Application Case Study Themes
Publications
Plenary/Keynote/Invited Talks/Toturials/Presentation
Special Sessions
Special Issues
Symposia/workshop
Engage with the Aquaculture Ecosystem
Capability
Actively Work with Industry Partners
Establish Relationships with Existing Aligned Government-Funded Research
Collaborations
Initial Pipeline of Scholarships/Internships to Attract Maori Students
Additional Information

Application Case Study Themes

Case Study Theme 1: Shellfish farm production, performance and health, and risk in their environment

(spat settlement, monitoring floats/structures, mussel gapping monitor, shell colour, monitoring marine mammals, birds, bio-fouling of nets,...)

The goal of this theme is to develop case studies of projects around enabling shellfish farmers to more effectively manage their farms in a challenging and highly dynamic environment.

  • Project1: Automated eyes on the farm: Monitoring Mussel Floats

    Develop AI techniques to automate the monitoring of mussel floats to give farmers warnings of where additional floatation is required
    Team: Dylon Zeng (VUW PhD), Ying Bi (VUW), Bing Xue (VUW), Ivy Liu (VUW), Dana Briscoe (Cawthron), Ross Vennell (Cawthron), Mengjie Zhang (VUW)

  • Project2: Predicting Settlement of Mussel Spat at the Top of the South Island

    Enable farmers to minimise the effects of invasive blue mussel settlement and catch local commercial green mussel spat
    Team: Ross Vennell(Cawthron), Richard Arnold(VUW), Nokuthaba Sibanda (VUW), Javier Atalah (Cawthron), Dana Briscoe (Cawthron)

  • Project3: Shellfish Harvest Assessments

    Create AI models that generate accurate pre and post harvest assessment data from shellfish images
    Team: Cris Lovell-Smith (NAI), Hamish O'Keeffe (VUW MSc student/NAI), Bing Xue (VUW), Nikki Hawes (NAI)

  • Project4: Shellfish Identification

    Develop a deep learning model to recognise individual shellfish by their shell patterns
    Team: Nick King (Cawthron), Cris Lovell-Smith (NAI)

All these projects have been going well, particularly, we focus on the following aspects at the current stage.

  • Automated eyes on mussel floats: has required processing of both the data and development of techniques to subdivide the data set. Work to explore existing techniques and develop new methods is ongoing.
  • Mussel spat larval sources: This has required the development of improved methods to quantify the likelihood of a connection between areas of our coastal ocean. This much more efficient particle tracking code is 100 times faster than existing code. This speed is key to simulating the 100s of millions of particles needed to give high quality probabilities of connection, as the foundation for prediction of mussel spat sources (Vennell et. al. 2021).

In addition, we also continue to explore new aquaculture-related data, including benchmark and real-world data. We have:

  • Secured access to decades long mussel spat settlement data, collected by the industry for use in project 3 to identify sources of mussel spat in the upper South Island.
  • Have identified significant new industry data sets for harmful algae blooms in the upper South Island. Shellfish consumed from water with these algae present can result in serious illness and death. Since 2010 these blooms have become more frequent and widespread, leaving farmers unable to harvest for long periods. We are in the process of securing permission from the NZ Mussel Farming association to use their data in a new project. This project would develop a short-term forecasting system, which will better enable farmers to decide where and when they can harvest.

Case Study Theme 2: Genomic data analyses to support finfish breeding

The goal of this theme is to analyse genomic datasets alongside performance indicators to identify causal genomic variants that can be used to predict breeding outcomes.

Team: Maren Wellenreuther (PFR), Linley Jesson (PFR), Julie Blommaert (PFR), Andrew Catanach (PFR), Marcus Davy (PFR), Yi Mei (VUW), Grant Dick (Otago), Bing Xue (VUW), Caitlin Owen (Otago)

This theme has progressed smoothly. Some key points of current research on this theme are shown as follows.

  • The key case studies are examining genomic features of fish quality where quality has been determined by phenotypic measures such as growth, disease or other indicators of health. Data exist for three key species: snapper, trevally and salmon.
  • We have data where the environment of fish has been experimentally manipulated to understand how genotype and environment interact to determine fish quality. These data have been explored using a variety of methods including data imputation, feature selection, model selection and assessment of prediction accuracy and model performance.
  • Data cleaning has involved linking environmental conditions to final fish performance as well as linking the genomic information.
  • Model selection has occurred on the snapper and trevally datasets, and the salmon data will be included in future studies.

In addition, we also continue to explore new aquaculture-related data, including benchmark and real-world data. We have:

  • New genomic data are being generated to address various aims around growth and performance of snapper in aquaculture. Improved genome assemblies and structural variant calling will be enabled through long-read sequencing or wild broodstock and short-read sequencing of a subset of the newest generation of fish in the growth-selected snapper line. A larger samples of these same fish are being SNP genotyped.
  • The impact of the gut microbiome will be analysed from short-read metagenomics, enabling comparisons between wild-type fish, the growth-selected fish, and fish living in the sea versus the fish facility. All of these datasets are highly dimensional, with outputs directly relevant to the health, wellbeing and performance of snapper under aquaculture conditions.

Case Study Theme 3: Fish performance and health (performance, modelling, diseases, ...)

The goal of this theme is to identify the main features and their relationship for measuring the fish performance and health. In addition, more advanced models will be built with machine learning techniques to predict the fish performance.

  • Project1: A tool for the interpretation of salmon blood test results

    Develop refined reference intervals for salmon health indicators that can be applied to improve salmon health diagnostics. The results will be made available to a commercial testing laboratory so that farmers can have access to the results to improve fish health diagnostics.
    Team: Cawthron: Paula Casanovas, Jessica Schattschneider, Jane Symonds, Seumas Walker.

  • Project2: Genetic programming for improving fish health prediction and disease detection

    Provide critical information to the industry about which health indicators can be used to predict health. This can then be used by the industry to improve on-farm health management and to take proactive measures prior to health issues arising.
    Team: Cawthron: Jane Symonds, Ross Vennell, Dana Briscoe VUW: Bing Xue, Mengjie Zhang, Ying Bi, Fangfang Zhang

  • Project3: Predicting salmon health and biomarker discovery

    Develop methods and identify optimal biomarkers for improving salmon health prediction
    Team: Cawthron: Paula Casanovas, Jane Symonds, Ross Vennell VUW: Ivy Liu, Richard Arnold, Binh Nguyen, Louise McMillan, Ying Cui, Laia Egea, Alex Wang

  • Project4: Streamlining skeletal deformity diagnostics

    Produce an automated method for reliably scoring skeletal deformity that industry can use, and researchers can apply when analysing industry fish in their trials
    Team: Cawthron: Jane Symonds, Seumas Walker, Paula Casanovas VUW: Binh Nguyen, Loc Nguyen

Our main progresses are shown as follows.

  • VUW (Ivy Liu, Richard Arnold, Binh Nguyen and Louise McMillan) and Otago (Grant Dick) have established collaborations with Cawthron (Jane Symonds and Paula Casanovas). We have been co-supervising the two PhD students Ying Cui (started Sept 2021) and Laia Egea (started March 2022), and Loc Nguyen. We have had regular meetings between Cawthron and VUW to discuss data transfer, methodologies and applications (Projects 2, 3 and 4).
  • Project 2: Our postdoc Fanfang Zhang has been working on this project since May 2022. She has read a number of papers on fish health prediction. Fangfang has made a plan with Bing Xue to use machine learning techniques for fish health prediction.
  • Binh Nguyen and a student Loc Nguyen have been working on Project 4, and Cawthron has provided additional X-rays for analysis. Good progress has been made in processing the X-rays (e.g. automatic image rotation), identifying individual vertebra and the detection of specific vertebral anomalies.

