Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Wei Quan has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Respiratory Disease Classification Using NMF-Enhanced Log-Mel Spectrograms and Convolutional Recurrent Neural Networks

    by Bowen Han, Wei Quan, Bogdan Matuszewski, Dennis Corbett

    Respiratory disease classification using lung sound recordings remains challenging due to signal interference, heterogeneous acquisition conditions, and substantial overlap among clinically related acoustic patterns. This study presents a framework for respiratory disease classification using NMF-enhanced log-mel spectrograms and deep neural classifiers. Respiratory sound recordings from two publicly available datasets were harmonized into a unified label space comprising Asthma, Bronchiectasis, Bronchiolitis, COPD, Healthy, Pneumonia and URTI. Following signal standardization and fixed-length segmentation, a non-negative matrix factorization (NMF)-based enhancement stage was applied to increase the salience of respiratory components prior to log-mel spectrogram generation. The proposed classifier was a convolutional recurrent neural network (CRNN) that combined convolutional feature extraction, bidirectional recurrent modelling, and attention-based temporal aggregation. For comparison, RDLINet, a conventional CNN, ResNet, and a YOLO-style backbone were implemented under the same preprocessing and training framework. Experimental results demonstrated that the proposed CRNN achieved the best overall performance, attaining 96.14 ± 0.50% accuracy and 94.05 ± 1.21% Macro-F1 on the unified seven-class cohort. Class-wise analysis, confusion-matrix evaluation, and output-space visualization further showed that the CRNN provided more balanced recognition across disease categories and clearer class separation than competing architectures. These findings indicate that NMF-enhanced spectro-temporal modelling combined with convolutional recurrent learning offers an effective approach for automated multi-class respiratory disease classification.


  • Open Access

    Real-time Monitoring of 3D Printing Using Between-layer Structural Similarity (BLSS)

    by Milan Sumegi, Wei Quan, Hadley L. Brooks, Lik-Kwan Shark

    This research introduces an innovative method specifically designed for comprehensive error detection in the 3D printing process. The Between-layer Structural Similarity (BLSS) technique gauges the similarity between displacement maps, which are generated using the Structural Similarity Index Measure (SSIM). This allows for the differentiation between consecutive layers in both simulated and actual prints. Utilising the Fast Fourier Transform (FFT), the displacement maps can be converted to the frequency domain and assessed for similarity. The proposed approach involves three key processing stages: print simulation and processing, print capture and processing, and BLSS-based structural analysis and evaluation. This methodology not only reduces material wastage but also lays the foundation for automated systems capable of halting or terminating live printing processes upon error detection. Experimental results reveal that printing defects occur below 97.5 % of the similarity value, establishing this threshold as appropriate. This underscores the effectiveness of the system in error detection and its potential for real-time quality control in 3D printing.


  • Open Access

    Development of Landmark-based Facial Asymmetry Evaluation

    by Wei Quan, Ziyu Ye, Bogdan J. Matuszewski

    This paper presents a novel development of a real-time evaluation system for facial asymmetry. Using this tool, it is expected possibly to assess the severity of facial asymmetry based on local and global comparisons of facial components. While the local one measures distances between the landmarks inside each facial region, the global one focuses on the overall difference of all facial regions about the sagittal plane. This reported preliminary work is focused on assessing the suitability of the existing image landmark detection methods for a real-time evaluation. Three commonly used deep learning-based methodologies have been implemented and tested in order to identify robust facial landmark detection under various challenging conditions. It is hypothesized, that the proposed system will be able to provide a more accurate measurement of facial asymmetry. The key is the proposed use of the geodesic distance calculated based on the geometry of human faces, with the help of the state-of-art depth camera.