EEG-based Mental Fatigue Detection Using Cognitive Tests and RVM Classification

This research has three parts addressing classification, especially the imbalanced data problem, which is one of the most popular and essential issues in the domain of classification. The first part is to study the Adaptive Boosting (AdaBoost) algorithm. AdaBoost is an effective solution for classification, but it still needs improvement in the imbalanced data problem. This part proposes a method to improve the AdaBoost algorithm using the new weighted vote parameters for the weak classifiers. Our proposed weighted vote parameters are determined not only by the global error rate but also by the classification accuracy rate of the positive class, which is our primary interest. The imbalanced index of the data is also a factor in constructing our algorithms. The numeric studies show that our proposed algorithms outperform the traditional ones, especially regarding the evaluation criterion of the F--1 Measure. Theoretic proofs of the advantages of our proposed algorithms are presented. The second part treats the Relevance Vector Machine (RVM), which is a supervised learning algorithm extended from the Support Vector Machine (SVM) based on the Bayesian sparsity model. Compared with the regression problem, RVM classification is challenging to conduct because there is no closed-form solution for the weight parameter posterior. The original RVM classification algorithm uses Newton's method in optimization to obtain the mode of weight parameter posterior, then approximates it by a Gaussian distribution in Laplace's method. This original model would work, but it just applies the frequency methods in a Bayesian framework. This part first proposes a Generic Bayesian RVM classification, which is a pure Bayesian model. We conjecture that our algorithm achieves convergent estimates of the quantities of interest compared with the nonconvergent estimates of the original RVM classification algorithm. Furthermore, a fully Bayesian approach with the hierarchical hyperprior structure for RVM classification is proposed, which improves the classification performance, especially in the imbalanced data problem. The third part is an extended work of the second one. The original RVM classification model uses the logistic link function to build the likelihood, which makes the model hard to conduct since the posterior of the weight parameter has no closed-form solution. This part proposes the probit link function approach instead of the logistic one for the likelihood function in RVM classification, namely PRVM (RVM with the Probit link function). We show that the posterior of the weight parameter in our model follows the multivariate normal distribution and achieves a closed-form solution. A latent variable is needed in our algorithm to simplify the Bayesian computation greatly, and its conditional posterior follows a truncated normal distribution. Compared with the original RVM classification model, our proposed one is another pure Bayesian approach and it has a more efficient computation process. For the prior structure, we first consider the Normal-Gamma independent prior to propose a Generic Bayesian PRVM algorithm. Furthermore, the Fully Bayesian PRVM algorithm with a hierarchical hyperprior structure is proposed, which improves the classification performance, especially in the imbalanced data problem.

Microcalcification (MC) clusters in mammograms can be important early signs of breast cancer in women. Accurate detection of MC clusters is an important but challenging problem. In this paper, we propose the use of a recently developed machine learning technique -- relevance vector machine (RVM) -- for automatic detection of MCs in digitized mammograms. RVM is based on Bayesian estimation theory, and as a feature it can yield a decision function that depends on only a very small number of so-called <i>relevance vectors</i>. We formulate MC detection as a supervised-learning problem, and use RVM to classify if an MC object is present or not at each location in a mammogram image. MC clusters are then identified by grouping the detected MC objects. The proposed method is tested using a database of 141 clinical mammograms, and compared with a support vector machine (SVM) classifier which we developed previously. The detection performance is evaluated using the free-response receiver operating characteristic (FROC) curves. It is demonstrated that the RVM classifier matches closely with the SVM classifier in detection performance, and does so with a much sparser kernel representation than the SVM classifier. Consequently, the RVM classifier greatly reduces the computational complexity, making it more suitable for real-time processing of MC clusters in mammograms.