In addition, we also continue to explore new aquaculture-related data, including benchmark and real-world data. Specifically,

  • The Cawthron team completed the design and development of the finfish research database, combining data from three trials completed in Cawthron’s Finfish Research Centre (2018 to 2021), containing over 550,000 records (funded by the MBIE Endeavour “Feed Efficient Salmon” programme, CAWX1606). Data sharing methods were also developed to allow data to be accessed by the project team. Background information about the data and methods used to collect the data were also provided. A new “DSFA Theme 3 Finfish performance and health” Team was established in Microsoft Teams to share information.
  • VUW and Otago University signed the “Data Sharing Agreement – Science For Aquaculture” with Cawthon in May 2022. VUW is able to work on the newly provided king salmon data using machine learning algorithms. This will directly contribute to projects 2 and 3.
  • On-farm data collected during health-related field sampling for research within the Aquatic Animal Health MBIE Endeavour programme (CAW1707) will be made available for inclusion in the analysis.
  • Regular discussions with fish veterinarians from the industry provide an ongoing opportunity to obtain additional data sets in the future.

Case Study Theme 4: VM (high-school, undergraduate, postgraduate coursework, Master/PhD thesis students)

Team: Bing Xue, Fangfang Zhang, Kirita-Rose Escott, Kevin Shedlock, Neb Svrzikapa, Terence Hikawai, Yi Mei, Monoa Taepa, Morgan Holschier, Cecilia Tuiomanufili, Maren Wellenreuther, Chris Cornelisen, Mengjie Zhang

Project1: Mini Seminar series to high-school students To start the connections with schools that have high proportion of Māori students

Project2: Hackathon Have one-day or two-day hackthon, with the first day introducing/teaching knowledge, say a software, then give students some time to complete a task.

Project3: Data Science Bootcamp RRI has been a very successful one-week bootcamp each summer, and we can be one of them to get it starts to promote data science, to explore the possibility of starting our own bootcamp.

Project4: Mentoring Program To establish connections with students from high-school, who will be our potential students
  • Bing and Fangfang had a number of discussions with research office at VUW about the Mini Lectures Program to introduce data science programme to high school students in New Zealand. We have made posters including one for teachers and one for students. Currently, our research office is working with related departments to issue this, 2021-2022.
  • Terence, Kevin, and Kirita delivered four talks on Maori Data Sovereignty, Relationship, iwi, and ECS Maori Digital platform. We are planning to invite Willy John from MBIE to deliver a talk.
  • Establish an initial pipeline of scholarships/internships to attract Maori students to our programme
  • Internships and bootcamp to attract high-school Maori students to our Data Science and AI (DSAI) undergraduate programmes (one or two weeks, labs, demonstrations, programming assignments, etc.)
  • Workshops/seminars/Webinars (with food and drinks) and Maori Junior Undergraduate Internships to attract Year 1 students to Year 2 in DSAI ($2,000 for tuition fees or accommodation each internship)
  • Workshops/seminars/webinars (with food and drinks) and Maori Senior Undergraduate Internship to attract Year 2 to Year 3 in DSAI ($5,000 for Tuition fees or Accommodation each internship)
  • Summer scholarships and Maori Graduate Awards to attract Maori Year 3 students to our PG DSAI coursework programmes ($10,000 each)
  • Strategic Maori Master by Research scholarships to attract PG DSAI coursework students to our MSc in DSAI programmes (Tuition fees + $22K stipend)
  • Strategic Maori PhD Scholarships to attract Maori students to our PhD programmes (Tuition fees + $35K p.a. stipend for three years)

Publications

Authored Book

  1. Fangfang Zhang, Su Nguyen, Yi Mei, and Mengjie Zhang. “Genetic Programming for Production Scheduling: An Evolutionary Learning Approach”. Springer Book Series on Machine Learning: Foundations, Methodologies, and Applications，2021. DOI: 10.1007/978-981-16-4859-5 (the first book on hyper-heuristic for production scheduling)

