Massive open online courses (MOOCs) have been an important learning tool in education. In order to reduce the high dropout rate and improve learners' satisfactions, it is urgent for MOOCs platform to provide course recommendation and tutoring service. To achieve it, it is necessary to determine and trace learners' learning state. Cognitive diagnosis in psychometric is a good way to quantify learners' capacities, but it demands explicit learner feedback, which does not always exist in MOOCs platform, such a typical weak-interaction scenario. Therefore, in this article, multidimensional item response theory (MIRT) is exploratively integrated into recommendation models in MOOCs by introducing a time-effectiveness hypothesis to obtain the implicit response on a followed course. To dynamically update learners' capacities by considering real-time and capacity multidimensionality, MIRT is extended to a capacity tracing model. The estimation for learner capacity is treated as attributes and integrated into collaborative filtering framework in course recommendation. To the best of our knowledge, this is the first work to integrate capacity tracing into course recommendation in MOOCs. Extensive experiments are conducted on a real-world dataset, demonstrating that the capacity tracing-enhanced course recommendation has improved effectiveness and explainability in MOOCs.

Noise level is an important parameter in many visual applications, especially in image denoising. How to accurately estimate the noise level from a noisy image is a challenging problem. However, for color image denoising, it is not that the more accurate the noise level is, the better the denoising performance is, but that the noise level higher than the true noise can achieve a better denoising result. For better denoising, we propose a statistical iterative method based on low-rank image patches. We select the low-rank patches in the image and calculate the eigenvalues of the covariance matrix of these patches. Unlike the existing methods that take the smallest eigenvalue as the estimated noise level, the proposed method analyzes the relationship between the median value and the mean value of the eigenvalue according to the statistical property and selects an appropriate number of eigenvalues to average as the estimated noise level. Extensive experiments are conducted, demonstrating that our estimated noise level reaches the highest value of all comparison methods. And the denoising results on color images of our method outperform all the state-of-the-art methods and the true noise level.

The scarcity of high-quality large-scale labeled datasets poses a huge challenge for employing deep learning models in video deception detection. To address this issue, inspired by the psychological theory on the relation between deception and expressions, we propose a novel method called AFFAKT in this paper, which enhances the classification performance by transferring useful and correlated knowledge from a large facial expression dataset. Two key challenges in knowledge transfer arise: 1) how much knowledge of facial expression data should be transferred and 2) how to effectively leverage transferred knowledge for the deception classification model during inference. Specifically, the optimal relation mapping between facial expression classes and deception samples is firstly quantified using proposed H-OTKT module and then transfers knowledge from the facial expression dataset to deception samples. Moreover, a correlation prototype within another proposed module SRKB is well designed to retain the invariant correlations between facial expression classes and deception classes through momentum updating. During inference, the transferred knowledge is fine-tuned with the correlation prototype using a sample-specific re-weighting strategy. Experimental results on two deception detection datasets demonstrate the superior performance of our proposed method. The interpretability study reveals high associations between deception and negative affections, which coincides with the theory in psychology.

Introduction: Emotion and attention regulation significantly influence various aspects of human functioning and behavior. However, the interaction between emotion and attention in affecting performance remains underexplored. This study aims to investigate how individual differences in sustained attention, influenced by varying emotional states.Methods: A total of 12 participants underwent emotion induction through Virtual Reality (VR) videos; completed an AX-CPT (continuous performance test) task to measure sustained attention, for which task performance is evaluated from two aspects, task accuracy and task reaction times; and reported their flow states. EEG and PPG data were collected throughout the sessions, as supporting evidence for sustained attention.Results: Our findings suggest that emotional valence and arousal significantly influence task reaction times and sustained attention, when gender differences are accounted for, but do not significantly impact task accuracy. Specifically, males responded faster under high-arousal negative emotions, while females responded faster under high-arousal positive emotions. Additionally, we find that flow experience is not significantly impacted by emotions states or sustained attention.Discussion: The study underscores the nuanced interplay between emotion, sustained attention, and task performance, suggesting that emotional states can differentially impact cognitive processes. Also, it support the use of VR, EEG, and PPG technologies in future research on related topics. Future research could expand upon this study by including larger sample sizes and a wider range of emotional inductions to generalize the findings.

Forced-choice questionnaires involve presenting items in blocks and asking respondents to provide a full or partial ranking of the items within each block. To prevent involuntary or voluntary response distortions, blocks are usually formed of items that possess similar levels of desirability. Assembling forced-choice blocks is not a trivial process, because in addition to desirability, both the direction and magnitude of relationships between items and the traits being measured (i.e., factor loadings) need to be carefully considered. Based on simulations and empirical studies using item pairs, we provide recommendations on how to construct item pairs matched by desirability. When all pairs contain items keyed in the same direction, score reliability is improved by maximizing within-block loading differences. Higher reliability is obtained when even a small number of pairs consist of unequally keyed items.