NZCDP(Stage III), BSc, PGCertTertT, PGDipSci, MSc, PhD (Otago)
Dr Brendon Woodford lectures in the diverse areas of knowledge engineering, machine learning, information systems development, and health informatics.
He conducts research for the Knowledge, Intelligence and Web Informatics (KIWI) Laboratory in the areas of artificial neural networks, fuzzy systems, data visualisation, and image processing and recognition. Since 1998 the overall aim of this research is in the area of computational intelligence. The main objective of his work has been to create adaptive learning systems which generate new knowledge from data that they process and allow for improved decision making in difficult real-world domains.
In the past the application of this work has been improving upon existing machine learning techniques to support decision making and data mining primarily in the horticultural domain but the current focus in now in the health data analytics domain.
This research has contributed to 27 publications to date in both international journals and in some of the top international conferences. In 2008 he completed a PhD which primarily looked at the development and implementation of intelligent decision support systems for New Zealand’s horticulture industry.
Lin, H., Deng, J. D., & Woodford, B. J. (2016). Shot boundary detection using multi-instance incremental and decremental one-class support vector machine. In J. Bailey, L. Khan, T. Washio, G. Dobbie, J. Z. Huang & R. Wang (Eds.), Advances in knowledge discovery and data mining: Lecture Notes in Artificial Intelligence (Vol. 9651). (pp. 165-176). Cham, Switzerland: Springer. doi: 10.1007/978-3-319-31753-3_14
Lin, H., Deng, J. D., Woodford, B. J., & Shahi, A. (2016). Online weighted clustering for real-time abnormal event detection in video surveillance. Proceedings of the Association for Computing Machinery (ACM) on Multimedia Conference. (pp. 536-540). New York, NY: ACM. doi: 10.1145/2964284.2967279
Shah, M., Deng, J. D., & Woodford, B. J. (2015). A Self-Adaptive CodeBook (SACB) model for real-time background subtraction. Image & Vision Computing, 38, 52-64. doi: 10.1016/j.imavis.2015.02.001
Shahi, A., Woodford, B. J., & Deng, J. D. (2015). Event classification using adaptive cluster-based ensemble learning of streaming sensor data. In B. Pfahringer & J. Renz (Eds.), Advances in artificial intelligence: Lecture notes in artificial intelligence (Vol. 9457). (pp. 505-516). Cham, Switzerland: Springer. doi: 10.1007/978-3-319-26350-2_45
Lin, H., Deng, J. D., & Woodford, B. J. (2015). Anomaly detection in crowd scenes via online adaptive one-class support vector machines. Proceedings of the IEEE International Conference on Image Processing (ICIP). (pp. 2434-2438). IEEE. doi: 10.1109/icip.2015.7351239