Dr. Jeremiah D. Deng

Associate Professor
Department of Information Science
University of Otago
Po Box 56, Dunedin, New Zealand
Tel: 64-3-479 8090, Fax: 64-3-479 8311
E-mails - jddeng at ieee dot org / jeremiah.deng at otago.ac.nz -

Office: Room CO8.13, Commerce Bld., Cnr Union St. & Clyde St.

Teaching

S2: INFO411 - Machine Learning and Data Mining S2: INFO204 - Introduction to Data Science

Research

I lead the PRML Lab, and also coordinate the Telecommunications Programme.

Selected recent publications:

Machine learning & computational intelligence

Superpixel-based graph algorithms for image segmentation
  • X Gu, JD Deng, A Multi-Feature Bipartite Graph Ensemble for Image Segmentation, accepted by Pattern Recognition Letters, 2019 (doi)
  • X. Gu, J. D. Deng, M. K. Purvis, Improving superpixel-based image segmentation by incorporating color covariance matrix Manifolds, Proc. ICIP'14 Paris. (Top 10% Paper)
Deep learning and domain adaptation
  • J Hou, X Ding, JD Deng, S Cranefield. Unsupervised Domain Adaptation using Deep Networks with Cross-Grafted Stacks, Proceedings of ICCV'19 Workshops, Seoul, Korea pdf (Honorary Mention, TASK-CV)
Benchmarking and performance evaluation in computational intelligence
  • Q. Liu; W-N Chen; J. D. Deng; T. Gu; H. Zhang; Z. Yu; J. Zhang. Benchmarking stochastic algorithms for global optimization problems by visualizing confidence intervals, IEEE Transactions on Cybernetics, 2017, 47(9):2924 - 2937. (doi)
Online anomaly detection in video surveillance
  • H. Lin, J. D. Deng, B. J. Woodford, A. Shahi: Online weighted clustering for real-time abnormal event detection in video surveillance. ACM Multimedia 2016: 536-540. (doi)
  • H. Lin, J. D. Deng, B. J. Woodford, Shot boundary detection using multi-instance incremental and decremental one-class support vector machines, PAKDD (1) 2016: 165-176. (doi)
  • H. Lin, J. D. Deng, B. J. Woodford, Anomaly detection in crowd scenes via online adaptive one-class support vector machines, Proc. ICIP'15 Quebec.
Adaptive swarm optimization
  • Q. Yang; W. N. Chen; J. D. Deng; Y. Li; J. Zhang, A level-based learning swarm optimizer for large scale optimization, IEEE Transactions on Evolutionary Computation, 22:578-594, 2017. (doi)
  • Q. Yang; W-N Chen; T. Gu; H. Zhang; J. D. Deng; Y. Li; J. Zhang. Segment-based predominant learning swarm optimizer for large-scale optimization, IEEE Transactions on Cybernetics, 2017, 47(9):2896 - 2910. (doi)
Scene analysis and anomaly detection
  • SP Yong, J. D. Deng, M. K. Purvis, Wildlife video key-frame extraction based on novelty detection in semantic context, Multimedia Tools and Applications, Springer, 2013. [doi]
  • SP Yong, J. D. Deng, M. K. Purvis, Novelty detection in wildlife scenes through semantic context modelling. Pattern Recognition 45(9): 3439-3450 (2012) [pdf]

