@article{luo_stroke_2025,

title = {Stroke features in the Chinese character recognition},

author = {F. Luo and Y. Zhang and W. Liang and C. Blais and M. -P. Plouffe Demers and D. Fiset and D. Sun and B. Chen},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105024609336&doi=10.1177%2F17470218251357441&partnerID=40&md5=04053a28f9602f36a971eadd4f981cdb},

doi = {10.1177/17470218251357441},

issn = {17470218 (ISSN)},

year  = {2025},

date = {2025-01-01},

journal = {Quarterly Journal of Experimental Psychology},

abstract = {While line vertices, terminations, and midsegments are critical for Roman letter identification, the diagnostic features of Chinese character strokes remain unclear. This study examines how local stroke-level features and global line-relation mechanisms contribute to Chinese character recognition. In Experiment 1, we applied the Bubbles classification image technique to native Chinese readers to identify diagnostic stroke features. Results revealed four key features: horizontal hooks, dots, vertical turnings, and raises. These features, while analogous to terminations in alphabetic systems, reflect unique dynamics of Chinese stroke production, marking stroke origins and terminations. Experiment 2 employed a delayed-segment paradigm to assess functional significance of these features. Greater degradation of vertices and midsegments significantly prolonged reaction times, and removal of stroke-based terminations (e.g., hooks) impaired recognition accuracy. Together, these findings support a two-tiered hierarchy in Chinese character recognition: stroke-specific terminals enable fine-grained feature discrimination, while line-relation features support global structural integration. The results affirm script-general principles (midsegments and vertices as perceptual anchors) and highlight language-specific adaptations, where stroke terminations function as dynamic positional cues. © Experimental Psychology Society 2025},

keywords = {Bubbles technique, Chinese stroke recognition, delayed-segment paradigm, script-specific adaptations, visual features},

pubstate = {published},

tppubtype = {article}

}

@article{joudeh_predicting_2024,

title = {Predicting the Arousal and Valence Values of Emotional States Using Learned, Predesigned, and Deep Visual Features †},

author = {I. O. Joudeh and A. -M. Cretu and S. Bouchard},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85198382238&doi=10.3390%2fs24134398&partnerID=40&md5=cefa8b2e2c044d02f99662af350007db},

doi = {10.3390/s24134398},

issn = {14248220 (ISSN)},

year  = {2024},

date = {2024-01-01},

journal = {Sensors},

volume = {24},

number = {13},

publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},

abstract = {The cognitive state of a person can be categorized using the circumplex model of emotional states, a continuous model of two dimensions: arousal and valence. The purpose of this research is to select a machine learning model(s) to be integrated into a virtual reality (VR) system that runs cognitive remediation exercises for people with mental health disorders. As such, the prediction of emotional states is essential to customize treatments for those individuals. We exploit the Remote Collaborative and Affective Interactions (RECOLA) database to predict arousal and valence values using machine learning techniques. RECOLA includes audio, video, and physiological recordings of interactions between human participants. To allow learners to focus on the most relevant data, features are extracted from raw data. Such features can be predesigned, learned, or extracted implicitly using deep learners. Our previous work on video recordings focused on predesigned and learned visual features. In this paper, we extend our work onto deep visual features. Our deep visual features are extracted using the MobileNet-v2 convolutional neural network (CNN) that we previously trained on RECOLA’s video frames of full/half faces. As the final purpose of our work is to integrate our solution into a practical VR application using head-mounted displays, we experimented with half faces as a proof of concept. The extracted deep features were then used to predict arousal and valence values via optimizable ensemble regression. We also fused the extracted visual features with the predesigned visual features and predicted arousal and valence values using the combined feature set. In an attempt to enhance our prediction performance, we further fused the predictions of the optimizable ensemble model with the predictions of the MobileNet-v2 model. After decision fusion, we achieved a root mean squared error (RMSE) of 0.1140, a Pearson’s correlation coefficient (PCC) of 0.8000, and a concordance correlation coefficient (CCC) of 0.7868 on arousal predictions. We achieved an RMSE of 0.0790, a PCC of 0.7904, and a CCC of 0.7645 on valence predictions. © 2024 by the authors.},

note = {Publisher: Multidisciplinary Digital Publishing Institute (MDPI)},

keywords = {adult, Affective interaction, Arousal, artificial neural network, Cognitive state, Cognitive/emotional state, Collaborative interaction, computer, Convolutional neural networks, correlation coefficient, Deep learning, emotion, Emotional state, Emotions, female, Forecasting, Helmet mounted displays, human, Humans, Learning algorithms, Learning systems, Long short-term memory, Machine learning, Machine-learning, male, Mean square error, Neural networks, physiology, Regression, Root mean squared errors, Video recording, virtual reality, Visual feature, visual features},

pubstate = {published},

tppubtype = {article}

}