system. If the test performance is consistently satisfactory, the subject executes the real-time control experiments. During the navigation experiments, the subject controls the robot in an indoor maze using the BCI system while surveying the environment through visual feedback. The results show that BCI control was comparable to manual control with a performance ratio of 81%. The evaluation of the results validates the feasibility and power of the proposed system.

BCI based hybrid interface for 3D object control in virtual reality

People attempts to apply the virtual reality (VR) technology in various fields recently, however, there are many limitations to apply the VR technology in existing interfaces in various fields such as 3D object control. To solve this problem, we propose a combination of eye-tracking and BCI technique to control 3D objects in a three-dimensional VR as an alternative interface. In our proposed interface, users select a virtual 3D object in VR by eye-gazing which is detect by the eye-tracking module of the system and manipulate the object by concentrating their mind via the BCI module. To evaluate the performance of our system, subjects perform the same experiments using the proposed system comparing to other existing interfaces. The result shows that the proposed interface has similar or better performance than other interfaces. This result suggests that our proposed interface can be used as an alternative interface of VR.

Dynamic motion artifact removal using inertial sensors for mobile BCI

EEG signals are vulnerable to several noise and artifacts occurred by muscle activities and body movements. Reducing these artifacts has been a challenge issue to design and develop a reliable mobile EEG system for various real-life applications including home entertainment as well as clinical monitoring, assessment and rehabilitation. In this paper, we describe a method for removing motion artifacts occurred by body movement using inertial sensors. The key contribution of this work is the automatic identification of independent components representing motion artifacts from EEG signals, incurring minimal computation in real-time. The experimental results from the application of the method show that it is able to remove, in real-time, the motion noise of body movement in an real-world environment with improving the quality of EEG signals up to 82% compared with recorded in seated condition.

Lock n' LoL: Mitigating Smartphone Disturbance in Co-located Social Interactions

We aim to improve the quality of time spent in co-located social interactions by encouraging people to limit their smartphone usage together. We present a prototype called Lock n LoL, an app that allows co-located users to lock their smartphones and limit their usage by enforcing users to ask for explicit use permission. From our preliminary study, we designed two modes to deal with the dynamics of smartphone use during the co-located social interactions: (1) socializing mode (i.e., locking smartphones to limit usage together) and (2) temporary use mode (i.e., requesting/granting temporary smartphone use). We conducted a pilot study (n = 20) with our working prototype, and the results documented the helpfulness of Lock n LoL when used in socializing.

Hybrid SSVEP/ ERD BCI for humanoid navigation

In this paper, we proposes a hybrid brain computer interface (BCI) system of the steady state visually evoked potential (SSVEP), and event-related de-synchronization (ERD) for humanoid navigation. This study also aims to demonstrate the possibility of using a low-cost hybrid BCI system. An experimental scenario is proposed in which a subject remotely controls a humanoid robot in a properly sized maze. Results show the performance of the BCI system were comparable to a keyboard-based interface. This study presents that hybrid approaches of simple BCI protocols extend usability and controllability of the low-cost BCI systems.