arXiv subjects

Chin-Teng Lin

Publications and source records attributed to Chin-Teng Lin.

89 records · Page 5Linked to original sources

arXiv2019

Quantum topology identification with deep neural networks and quantum walks

Topologically ordered materials may serve as a platform for new quantum technologies such as fault-tolerant quantum computers. To fulfil this promise, efficient and general methods are needed to discover and classify new topological phases of matter. We demonstrate that deep neural networks augmented with external memory can use the density profiles formed in quantum walks to efficiently identify properties of a topological phase as well as phase transitions. On a trial topological ordered model, our method's accuracy of topological phase identification reaches 97.4%, and is shown to be robust to noise on the data. Furthermore, we demonstrate that our trained DNN is able to identify topological phases of a perturbed model and predict the corresponding shift of topological phase transitions without learning any information about the perturbations in advance. These results demonstrate that our approach is generally applicable and may be used to identify a variety of quantum topological materials.

quant-ph↗

arXiv2019

On the Functional Equivalence of TSK Fuzzy Systems to Neural Networks, Mixture of Experts, CART, and Stacking Ensemble Regression

Fuzzy systems have achieved great success in numerous applications. However, there are still many challenges in designing an optimal fuzzy system, e.g., how to efficiently optimize its parameters, how to balance the trade-off between cooperations and competitions among the rules, how to overcome the curse of dimensionality, how to increase its generalization ability, etc. Literature has shown that by making appropriate connections between fuzzy systems and other machine learning approaches, good practices from other domains may be used to improve the fuzzy systems, and vice versa. This paper gives an overview on the functional equivalence between Takagi-Sugeno-Kang fuzzy systems and four classic machine learning approaches -- neural networks, mixture of experts, classification and regression trees, and stacking ensemble regression -- for regression problems. We also point out some promising new research directions, inspired by the functional equivalence, that could lead to solutions to the aforementioned problems. To our knowledge, this is so far the most comprehensive overview on the connections between fuzzy systems and other popular machine learning approaches, and hopefully will stimulate more hybridization between different machine learning algorithms.

cs.LG↗

arXiv2019

Protecting Privacy of Users in Brain-Computer Interface Applications

Machine learning (ML) is revolutionizing research and industry. Many ML applications rely on the use of large amounts of personal data for training and inference. Among the most intimate exploited data sources is electroencephalogram (EEG) data, a kind of data that is so rich with information that application developers can easily gain knowledge beyond the professed scope from unprotected EEG signals, including passwords, ATM PINs, and other intimate data. The challenge we address is how to engage in meaningful ML with EEG data while protecting the privacy of users. Hence, we propose cryptographic protocols based on Secure Multiparty Computation (SMC) to perform linear regression over EEG signals from many users in a fully privacy-preserving (PP) fashion, i.e.~such that each individual's EEG signals are not revealed to anyone else. To illustrate the potential of our secure framework, we show how it allows estimating the drowsiness of drivers from their EEG signals as would be possible in the unencrypted case, and at a very reasonable computational cost. Our solution is the first application of commodity-based SMC to EEG data, as well as the largest documented experiment of secret sharing based SMC in general, namely with 15 players involved in all the computations.

cs.CR↗

arXiv2019

Tensor Decomposition for EEG Signal Retrieval

Prior studies have proposed methods to recover multi-channel electroencephalography (EEG) signal ensembles from their partially sampled entries. These methods depend on spatial scenarios, yet few approaches aiming to a temporal reconstruction with lower loss. The goal of this study is to retrieve the temporal EEG signals independently which was overlooked in data pre-processing. We considered EEG signals are impinging on tensor-based approach, named nonlinear Canonical Polyadic Decomposition (CPD). In this study, we collected EEG signals during a resting-state task. Then, we defined that the source signals are original EEG signals and the generated tensor is perturbed by Gaussian noise with a signal-to-noise ratio of 0 dB. The sources are separated using a basic non-negative CPD and the relative errors on the estimates of the factor matrices. Comparing the similarities between the source signals and their recovered versions, the results showed significantly high correlation over 95%. Our findings reveal the possibility of recoverable temporal signals in EEG applications.

eess.SP↗

arXiv2019

Dynamically Weighted Ensemble-based Prediction System for Adaptively Modeling Driver Reaction Time

