Prioritizing insect pests with Kohonen SOM

My research interests and activities are split between two fields: computational intelligence (obviously) and ecological modelling. Although I got into ecological modelling via computational intelligence, many of my recent publications in ecological modelling haven't had anything to do with computational intelligence. An exception to this is a recently published paper in the journal Neobiota that I am a coauthor of: "Prioritizing the risk of plant pests by clustering methods: self-organising maps, k-means and hierarchical clustering".

The problem is this: given the species that are known to exist in various geo-political regions of the world, what is the likelihood of one of those species establishing in a region where it is not already present? Species presences and absences are represented by binary vectors, where each region has a vector, a one represents a presence of a particular species in that region, and a zero represents an absence in that region. By clustering the assemblage vectors using a SOM, it is possible to infer which species pose the greatest threat to any particular region.

The rationale behind this approach is that regions that have similar species assemblages are likely to have similar environments. So if several assemblages end up in the same cluster, and a species is present in many of those regions but absent in others, then that species is likely to become established in the regions from which it is absent.

In this work the SOM were used as data clustering algorithms, with the vector quantisation abilities of the SOM being largely underutilized. My own contribution to the work was the realisation that the SOM were being used to cluster data, and hence to test the approach against the much-faster k-means clustering algorithm. I found that k-means is just as effective at producing good clusters as the SOM, and is much faster.

There are some problems with this work as well: it is virtually impossible to determine which approach is better without testing data. Which means that if you are clustering a set of species assemblages, you also need some more up-to-date data to validate the predictions. I do have some thoughts on getting around this, which I am currently investigating.

Call for papers: Special Session for WCCI 2014 "Applications of Computational lntelligence in Ecological Informatics and Environmental Modelling"

Aim

The aim of this special session is to provide a forum for recent research in the application of computational intelligence in the areas of ecological informatics, ecological modelling and environmental modelling.

Ecological informatics and the related field of ecological modelling involve constructing computational models of ecological systems. These models include such things as the distribution or abundance of particular species, models of the interaction between multiple species, and models of the future development of populations. Environmental modelling is closely related and involves constructing models of the physical environment that biological eco-systems inhabit. These models cover such topics as the climate and climate change and the detection of landscape features from geographical data. Models have also been constructed of such environmental topics as waste management systems, water quality and drainage systems and air pollution. As these are highly-complex systems, algorithms from the field of computational intelligence have already been widely applied to modelling this data. Previous work has successfully applied artificial neural networks, fuzzy systems, evolutionary algorithms, support vector machines and combinations of these including neuro-fuzzy and neuro-evolutionary approaches. In each case, computational intelligence methods were shown to be more effective at solving the problem than the alternative methods.

Scope

Topics relevant to this special session include, but are not limited to, the following applications of computational intelligence, including Artificial Neural Networks, Fuzzy Systems, and Evolutionary Algorithms:

•    Species distribution and ecological niche modelling
•    Predicting species abundance
•    Remote sensing image analysis and content-based image retrieval for Ecological Informatics and Environmental Modelling
•    Analysis of species assemblages
•    Issues in the preparation of ecological data for modelling
•    Modelling of pollutants in air, land or water
•    Modelling water quality
•    Predicting the effects of climate change
•    Predicting crop hazards, pests or diseases
•    Identifying landscape features
•    Modelling ecosystem biomass

Deadline

The deadline for submissions to this special session is 20 December 2013.

Information for Authors

1)    Information on the format and templates for papers can be found here:
       http://www.ieee-wcci2014.org/Paper%20Submission.htm
2)    Papers should be submitted via the IJCNN 2014 paper submission site:
       http://ieee-cis.org/conferences/ijcnn2014/upload.php3) 
       Select the Special Session name in the Main Research topic dropdown list
4)    Fill out the input fields, upload the PDF file of your paper and finalize your submission by the deadline of December 20, 2013

Organisers

•    Dr Michael J Watts, AIS St Helens, Auckland, New Zealand. mjwatts@ieee.org
•    Associate Professor Russel Pears, Auckland University of Technology, Auckland, New Zealand, russel.pears@aut.ac.nz
•    Professor Jie Yang, Shanghai Jiao Tong University, Shanghai, China, jieyang@sjtu.edu.cn

Conference paper deadline: KES 2014

The deadline for submitting papers to the 18th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES) 2014 is 15 March, 2014. This conference will be held in Gdynia, Poland, 15-17 September, 2014.