Journal Papers

  1. Ying Bi, Bing Xue, Dana Briscoe, Ross Vennell, and Mengjie Zhang. "A New Artificial Intelligent Approach to Buoy Detection for Mussel Farming". Journal of the Royal Society of New Zealand. 24pp, 2022 (Q1)
  2. Atalah Javier, Paul M. South, Dana K. Briscoe, and Ross Vennell. "Inferring parental areas of juvenile mussels using hydrodynamic modelling." Aquaculture, 555, 738227, 2022 (Q1)
  3. Valenza‐Troubat Noemie, Elena Hilario, Sara Montanari, Peter Morrison‐Whittle, David Ashton, Peter Ritchie, and Maren Wellenreuther. "Evaluating new species for aquaculture: A genomic dissection of growth in the New Zealand silver trevally (Pseudocaranx georgianus)." Evolutionary Applications, 15(4), 591-602, 2022. (Q1)
  4. Nicholas P. L. Tuckey, David T. Ashton, Jiakai Li, Harris T. Lin, Seumas P. Walker, Jane E. Symonds, Maren Wellenreuther. "Automated image analysis as a tool to measure individualised growth and population structure in Chinook salmon (Oncorhynchus tshawytscha)" in Aquaculture, Fish and Fisheries, 2022 (Q1)
  5. Sara Montanari, Cecilia Deng, Emily Koot, Chris Kirk, Nahla V. Bassil, Peter Morrison-Whittle, Margaret L. Worthington, Julien Pradelles, Maren Wellenreuther, David Chagné. A multi-species plant-animal SNP chip enables diverse breeding and management applications (in press) PlosOne (Q1)
  6. Quang H.Nguyena, Binh P.Nguyenb, Minh T.Nguyena, Matthew C.H.Chuac, Trang T.T.Do, Nhung Nghieme. Bone age assessment and sex determination using transfer learning, Expert Systems with Applications, 2022 (Q1)
  7. Vennell, Ross, Max Scheel, Simon Weppe, Ben Knight, and Malcolm Smeaton. "Fast lagrangian particle tracking in unstructured ocean model grids." Ocean Dynamics 71, no. 4, 423-437, 2021 (Q2)
  8. Vien T. Truong, Binh P. Nguyen, Thanh-Hoang Nguyen-Vo, Wojciech Mazur, Eugene S. Chung, Cassady Palmer, Justin T. Tretter, Tarek Alsaied, Vy T. Pham, Huan Q. Do, Phuong T. N. Do, Vinh N. Pham, Ban N. Ha, Hoa N. Chau & Tuyen K. Le, Application of machine learning in screening for congenital heart diseases using fetal echocardiography, The International Journal of Cardiovascular Imaging, 2022 (Q2)
  9. Valenza-Troubat Noemie, Sara Montanari, Peter Ritchie, and Maren Wellenreuther. "Unraveling the complex genetic basis of growth in New Zealand silver trevally (Pseudocaranx georgianus)." G3, 12(3), 2022 (Q2)
  10. Sandoval-Castillo Jonathan, Luciano B. Beheregaray, and Maren Wellenreuther. "Genomic prediction of growth in a commercially, recreationally, and culturally important marine resource, the Australian snapper (Chrysophrys auratus)." G312, no. 3, 2022 (Q2)
  11. Irving Kate, Wellenreuther Maren, Ritchie Peter A. "Description of the growth hormone gene of the Australasian snapper, Chrysophrys auratus, and associated intra- and interspecific genetic variation". Journal of Fish Biology. 2021, 11pp (Q2)
  12. Mike Ruigrok, Bing Xue, Andrew Catanach, Mengjie Zhang, Linley Jesson, Marcus Davy, Maren Wellenreuther. “The Relative Power of Structural Genomic Variation versus SNPs in Explaining the Quantitative Trait Growth in the Marine Teleost Chrysophrys auratus”. Genes in press (Q2)
  13. Anastasiadi D, Piferrer F, WELLENREUTHER M, Burraco AB. “Fish as model systems to study epigenetic drivers in human self-domestication and neurodevelopmental cognitive disorders”, Genes, 2022 (Q2)
  14. Peng Wang, Bing Xue, Jing Liang and Mengjie Zhang. "Differential Evolution Based Feature Selection: A Niching-based Multi-objective Approach", IEEE Transactions on Evolutionary Computation, 2022. DOI: 10.1109/TEVC.2022.3168052 (Q1)
  15. Xinye Cai, Qi Sun, Zhenhua Li, Xiao Yushun, Yi Mei, Qingfu Zhang, and Xiaoping Li. Cooperative coevolution with knowledge-based dynamic variable decomposition for bilevel multiobjective optimization. IEEE Transactions on Evolutionary Computation, 2022 (Q1)
  16. Fangfang Zhang, Yi Mei, Su Nguyen, Mengjie Zhang, and Kay Chen Tan. Surrogate-assisted evolutionary multitasking genetic programming for dynamic flexible job shop scheduling. IEEE Transactions on Evolutionary Computation, 25(4):651--665, 2021 (Q1)
  17. Shaolin Wang, Yi Mei, Mengjie Zhang, and Xin Yao. Genetic programming with niching for uncertain capacitated arc routing problem. IEEE Transactions on Evolutionary Computation, 26(1):73--87, 2022 (Q1)
  18. Qinglan Fan, Ying Bi, Bing Xue, and Mengjie Zhang. "Genetic Programming for Image Classification: A New Program Representation with Flexible Feature Reuse". IEEE Transactions on Evolutionary Computation. 2022. 15pp.  DOI: 10.1109/TEVC.2022.3169490. (Q1)
  19. Andrew Lensen, Bing Xue and Mengjie Zhang." Genetic Programming for Manifold Learning: Preserving Local Topology ", IEEE Transactions on Evolutionary Computation, vol. 26, no. 4, pp. 661-675, Aug. 2022, doi: 10.1109/TEVC.2021.3106672. (Q1)
  20. Ying Bi, Bing Xue, and Mengjie Zhang, "Learning and Sharing: A Multitask Genetic Programming Approach to Image Feature Learning," in IEEE Transactions on Evolutionary Computation, vol. 26, no. 2, pp. 218-232, April 2022, doi: 10.1109/TEVC.2021.3097043. (Q1)
  21. Ke Chen, Bing Xue, Mengjie Zhang and Fengyu Zhou, "Evolutionary Multitasking for Feature Selection in High-Dimensional Classification via Particle Swarm Optimization," in IEEE Transactions on Evolutionary Computation, vol. 26, no. 3, pp. 446-460, June 2022, doi: 10.1109/TEVC.2021.3100056. (Q1)
  22. Ke Chen, Bing Xue, Mengjie Zhang, and Fengyu Zhou. "Correlation-Guided Updating Strategy for Feature Selection in Classification with Surrogate-Assisted Particle Swarm Optimisation", IEEE Transactions on Evolutionary Computation, 2021. (DOI: 10.1109/TEVC.2021.3134804) (Q1)
  23. Bach Hoai Nguyen, Bing Xue, and Mengjie Zhang."A Constrained Competitive Swarm Optimiser with an SVM-based Surrogate Model for Feature Selection". IEEE Transactions on Evolutionary Computation. 2022. 15pp. (Accepted on 7-May-2022) (Q1)
  24. C. A. Owen, G. Dick and P. A. Whigham, "Standardisation and Data Augmentation in Genetic Programming," in IEEE Transactions on Evolutionary Computation, doi: 10.1109/TEVC.2022.3160414. (Q1)
  25. Ying Bi, Bing Xue, and Mengjie Zhang. "Dual-Tree Genetic Programming for Few-Shot Image Classification".  IEEE Transactions on Evolutionary Computation. 2021. 15pp.  DOI: 10.1109/TEVC.2021.3100576. (Q1)
  26. Ying Bi, Bing Xue, and Mengjie Zhang. "Learning and Sharing: A Multitask Genetic Programming Approach to Image Feature Learning". IEEE Transactions on Evolutionary Computation. 2021. 15pp. DOI: 10.1109/TEVC.2021.3097043. (Q1)
  27. Yanan Sun, Ziyao Ren, Gary G. Yen, Bing Xue, Mengjie Zhang,and Jiancheng Lv."ArcText: An Unified Text Approach to Describing Convolutional Neural Network Architectures", IEEE Transactions on Artificial Intelligence. Accepted Nov 2021 (DOI: 10.1109/TAI.2021.3128502) (Q1)
  28. Cuie Yang, Yiu-ming Cheung, Jinliang Ding, Kay Chen Tan, Bing Xue, and Mengjie Zhang."Contrastive Learning Assisted Alignment for Partial Domain Adaptation", IEEE Transactions on Neural Networks and Learning Systems, 2022 (DOI: 10.1109/TNNLS.2022.3145034) (accepted Jan 2022) (Q1)
  29. Emrah Hancer, Bing Xue, and Mengjie Zhang."Fuzzy filter cost-sensitive feature selection with differential evolution", Knowledge-Based Systems, vol. 241 , no. , pp.108259, 9 pages, 2022 (Q1)
  30. Peng Wang, Bing Xue, Jing Liang and Mengjie Zhang."Multi-objective Differential Evolution for Feature Selection in Classification", IEEE Transactions on Cybernetics, pp. 1-15, 2021. (DOI: 10.1109/TCYB.2021.3128540) (Q1)
  31. Qurrat Ul Ain, Bing Xue, Harith Al-Sahaf and Mengjie Zhang. "Automatically Diagnosing Skin Cancers from Multi-Modality Images Using Two-Stage Genetic Programming".  IEEE Transactions on Cybernetics. 2022. 14pp. (Accepted on 04-Jun-2022) (Q1)
  32. Ruwang Jiao, Bing Xue, and Mengjie Zhang. " A Multiform Optimization Framework for Constrained Multi-Objective Optimization".  IEEE Transactions on Cybernetics. 2022. 14pp. DOI: 10.1109/TCYB.2022.3178132 (Q1)
  33. Ying Bi, Bing Xue, and Mengjie Zhang."Multitask Feature Learning as Multiobjective Optimisation: A New Genetic Programming Approach to Image Classification", IEEE Transactions on Cybernetics, DOI: DOI: 10.1109/TCYB.2021.3128540. (Accepted May 2022) (Q1)
  34. Ying Bi, Bing Xue, and Mengjie Zhang. "Instance Selection Based Surrogate-Assisted Genetic Programming for Feature Learning in Image Classification".  IEEE Transactions on Cybernetics. 2021. 14pp. DOI: 10.1109/TCYB.2021.3105696 (Q1)
  35. Wenlong Fu, Bing Xue, Xiaoying Gao, and Mengjie Zhang."Transductive transfer learning based Genetic Programming for balanced and unbalanced document classification using different types of features", Applied Soft Computing, Vol. 103, pp. 107172, 2021 (Q1)
  36. Xiangning Xie, Yuqiao Liu, Yanan Sun, Gary G. Yen, Bing Xue and Mengjie Zhang ."BenchENAS: A Benchmarking Platform for Evolutionary Neural Architecture Search", IEEE Transactions on Evolutionary Computation, 2022. (DOI: 10.1109/TEVC.2022.3147526) (Q1)
  37. Qurrat Ul Ain, Harith Al-Sahaf, Bing Xue and Mengjie Zhang."Genetic Programming for Automatic Skin Cancer Image Classification", Expert Systems with Applications, vol. 197, no. , pp.116680, 15 pages 2022 (Q1)
  38. Ying Bi, Bing Xue, and Mengjie Zhang."Using a small number of training instances in genetic programming for face image classification", Information Sciences, vol. 593, pp. 488-504, 2022 (Q1)
  39. Qinglan Fan, Ying Bi, Bing Xue, and Mengjie Zhang."Genetic programming for feature extraction and construction in image classification", Applied Soft Computing, vol. 118, pp. 108509, 13 pages, 2022 (Q1)
  40. Wenbin Pei, Bing Xue, Lin Shang, and Mengjie Zhang. "High-dimensional Unbalanced Binary Classification by Genetic Programming with Multi-criterion Fitness Evaluation and Selection Evolutionary Computation". Evolutionary Computation. 2021. 25pp.  DOI: 10.1162/evco_a_00304. (Q1)
  41. Fernandez, D., McMillan, L., Arnold, R., Spiess, M. and Liu, I. Goodness-of-Fit and Generalized Estimating Equation Methods for Ordinal Responses based on the Stereotype Model. Stats 5(2), 507-520. DOI: 10.3390/stats5020030, 2022