Predicting a driver's cognitive state, or more specifically, modeling a driver's reaction time (RT) in response to the appearance of a potential hazard warrants urgent research. In the last two decades, the electric field that is generated by the activities in the brain, monitored by an electroencephalogram (EEG), has been proven to be a robust physiological indicator of human behavior. However, mapping the human brain can be extremely challenging, especially owing to the variability in human beings over time, both within and among individuals. Factors such as fatigue, inattention and stress can induce homeostatic changes in the brain, which affect the observed relationship between brain dynamics and behavioral performance, and thus make the existing systems for predicting RT difficult to generalize. To solve this problem, an ensemble-based weighted prediction system is presented herein. This system comprises a set of prediction submodels that are individually trained using groups of data with similar EEG-RT relationships. To obtain a final prediction, the prediction outcomes of the sub-models are then multiplied by weights that are derived from the EEG alpha coherences of 10 channels plus theta band powers of 30 channels, whose changes were found to be indicators of variations in the EEG-RT relationship. The results thus obtained reveal that the proposed system with a time-varying adaptive weighting mechanism significantly outperforms the conventional system in modeling a driver's RT. The adaptive design of the proposed system demonstrates its feasibility in coping with the variability in the brain-behavior relationship. In this contribution surprisingly simple EEG-based adaptive methods are used in combination with an ensemble scheme to significantly increase system performance.

cs.HC↗

arXiv2018

Semi-supervised Feature Learning For Improving Writer Identification

Data augmentation is usually used by supervised learning approaches for offline writer identification, but such approaches require extra training data and potentially lead to overfitting errors. In this study, a semi-supervised feature learning pipeline was proposed to improve the performance of writer identification by training with extra unlabeled data and the original labeled data simultaneously. Specifically, we proposed a weighted label smoothing regularization (WLSR) method for data augmentation, which assigned the weighted uniform label distribution to the extra unlabeled data. The WLSR method could regularize the convolutional neural network (CNN) baseline to allow more discriminative features to be learned to represent the properties of different writing styles. The experimental results on well-known benchmark datasets (ICDAR2013 and CVL) showed that our proposed semi-supervised feature learning approach could significantly improve the baseline measurement and perform competitively with existing writer identification approaches. Our findings provide new insights into offline write identification.

cs.LG↗

arXiv2018

Effects of Repetitive SSVEPs on EEG Complexity using Multiscale Inherent Fuzzy Entropy

Multiscale inherent fuzzy entropy is an objective measurement of electroencephalography (EEG) complexity, reflecting the habituation of brain systems. Entropy dynamics are generally believed to reflect the ability of the brain to adapt to a visual stimulus environment. In this study, we explored repetitive steady-state visual evoked potential (SSVEP)-based EEG complexity by assessing multiscale inherent fuzzy entropy with relative measurements. We used a wearable EEG device with Oz and Fpz electrodes to collect EEG signals from 40 participants under the following three conditions: a resting state (closed-eyes (CE) and open- eyes (OE) stimulation with five 15-Hz CE SSVEPs and stimulation with five 20-Hz OE SSVEPs. We noted monotonic enhancement of occipital EEG relative complexity with increasing stimulus times in CE and OE conditions. The occipital EEG relative complexity was significantly higher for the fifth SSVEP than for the first SSEVP (FDR-adjusted p < 0.05). Similarly, the prefrontal EEG relative complexity tended to be significantly higher in the OE condition compared to that in the CE condition (FDR-adjusted p < 0.05). The results also indicate that multiscale inherent fuzzy entropy is superior to other competing multiscale-based entropy methods. In conclusion, EEG relative complexity increases with stimulus times, a finding that reflects the strong habituation of brain systems. These results suggest that multiscale inherent fuzzy entropy is an EEG pattern with which brain complexity can be assessed using repetitive SSVEP stimuli.

eess.SP↗

arXiv2018

Extraction of SSVEPs-based Inherent Fuzzy Entropy Using a Wearable Headband EEG in Migraine Patients

Inherent fuzzy entropy is an objective measurement of electroencephalography (EEG) complexity, reflecting the robustness of brain systems. In this study, we present a novel application of multi-scale relative inherent fuzzy entropy using repetitive steady-state visual evoked potentials (SSVEPs) to investigate EEG complexity change between two migraine phases, i.e. inter-ictal (baseline) and pre-ictal (before migraine attacks) phases. We used a wearable headband EEG device with O1, Oz, O2 and Fpz electrodes to collect EEG signals from 80 participants (40 migraine patients and 40 healthy controls [HCs]) under the following two conditions: during resting state and SSVEPs with five 15-Hz photic stimuli. We found a significant enhancement in occipital EEG entropy with increasing stimulus times in both HCs and patients in the inter-ictal phase but a reverse trend in patients in the pre-ictal phase. In the 1st SSVEP , occipital EEG entropy of the HCs was significantly higher than that of patents in the pre-ictal phase (FDR-adjusted p < 0.05). Regarding the transitional variance of EEG entropy between the 1st and 5th SSVEPs, patients in the pre-ictal phase exhibited significantly lower values than patients in the inter-ictal phase (FDR-adjusted p < 0.05). Furthermore, in the classification model, the AdaBoost ensemble learning showed an accuracy of 81% and AUC of 0.87 for classifying inter-ictal and pre-ictal phases. In contrast, there were no differences in EEG entropy among groups or sessions by using other competing entropy models, including approximate entropy, sample entropy and fuzzy entropy on the same dataset. In conclusion, inherent fuzzy entropy offers novel applications in visual stimulus environments and may have the potential to provide a pre-ictal alert to migraine patients.