Conference paper deadline: EAIS 2014

The deadline for submitting papers to the IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS) 2014 is January 15, 2014. This conference will be held in Linz, Austria, June 2-4, 2014.

Reminder: paper submission deadline: ICAISC 2014

A reminder that the deadline for submitting papers to the 13th International Conference on Artificial Intelligence and Soft Computing (ICAISC) 2014 is November 20, 2013 (beware the front page linked to has embedded folk-music playing). This conference will be held in Zakopane, Poland, June 1-5 2014.

Video: How to publish your research in IEEE CIS publications

A panel discussion on how to publish in the IEEE Computational Intelligence Society's publications. This discussion wraps up the individual talks by Professors Xin Yao, Kay Chen Tan, Derong Liu, Garrison Greenwood, Chin-Teng Lin and Simon M. Lucas . This panel session was part of the CEC 2013 conference.

How to publish your research: Video of Professor Simon M. Lucas

Professor Simon M. Lucas talks about how to publish research in IEEE Transactions on Computational Intelligence and Artificial Intelligence in Games. This talk was part of a panel session at CEC 2013 and mostly talks about what kind of papers are published in TCIAIG.

How to publish your research: Video of Professor Chin-Teng Lin

Professor Chin-Teng Lin, who is the editor-in-chief of IEEE Transactions on Fuzzy Systems, speaks about publishing in that journal. This talk was part of a panel discussion at the CEC 2013 conference. Some of the points he makes in this talk are applicable to publishing in most journals:

• Read existing papers, know the field
• Present an issue of significance
• Choose a journal that fits well with your research
• Use the correct format for that journal
• Have focus & vision, don't be too ambitious with your paper
• Write clearly
• Get pre-review, ask  your colleagues to check your paper before submission
• Proofread!
• Be patient, reviews take time

How to publish your research: Video of Professor Garrison Greenwood

Professor Garrison Greenwood talks about how to publish your research in the IEEE Transactions on Evolutionary Computation. This talk was part of a panel session at the CEC 2013 conference.

The main points of this talk are:

• Establish the context of your research in the Related Research section following the introduction (as a side-note, in other fields this is the introduction: why does computer science insist of separating them?

• Use enough citations, and no more

• Write enough detail for a competent researcher to replicate your work, don't try to write a tutorial

• Read the instructions for authors

• Use good grammar and spelling

How to publish your research: Video of Professor Derong Liu

Professor Derong Liu talks about how to publish your research in IEEE Transactions on Neural Networks and Learning Systems at a panel session at the CEC 2013 conference. This talk gives a lot of information about the editorial and review process, as well as how to increase your chances of having a paper accepted and even how to get on the editorial board of the journal.

Call for papers: Special Session for WCCI 2014 "Applications of Computational lntelligence in Ecological Informatics and Environmental Modelling"

Aim

The aim of this special session is to provide a forum for recent research in the application of computational intelligence in the areas of ecological informatics, ecological modelling and environmental modelling.

Ecological informatics and the related field of ecological modelling involve constructing computational models of ecological systems. These models include such things as the distribution or abundance of particular species, models of the interaction between multiple species, and models of the future development of populations. Environmental modelling is closely related and involves constructing models of the physical environment that biological eco-systems inhabit. These models cover such topics as the climate and climate change and the detection of landscape features from geographical data. Models have also been constructed of such environmental topics as waste management systems, water quality and drainage systems and air pollution. As these are highly-complex systems, algorithms from the field of computational intelligence have already been widely applied to modelling this data. Previous work has successfully applied artificial neural networks, fuzzy systems, evolutionary algorithms, support vector machines and combinations of these including neuro-fuzzy and neuro-evolutionary approaches. In each case, computational intelligence methods were shown to be more effective at solving the problem than the alternative methods.

