Contact Jun Cao
Areas of expertise
- Bioinformatics
- Computing, Simulation & Modelling
- Through-life Engineering Services
Background
Jun awarded Bachelor's degree in Detection and Guidance and Control Techniques at Beihang University (China, 2017). He moved on to complete an MSc in Digital Signal Processing at the University of Manchester (England, 2018). He chose the MSc to further advance his knowledge in signal processing, communication, and machine learning. Now, Jun is pursuing a Ph.D. in Manufacturing at Cranfield University. This Ph.D. project aims to develop an EEG-based brain functional and effective connectivity (BiFEC) estimation and visualisation technique to identify new sensitive, non-invasive, and reproducible biomarkers for diagnosing and monitoring neurological diseases.Current activities
Review and Case study
- To systematically review brain functional and effective connectivity methods in accordance with their properties, such as linear or nonlinear, parametric or non-parametric, time, frequency or time-frequency domain and directed or undirected.
- To review various distinct approaches of brain connectivity visualisation
- A case study related to Alzheimer’s disease, supported by Support Vector Machine (SVM) classification method, to evaluate several brain connectivity methods.
Originality and Novelty of brain connectivity methods
- To develop estimation methods of Functional and Effective connectivity
- To extract and comprehensively analyse the information in Time, frequency and
time-frequency domain
- To develop Nonlinear and Dynamic methods
Evaluation of the proposed methods
- To implement the Functional and Effective connectivity methods in several cases, such as Alzheimer's disease, epilepsy and Parkinson’s disease
- Quantification analysis supported by Machine learning, such as Support Vector Machine(SVM), Random Forest, K-Nearest Neighbour (KNN) and Naïve Bayes.
- Multiple dimensions to evaluate the classification results, like accuracy, sensitivity, and Specificity, as well as the receiver operating characteristic (ROC) curve, and the area under the ROC curve (AUC).
Increase of Interpretability
- To devolve appropriate Visualisation methods
- To achieve Real-time monitoring of brain connectivity
- Supported by Augmented Reality
Validation of the imaging system
- EEG data resources is provided by a local NHS hospital
- Supported by Doctors’ knowledge and experience
- To explore medical and neuroscience findings
Publications
Articles In Journals
- Shan X, Cao J, Huo S, Chen L, Sarrigiannis PG & Zhao Y (2022) Spatial–temporal graph convolutional network for Alzheimer classification based on brain functional connectivity imaging of electroencephalogram, Human Brain Mapping, 43 (17) 5194-5209.
- Cao J, Martin Garro E & Zhao Y (2022) EEG/fNIRS Based workload classification using functional brain connectivity and machine learning, Sensors, 22 (19) Article No. 7623.
- Cao J, Zhao Y, Shan X, Blackburn D, Wei J, Erkoyuncu JA, Chen L & Sarrigiannis PG (2022) Ultra-high-resolution time-frequency analysis of EEG to characterise brain functional connectivity with the application in Alzheimer's disease, Journal of Neural Engineering, 19 (4) Article No. 046034.
- Cao J, Zhao Y, Shan X, Wei H-L, Guo Y, Chen L, Erkoyuncu JA & Sarrigiannis PG (2022) Brain functional and effective connectivity based on electroencephalography recordings: a review, Human Brain Mapping, 43 (2) 860-879.
- Cao J, Grajcar K, Shan X, Zhao Y, Zou J, Chen L, Li Z, Grunewald R, Zis P, De Marco M, Unwin Z, Blackburn D & Sarrigiannis PG (2021) Using interictal seizure-free EEG data to recognise patients with epilepsy based on machine learning of brain functional connectivity, Biomedical Signal Processing and Control, 67 (May) Article No. 102554.
- Shan X, Huo S, Yang L, Cao J, Zou J, Chen L, Sarrigiannis PG & Zhao Y (2021) A revised Hilbert-Huang transformation to track non-stationary association of electroencephalography signals, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 29 841-851.