Application of hybrid fuzzy interval-based machine learning models on financial time series - A case study of Taiwan biotech index during the epidemic period.

In recent years, the use of machine learning to predict stock market indices has emerged as a vital concern in the FinTech domain. However, the inherent nature of point estimation in traditional supervised machine learning models leads to an almost negligible probability of achieving perfect predictions, significantly constraining the applicability of machine learning prediction models. This study employs 4 machine learning models, namely BPN, LSTM, RF, and ELM, to establish predictive models for the Taiwan biotech index during the COVID-19 period. Additionally, it integrates the Gaussian membership function MF from fuzzy theory to develop 4 hybrid fuzzy interval-based machine learning models, evaluating their predictive accuracy through empirical analysis and comparing them with conventional point estimation models. The empirical data is sourced from the financial time series of the "M1722 Listed Biotechnology and Medical Care Index" compiled by the Taiwan Economic Journal during the outbreak of the COVID-19 pandemic, aiming to understand the effectiveness of machine learning models in the face of significant disruptive factors like the pandemic. The findings demonstrate that despite the influence of COVID-19, machine learning remains effective. LSTM performs the best among the models, both in traditional mode and after fuzzy interval enhancement, followed by the ELM and RF models. The predictive results of these three models reach a certain level of accuracy and all outperform the BPN model. Fuzzy-LSTM effectively predicts at a 68% confidence level, while Fuzzy-ELM and Fuzzy-RF yield better results at a 95% confidence level. Fuzzy-BPN exhibits the lowest predictive accuracy. Overall, the fuzzy interval-based LSTM excels in time series prediction, suggesting its potential application in forecasting time series data in financial markets to enhance the efficacy of investment analysis for investors.

EFFECTIVE INDICES FOR MONITORING MENTAL WORKLOAD WHILE PERFORMING MULTIPLE TASKS.

This study identified several physiological indices that can accurately monitor mental workload while participants performed multiple tasks with the strategy of maintaining stable performance and maximizing accuracy. Thirty male participants completed three 10-min. simulated multitasks: MATB (Multi-Attribute Task Battery) with three workload levels. Twenty-five commonly used mental workload measures were collected, including heart rate, 12 HRV (heart rate variability), 10 EEG (electroencephalography) indices (α, ß, θ, α/θ, θ/ß from O1-O2 and F4-C4), and two subjective measures. Analyses of index sensitivity showed that two EEG indices, θ and α/θ (F4-C4), one time-domain HRV-SDNN (standard deviation of inter-beat intervals), and four frequency-domain HRV: VLF (very low frequency), LF (low frequency), %HF (percentage of high frequency), and LF/HF were sensitive to differentiate high workload. EEG α/θ (F4-C4) and LF/HF were most effective for monitoring high mental workload. LF/HF showed the highest correlations with other physiological indices. EEG α/θ (F4-C4) showed strong correlations with subjective measures across different mental workload levels. Operation strategy would affect the sensitivity of EEG α (F4-C4) and HF.

Evaluating the effectiveness of using electroencephalogram power indices to measure visual fatigue.

Electroencephalography (EEG) is widely used in cognitive and behavioral research. This study evaluates the effectiveness of using the EEG power index to measure visual fatigue. Three common visual fatigue measures, critical-flicker fusion (CFF), near-point accommodation (NPA), and subjective eye-fatigue rating, were used for comparison. The study participants were 20 men with a mean age of 20.4 yr. (SD = 1.5). The experimental task was a car-racing video game. Results indicated that the EEG power indices were valid as a visual fatigue measure and the sensitivity of the objective measures (CFF and EEG power index) was higher than the subjective measure. The EEG beta and EEG alpha were effective for measuring visual fatigue in short- and long-duration tasks, respectively. EEG beta/alpha were the most effective power indexes for the visual fatigue measure.