Conference Papers

  1. Hoai Bach Nguyen; Bing Xue; Mengjie Zhang. "Automated and Efficient Sparsity-based Feature Selection via a Dual-component Vector". Proceedings of the International Conference on Data Mining (ICDM 2021). IEEE Press. Auckland, New Zealand, 7-10 December, pp 833-842, 2021 (A)
  2. Kaan Demir, Bach Nguyen, Bing Xue, and Mengjie Zhang. "Automated and Efficient Sparsity-based Feature Selection via a Dual-component Vector". Proceedings of the International Conference on Data Mining (ICDM). IEEE Press. Auckland, New Zealand, 7-10 December, pp 823-832, 2021 (A)
  3. Grant Dick. Genetic programming, standardisation, and stochastic gradient descent revisited: initial findings on SRBench. In Proceedings of the Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, New York, NY, USA, 2265–2273, 2022.(A)
  4. Grant Dick and Peter A. Whigham. Initialisation and grammar design in grammar-guided evolutionary computation. In Proceedings of the Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, New York, NY, USA, 534–537, 2022 (A)
  5. Yunhan Yang, Bing Xue, Linley Jesson and Mengjie Zhang. "Genetic Programming for Symbolic Regression: A Study on Fish Weight Prediction." IEEE Congress on Evolutionary Computation (CEC). Krakow, Poland, 28 June - 1 July 2021, 8pp (A)
  6. Bin Wang, Bing Xue, and Mengjie Zhang. "An Efficient Evolutionary Deep Learning Framework Based on Multi-source Transfer Learning to Evolve Deep Convolutional Neural Networks". Proceedings of 2021 Genetic and Evolutionary Computation Conference (GECCO). ACM Press. July 10-14, 2021, pp 287–288, Online-only Conference. (A)
  7. Bin Wang, Wenbin Pei, Bing Xue, and Mengjie Zhang. "Evolving Local Interpretable Model-agnostic Explanations for Deep Neural Networks in Image Classification". Proceedings of 2021 Genetic and Evolutionary Computation Conference (GECCO). ACM Press. July 10-14, 2021, pp 173–174, Online-only Conference. (A)
  8. Ramya Anasseriyil Viswambaran, Gang Chen, Bing Xue and Mohammad Nekooei. "Two-Stage Genetic Algorithm for Designing Long Short Term Memory (LSTM) Ensembles." IEEE Congress on Evolutionary Computation (CEC). Krakow, Poland, 28 June - 1 July 2021, 8pp (A)
  9. Peng Wang, Bing Xue, Jing Liang and Mengjie Zhang. " A Grid-dominance based Multi-objective Algorithm for Feature Selection in Classification." IEEE Congress on Evolutionary Computation (CEC). Krakow, Poland, 28 June - 1 July 2021, 8pp. (A)
  10. Zichu Yan, Ying Bi, Bing Xue and Mengjie Zhang. "Automatically Extracting Features Using Genetic Programming for Low-Quality Fish Image Classification." IEEE Congress on Evolutionary Computation (CEC). Krakow, Poland, 28 June - 1 July 2021, 8pp (A)
  11. Shaolin Wang, Yi Mei, and Mengjie Zhang. A two-stage multi-objective genetic programming with archive for uncertain capacitated arc routing problem. In Proceedings of the ACM Genetic and Evolutionary Computation Conference (GECCO), pages 287--295. ACM, 2021 (A)
  12. Shaolin Wang, Yi Mei, and Mengjie Zhang. A multi-objective genetic programming approach with self-adaptive alpha dominance to uncertain capacitated arc routing problem. In Proceedings of the IEEE Congress on Evolutionary Computation (CEC), pages 636--643. IEEE, 2021 (A)
  13. Yunhan Yang, Bing Xue, Linley Jesson, Matthew Wylie, and Mengjie Zhang. "Deep Convolutional Neural Networks for Fish Weight Prediction from Images". Proceedings of the International Conference on Image and Vision Computing New Zealand (IVCNZ). IEEE Press. Tauranga, New Zealand, 9-10 December, 2021, (DOI: 10.1109/IVCNZ54163.2021.9653412) (B)
  14. Alistair John McLeay, Abigail McGhie, Dana Briscoe, Ying Bi, Bing Xue, Ross Vennell and Mengjie Zhang. "Deep Convolutional Neural Networks with Transfer Learning for Waterline Detection in Mussel Farms". Proceedings of 2021 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE Press. Orlando, FL, USA, 5-7 December, pp 01-08, 2021 (DOI: 10.1109/SSCI50451.2021.9659987) (B)
  15. Caleb Buchanan, Ying Bi, Bing Xue, Ross Vennell, Simon Childerhouse, Matthew K. Pine, Dana Briscoe, Mengjie Zhang. "Deep Convolutional Neural Networks for Detecting Dolphin Echolocation Clicks". Proceedings of the International Conference on Image and Vision Computing New Zealand (IVCNZ 2021). Tauranga, New Zealand. 9-10 Dec. 2021. (B)
  16. Gonglin Yuan, Bing Xue and Mengjie Zhang. "A Two-Stage Efficient Evolutionary Neural Architecture Search Method for Image Classification". The 18th Pacific Rim International Conference on Artificial Intelligence (PRICAI). Lecture Notes in Computer Science. Vol. 13031, virtually in Hanoi, Vietnam between November 8-12, 2021. pp. 469-484 (B)
  17. Ziyi Wang, Yujie Zhou, Chun Li, Lin Shang and Bing Xue. "MGEoT: A Multi-Grained Ensemble Method for Time Series Classification". The 18th Pacific Rim International Conference on Artificial Intelligence (PRICAI 2021). Lecture Notes in Computer Science. Vol. 13031, Springer, Cham, virtually in Hanoi, Vietnam, 8-12 November 2021. pp. 397-410 (B)
  18. Fergus Currie, Yi Mei, Mengjie Zhang, Linley Jesson, and Maren Wellenreuther. An investigation on multi-objective fish breeding program design. In Proceedings of the IEEE Symposium Series on Computational Intelligence (SSCI), pages 1--8. IEEE, 2021 (B)
  19. Shaolin Wang, Yi Mei, and Mengjie Zhang. An improved multi-objective genetic programming hyper-heuristic with archive for uncertain capacitated arc routing problem. In Proceedings of the IEEE Symposium Series on Computational Intelligence (SSCI), pages 1--8. IEEE, 2021 (B)