BackgroundMental fatigue is a common and potentially debilitating state that can affect individuals’ health and quality of life. In some cases, its manifestation can precede or mask early signs of other serious mental or physiological conditions. Detecting and assessing mental fatigue can be challenging nowadays as it relies on self-evaluation and rating questionnaires, which are highly influenced by subjective bias. Introducing more objective, quantitative, and sensitive methods to characterize mental fatigue could be critical to improve its management and the understanding of its connection to other clinical conditions.ObjectiveThis paper aimed to study the feasibility of using keystroke biometrics for mental fatigue detection during natural typing. As typing involves multiple motor and cognitive processes that are affected by mental fatigue, our hypothesis was that the information captured in keystroke dynamics can offer an interesting mean to characterize users’ mental fatigue in a real-world setting.MethodsWe apply domain transformation techniques to adapt and transform TypeNet, a state-of-the-art deep neural network, originally intended for user authentication, to generate a network optimized for the fatigue detection task. All experiments were conducted using 3 keystroke databases that comprise different contexts and data collection protocols.ResultsOur preliminary results showed area under the curve performances ranging between 72.2% and 80% for fatigue versus rested sample classification, which is aligned with previously published models on daily alertness and circadian cycles. This demonstrates the potential of our proposed system to characterize mental fatigue fluctuations via natural typing patterns. Finally, we studied the performance of an active detection approach that leverages the continuous nature of keystroke biometric patterns for the assessment of users’ fatigue in real time.ConclusionsOur results suggest that the psychomotor patterns that characterize mental fatigue manifest during natural typing, which can be quantified via automated analysis of users’ daily interaction with their device. These findings represent a step towards the development of a more objective, accessible, and transparent solution to monitor mental fatigue in a real-world environment.

Modern mental fatigue detection methods include many parameters for evaluation. For example, many researchers use human subjective evaluation or driving parameters to assess this human condition. Development of a method for detecting the functional state of mental fatigue is an extremely important task. Despite the fact that human operator support systems are becoming more and more widespread, at the moment there is no open-source solution that can monitor this human state based on eye movement monitoring in real time and with high accuracy. Such a method allows the prevention of a large number of potential hazardous situations and accidents in critical industries (nuclear stations, transport systems, and air traffic control). This paper describes the developed method for mental fatigue detection based on human eye movements. We based our research on a developed earlier dataset that included captured eye-tracking data of human operators that implemented different tasks during the day. In the scope of the developed method, we propose a technique for the determination of the most relevant gaze characteristics for mental fatigue state detection. The developed method includes the following machine learning techniques for human state classification: random forest, decision tree, and multilayered perceptron. The experimental results showed that the most relevant characteristics are as follows: average velocity within the fixation area; average curvature of the gaze trajectory; minimum curvature of the gaze trajectory; minimum saccade length; percentage of fixations shorter than 150 ms; and proportion of time spent in fixations shorter than 150 milliseconds. The processing of eye movement data using the proposed method is performed in real time, with the maximum accuracy (0.85) and F1-score (0.80) reached using the random forest method.

Mental fatigue is a state that may occur due to excessive work or long-term stress. Electroencephalography (EEG) is considered a reliable standard for mental fatigue detection. The existing EEG fatigue detection methods mainly use traditional machine learning models to classify mental fatigue after manual feature extraction. However, manual feature extraction is difficult and complicated. The quality of feature extraction largely determines the quality of the model. In this article, we collected EEG signals from 30 medical staff. The wavelet threshold denoising method was then applied to the measured EEG signal data to denoise the original EEG data, and a method based on a convolution and long short-term memory (CNN + LSTM) neural network to determine the fatigue state of medical staff. The extensive experiment on the established dataset clearly proves the advancement of our proposed algorithm compared to other neural network-based methods. Compared with the existing DNN, CNN and LSTM, the proposed model can quickly learn the information before and after the time series, so as to obtain higher classification accuracy.

ABSTRACTAddressing the challenges of low feature extraction dimensions and insufficient distinct information for gesture differentiation for smart home appliances, this article proposed an innovative gesture recognition algorithm, integrating fractional Fourier transform (FrFT) with relevance vector machine (RVM). The process involves using FrFT to transform raw gesture data into the fractional domain, thereby expanding the dimensions of information extraction. Subsequently, high‐dimensional feature vectors are created from fractional domain, and RVM classifiers are employed for joint optimization of feature selection and classification decision functions, achieving optimal classification performance. A dataset was constructed using five different types of gestures recorded on the TI millimeter‐wave radar platform to validate the effectiveness of this method. The experimental results demonstrate that the RVM selected the optimal FrFT order of 0.6, with the best feature set comprising fractional spectral entropy, peak factor, and second‐order central moment. Recognition rates for each gesture exceeded 96.2%, with an average rate of 98.5%. This performance surpasses three comparative methods in both recognition accuracy and real‐time processing, indicating high potential for future applications.