Scope

Topics relevant to this special session include, but are not limited to, the following applications of computational intelligence, including Artificial Neural Networks, Fuzzy Systems, and Evolutionary Algorithms:

•    Species distribution and ecological niche modelling
•    Predicting species abundance
•    Remote sensing image analysis and content-based image retrieval for Ecological Informatics and Environmental Modelling
•    Analysis of species assemblages
•    Issues in the preparation of ecological data for modelling
•    Modelling of pollutants in air, land or water
•    Modelling water quality
•    Predicting the effects of climate change
•    Predicting crop hazards, pests or diseases
•    Identifying landscape features
•    Modelling ecosystem biomass

Deadline

The deadline for submissions to this special session is 20 December 2013.

Information for Authors

1)    Information on the format and templates for papers can be found here:
       http://www.ieee-wcci2014.org/Paper%20Submission.htm
2)    Papers should be submitted via the IJCNN 2014 paper submission site:
       http://ieee-cis.org/conferences/ijcnn2014/upload.php3) 
       Select the Special Session name in the Main Research topic dropdown list
4)    Fill out the input fields, upload the PDF file of your paper and finalize your submission by the deadline of December 20, 2013

Organisers

•    Dr Michael J Watts, AIS St Helens, Auckland, New Zealand. mjwatts@ieee.org
•    Associate Professor Russel Pears, Auckland University of Technology, Auckland, New Zealand, russel.pears@aut.ac.nz
•    Professor Jie Yang, Shanghai Jiao Tong University, Shanghai, China, jieyang@sjtu.edu.cn

How to publish your research: Video of Professor Kay Chen Tan

A video of a talk by Professor Kay Chen Tan as part of a panel session at the CEC 2013 conference. In this video he describes the IEEE CIS Computational Intelligence Magazine.

How to publish your research: Video of Professor Xin Yao

This is a video of a talk given by Professor Xin Yao as part of a panel session at the CEC 2013 conference. A couple of the most salient points that I noticed:

1) If you want to publish your research, you must first do good research
2) Contact the editors of the journals you want to publish in before submitting

IEEE Transactions on Computational Intelligence and AI in Games: Volume 5, Issue 3, September 2013

1. Monte Carlo Search Algorithm Discovery for Single-Player Games
Author(s): F. Maes, D. L. St-Pierre, and D. Ernst
Pages: 201-213

2. On Scalability, Generalization, and Hybridization of Coevolutionary Learning: A Case Study for Othello
Author(s): M. Szubert, W. Jaśkowski, and K. Krawiec
Pages: 214-226

3. Database-Driven Real-Time Heuristic Search in Video-Game Pathfinding
Author(s): R. Lawrence and V. Bulitko
Pages: 227-241

4. Backward Induction and Repeated Games With Strategy Constraints: An Inspiration From the Surprise Exam Paradox
Author(s): J. Li, G. Kendall, and A. V. Vasilakos
Pages: 242-250

5. An Efficient Approach to Solving Nonograms
Author(s): I.-C. Wu, D.-J. Sun, L.-P. Chen, K.-Y. Chen, C.-H. Kuo, H.-H. Kang, and H.-H. Lin
Pages: 251-264

6. Applicability of GPGPU Computing to Real-Time AI Solutions in Games
Author(s): W. Blewitt, G. Ushaw, and G. Morgan
Pages: 265-275

7. Crowdsourcing the Aesthetics of Platform Games
Author(s): N. Shaker, G. N. Yannakakis, and J. Togelius
Pages: 276-290

IEEE Transactions on Autonomous Mental Development: Volume 5, Issue 3, 2013

1. GUEST EDITORIAL: Microdynamics of Interaction: Capturing and Modeling Infants’ Social Learning
Author(s): K. J. Rohlfing and G. O. Deák
Pages: 189-191

2. Mothers’ infant-directed gaze during object demonstration highlights action boundaries and goals
Author(s): R. J. Brand, E. Hollenbeck, and J. F. Kominsky
Pages: 192-201

3. From Action to Interaction: Infant Object Exploration and Mothers’ Contingent Responsiveness
Author(s): C. S. Tamis-LeMonda, Y. Kuchirko, and L. Tafuro
Pages: 202-209

4. Young Children’s Dialogical Actions: The Beginnings of Purposeful Intersubjectivity
Author(s): J. Rączaszek-Leonardi, I. Nomikou, and K.J.Rohlfing
Pages: 210-221