cs.HC↗

arXiv2018

Multi-channel EEG recordings during a sustained-attention driving task

We described driver behaviour and brain dynamics acquired from a 90-minute sustained-attention task in an immersive driving simulator. The data include 62 copies of 32 channel electroencephalography (EEG) data for 27 subjects that drove on a four lane highway and were asked to keep the car cruising in the centre of the lane. Lane departure events were randomly induced to make the car drift from the original cruising lane towards the left or right lane. A complete trial includes events with deviation onset, response onset, and response offset. The next trial, in which the subject has to drive back to the original cruising lane, occurs from 5 to 10 seconds after finishing the current trial. We hope that this dataset will lead to the development of novel neural processing assays that can be used to index brain cortical dynamics and detect driving fatigue and drowsiness. This publicly available dataset is beneficial to the neuroscientific and brain computer interface communities.

eess.SP↗

arXiv2018

Identifying Ketamine Responses in Treatment-Resistant Depression Using a Wearable Forehead EEG

This study explores the responses to ketamine in patients with treatment-resistant depression (TRD) using a wearable forehead electroencephalography (EEG) device. We recruited fifty-five outpatients with TRD who were randomised into three approximately equal-sized groups (A: 0.5 mg/kg ketamine; B: 0.2 mg/kg ketamine; and C: normal saline) under double-blind conditions. The ketamine responses were measured by EEG signals and Hamilton Depression Rating Scale (HDRS) scores. At baseline, responders showed a significantly weaker EEG theta power than did non- responders (p < 0.05). Responders exhibited a higher EEG alpha power but lower EEG alpha asymmetry and theta cordance at post-treatment than at baseline (p < 0.05). Furthermore, our baseline EEG predictor classified responders and non-responders with 81.3 +- 9.5% accuracy, 82.1 +- 8.6% sensitivity and 91.9 +- 7.4% specificity. In conclusion, the rapid antidepressant effects of mixed doses of ketamine are associated with prefrontal EEG power, asymmetry and cordance at baseline and early post-treatment changes. The prefrontal EEG patterns at baseline may account for recognising ketamine effects in advance. Our randomised, double- blind, placebo-controlled study provides information regarding clinical impacts on the potential targets underlying baseline identification and early changes from the effects of ketamine in patients with TRD.

eess.SP↗

arXiv2018

Active Learning for Regression Using Greedy Sampling

Regression problems are pervasive in real-world applications. Generally a substantial amount of labeled samples are needed to build a regression model with good generalization ability. However, many times it is relatively easy to collect a large number of unlabeled samples, but time-consuming or expensive to label them. Active learning for regression (ALR) is a methodology to reduce the number of labeled samples, by selecting the most beneficial ones to label, instead of random selection. This paper proposes two new ALR approaches based on greedy sampling (GS). The first approach (GSy) selects new samples to increase the diversity in the output space, and the second (iGS) selects new samples to increase the diversity in both input and output spaces. Extensive experiments on 12 UCI and CMU StatLib datasets from various domains, and on 15 subjects on EEG-based driver drowsiness estimation, verified their effectiveness and robustness.

cs.LG↗

arXiv2018

Offline EEG-Based Driver Drowsiness Estimation Using Enhanced Batch-Mode Active Learning (EBMAL) for Regression

There are many important regression problems in real-world brain-computer interface (BCI) applications, e.g., driver drowsiness estimation from EEG signals. This paper considers offline analysis: given a pool of unlabeled EEG epochs recorded during driving, how do we optimally select a small number of them to label so that an accurate regression model can be built from them to label the rest? Active learning is a promising solution to this problem, but interestingly, to our best knowledge, it has not been used for regression problems in BCI so far. This paper proposes a novel enhanced batch-mode active learning (EBMAL) approach for regression, which improves upon a baseline active learning algorithm by increasing the reliability, representativeness and diversity of the selected samples to achieve better regression performance. We validate its effectiveness using driver drowsiness estimation from EEG signals. However, EBMAL is a general approach that can also be applied to many other offline regression problems beyond BCI.

cs.LG↗

arXiv2018

Agreement Rate Initialized Maximum Likelihood Estimator for Ensemble Classifier Aggregation and Its Application in Brain-Computer Interface