Plenary/Keynote/Invited Talks/Toturials/Presentation

  1. Mengjie Zhang: Keynote: IEEE International Conference on Software Engineering and Artificial Intelligence, June 2022.
  2. Mengie Zhang gave a presentation with a title of “AI, Machine Learning and Data Science at VUW” at AgReesarch in March 2022.
  3. Bing Xue: Invited Talk: Data Science and AI at VUW. Women in Data Science New Zeland , 10th and 17th March 2022
  4. Bing Xue: Invited Talk: Evolutionary Deep Learning for Image Classification. The 34th Australasian Joint Conference on Artificial Intelligence (AJCAI 2021), 2-4 February 2022
  5. Bing Xue: Keynote: Evolutionary Deep Learning for Image Classification. International Conference on Computational Intelligence and Data Analytics (ICCIDA), 8-9 January 2022
  6. Liu, I., Arnold, R., Fernandez, D., and Pledger, S. (2022). Cluster Analysis for Ordered Categorical Data. IASC-ARS conference, Kyoto, Japan, 21-24 Feb 2022.
  7. Li, S., Fan, Z., Liu, D. Liu, I., Morrison, P. (2022). Partial Association Between Mixed Data: Assessing the Impact of COVID-19 on College Student Well-Being. 2022 Symposium on Data Science & Statistics. Pittsburgh, Pennsylvania, 7-10 June 2022.
  8. Ross Vennell gave a talk on using imagery to automate the monitoring mussel floats using Artificial Intelligence at a Marlborough Sounds Smart+Connected Aquaculture event on 13 April 2022 via zoom.
  9. Chris Cornelisen gave a presentation on using data-driven technologies for aquaculture at the New Zealand Marine Sciences Society conference, 5-8 July 2022 in Tauranga.
  10. Dana Briscoe gave an invited presentation and programme overview at the 2022 Women in Data Science New Zealand Conference, hosted by VUW on 10 March 2022 via Zoom.
  11. Maren gave a talk on Fisheries Genetics at the Speaker's Science Forum organised for Members of Parliament, in collaboration with the Speaker of the New Zealand Parliament and in conjunction with Universities New Zealand, Science New Zealand, and the Independent Research Association of New Zealand (IRANZ), May 11th 2022, Parliament, Wellington, New Zealand
  12. Liu, I., Arnold, R., Fernandez, D., and Pledger, S. Cluster Analysis for Ordered Categorical Data. IASC-ARS conference, Kyoto, Japan, 21-24 Feb, 2022.
  13. A/Prof. Maren Wellenreuther, “Plenary 8 - Genomic applications in aquaculture for future food security”, a Plenary Lecture at the 38th International Society for Animal Genetics (ISAG) Conference, Cape Town, South Africa title: Harnessing the power of genomics and AI to breed new species for aquaculture, 27th July, 2021
  14. J. Blommaert and M. Wellenreuther, “ Transposable element dynamics in Sparidae genomes”, Presentation at MapNet, March 15, 2022
  15. Fangfang Zhang, Yi Mei, Su Nguyen, Mengjie Zhang. Tutorial of “Genetic Programming for Job Shop Scheduling”, in the EEE Symposium Series on Computational Intelligence, 5-7th, 2021.
  16. Dani Liu, Binh Nguyen, Jane Symonds, Paula Casanovas, and Ivy Liu. “Predict Gastric Dilation and Air Sacculitis in Chinook Salmon Using Machine Learning”. Australian and New Zealand Virtual Statistical Conference (ANZSC), 05-09 July 2021.
  17. Samuel Meenken, Ivy Liu, Paula Casanovas, Jane Symonds. “Investigating Salmon Data Using Partial Associations Based on Surrogate Residuals”. New Zealand Virtual Statistical Conference (ANZSC), 05-09 July 2021.
  18. Cornelisen, C., Vennell, R., Briscoe D., Barter P., Graham S., Scheel M., Green, R., Zhang, M. “Enhancing the blue economy through data-driven technologies for aquaculture”. New Zealand Marine Sciences Conference 2021, Tauranga, NZ
  19. Maren Wellenreuther and Chris Cornelisen gave talks at the Speaker's Science Forum organised for Members of Parliament, in collaboration with the Speaker of the New Zealand Parliament and in conjunction with Universities New Zealand, Science New Zealand, and the Independent Research Association of New Zealand (IRANZ), Parliament, Wellington, New Zealand.
  20. Our team has published the first newsletter of introducing this programme in June 2022.

Special Sessions

  1. Pablo Mesejo, Harith Al-Sahaf, and Ying Bi. “Evolutionary Computer Vision and Image Processing”, IEEE Congress on Evolutionary Computation, 2022
  2. Pablo Mesejo, and Harith Al-Sahaf. “Image & Signal Processing, Vision & Pattern Recognition”, EvoStar (EvoApps), 2022
  3. Bing Xue, Mengjie Zhang. “Evolutionary Transfer Learning and Domain Adaptation”, IEEE Symposium Series on Computational Intelligence (IEEE SSCI), Dec 2021
  4. Ying Bi, Bing Xue, Mengjie Zhang. “Evolutionary Computation for Computer Vision and Image Analysis (ECCVIA)”, IEEE Symposium Series on Computational Intelligence (IEEE SSCI), Dec 2021
  5. Bing Xue, Mengjie Zhang. “Evolutionary Computation for Feature Selection, Extraction and Dimensionality”, IEEE Congress on Evolutionary Computation (IEEE CEC), 28.06-1.07, 2021
  6. Bing Xue, Mengjie Zhang. “Evolutionary Transfer Learning and Transfer Optimisation”, IEEE Congress on Evolutionary Computation (IEEE CEC), 28.06-1.07, 2021
  7. Bing Xue, Mengjie Zhang. “Evolutionary Deep Learning and Applications”, IEEE Congress on Evolutionary Computation (IEEE CEC), 28.06-1.07,2021
  8. Fanfgang Zhang, Mengjie Zhang, Yi Mei, and Su Nguyen. “Genetic Programming and Machine Learning for Scheduling”, IEEE Symposium Series on Computational Intelligence, December 2021 via zoom (hold in USA).
  9. Mengjie Zhang, Bing Xue. “Evolutionary Transfer Learning and Transfer Optimisation”, IEEE Congress on Evolutionary Computation, July 2021
  10. Mengjie Zhang, Bing Xue. “Evolutionary Deep Learning and Applications”, IEEE Congress on Evolutionary Computation, July 2021
  11. Bing Xue, Mengjie Zhang. “Evolutionary Computation for Feature Selection, Extraction and Dimensionality”, IEEE Congress on Evolutionary Computation (IEEE CEC), 28.06-1.07.2021

