Laboratory for Computational Neuroergonomics
We are recruiting! 招募中! 計算神經人因工程實驗室
We are seeking prospective students, undergraduates and postgraduates, to join our group in a variety of research topic. If interested, please take a look at our current research focus and contact us (email@example.com).
We are Laboratory for Computational Neuroergonomics & Neural Engineering (CNE LAB).
Research on Brain-Computer Interfaces (BCIs) began in the 1970s at the University of California, Los Angeles. Since then it has become a flourishing research area in many leading institutions worldwide. BCI is also the key research topic in the two largest-scale brain research projects in the world: the Brain Initiative Project (2014-2024, 1 billion USD) in the US, and the Human Brain Project (2014-2024, 1.2 billion Euros) in the EU. These intensive research projects are funded by governments and invested in by industries and offer a great boost to the BCI market, which is expected to reach $1.46 billion by 2020. Advancing the development of effective BCI technologies will foster growth and innovation in neuromarketing and neuroergonomics.
We have made substantial contributions to the field of biomedical signal processing, brain-computer interface (BCI), and machine learning, with several research articles published in high quality journals. We have built a strong network of collaborators based at University of California, San Diego (UCSD), US Army Research Laboratory (US ARL), National Chiao Tung University (NCTU), University of Technology Sydney, Indian Statistical Institute, Technical University of Berlin, and Taipei Veterans General Hospital. This experience of independent theoretical exploration has given us valuable insights and useful technical toolkits, and more importantly, an in-depth understanding of the field and the confidence to confront challenging problems.
- Leveraging Data Science Technique to Bring New Insight into Neuroscientific Problem
- Developing Adaptive Computational Algorithms and Brain-Computer Interfaces for Real-Life Applications
- Building Multimodal Data Streaming Infrastructure in Support of Personal Healthcare Solutions at Home
- Identify brain networks associated with mind-wandering during driving using Granger causality model
- Investigate the effects of kinesthetic stimuli on brain activities in drowsy driving
- Decipher key co-modulatory systems in motion sickness while travelling
- Design an independent component ensemble for adaptive BCIs
Leveraging Data Science Technique to Bring New Insight into Neuroscientific Problem
Mind-wandering tends to occur under low perceptual demands during driving
Even when a driver is alert and in the absence of external distractions fluctuations in attention are inevitable. Such fluctuations, often referred to as mind-wandering, impair drivers’ ability to maintain consistent speed and lane integrity and respond to emergency situations and is likely a contributing factor in more than half of all car crashes. We posit that changes in driving task demand may promote a shift of brain activity between these two modes of processing. Furthermore, fluctuations in performance during driving may be related to fluctuations in internal and external attentional states associated with dynamic changes in functional coupling between the brain’s default and task-positive networks.
Kinesthesia in a sustained-attention driving task
This study investigated the effects of kinesthetic stimuli on brain activities during a sustained-attention task in an immersive driving simulator. In contrast to the static environment with visual input only, kinesthetic feedback reduced theta-power augmentation in the central and frontal components when preparing for action and error monitoring, while strengthening alpha suppression in the central component while steering the wheel. In terms of behavior, subjects tended to have a short response time to process unexpected events with the assistance of kinesthesia, yet only when their performance was optimal. Decrease in attentional demand, facilitated by kinesthetic feedback, eventually significantly increased the reaction time in the suboptimal-performance state.
Neuroimage 2014 [full article]
Developing Adaptive Computational Algorithms and Brain-Computer Interfaces for Real-Life Applications
Independent component ensemble of EEG for brain-computer interface
Successful applications of independent component analysis (ICA) to electroencephalographic (EEG) signals have yielded tremendous insights into brain processes that underlie human cognition. Many studies have further established the feasibility of using independent processes to elucidate human cognitive states. However, various technical problems arise in the building of an on-line Brain-Computer Interface (BCI). These include the lack of an automatic procedure for selecting independent components of interest (ICi) and the potential risk of not obtaining a desired ICi. Therefore, this study proposes an ICi-ensemble method that uses multiple classifiers with ICA processing to improve upon existing algorithms.