5. From Language to Motor Gavagai: Unified Imitation Learning of Multiple Linguistic and Nonlinguistic Sensorimotor Skills
Author(s): T. Cederborg and P.-Y. Oudeyer
Pages: 222-239

6. Supporting Early Vocabulary Development: What Sort of Responsiveness Matters?
Author(s): M. L. McGillion, J. S. Herbert, J. M. Pine, T. Keren-Portnoy, M. M. Vihman, and D. E. Matthews
Pages: 240-248

7. SEED Framework of Early Language Development: The Dynamic Coupling of Infant–Caregiver Perceiving and Acting Forms a Continuous Loop during Interaction
Author(s): P. Zukow-Goldring and N. d. V. Rader
Pages: 249-257

8. Methodological Considerations For Investigating the Microdynamics of Social Interaction Development
Author(s): K. de Barbaro, C. M. Johnson, D. Forster, and G. O. Deák
Pages: 258

IEEE Transactions on Evolutionary Computation: Volume 17, Issue 5, October 2013

1. On the Convergence of Chemical Reaction Optimization for Combinatorial Optimization
Author(s): A. Y. S. Lam, V. O. K. Li, and J. Xu
Pages: 605-620

2. A Computational Study of Representations in Genetic Programming to Evolve Dispatching Rules for the Job Shop Scheduling Problem
Author(s): S. Nguyen, M. Zhang, M. Johnston, and K. C. Tan
Pages: 621-639

3. An Evolutionary Negative-Correlation Framework for Robust Analog-Circuit Design Under Uncertain Faults
Author(s): M. Liu and J. He
Pages: 640-665

4. Multimodal Optimization Using a Biobjective Differential Evolution Algorithm Enhanced With Mean Distance-Based Selection
Author(s): A. Basak, S. Das, and K. C. Tan
Pages: 666-685

5. Correlation as a Heuristic for Accurate and Comprehensible Ant Colony Optimization Based Classifiers
Author(s): A. R. Baig, W. Shahzad, and S. Khan
Pages: 686-704

6. An Adaptive Particle Swarm Optimization With Multiple Adaptive Methods
Author(s): M. Hu, T. Wu, and J. D. Weir
Pages: 705-720

7. A Grid-Based Evolutionary Algorithm for Many-Objective Optimization
Author(s): S. Yang, M. Li, X. Liu, and J. Zheng
Pages: 721

IEEE Transactions on Neural Networks and Learning Systems: Volume 24, Issue 10, October 2013

1. Adaptive Optimal Control of Unknown Constrained-Input Systems Using Policy Iteration and Neural Networks
Author(s): H. Modares, F. L. Lewis, and M.-B. Naghibi-Sistani
Pages: 1513-1525

2. Lattice Computing Extension of the FAM Neural Classifier for Human Facial Expression Recognition
Author(s): V. G. Kaburlasos, S. E. Papadakis, and G. A. Papakostas
Pages: 1526-1538

3. Rapid Feedforward Computation by Temporal Encoding and Learning With Spiking Neurons
Author(s): Q. Yu, H. Tang, K. C. Tan, and H. Li
Pages: 1539-1552

4. Mean Vector Component Analysis for Visualization and Clustering of Nonnegative Data
Author(s): R. Jenssen
Pages: 1553-1564

5. RBF-Based Technique for Statistical Demodulation of Pathological Tremor
Author(s): F. Gianfelici
Pages: 1565-1574

6. Automated Induction of Heterogeneous Proximity Measures for Supervised Spectral Embedding
Author(s): E. Rodriguez-Martinez, T. Mu, J. Jiang, and J. Y. Goulermas
Pages: 1575-1587

7. Coordination of Multiagents Interacting Under Independent Position and Velocity Topologies
Author(s): J. Qin and C. Yu
Pages: 1588-1597

8. Learning Capability of Relaxed Greedy Algorithms
Author(s): S. Lin, Y. Rong, X. Sun, and Z. Xu
Pages: 1598-1608

9. Minimax Sparse Logistic Regression for Very High-Dimensional Feature Selection
Author(s): M. Tan, I. W. Tsang, and L. Wang
Pages: 1609-1622

