Boris Bačić

profile image

Senior Lecturer

Phone: +64 9 921 9999 Ext. 5115

Email: boris.bacic@aut.ac.nz

PhysicalAddress:
School of Computing and Mathematical Sciences (D-75),
Auckland University of Technology,
AUT Tower, 2-14 Wakefield Street,
Auckland, 1010

Qualifications

PhD, Auckland University of Technology, New Zealand 

BSc (Hons), University of Maribor, Slovenia

Postgraduate diploma (pedagogical curriculum), University of Ljubljana, Slovenia

Tennis coaching certificate, University of Ljubljana

 

Memberships and Affiliations

Association for Computing Machinery (ACM)

Institute of Electrical and Electronics Engineers (IEEE) 

International Society of Biomechanics in Sports (ISBS)

Sports Performance Research Institute New Zealand (SPRINZ)


Research Areas

Multi- and cross-disciplinary areas in computer science, mathematics and engineering.


Application of Computational Intelligence (CI) to sport science, rehabilitation, health, active life advancements and other related areas.

Computer science areas include: Video, image and signal processing, ubiquitous and wearable computing, data mining, machine learning, software engineering, human computer interaction, open source software integration, networking/data communication, embedded systems and multi-platform processing.

Research Summary

Boris' research interest bridges the disciplines of education, Computational Intelligence (CI), Computer Vision (CV), software engineering, and other computing domains, with sport domains including kinesiology, biomechanics and rehabilitation.

The unique contribution of Boris' research is in enabling (human) motion assessment/feedback automation. Multi- and cross-discipline approaches in on- and off-line Human Motion Modelling and Analysis (HMMA) are developed independently to be compatible with recent and future technologies. Examples of required technology include: stand-alone and distributed multi-platform systems with supporting infrastructures for streaming, communicating, storing and processing multi-modal motion data feedback and intervention.
Distinctive aspects of Boris' research include enabling automated coaching experiences (data capture/streaming/analysis/recommendation-intervention) for end-users to improve their motion control, skills, and technique by using the next generation of autonomous intelligent Augmented Coaching Systems (ACS), exergames, and virtual or immersive environments.

An essential component of coaching, injury recovery and (re)learning a new motion/skill/technique is the inherent ability of ACS to perform quantitative (objective measures obtained from motion data) and qualitative assessments based on subjective criteria (by combining traditional algorithmic and machine learning paradigms). A nature-inspired machine implementation of subjective and adaptive criteria found in qualitative assessment of human motion relates to a coach's implicit insights, personal knowledge of a subject and (short- to long-term) evolving improvement goals.

Boris' research interests and vision based on his current research, include the following:
Game dynamic modelling; talent identification; improving reaction time; umpiring support; qualitative model(s)' adaptation for a given task and context; pain pattern expression modelling; prioritising individual errors to guide feedback and the next intervention choice; finding simple and complex multi-goal deficient, defective or limiting motion patterns; and generating new hypotheses and common-sense rules validity from data. 


Near-future development:

  • Advancements in motion capture, sport science, and game developments. Based on diagnostic automation from his research, future exergames will provide a personalised 'coaching experience' to the end-users.
  • Game strategy support via analysis/feedback, decision support system, cognitive prosthetics. Related coaching tools to include pattern recognition inference engine and control of augmented coaching/sport performance equipment and environments.
  • Improving motor activation and neural pathway control in rehabilitation and regaining an active life for the disabled and less active ageing population (linked to personalised motor-unit stimulation or exoskeleton/intelligent prosthetics).

 

Current Research Projects

Scholarships and next research projects information will be updated  in 2017.

For collaborative projects and postgraduate supervision please email Boris directly.

Projects proposals for semester 2, 2016

Master level:
Temporal and spatial pattern extraction from low to high quality videos: Towards real-time data fusion for wearable and ubiquitous computing devices

Application closing date: 1 August 2016

Call for project and master scholarship funding application:


Undergraduate level – team projects:
  • Multi-sensor data streaming systems
  • Visual modelling toolkit for computational sport science

Selected past projects:

  • Augmented Coaching Toolkit (open-source integration, web-based, client/server  multi-platform and mobile distributed processing and data exchange): 
    --->sport events video crowdsourcing, with remote sharing and editing
    --->multi-platform, client/server based universal scoreboard (Android and Linux-based multiple integration scenarios)
    --->ZeroMQ(0MQ) protocol applications for augmented coaching data exchange
  • Personalised Portable Data Storage (embedded Linux)

Publications

(Selected References)

[1]       B. Bačić, "Prototyping and user interface design for augmented coaching systems with MATLAB and Delphi: Implementation of personal tennis coaching system," presented at the MATLAB Conference 2015, Auckland, 2015.

[2]       B. Bačić, "Echo state network for 3D motion pattern indexing: A case study on tennis forehands," presented at the VII Pacific Rim Symposium on Image and Video Technology – PSIVT 2015, Auckland, New Zealand, 2015.