Introduction: Fatigue is a gradual and cumulative process. This mindset is related to the lack of motivation to make any effort, as well as decreased efficiency, attentiveness, and, eventually, malfunction. Aim: The present study aims to investigate how mental and muscle fatigue affects spatial working memory. Method: The research method was quasi-experimental and was performed using the pretestposttest design. The participants in this study were 20 to 30 year old male students of Shahid Beheshti University of Tehran in 2021, of whom, 14 subjects were selected by convincing method as the sample using the G-Power approach and previous investigations. The Mental Fatigue Self-Assessment Scale, Corsi Block software, Stroop software, and the Monark Bike Ergometer were utilized. In addition, the repeated measurement analysis of variance test in SPSS-23 was used to analyze the data. Results: The results indicated that mental fatigue condition had a significant effect on working memory (P=0.002); and has reduced the efficiency of working memory. But muscle fatigue conditions had no significant effect on assessing working memory, and in these conditions there was a better performance in working memory (P=0.065). Conclusion: The findings of this study emphasize the importance of mental fatigue in reducing working memory performance, even though this type of fatigue is related to cognitive and cerebral functioning. Accordingly, the findings are in line with a top-down approach, as well as cognitive perspectives such as generalized motor program theory.

After long time cognitive work, most of people confronted with the mental fatigue, which can decrease the classification accuracy of cognitive, or even cause the traffic accidents for drivers. Therefore, the detection of the fatigue state is very essential. The study aims to explore an effective and novel approach based on electroencephalogram. All participants were instructed to implement the spelling experiments. Data were recorded on the awake condition, on sleep deprivation condition and after two hour spelling experiment. To comprehensively quantify the state of mental fatigue, spectral non-negative matrix factorization and a quantification fatigue index were proposed in the data analysis. The results indicated that the quantification fatigue index significantly increased with the greater level of fatigue (p <; 0.05), and this method we proposed can discriminate the different state of fatigue. Thus this method is promising in detecting the state of mental fatigue with electroencephalogram.

It has been shown that the mental fatigue induced by prolonged self-regulation increases perception of effort and reduces performance during subsequent endurance exercise. However, the physiological mechanisms underlying these negative effects of mental fatigue are unclear. The primary aim of this study was to test the hypothesis that mental fatigue exacerbates central fatigue induced by whole-body endurance exercise. Twelve subjects performed 30 min of either an incongruent Stroop task to induce a condition of mental fatigue or a congruent Stroop task (control condition) in a random and counterbalanced order. Both cognitive tasks (CTs) were followed by a whole-body endurance task (ET) consisting of 6 min of cycling exercise at 80% of peak power output measured during a preliminary incremental test. Neuromuscular function of the knee extensors was assessed before and after CT, and after ET. Rating of perceived exertion (RPE) was measured during ET. Both CTs did not induce any decrease in maximal voluntary contraction (MVC) torque (p = 0.194). During ET, mentally fatigued subjects reported higher RPE (mental fatigue 13.9 ± 3.0, control 13.3 ± 3.2, p = 0.044). ET induced a similar decrease in MVC torque (mental fatigue –17 ± 15%, control –15 ± 11%, p = 0.001), maximal voluntary activation level (mental fatigue –6 ± 9%, control –6 ± 7%, p = 0.013) and resting twitch (mental fatigue –30 ± 14%, control –32 ± 10%, p < 0.001) in both conditions. These findings reject our hypothesis and confirm previous findings that mental fatigue does not reduce the capacity of the central nervous system to recruit the working muscles. The negative effect of mental fatigue on perception of effort does not reflect a greater development of either central or peripheral fatigue. Consequently, mentally fatigued subjects are still able to perform maximal exercise, but they are experiencing an altered performance during submaximal exercise due to higher-than-normal perception of effort.

ECG Arrhythmia Detection and Classification Using Relevance Vector Machine

Abstract—Existing electroencephalography (EEG) based Alzheimer’s disease (AD) diagnostic systems typically rely on experts to visually inspect and segment the collected signals into artefact-free epochs and on support vector machine (SVM) based classifiers. The manual selection process, however, introduces biases and errors into the diagnostic procedure, renders it “semi-automated, ” and makes the procedure costly and labour-intensive. In this paper, we overcome these limitations by proposing the use of an automated artefact removal (AAR) algorithm to remove artefacts from the EEG signal without the need for human intervention. We investigate the effects of the so-called wavelet-enhanced independent component analysis (wICA) AAR on three classes of EEG features, namely spectral power, coherence, and amplitude modulation, and ultimately, on diagnostic accuracy, specificity and sensitivity. Furthermore, we propose to replace the binary SVM classifier with a soft-decision relevance vec-tor machine (RVM) classifier. Experimental results show the proposed RVM-based system outperforming the SVM trained on features extracted from both manually-selected and wICA-processed epochs. Moreover, the class membership information output by the RVM is shown to provide clinicians with a richer pool of information to assist with AD assessment. Keywords—Alzheimer’s disease, electroencephalography, support vector machine (SVM), relevance vector machine (RVM), wICA. I.

