Browsing by Author "Chang, Yang"

Now showing 1 - 4 of 4

Decision Support System for Real-Time Trading based on On-Line Learning and Parallel Computing Techniques
(2016-01-01)
Chen, Chiao-Ting
;
Huang, Shih-Jung
;
Chang, Yang
;
Hsiao, Chih-Yen
;
Lin, Jiun-Yi
A novel intraday algorithmic trading strategy is developed based on various machine learning techniques and paralleled computing architectures in this paper. The proposed binary classification framework can predict the price trends of Taiwan stock index futures after thirty minutes. Traditional learning-based approaches collect all samples during the training period as the learning materials. The major contribution of this paper is to collect a subset of similar historical financial data to train the real-time trading model. This goal can be achieved by an on-line learning technique which is required to calculate an accurate model with training time limitation. In addition, the proposed joint-AdaBoost algorithm is to improve the system performance based on the concept of paired feature learning and planar weak classifier design. The core execution components in this algorithm can be further accelerated with the aid of Open Computing Language (OpenCL) parallel computing platform. The experimental results show that the proposed learning algorithm can improve the prediction accuracy of final classifier from 53.8% to 61.68%. Compared to the pure CPU implementation, the OpenCL version which uses CPU and GPGPU simultaneously can reduce the calculation time around 83.02 times. The efficiency improvement can decrease the delay of investment opportunity which is a critical issue in real-time financial decision support system application. To sum up, this paper proposed a novel learning framework based on joint-AdaBoost algorithm with similar learning samples and OpenCL parallel computation. The extended financial decision support system is also proven to work effectively and efficiently in our simulation experiments to trade the Taiwan stock index futures.
Development of a Smart Helmet for Strategical BCI Applications
(2019-04-02)
Ko, Li-Wei
;
Chang, Yang
;
Wu, Pei-Lun
;
Tzou, Heng-An
;
Chen, Sheng-Fu
Conducting electrophysiological measurements from human brain function provides a medium for sending commands and messages to the external world, as known as a brain-computer interface (BCI). In this study, we proposed a smart helmet which integrated the novel hygroscopic sponge electrodes and a combat helmet for BCI applications; with the smart helmet, soldiers can carry out extra tasks according to their intentions, i.e., through BCI techniques. There are several existing BCI methods which are distinct from each other; however, mutual issues exist regarding comfort and user acceptability when utilizing such BCI techniques in practical applications; one of the main challenges is the trade-off between using wet and dry electroencephalographic (EEG) electrodes. Recently, several dry EEG electrodes without the necessity of conductive gel have been developed for EEG data collection. Although the gel was claimed to be unnecessary, high contact impedance and low signal-to-noise ratio of dry EEG electrodes have turned out to be the main limitations. In this study, a smart helmet with novel hygroscopic sponge electrodes is developed and investigated for long-term usage of EEG data collection. The existing electrodes and EEG equipment regarding BCI applications were adopted to examine the proposed electrode. In the impedance test of a variety of electrodes, the sponge electrode showed performance averaging 118 k, which was comparable with the best one among existing dry electrodes, which averaged 123 k. The signals acquired from the sponge electrodes and the classic wet electrodes were analyzed with correlation analysis to study the effectiveness. The results indicated that the signals were similar to each other with an average correlation of 90.03% and 82.56% in two-second and ten-second temporal resolutions, respectively, and 97.18% in frequency responses. Furthermore, by applying the proposed differentiable power algorithm to the system, the average accuracy of 21 subjects can reach 91.11% in the steady-state visually evoked potential (SSVEP)-based BCI application regarding a simulated military mission. To sum up, the smart helmet is capable of assisting the soldiers to execute instructions with SSVEP-based BCI when their hands are not available and is a reliable piece of equipment for strategical applications.
Multimodal Fuzzy Fusion for Enhancing the Motor-Imagery-Based Brain Computer Interface
(2019-02-01)
Ko, Li-Wei
;
Lu, Yi-Chen
;
Chang, Yang
;
Bustince, Humberto
;
Fernandez, Javier
Brain-computer interface technologies, such as steady-state visually evoked potential, P300, and motor imagery are methods of communication between the human brain and the external devices. Motor imagery-based brain-computer interfaces are popular because they avoid unnecessary external stimuli. Although feature extraction methods have been illustrated in several machine intelligent systems in motor imagery-based brain-computer interface studies, the performance remains unsatisfactory. There is increasing interest in the use of the fuzzy integrals, the Choquet and Sugeno integrals, that are appropriate for use in applications in which fusion of data must consider possible data interactions. To enhance the classification accuracy of brain-computer interfaces, we adopted fuzzy integrals, after employing the classification method of traditional brain-computer interfaces, to consider possible links between the data. Subsequently, we proposed a novel classification framework called the multimodal fuzzy fusion-based brain-computer interface system. Ten volunteers performed a motor imagery-based brain-computer interface experiment, and we acquired electroencephalography signals simultaneously. The multimodal fuzzy fusion-based brain-computer interface system enhanced performance compared with traditional brain-computer interface systems. Furthermore, when using the motor imagery-relevant electroencephalography frequency alpha and beta bands for the input features, the system achieved the highest accuracy, up to 78.81% and 78.45% with the Choquet and Sugeno integrals, respectively. Herein, we present a novel concept for enhancing brain-computer interface systems that adopts fuzzy integrals, especially in the fusion for classifying brain-computer interface commands.
Novel Moisture Retention Sponge Electrodes for Developing a Wireless EEG SSVEP-based BCI System
(2018-01-01)
Ko, Li-Wei
;
Chang, Yang
;
Wu, Pei-Lun
;
Lu, Yi-Chen
;
Yeh, Chia-Lung
Brain computer interface (BCI) is a method of communication between human brain and external device. Among the existing BCIs, steady-state visual evoked potential (SSVEP) is a common BCI technique due to its excellent signal-to-noise ratio (SNR) and relative immunity against artifacts. However, it remains some limitations regarding applying such technique in practical scenarios; one of the limitations is the trade-off between wet and dry EEG electrodes. In this study, we proposed a novel moisture retention sponge electrode and an innovative differentiable power algorithm for developing SSVEP-based BCI applications. The test of impedance suggested that the sponge electrode exhibited lower impedance compared with metal electrodes, which is adequate when hair is present. The proposed algorithm also demonstrated better accuracy regarding SSVEP-based BCI application. Adopting both innovations could strengthen the feasibility of the real-world applications of BCI.