[3]       B. Bačić, "Extracting player’s stance information from 3D motion data: A case study in tennis groundstrokes," presented at the VII Pacific Rim Symposium on Image and Video Technology – PSIVT 2015 Workshop on Video Surveillance, Auckland, New Zealand, 2015.

[4]       B. Bačić, "Open-source video players for coaches and sport scientists," in XXXIII International Symposium on Biomechanics in Sports, Poitiers, France, 2015.

[5]       B. Bačić, S. Iwamoto, and D. Parry, "Open source software and interdisciplinary data management: Post-surgery rehabilitation case study " presented at the Health Informatics New Zealand (HINZ 2014), Auckland, New Zealand, 2014.

[6]       B. Bačić, "Learning golf drive: Natural swing path tendency to slice, fade or pull," in XXII International Symposium on Biomechanics in Sports (ISBS), Johnson City, TN, 2014, pp. 276-279.

[7]       B. Bačić, "The hypergeometric distribution can help reduce cross-validation incidents: Two case studies," in 2014 Mathematical Sciences Symposium, Auckland, New Zealand, 2014.

[8]       B. Bačić, "Connectionist methods for data analysis and modelling of human motion in sporting activities," Doctor of Philosophy Ph.D. Thesis, School of Computing and Mathematical Sciences, Auckland University of Technology, Auckland, 2013.

[9]       B. Bačić and P. Hume, "Augmented video coaching, qualitative analysis and post-production using open source software," presented at the XXX International Symposium on Biomechanics in Sports (ISBS), Melbourne, Australia, 2012.

[10]     B. Bacic, N. Kasabov, S. MacDonell, and S. Pang, "Evolving connectionist systems for adaptive sport coaching," in 14th International Conference, ICONIP 2007, M. Ishikawa, K. Doya, H. Miyamoto, and T. Yamakawa, Eds., ed Kitakyushu, Japan: Springer-Verlag, 2008, pp. 416-425.

[11]     B. Bacic, "Evolving connectionist systems for adaptive sports coaching," Neural Information Processing - Letters and Reviews, vol. 12 pp. 53-62, 2008.

[12]     B. Bacic, "A novel generic algorithm for cluster split iB-fold cross-validation," in 30th International Conference on Information Technology Interfaces (ITI 2008), Cavtat, Croatia, 2008, pp. 919-924.

[13]     B. Bacic, N. Kasabov, S. MacDonell, and S. Pang, "Evolving connectionist systems for adaptive sport coaching," presented at the 14th International Conference, ICONIP 2007, Kitakyushu, Japan, 2007, pp. 416-425.

[14]     B. Bačić, "Using probability in estimating the size of a test data sample," in 6th International Conference on Hybrid Intelligent Systems (HIS'06) and the 4th International Conference on Neuro Computing and Evolving Intelligence (NCEI'6), Auckland, New Zealand, 2006, pp. 55-56.

[15]     B. Bačić, "Bridging the gap between biomechanics and artificial intelligence," in XXIV International Symposium on Biomechanics in Sports (ISBS), Salzburg, Austria, 2006, pp. 371-374.

[16]     B. Bacic and D. H. Zhang, "Evaluation of ECOS for the discovery of tennis coaching rules," in 4th Conference on Neuro-Computing and Evolving Intelligence (NCEI'04), Auckland, New Zealand, 2004, pp. 93-94.

[17]     B. Bacic, "Towards a neuro fuzzy tennis coach: Automated extraction of the Region of Interest (ROI)," in International Conference on Fuzzy Systems (FUZZ-IEEE) and International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, 2004, pp. 703-708.

[18]     B. Bacic, "Automating systems for interpreting biomechanical 3D data using ANN: A case study on tennis," in 3rd Conference on Neuro-Computing and Evolving Intelligence (NCEI'03), vol. 1, pp. 101-102, 20-21 Nov. 2003.

[19]     B. Bacic, "Computer at the University: opportunities for tailoring automated marking and digital feedback," in 25th International Conference of Information Technology Interfaces (ITI 2003), Cavtat, Croatia, 2003, pp. 31-38.

[20]     B. Bacic and N. K. Kasabov, "A general connectionist development environment for sports data indexing and analysis - a case study on tennis," in Neuro-Computing Colloquium & Workshop (NCC&W'02), Auckland, New Zealand, 2002, pp. 25-26.

[21]     B. Bacic, "Constructing intelligent tutoring systems: Design guidelines," in 24th International Conference of Information Technology Interfaces (ITI 2002), Cavtat, Croatia, 2002, pp. 129-134.

(In press)

[1]       B. Bačić, "Predicting golf ball trajectories from swing plane: An artificial neural networks approach," Expert Systems with Applications.

[2]       B. Bačić, "Echo state network ensemble for human motion data temporal phasing: A case study on tennis forehands", The 23rd International Conference on Neural Information Processing – ICONIP 2016, Kyoto.