IEEE Transactions on Neural Systems and Rehabilitation Engineering 2014 [full article]
Wireless and wearable EEG system for evaluating driver vigilance
This work presents a novel dry EEG sensor based mobile wireless EEG system (referred to herein as Mindo) to monitor in real time a driver's vigilance status in order to link the fluctuation of driving performance with changes in brain activities. The proposed Mindo system incorporates the use of a wireless and wearable EEG device to record EEG signals from hairy regions of the driver conveniently. Additionally, the proposed system can process EEG recordings and translate them into the vigilance level. The study compares the system performance between different regression models. Moreover, the proposed system is implemented using JAVA programming language as a mobile application for online analysis.
Minority oversampling in kernel adaptive subspaces for class imbalanced datasets
The class imbalance problem in machine learning occurs when certain classes are underrepresented relative to the others, leading to a learning bias toward the majority classes. To cope with the skewed class distribution, many learning methods featuring minority oversampling have been proposed, which are proved to be effective. To reduce information loss during feature space projection, this study proposes a novel oversampling algorithm, named minority oversampling in kernel adaptive subspaces (MOKAS), which exploits the invariant feature extraction capability of a kernel version of the adaptive subspace self-organizing maps.
IEEE Transactions on Knowledge and Data Engineering 2017 [full article]
Building Multimodal Data Streaming Infrastructure in Support of Personal Healthcare Solutions at Home
Objective Entropy-based approaches to understanding the temporal dynamics of complexity have revealed novel insights into various brain activities. Herein, electroencephalogram complexity before migraine attacks was examined using an inherent fuzzy entropy approach, allowing the development of an electroencephalogram-based classification model to recognize the difference between interictal and preictal phases.
Cephalalgia 2018 [full article]
Forehead EEG in support of future feasible personal healthcare solutions at home
It is evident that frontal EEG activity is critically involved in sleep management, headache prevention, and depression treatment. The use of dry electrodes on the forehead allows for easy and rapid monitoring on an everyday basis. The advances in EEG recording and analysis ensure a promising future in support of personal healthcare solutions.
IEEE ACCESS 2017 [full article]
Resting-state EEG power and coherence vary between migraine phases
Migraine is characterized by a series of phases (inter-ictal, pre-ictal, ictal, and post-ictal). It is of great interest whether resting-state electroencephalography (EEG) is differentiable between these phases. We compared resting-state EEG energy intensity and effective connectivity in different migraine phases using EEG power and coherence analyses in patients with migraine without aura as compared with healthy controls (HCs). Inter-ictal and ictal patients had decreased EEG power and coherence relative to HCs, which were “normalized” in the pre-ictal or post-ictal groups.
Journal of Headache and Pain 2016 [full article]
We are exploring VR/AR world ...
Enhances Cognitive Control Ability for Elders via VR/AR Technology
BACKGROUND AND AIMS
It has been found that impairment in navigation ability in the elderly is one of the earliest markers of dementia or Alzheimer’s disease. In my previous MOST project, Navigation Task Training Enhances Cognitive Skills that Decline with Age or Diseases, I collaborated with Taipei Medical University to investigate the brain dynamics of patients when they were navigating in a virtual-reality environment. Navigation is a fundamental and multifaceted human ability involving complex cognitive functions that allow the exploration of new environments as well as fast and efficient negotiation of well-known space. Spatial abilities undergo an apparent decline across the life span; older adults commonly lose their way and engage in fewer out-of-home activities, leading to reduced mobility and quality of life. It is thus particularly urgent for an ever-aging society to develop some technology to promote health.
Many cognitive assessment methodologies and training paradigms have been proposed to tackle this problem, e.g. our previous work and a Nature paper. These works show that cognitive control ability, as reflected by EEG local and global coherence, can be assessed and remediated by training in goal-directed multitasking. Additionally, recent advances in AR shows a promising and portable headset solution to use in an everyday basis. I am planning to integrate EEG and AR with the multitasking contents to help elders prevent cognitive impairment.
This new and unique equipment, Virtuix Omnidirectional Treadmill, enables people to walk, run, and jump in any direction around virtual world that providing endless VR walking experience. We believe that this platform can offer a good opportunity to expand our knowledge in relation to natural human behaviors as well as subjects in the area of real-world brain dynamics if equiped with neuroimaging tools such as EEG. More information: https://www.youtube.com/user/VirtuixOmni