10. Ensemble Learning in Fixed Expansion Layer Networks for Mitigating Catastrophic Forgetting
Author(s): R. Coop, A. Mishtal, and I. Arel
Pages: 1623-1634

11. SVR Learning-Based Spatiotemporal Fuzzy Logic Controller for Nonlinear Spatially Distributed Dynamic Systems
Author(s): X.-X. Zhang, Y. Jiang, H.-X. Li, and S.-Y. Li
Pages: 1635-1647

12. Single Image Super-Resolution With Multiscale Similarity Learning
Author(s): K. Zhang, X. Gao, D. Tao, and X. Li
Pages: 1648-1659

13. Tracking Algorithms for Multiagent Systems
Author(s): D. Meng, Y. Jia, J. Du, and F. Yu
Pages: 1660-1676

14. A Robust Elicitation Algorithm for Discovering DNA Motifs Using Fuzzy Self-Organizing Maps
Author(s): D. Wang and S. Tapan
Pages: 1677-1688

15. EEG-Based Learning System for Online Motion Sickness Level Estimation in a Dynamic Vehicle Environment
Author(s): C.-T. Lin, S.-F. Tsai, and L.-W. Ko
Pages: 1689-1700

16. New Algebraic Criteria for Synchronization Stability of Chaotic Memristive Neural Networks With Time-Varying Delays
Author(s): G. Zhang and Y. Shen
Pages: 1701

Reminder: paper submission deadline for IEEE CIFEr 2014

A reminder that the deadline for submitting papers to the IEEE Computational Intelligence for Financial Engineering and Economics (CIFEr) 2014 is November 1, 2013. This conference will be held in London, UK, 27-28 March, 2014.

On the importance of a good supervisor

One day, a fox was walking through the forest when he met a rabbit sitting outside a rabbit hole reading a pile of papers. "What are you doing?" the fox asked the rabbit. The rabbit looked up at the fox and replied "I'm doing the literature review for my thesis. It's on the superiority of rabbits over foxes. Would you like to come inside and discuss it?". The fox hungrily licked his lips, followed the rabbit into the rabbit hole, and was never seen again. 

Some time later, a wolf was walking through the forest and saw the rabbit sitting outside of his rabbit hole making notes on a thick pile of paper with a big, red, pen. "What are you doing?" the wolf asked the rabbit. The rabbit looked up and replied "I'm revising my thesis". The wolf asked the rabbit "What's your thesis about?" and the rabbit said "It's on the superiority of rabbits over foxes and wolves. Would you like to come inside and discuss it?". The wolf hungrily licked his lips, followed the rabbit down the rabbit hole, and was never seen again.

Some time later, a hare was walking through the forest when he saw the rabbit sitting in the sun with a big, satisfied grin on this face. "Why are you looking so happy?" the hare asked the rabbit. The rabbit looked at the hare and said "I've just been awarded my PhD. My thesis was on the superiority of rabbits over foxes and wolves. Would you like to come inside and discuss it?". The hare, curious about such a topic, followed the rabbit down the rabbit hole into the warren. In one corner of the rabbit's room was a pile of fox bones. In another corner was a pile of wolf bones. Sitting between the two piles of bones was a lion.

So you see, it doesn't matter what your thesis is on, as long as your supervisor is a lion.

A newly published article (discussed in more detail by one of the authors here) has examined the influence of several factors that may determine how successful a scientist is in their career, where success is measured by the number of publications the scientist (biologists in this case) has. While factors such as gender and language had some slight effect, the factor that was most influential was the number of publications a scientist had before completing their PhD.

In other words, someone who has learned to produce papers before they finish their PhD is more likely to be able to continue producing papers after they have finished their PhD. To me this seems analagous to saying that someone who has learned how to drive can drive. Apparently, stating the blindingly obvious is original research as long as it uses statistics.

Who does a pre-PhD learn this paper-production skill from? Most of the time, from their supervisor. A supervisor who produces a lot of papers, and includes their students in the process of doing so, will produce PhD graduates who have the skills to produce papers post-PhD. If the supervisor doesn't teach the student how to publish, where else will they get this skill?

