Our Projects
01
​Automated radiation-free assessment of scoliosis using artificial intelligence and 3D ultrasound imaging
Adolescent idiopathic scoliosis (AIS) affects between 2-4% of adolescents in the general population. Curve progression is the most probable occurrence among teenagers with AIS, the regular observation is essential for monitoring curve progression. If not appropriately treated, progressive scoliosis may cause constant back pain, poor posture, shoulder humping, breathing problems, or even physical disability for life. Sometimes may require surgery. Thus, the early detection of scoliosis is critical to providing effective clinical treatments to prevent scoliosis progression during growth. Therefore, large-scale school scoliosis screening is part of the national health program in many countries. A common test used to screen for scoliosis is called the “Adams forward bending test”. Such screening methods often identify many false positives, thereby causing unnecessary anxiety amongst subjects and their parents, in addition to burdening the healthcare system. The gold standard for identifying and monitoring AIS has been standing anteroposterior and lateral X-ray imaging. A teenager with scoliosis may receive more than 20 X-rays over the course of their treatment. It will significantly pose health risks by repeated exposure to radiation. Also, people in rural areas can have limited access to X-ray imaging facilities.
In this project, an automatic ultrasound-based radiation-free 3D screening tool will be developed for large-scale diagnosis of AIS. Advanced artificial intelligence (AI) techniques will be developed to tackle the challenges associated with accurately analysing low-quality ultrasound images. An innovative and effective 2.5D sequencing approach will be developed to capture the 3D inter-slice information to boost accuracy without adding extra computational burden. The resultant low-cost automatic scoliosis assessment system can be used for large-scale school scoliosis screening across Australia, with AI breakthrough revitalising ultrasound based health care.
02
​Deep Classification of Electroencephalography Signals for Brain-Computer Interfacing Applications
The proposal outlines a research initiative focused on enhancing the classification of electroencephalography (EEG) signals using computational intelligence (CI) techniques for brain-computer interface (BCI) applications. The aims encompass employing CI technologies to improve EEG signal classification accuracy, developing variant-topologies for fusion-based convolutional neural network (CNN) classifiers, and introducing automated meta-heuristic designs for these networks. Stability analysis of the created networks will be performed to optimize the number of reliable classes, crucial for enhancing BCI reliability. Additionally, the project aims to develop innovative applications for the efficient utilization of the model in real-world scenarios, potentially advancing fields such as medicine, robotics, and military technology. By addressing these objectives, the research endeavors to enhance the performance, reliability, and practical applicability of EEG-based BCIs, paving the way for their widespread adoption and utilization across various domains.
03
Machine learning-based signal processing on vibration data from building mechanical system for structural health monitoring
The study focuses on the vital role of vibration analysis in maintaining mechanical services within buildings, emphasizing its early detection capability to prevent costly equipment failures. Traditional tools like time waveform (TWF) and fast Fourier transform (FFT) are widely used, but integrating machine learning (ML) with signal processing presents challenges such as data requirements and computational complexity. To address these, a comprehensive approach to data collection, model design, and optimization is necessary. The study proposes employing an intelligent and adaptive ML-based signal processing approach to enhance vibration data detection.
The objectives include reviewing advanced ML and signal processing applications, developing ML algorithms to create predictive models for future signal behavior, and testing these algorithms using real-world case studies. By achieving these objectives, the study aims to improve the accuracy and efficiency of defect detection in mechanical services within buildings, ultimately leading to proactive decision-making and preventive maintenance strategies. This research has the potential to significantly enhance the reliability and longevity of equipment, thereby reducing maintenance costs and minimizing disruptions to building operations.
04
A transformer-based voice classification model to determine D2 receptor binding affinity of antipsychotic medication
Extrapyramidal Side Effects (EPSE) are caused by the administration of antipsychotic (AP) medications. These medications bind to the Dopamine 2 Receptor (D2R) receptor inducing EPSE. The severity of the disease is directly related to the binding affinity to these receptors. The rigidity, bradykinesia, dystonia caused by these medications affects the patients voice, handwriting and motor function. Using novel artificial intelligence models, we can detect any changes in the symptoms. In this study a hybrid transformer encoder model would be used for analyzing sound waves. As sound is polluted with random frequencies, the signal would be first converted to Mel-frequency cepstral coefficients (MFCC) to give noise robustness. To combat the small data size, a pretrained model will be concatenated with the transformer encoder. Then a DR2 binding score would be achieved for each drug type and finally a correlation between the changes in the voice and type of antipsychotic would be conducted. To validate this model the subjective and objective EPSE symptom scale would be used. This study aims to develop a quick decision model for psychiatrists when prescribing APs, improving patient outcomes and care.