Special Issues

  1. Harith Al-Sahaf, Pablo Mesejo, Ying Bi, and Mengjie Zhang. “Evolutionary Deep Learning for Computer Vision and Image Processing”, Applied Soft Computing, 2022 (Q1)
  2. Ying Bi, Bing Xue, Mengjie Zhang. “Evolutionary and Memetic Algorithms for Computer Vision and Image Processing”, Memetic Computing, 2021-2022 (Q1)
  3. Bing Xue, Mengjie Zhang, Richard Green. “Artificial Intelligence: Applications and Innovation”, Journal of the Royal Society of New Zealand, 2021-2022 (Q1)
  4. Maren Wellenreuther, “Understanding climate change response in the age of genomics”, Journal of Animal Ecology, June 2022 (Q1)
  5. Ying Bi, Bing Xue, Mengjie Zhang. “Artificial Intelligence for Fault Detection and Diagnosis”, Journal of Algorithm, 2021-2022

Symposia or workshop

  1. Bing Xue, Mengjie Zhang, Chair: IEEE Symposium on Computational Intelligence in Feature Analysis, Selection, and Learning in Image and Pattern Recognition (FASLIP), in IEEE Symposium Series on Computational Intelligence (IEEE SSCI), 5-7th, Dec 2021
  2. Pablo Mesejo, Harith Al-Sahaf, Mengjie Zhang, and Ying Bi. “Computational Intelligence for Multimedia Signal and Vision Processing”, IEEE Symposium Series on Computational Intelligence, 4-7th December, 2022
  3. Ying Bi, Bing Xue, Mengjie Zhang: Workshop on Evolutionary Data Mining and Machine Learning (EDMML) in IEEE International Conference on Data Mining (IEEE ICDM), Dec 2021
  4. Shaobo Li, Zhaohu Fan, Dungang Liu, Ivy Liu, Philip S. Morrison. Partial Association Between Mixed Data: Assessing the Impact of COVID-19 on College Student Well-Being. 2022 Symposium on Data Science & Statistics. Pittsburgh, Pennsylvania, 7-10 June 2022.
  5. Maren Wellenreuther, Luciano Beheregaray and Louis Bernatchez organsied a symposium. “Advances in genomics for sustainable fisheries and aquaculture”, World Fisheries Congress in Adelaide, Australia (20 to 24 September 2021)

Engage with the Aquaculture Ecosystem

  1. Terence Hikawai from the research office at VUW was invited and discussed with the team about Māori data management, and discussed related policies on 11/02/2022.
  2. Maren Wellenreuther with colleagues have written an annual summary and shared that with Te tau ihu fisheries forum in June 2022.
  3. Maren Wellenreuther with colleagues, has provide an annual update to relevant iwi organisations, 2022
  4. Maren Wellenreuther in Plant and Food got funding, and as one of the KPIs has added work around the development of a data and IP management plan with Te Arawa, 2022
  5. Maren Wellenreuther in Plant and Food has built an Ingenious Genomics Platform (Genomics Aotearoa): Development of genomic resources to enable the selective breeding of kingfish/haku to support the Smart Maori Aquaculture, 2021-2022
  6. Maren Wellenreuther in Plant and Food has been connecting with iwi partners, and other key stakeholders to ensure that future work aligns with their needs while also advancing fundamental data science, 2021-2022
  7. Yi gave four presentations to introduce artificial intelligence in the workshops/forums for the iwi in the Northland (Kaikohe, Waitangi, Kawakawa) and Gisborne, July 2021
  8. Kirita-Rose Escott from VUW research group has discussed Māori data management and data sovereignty, two Fridays Oct 2021.
  9. Kevin Shedlock from VUW research group has discussed “Te Pataka Purorohiko: An overview of the ECS Māori Digital Lab” in May 2022.
  10. NAI established a working relationship with the technical director of Aquaculture New Zealand (AQNZ) as a key advisor on NAI projects applied to aquaculture, 2022.
  11. NAI established and strengthened relationships with industry with the view towards future collaboration, including discussions with MacLab, AQNZ, North Island Mussel Company, OP Columbia, Te Whānau-ā-Apanui, and several individual marine farmers, 2022.
  12. NAI met with Cawthron Institute to understand each other's capabilities and if there are collaboration opportunities, 2022.
  13. NAI established a working relationship with Moana New Zealand to apply AI to oyster aquaculture, through the successful recruitment of one summer student, 2022.
  14. NAI established a working relationship with MacLab to apply AI to shellfish assessments through the successful recruitment of two summer students and one Master student, 2021-2022.
  15. NAI, in collaboration with Waikato University, produced a proof-of-concept which showed that artificial intelligence can be used to accurately identify individuals in mussel & synthetic datasets in many cases. NAI has many ideas for future work to improve this model for commercial application in collaboration with industry. This would accelerate breeding programmes and the generation of higher value products, 2021-2022.
  16. NAI has been engaging fully with industry to refine technology requirements for all NAI projects and this feedback is incorporated into our project planning which will ensure better outcomes for industry, 2021-2022.

Capability

Postdocs
  1. Caitlin Owen, University of Otago, from December 2021
  2. Julie Blommaert, University of Otago, from November 2021
  3. Fangfang Zhang, Victoria University of Wellington, from May 2022
  4. Qurrat Ul Ain, Victoria University of Wellington, from May 2022
  5. Baligh Al-Helali, Victoria University of Wellington, from July 2021-March 2022

Masters
  1. David Knox, working on machine learning for image analysis, 2021-2022
  2. Fergus Currie, working on multi-criteria decision making for fish breeding program, 2021-2022
  3. Michael Stanley, working on machine learning for fish image segmentation and fish length prediction, 2021-2022

PhD Students
  1. Laia Egea: "Partial ordered stereotype modes and their applications", Victoria University of Wellington, from 1 March 2022 (supervised by A/Prof. Ivy Liu, Prof. Richard Arnold, Dr. Daniel Fernandez, Dr. Symonds, Dr. Paula Casanovas)
  2. Jesse Wood: Machine Learning for Fish Oil Analysis, PhD Thesis. 1 March 2022, Wellington Doctoral Scholarship. (with Prof Bing Xue and Dr Bach Nguyen)
  3. Zhiheng (Dylon) Zeng: Machine Learning and Computer Vision for Precision Farming Technology for Aquaculture, Victoria University of Wellington, from 1 October 2021 (supervised by Prof. Mengjie Zhang, Prof. Bing Xue, A/Prof. Ivy Liu)
  4. Ying Cui: Semi-supervised learning of model-based clustering for ordinal data, Victoria University of Wellington, from 1 Sep 2021 (supervised by A/Prof. Ivy Liu, Prof. Richard Arnold, Dr. Louise McMillan, Dr. Symonds, Dr. Paula Casanovas)
  5. Qinyu Wang: Evolutionary Computation for Image Analysis, Victoria University of Wellington, from Sep 2021 (supervised by Prof. Bing Xue, Dr Ying Bi, and Prof. Mengjie Zhang)
  6. Loc Nguyen (PhD student on another project but helping on the Salmon X-rays project, started from 1 June 2022)

