A wearable system for the personalized EEG-based detection of engagement in learning 4.0 is proposed. In particular, the effectiveness of the proposed solution is assessed by means of the classification accuracy in predicting engagement. The system can be used to make an automated teaching platform adaptable to the user, by managing eventual drops in the cognitive and emotional engagement. The effectiveness of the learning process mainly depends on the engagement level of the learner. In case of distraction, lack of interest or superficial participation, the teaching strategy could be personalized by an automatic modulation of contents and communication strategies. The system is validated by an experimental case study on twenty-one students. The experimental task was to learn how a specific human-machine interface works. Both the cognitive and motor skills of participants were involved. De facto standard stimuli, namely (1) cognitive task (Continuous Performance Test), (2) music background (Music Emotion Recognition—MER database), and (3) social feedback (Hermans and De Houwer database), were employed to guarantee a metrologically founded reference. In within-subject approach, the proposed signal processing pipeline (Filter bank, Common Spatial Pattern, and Support Vector Machine), reaches almost 77% average accuracy, in detecting both cognitive and emotional engagement.
30 March 2023 in Engineering Applications of Artificial Intelligence
In recent years, Artificial Neural Networks (ANNs) have been introduced in Structural Health Monitoring (SHM) systems. A semi-supervised method with a data-driven approach allows the ANN training on data acquired from an undamaged structural condition to detect structural damages. In standard approaches, after the training stage, a decision rule is manually defined to detect anomalous data. However, this process could be made automatic using machine learning methods. This paper proposes a semi-supervised method with a data-driven approach to detect structural anomalies. The methodology consists of: 1) a Variational Autoencoder (VAE) to approximate undamaged data distribution and 2) a One-Class Support Vector Machine (OC-SVM) to discriminate different health conditions using damage-sensitive features extracted from VAE’s signal reconstruction. The method is applied to a scale steel structure that was tested in nine damage scenarios by IASC-ASCE Structural Health Monitoring Task Group.
An electroencephalography (EEG)-based classification system of three levels of fear of heights is proposed. A virtual reality (VR) scenario representing a canyon was exploited to gradually expose the subjects to fear inducing stimuli with increasing intensity. An elevating platform allowed the subjects to reach three different height levels. Psychometric tools were employed to initially assess the severity of fear of heights and to assess the effectiveness of fear induction. A feasibility study was conducted on eight subjects who underwent three experimental sessions. The EEG signals were acquired through a 32-channel headset during the exposure to the eliciting VR scenario. The main EEG bands and scalp regions were explored in order to identify which are the most affected by the fear of heights. As a result, the gamma band, followed by the high-beta band, and the frontal area of the scalp resulted the most significant. The average accuracies in the within-subject case for the three-classes fear classification task, were computed. The frontal region of the scalp resulted particularly relevant and an average accuracy of (68.20 ± 11.60) % was achieved using as features the absolute powers in the five EEG bands. Considering the frontal region only, the most significant EEG bands resulted to be the high-beta and gamma bands achieving accuracies of (57.90 ± 10.10) % and of (61.30 ± 8.43) %, respectively. The Sequential Feature Selection (SFS) confirmed those results by selecting for the whole set of channels, in the 48.26 % of the cases the gamma band and in the 22.92 % the high-beta band and by achieving an average accuracy of (86.10 ± 8.29) %.
The specialized language and complex concepts in physics pose significant challenges for information extraction through Natural Language Processing (NLP). Central to effective NLP applications is the text embedding model, which converts text into dense vector representations for efficient information retrieval and semantic analysis. In this work, we introduce PhysBERT, the first physics-specific text embedding model. Pre-trained on a curated corpus of 1.2 × 106 arXiv physics papers and fine-tuned with supervised data, PhysBERT outperforms leading general-purpose models on physics-specific tasks, including the effectiveness in fine-tuning for specific physics subdomains.