Currently, huge sizes of indeterminate data are effortlessly collected or created at a very high pace in numerous real-life applications. Classifying this indefinite big data, is computationally intensive as large amount of data is related with existential probability of undefined or undetermined values of raw data. In this study, we propose a data mining approach for the classification of big dataset based on death toll by epidemic outbreak of Ebola virus and comparing its relevance with other epidemic diseases and generalizing error and intra class separability using relevance vector machine classifier.

Hughes phenomenon is a serious problem in supervised classification of hyperspectral images in particular for small land-cover patches. A solution for this problem through integrating the capabilities of a nonlinear discriminating analysis with relevance vector machine (RVM) is proposed in this paper. It first transforms the hyperdimensional data to a new space with a better class separability. Then, a multiclass RVM classifier processes the transformed data for precise labeling of the classes. The results show that the proposed approach outperforms both RVM as well as support vector machine (SVM), when they are applied to the original hyperdimensional data space. Indeed, it is an advantage for key information detection in the classification context.

Health has effects on children's academic performance. Qi deficiency is generally used to assess an individual's health in the Chinese traditional medicine theory. This study explores the effects of qi deficiency on children's academic performance and examines whether mental fatigue mediates these effects. A total of 550 students aged 10-13 in fifth-grade were surveyed in a big primary school in Sichuan Province in November 2023 using paper-pencil-based questionnaires. Qi deficiency and mental fatigue were assessed, and exam scores in Chinese and Mathematics were recorded. Pearson's correlation and linear regression analyses were used to test the mediation model and hypotheses. The fifth-grade students had mild qi deficiency (M = 2.09) and a mild state of mental fatigue (M = 2.38) on a five-point Likert scale. The average exam scores in Mathematics and Chinese were 70.07 and 74.44 points out of 100, respectively. Qi deficiency was associated with Mathematics scores (r = -0.37, p < 0.01) and Chinese scores (r = -0.30, p < 0.01), and mental fatigue (r = 0.47, p < 0.01). Furthermore, mental fatigue was associated with Mathematics scores (r = -0.46, p < 0.01) and Chinese scores (r = -0.34, p < 0.01). Linear regression analyses showed that qi deficiency significantly predicted Mathematics scores (β = -0.26, p < 0.01), Chinese scores (β = -0.19, p < 0.01), and mental fatigue (β = 0.41, p < 0.01). When qi deficiency was controlled for, mental fatigue significantly predicted Mathematics scores (β = -0.28, p < 0.01) and Chinese scores (β = -0.17, p < 0.01). The mediation model and hypotheses were well supported, indicating that mental fatigue mediated the influence of qi deficiency on academic performance of fifth-grade students. Furthermore, the mediation effect of mental fatigue on Mathematics scores was a little stronger than that on Chinese scores.

This study investigated the impact of mental fatigue and self-controlled versus yoked feedback on learning a force production task. We randomly assigned 44 non-athlete male students (Mage = 21.4, SD = 1.4 years) to four groups; (a) MF&SCF = mental fatigue & self-controlled feedback, (b) MF&Y = mental fatigue & yoked, (c) NMF&SCF = no mental fatigue & self-controlled feedback, and (d) NMF&Y = no mental fatigue & yoked). SCF group participants were provided feedback whenever they requested it, while YK group participants received feedback according to a schedule created by their SCF counterparts. To induce mental fatigue, participants performed a Stroop color-word task for one hour. During the acquisition (practice) phase, participants were asked to produce a given percentage of their maximum force (20%) in 12 blocks of six trials. We recorded the participants' absolute error at the end of the acquisition phase, the immediate retention test, the first transfer test, and the second transfer test (after 24 hours and without any further mental fatigue). The acquisition phase data were analyzed in a 2 (feedback) × 2 (mental fatigue) × 12 (block) ANOVA with repeated measures on the last factor, while the retention and transfer data were analyzed in 2 (feedback) × 2 (mental fatigue) ANOVAs. We found that all four groups made significant progress during practice (p < .001), but there were no significant group differences during this phase (p>.05). There was a significant interaction effect of self-controlled feedback and mental fatigue at retention (p = .018) and transfer testing (p < .001). In the mental fatigue condition, participants in the self-controlled group had poorer learning compared to participants in the yoked group; but when not mentally fatigued, participants in the self-controlled group had better learning than those in the yoked group. These findings suggest that mental fatigue reduces typical advantages of self-controlled feedback in motor learning.