Summer Scholars
  1. Fay Lu, "Feature Selection for Multi-label Classification", Victoria University of Wellington, 14 Nov 2021 -- 18 Feb 2022 (co-supervised with Dr Bach Hoai Nguyen)
  2. Demelza Robinson: Genetic programming and machine learning for feature selection and classification for quantitative assessment of nutrient content in horticultural products. Nov. 2021 (with Prof Mengjie Zhang)
  3. Jackson Jourdain: Machine learning for tree species identification. Nov. 2021 (with Prof. Bing Xue)
  4. Fintan O'Sullivan: Artificial Intelligence based methods for recognising individual kākā. Nov. 2021 (with Dr Andrew Lense)
  5. Luis Slyfield: Explainable artificial intelligence using genetic programming. Nov. 2021 (with Dr Andrew Lense)
  6. Yan Lu: Feature selection for multi-label classification. Nov. 2021 (with Bach Nguyen)
  7. Taran John: An automated approach to evolving scoring module for cuckoo Sandbox by utilising genetic programming. Nov. 2021 (with Harith Al-Sahaf)
  8. Amer Hussian: Genetic programming for symbolic regression. Nov. 2021 (with Dr Qi Chen)
  9. Sean McGifford: Transfer learning for AI planning. Nov. 2021 (with Dr Yi Mei)
  10. Yuan Gao: Genetic programming for real-world image segmentation. Nov. 2021 (with Dr Ying Bi)
  11. Flynn Oberdries at University of Otago Nov. 2021
  12. Morkie Morea: Shellfish Identification using Machine Learning with Waikato University, 2022 (with Dr Nikki Hawes, Dr Julian Maclaren, Cris Lovell-Smith, Dr Michael Mayo)
  13. Hamish O’keeffe and Roger Jin: work on AI for Shellfish Assessments, 2021 (with Dr Nikki Hawes, Dr Julian Maclaren, Cris Lovell-Smith)

Honours Students
  1. Ze Chen, “Fish growth rate prediction from genetic data using machine learning techniques”, VUW, 2022
  2. Flynn Oberdries, “Modelling Salmon Feed Efficiency through a Data Science Workflow”, University of Otago (supervised by Grant Dick), 2021
  3. Hamish O’keeffe, working on machine learning techniques for modeling shellfish harvest assessments, 2021-2022

Actively Work with Industry Partners

  1. VUW have Prof. Ali Knott to visit our group and given a seminar on two topics, i.e., “How can we talk about what we see and do? The interface between language and sensorimotor cognition” and “How should governments oversee AI technologies? National and international perspectives” on 16th August 2022
  2. Meng/Baligh/Dylon/Ying have visited Prof. Richard Green's group in December 2021 and there was a one-day workshop to discuss research related to AI/DS and applications to aquaculture. Ross and Dana from Cawthron have joined it remotely.
  3. The workshop organised by Jane on 18 August 2021 was cancelled due to COVID close down and postponed to August in 2022. We recently have scheduled it on 29th-30th August 2022 to visit King Salmon and Mussel farms and aquaculture park.
  4. The Cawthron team has well established relationships with all NZ salmon farmers and will continue to utilize these to share results from the programme and to get their input.
  5. NAI has established working relationships with domestic industry partners, including with Moana New Zealand, Aquaculture New Zealand, and MacLab.
  6. Cawthron are members of the New Zealand Salmon Farmers Association.
  7. A salmon industry advisory group meeting is planned for late 2022 or early 2023.
  8. Jane Symonds organises Regular theme meetings took place and a new on-line Team was established for information sharing. Fish trial data sharing has commenced, 2021-2022
  9. Jane Symonds has had discussions with salmon industry stakeholders about the projects and will continue to keep them informed, 2021-2022.
  10. We have also connected with the National Genomics Platform and scheduled 30 September for a meeting --- the Platform Programme Manager and the Maori Manager will visit VUW to discuss further collaborations and Maori capability building.
  11. Ross and Dana (Cawthron Institute) visited Mengjie Zhang (VUW) to discuss further collaborations in August 2021.
  12. Maren Wellenreuther (PFR) visited Mengjie Zhang, Bing Xue, Yi Mei, Ying Bi, and Fangfang Zhang (VUW) for further collaborations in December 2021.
  13. Chris Cornelisen visited Mengjie Zhang and Fangfang Zhang to discuss industry engagement, e.g., seafood conference and aquaculture conference May 2022.
  14. 2021, Maren Wellenreuther is in the Advisory Group – Aotearoa Circle a Climate Change Adaptation Strategy for the Seafood Sector of New Zealand.
  15. 2021, Maren Wellenreuther is a Member of the College of Assessors, the New Zealand Ministry of Business, Innovation and Employment (MBIE)
  16. 2021, Maren Wellenreuther is a Member of Advisory Board, Trends in Ecology & Evolution (TREE)
  17. 2021, Maren Wellenreuther is a Part of the Science Advisory Board, Blue Economy CRC Australia
  18. Cawthron are members of the New Zealand Salmon Farmers Association and regularly hold meetings with the industry, 2021.

Establish Relationships with Existing Aligned Government-Funded Research Programmes

  1. Cyber-physical seafood systems: Intelligent and optimised green manufacturing for marine co-products. MBIE Endeavour Research Program. Oct 2020-Sep 2025
  2. Bridging the gap between remote sensing and tree modelling with data science. NZ-Singapore MBIE SSIF/Catalyst Fund on Data Science. Oct 2020-Sep 2023
  3. Precision Farming. National Science Challenge SfTI Spearhead. 2019-2022 (Trench 2)
  4. Karetao Hangarau-a-Mahi: Adaptive learning robots to complement the human workforce. National Science Challenge SfTI Spearhead. 2019-2022
  5. AI and Machine Learning for Medical Applications. Huayin Medical (Industry) and Academician Workstation. Oct 2020-Sep 2023
  6. Deep Learning Architecture with Context Adaptive Features for Image Parsing (DP200102252). Australia ARC Discover Project. 2020-2022
  7. Genetic Programming for Evolving Interpretable Models for Symbolic Regression. Marsden Fund of NZ. 2021-2024
  8. Genetic Programming for Symbolic Regression. Marsden Fund of New Zealand, 2020-2023
  9. Evolutionary Automated Design of Deep Convolutional Neural Networks for Image Classification. Marsden Fund of New Zealand, 2020-2023
  10. A Novel Genetic Programming Approach to Image Classification, Marsden Fund of New Zealand, 2022-2025
  11. Connect to Genomics platform (Jayashree Panjabi) to discuss the engagement with Māori communities. Jayashree will visit VUW at wellington on 29th September 2022
  12. Connect to Smart&Connect to introduce more about our programme and engage with researchers who work in aquaculture in national NZ. We can regular catch up each month. 2022
  13. Connect MPI Aquaculture Team to discuss potential collaborations. We have built connections with Philip Heath, Campbell Murray, Mat Bartholomew, Bailey Lovett and Annaliese Ludwig from MPI, and invited Philip Heath to VUW to have more detailed discussions in August 2022

Collaborations

  1. Co-supervise Dylon with Cawthron working on the automate detection of a key part of mussel farm surface, the surface floats.
  2. Cawthron-VUW on Ying Cui, laia, Fergus for VUW-PFR, many collaborations via summer/Hons projects
  3. Developed collaboration with MBIE funded Strategic Science Investment Science Platform Shellfish Aquaculture, with work resulting in an initial paper on the potential source regions for mussel spat, the foundation of the mussel aquaculture (Atalah et al 2021). This work and collaboration are continuing within this program as project 2 above, to identify sources of mussel spat in the upper South Island. This is key to an industry currently heavily reliant on spat washed up on 90-mile beach in Northland.
  4. Ongoing collaboration with Science for Technological Innovation National Science Challenge to automate monitoring of aquaculture farms structures.
  5. The shared results are found in papers (Bi et al 2022, McLeay 2021, Buchanan 2021) and ongoing work with PhD student in project 1 above.
  6. Developed collaboration with independent researcher and Cawthron researchers to detect dolphin clicks, as interaction of farms with marine mammals is a key part of gaining the social license to operate sustainable (Buchanan et al 2021).
  7. NAI is Co-supervising a Masters student with Bing Xue and Mengjie Zhang on a project titled Machine Learning Techniques for Modeling Shellfish Harvest Assessments.