Ensemble learning is a powerful approach to construct a strong learner from multiple base learners. The most popular way to aggregate an ensemble of classifiers is majority voting, which assigns a sample to the class that most base classifiers vote for. However, improved performance can be obtained by assigning weights to the base classifiers according to their accuracy. This paper proposes an agreement rate initialized maximum likelihood estimator (ARIMLE) to optimally fuse the base classifiers. ARIMLE first uses a simplified agreement rate method to estimate the classification accuracy of each base classifier from the unlabeled samples, then employs the accuracies to initialize a maximum likelihood estimator (MLE), and finally uses the expectation-maximization algorithm to refine the MLE. Extensive experiments on visually evoked potential classification in a brain-computer interface application show that ARIMLE outperforms majority voting, and also achieves better or comparable performance with several other state-of-the-art classifier combination approaches.

cs.LG↗

arXiv2017

EEG-Based User Reaction Time Estimation Using Riemannian Geometry Features

Riemannian geometry has been successfully used in many brain-computer interface (BCI) classification problems and demonstrated superior performance. In this paper, for the first time, it is applied to BCI regression problems, an important category of BCI applications. More specifically, we propose a new feature extraction approach for Electroencephalogram (EEG) based BCI regression problems: a spatial filter is first used to increase the signal quality of the EEG trials and also to reduce the dimensionality of the covariance matrices, and then Riemannian tangent space features are extracted. We validate the performance of the proposed approach in reaction time estimation from EEG signals measured in a large-scale sustained-attention psychomotor vigilance task, and show that compared with the traditional powerband features, the tangent space features can reduce the root mean square estimation error by 4.30-8.30%, and increase the estimation correlation coefficient by 6.59-11.13%.

cs.HC↗

arXiv2017

Measuring Cognitive Conflict in Virtual Reality with Feedback-Related Negativity

As virtual reality (VR) emerges as a mainstream platform, designers have started to experiment new interaction techniques to enhance the user experience. This is a challenging task because designers not only strive to provide designs with good performance but also carefully ensure not to disrupt users' immersive experience. There is a dire need for a new evaluation tool that extends beyond traditional quantitative measurements to assist designers in the design process. We propose an EEG-based experiment framework that evaluates interaction techniques in VR by measuring intentionally elicited cognitive conflict. Through the analysis of the feedback-related negativity (FRN) as well as other quantitative measurements, this framework allows designers to evaluate the effect of the variables of interest. We studied the framework by applying it to the fundamental task of 3D object selection using direct 3D input, i.e. tracked hand in VR. The cognitive conflict is intentionally elicited by manipulating the selection radius of the target object. Our first behavior experiment validated the framework in line with the findings of conflict-induced behavior adjustments like those reported in other classical psychology experiment paradigms. Our second EEG-based experiment examines the effect of the appearance of virtual hands. We found that the amplitude of FRN correlates with the level of realism of the virtual hands, which concurs with the Uncanny Valley theory.

cs.HC↗

arXiv2017

Spatial Filtering for EEG-Based Regression Problems in Brain-Computer Interface (BCI)

Electroencephalogram (EEG) signals are frequently used in brain-computer interfaces (BCIs), but they are easily contaminated by artifacts and noises, so preprocessing must be done before they are fed into a machine learning algorithm for classification or regression. Spatial filters have been widely used to increase the signal-to-noise ratio of EEG for BCI classification problems, but their applications in BCI regression problems have been very limited. This paper proposes two common spatial pattern (CSP) filters for EEG-based regression problems in BCI, which are extended from the CSP filter for classification, by making use of fuzzy sets. Experimental results on EEG-based response speed estimation from a large-scale study, which collected 143 sessions of sustained-attention psychomotor vigilance task data from 17 subjects during a 5-month period, demonstrate that the two proposed spatial filters can significantly increase the EEG signal quality. When used in LASSO and k-nearest neighbors regression for user response speed estimation, the spatial filters can reduce the root mean square estimation error by 10.02-19.77%, and at the same time increase the correlation to the true response speed by 19.39-86.47%.

cs.LG↗

arXiv2017

Driver Drowsiness Estimation from EEG Signals Using Online Weighted Adaptation Regularization for Regression (OwARR)

One big challenge that hinders the transition of brain-computer interfaces (BCIs) from laboratory settings to real-life applications is the availability of high-performance and robust learning algorithms that can effectively handle individual differences, i.e., algorithms that can be applied to a new subject with zero or very little subject-specific calibration data. Transfer learning and domain adaptation have been extensively used for this purpose. However, most previous works focused on classification problems. This paper considers an important regression problem in BCI, namely, online driver drowsiness estimation from EEG signals. By integrating fuzzy sets with domain adaptation, we propose a novel online weighted adaptation regularization for regression (OwARR) algorithm to reduce the amount of subject-specific calibration data, and also a source domain selection (SDS) approach to save about half of the computational cost of OwARR. Using a simulated driving dataset with 15 subjects, we show that OwARR and OwARR-SDS can achieve significantly smaller estimation errors than several other approaches. We also provide comprehensive analyses on the robustness of OwARR and OwARR-SDS.

cs.LG↗