The most disturbing implication of this is that if a student chooses the wrong supervisor, they will have little chance of a successful career. The article linked to above states that the institution that the PhD graduates from has no influence on success and the influence of other factors is weak. As an aside, this reinforces something I've been saying for a while - that the reputation of an institution is good for marketing, but says little about the quality of the staff there.

The sentiment behind the story at the top of this post, is that as long as your supervisor is a good supervisor, you will be successful. This makes choosing the right supervisor probably the most critical decision an aspiring academic can ever make, yet they must make it when they have little knowledge and no experience on which to draw to make that decision. This is a huge problem - how many perfectly capable researchers have had their careers destroyed, before they have even begun, by a bad choice of supervisor? More importantly, how do those of us who are post-PhD stop it from happening in the future?

I really wish I had an answer to that question.

Neural Networks Volume 47 Pages 1-150

1. Computation in the Cerebellum  
Author(s): Dieter Jaeger, Henrik Jorntell, Mitsuo Kawato
Pages: 1-2

2. The importance of stochastic signaling processes in the induction of long-term synaptic plasticity  
Author(s): Erik De Schutter
Pages: 3-10

3. Dendritic calcium signaling in cerebellar Purkinje cell  
Author(s): Kazuo Kitamura, Masanobu Kano
Pages: 11-17

4. Bistability in Purkinje neurons: Ups and downs in cerebellar research  
Author(s): Jordan D.T. Engbers, Fernando R. Fernandez, Ray W. Turner
Pages: 18-31

5. Mechanisms producing time course of cerebellar long-term depression  
Author(s): Taegon Kim, Keiko Tanaka-Yamamoto
Pages: 32-35

6. Cerebellar LTD vs. motor learning—Lessons learned from studying GluD2  
Author(s): Michisuke Yuzaki
Pages: 36-41

7. Adaptive coupling of inferior olive neurons in cerebellar learning  
Author(s): Isao T. Tokuda, Huu Hoang, Nicolas Schweighofer, Mitsuo Kawato
Pages: 42-50

8. Solution to the inverse problem of estimating gap-junctional and inhibitory conductance in inferior olive neurons from spike trains by network model simulation  
Author(s): Miho Onizuka, Huu Hoang, Mitsuo Kawato, Isao T. Tokuda, Nicolas Schweighofer, Yuichi Katori, Kazuyuki Aihara, Eric J. Lang, Keisuke Toyama
Pages: 51-63

9. Nucleo-olivary inhibition balances the interaction between the reactive and adaptive layers in motor control  
Author(s): Ivan Herreros, Paul F.M.J. Verschure
Pages: 64-71

10. Transfer of memory trace of cerebellum-dependent motor learning in human prism adaptation: A model study  
Author(s): Soichi Nagao, Takeru Honda, Tadashi Yamazaki
Pages: 72-80
   
11. Classical conditioning of motor responses: What is the learning mechanism?  
Author(s): Germund Hesslow, Dan-Anders Jirenhed, Anders Rasmussen, Fredrik Johansson
Pages: 81-87

12. Cross-correlations between pairs of neurons in cerebellar cortex in vivo  
Author(s): Fredrik Bengtsson, Pontus Geborek, Henrik Jörntell
Pages: 88-94

13. Using a million cell simulation of the cerebellum: Network scaling and task generality  
Author(s): Wen-Ke Li, Matthew J. Hausknecht, Peter Stone, Michael D. Mauk
Pages: 95-102
   
14. Realtime cerebellum: A large-scale spiking network model of the cerebellum that runs in realtime using a graphics processing unit  
Author(s): Tadashi Yamazaki, Jun Igarashi
Pages: 103-111

15. Modeling the generation of output by the cerebellar nuclei  
Author(s): Volker Steuber, Dieter Jaeger
Pages: 112-119

16. Modeling cancelation of periodic inputs with burst-STDP and feedback  
Author(s): K. Bol, G. Marsat, J.F. Mejias, L. Maler, A. Longtin
Pages: 120-133

17. Adaptive filters and internal models: Multilevel description of cerebellar function  
Author(s): John Porrill, Paul Dean, Sean R. Anderson
Pages: 134-149