    Other recent papers

  • S H-S Lee, J. D. Deng, M. K. Purvis, M. Purvis: Hierarchical Population-Based Learning for Optimal Large-Scale Coalition Structure Generation in Smart Grids. Australasian Conference on Artificial Intelligence 2018: 16-28
  • J. D. Deng, Online outlier detection of energy data streams using incremental and kernel PCA algorithms, Proc. 2016 IEEE ICDM Workshops, December 12, Barcelona, pp.390-397. (doi)
  • A. Shahi, J. D. Deng, B. Woodford, A streaning ensemble with multi-class imbalance learning for activity recognition, Proc. IEEE Inter. Joint Conf. on Neural Networks (IJCNN) 2017: 3983-3990. (doi)
  • S H-S Lee, J. D. Deng, L. Peng, M. K. Purvis, M. Purvis: Top-k merit weighting PBIL for optimal coalition structure generation of smart grids. ICONIP (4) 2017: 171-181 (doi)
  • A. Shahi, J. D. Deng, B. J. Woodford: Online hidden conditional random fields to recognize activity-driven behavior using adaptive resilient gradient learning. ICONIP (1) 2017: 515-525
  • X. Gu, J. D. Deng, M. K. Purvis, A hierarchical segmentation tree for superpixel-based image segmentation, IVCNZ'16. (doi)
  • H. Lin, J. D. Deng, B. J. Woodford, Anomaly detection in crowd scenes via online adaptive one-class support vector machines, Proc. ICIP'15 Quebec.
  • M. Shah, J. D. Deng, B. J. Woodford: A Self-adaptive CodeBook (SACB) model for real-time background subtraction. Image Vision Comput. 38: 52-64 (2015)
  • J. D. Deng, C. Simmermacher and S. Cranefield. A study on feature analysis for musical instrument classification. IEEE Trans. System, Man and Cybernetics - Part B, vol. 38, no. 2, pp.429-438, 2008. [preprint] [IEEExplore]
  • D. Deng, Content-based image collection summarization and comparison using self-organizing maps. Pattern Recognition, 40:2, pp.718-727, 2007. [doi]

Performance modeling and mobile computing

  • S. Zareei, J. D. Deng: Energy harvesting modelling for self-powered fitness gadgets: a feasibility study. IJPEDS 34(4): 412-429 (2019) (doi)
  • J. D. Deng, Performance Modelling of Synchronized Predictive Sensing for Clustered Wireless Sensor Networks, accepted by APCC'19, Ho Chi Minh City, 2019.
  • S. Zareei, J. D. Deng. Energy harvesting modelling for self-powered fitness gadgets: a feasibility study, Inter. Journal on Parallel, Emergent and Distributed Systems, 2017, online. (doi)
  • S. Zareei, A. Sedigh, J. D. Deng, M. Purvis, Buffer management using integrated queueing models for mobile energy harvesting sensors, PIMRC'17, 2017.
  • X-F Liu; Z-H Zhan; J. D. Deng; Y. Li; T. Gu; J. Zhang. An energy efficient ant colony system for virtual machine placement in cloud computing, IEEE Transactions on Evolutionary Computation, 2016, online. (doi)
  • S. Zareei, J. D. Deng, Energy management policy for fitness gadgets: a case study of human daily routines, ITNAC'16.
  • Y. Xu, J. D. Deng, M. Nowostawski, M. K. Purvis, Optimized routing for video streaming in multi-hop wireless networks using analytical capacity estimation, Journal of Computer and System Sciences, 81(1): 145-157, 2015.
  • J. D. Deng: Empirical capacity modeling and evaluation of delay tolerant network routing protocols, 33rd IEEE International Performance Computing and Communications Conference (IPCCC’14).
  • A. Javed, H. Zhang, Z. Huang, J. D. Deng, BWS: Beacon-driven wake-up scheme for train localization using wireless sensor networks, Proc. IEEE ICC 2014, pp.276-281.
  • J. D. Deng, M. K. Purvis, Multi-core application performance optimization using a constrained tandem queueing model, Journal of Network and Computer Applications, 34(6):1990-1996, Elsevier, 2011. [doi]
  • F. A. Aderohunmu, J. D. Deng, M. K. Purvis, Enhancing clustering in wireless sensor networks with energy heterogeneity, Inter. J. Business Data Communications and Networking, 7(4):18-32, IGI, 2011. PDF

Edited books

  • Proceedings of the Australasian Joint Conference on Artificial Intelligence - Workshops (AIW'19), J. D. Deng and A. Rahman Eds., ACM, 2019.
  • Proceedings of the 2nd Workshop on Machine Learning for Sensory Data Analysis (MLSDA'14), A. Rahman, J. D. Deng and J. Li Eds., ACM, 2014 (in conjunction with PRICAI'14).
  • Proceedings of the 1st Workshop on Machine Learning for Sensory Data Analysis (MLSDA'13), J. D. Deng and H. Zhang Eds., ACM, 2013 (in conjunction with AI'13).
  • Proceedings of the 27th Conf. on Image and Vision Computing New Zealand (IVCNZ'12), edited by B. McCane, S. Mills and J. D. Deng, ACM, 2012.

Talks

Services

Life beyond academia


Last modified: 6/9/2019