Initial Pipeline of Scholarships/Internships to Attract Maori Students

  1. Internships and bootcamp to attract high-school Maori students to our Data Science and AI (DSAI) undergraduate programmes (one or two weeks, labs, demonstrations, programming assignments, etc.)
  2. Workshops/seminars/Webinars (with food and drinks) and Maori Junior Undergraduate Internships to attract Year 1 students to Year 2 in DSAI ($2,000 for tuition fees or accommodation each internship)
  3. Workshops/seminars/webinars (with food and drinks) and Maori Senior Undergraduate Internship to attract Year 2 to Year 3 in DSAI ($5,000 for Tuition fees or Accommodation each internship)
  4. Summer scholarships and Maori Graduate Awards to attract Maori Year 3 students to our PG DSAI coursework programmes ($10,000 each)
  5. Strategic Maori Master by Research scholarships to attract PG DSAI coursework students to our MSc in DSAI programmes (Tuition fees + $22K stipend)
  6. Strategic Maori PhD Scholarships to attract Maori students to our PhD programmes (Tuition fees + $35K p.a. stipend for three years)

Additional Information

  1. Fuller Z and WELLENREUTHER M. Studying climate change effects in the era of omic sciences. Accepted in the book 'Effects of Climate Change on Insects: Physiological, Evolutionary, and Ecological Responses' by Oxford University Press, 2022
  2. Lancaster, Lesley T., Zachary L. Fuller, David Berger, Matthew A. Barbour, Sissel Jentoft, and Maren Wellenreuther. "Understanding climate change response in the age of genomics." Journal of Animal Ecology 91, no. 6 (2022): 1056-1063.
  3. Wellenreuther, Maren, Rachael Y. Dudaniec, Anika Neu, Jean-Philippe Lessard, Jon Bridle, José A. Carbonell, Sarah E. Diamond et al. "The importance of eco-evolutionary dynamics for predicting and managing insect range shifts." Current Opinion in Insect Science (2022): 100939.
  4. Bing Xue, Mengjie Zhang, Qi Chen and Bach Nguyen are writing two chapters on Evolutionary Regression and Evolutionary Classification. Accepted in the Book “Evolutionary Machine Learning” by Springer, 2022.
  5. Bing Xue successfully delivered a Plenary Talk on "Evolutionary Computation for Automated Design of Deep Neural Networks" for IEEE World Congress on Computational Intelligence WCCI 2022. WCCI is an umbrella of three large conferences IEEE Congress on Evolutionary Computation (IEEE CEC2022), International Joint Conferences on Neurla Networks (IJCNN2022) and IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2022). WCCI is held with the three big conferences together every two years (in the even years), and the three conferences are held independently in the odd years. WCCI is typically with about 2000 people. Typically the "plenary talk" speakers for WCCI are very senior people and famous in a particular direction. The speakers are invited by the three individual conferences are called "Keynote Speakers". This is a big reputation for our university. More information can be seen from https://wcci2022.org/invited-speakers/
  6. Mengjie Zhang was awarded the Fellow of Engineering in New Zealand.
  7. Bing Xue just received the 2023 IEEE Computational Intelligence Society Outstanding Early Career Award with the citation “For contributions to the development and application of evolutionary machine learning”. This is a very competitive award across all areas of Computational Intelligence, including Neural Networks, Fuzzy Systems, Evolutionary Computation and their hybridisations. Bing will receive a prize of $1000 USD and a Praque.
  8. Fangfang Zhang just received a "Honourary Mention" (runner-up) for the 2022 ACM SIGEVO Best PhD Dissertation Award. She will receive a prize of $1000 USD and a praque. Fangfang was supervised by Yi and me. Fangfang is our Postdoc Fellow and also the Project Coordinator for our large MBIE Data Science Programme.
  9. Shaolin Wang, Yi Mei, Mengjie Zhang received the Best Paper Award from GECCO 2022 ECOM Track. GECCO is a top conference in the area of Evolutionary Computation and this year it has ~950 attendees. The paper title is "Local Ranking Explanation for Genetic Programming Evolved Routing Policies for Uncertain Capacitated Arc Routing Problems".
  10. Zhixing Huang, Fangfang Zhang, Yi Mei and Mengjie Zhang received the Best Paper Award from EuroGP2022. EuroGP is the flagship conference in Genetic Programming, and all major GP researchers typically attend the conference. The title is: "An Investigation of Multitask Linear Genetic Programming for Dynamic Job Shop Scheduling".
  11. Bing Xue also received a recognition of 2022 Outstanding TEVC AE (IEEE Transactions on Evolutionary Computation Associate Editors). IEEE Transactions on Evolutionary Computation is the top journal in Evolutionary Computation and Learning, and it has been consistently ranked top 5 journals in the whole Computer Science and Artificial Intelligence. This year, its Impact Factor is 16.497, and typically accept 5-10% of quality submissions.
  12. Professor Carlos Coello Coello, Department of Computer Science, CINVESTAV-IPN, Mexico City, Mexico will be visiting us on 19-26 September. Carlos is a Fellow of IEEE, the Editor-in-Chief for IEEE Transactions on Evolutionary Computation, and 2021 IEEE CIS Evolutionary Computation Pioneer Awardee. He is also a big name in Multi-Objective Optimisation and has over 60,000 citations on Google Scholar. During his visit, he will provide a talk to the DSAI people, and seek research collaborations in Multi-objective Learning and Optimisation, Scheulding and Combinatorial Optimisation, Feature Selection and Dimensionality Reduction. We will seek to joint grant applications.
  13. Professor Wolfgang Banzhaf, John R. Koza Chair in Genetic Programming in the Department of Computer Science and Engineering at Michigan State University, will visit us from 29 September to 15 December. Wolfgang is one of the major leaders in Genetic Programming, and the founder of Linear Genetic Programming. He is the Founding Editor-in-Chief of the major jounral "Genetic Programming and Evolvable Machines", a Leader of ACM SigEVO, and a Senior Fellow of the former International Society for Genetic and Evolutionary Computation (ISGEC) and has received the EvoStar Award for Outstanding Achievements in Evolutionary Computation in Europe. He is currently on Dr Qi Chen's Marsden grant and will make deeper research collaborations with us in Genetic Programming and Evolutionary Machine Learning.
  14. Bing Xue: Publication Co-Chair of Proceedings of the 25th European Conference on Genetic Programming (EuroGP), April 2022
  15. Bing Xue: Track Chair of the Neurevolution Track (New) of ACM The Genetic and Evolutionary Computation Conference (GECCO), July 2021
  16. Bing Xue: Workshop Chair of IEEE 2021 21st IEEE International Conference on Data Mining (ICDM), Dec 2021
  17. Bing Xue: Conference Activities Chair of IEEE Symposium Series on Computational Intelligence (IEEE SSCI), Dec 2021
  18. Bing Xue: Publicity Chair of the Evolutionary Machine Learning track in IEEE Congress on Evolutionary Computation (CEC), 28.06-1.07. 2021
Print version | Backlinks |