Dr Gert Van Dijck
University position
Research Associate
Departments
Institutes
Behavioural and Clinical Neuroscience Institute
Home page
http://www.psychol.cam.ac.uk/index.html
Research Themes
Interests
Cell type identification is traditionally obtained using juxtacellular labelling or by means of intracellular techniques to assess membrane properties. These techniques are determined in anaesthetised animals. I developed a technique in which we are able to identify the cell type in both awake and anaesthetized animals using the spontaneous activity of extracellularly recorded cells. Properties extracted from the spike trains are used in a statistical model that assigns probabilities to each cell to belong to different cell types. Our technique allows to predict the cell type on-line and in real-time, which will lead to improved BCI (Brain Computer Interfaces).
Different cell types in the cerebellum can be identified up to 99 % accuracy and in the ventral tegmental area (VTA) up to 95 % accuracy.

View image full-size (2651x2798 pixels)
Research Focus
KeywordsNeuroscience Machine Learning Information Theory Causality Analysis |
Clinical conditionsAddiction Attention deficit hyperactivity disorder Obsessive compulsive disorder |
Equipment
Behavioural analysis
Computational modelling
Electrophysiological recording techniques
Field potential recording
Collaborators
Cambridge | InternationalReinoud Maex patrick Ruther Web: http://www.imtek.de/materia... Marc Van Hulle Web: http://simone.neuro.kuleuven.be/index.html |
Key publications
Van Dijck G, Van Hulle MM, Heiney SA, Blazquez PM, Meng H, Angelaki DE, Arenz A, Margrie TW, Mostofi A, Edgley S, Bengtsson F, Ekerot C-F, Jörntell H, Dalley JW, Holtzman T (2013), “Probabilistic Identification of Cerebellar Cortical Neurones Across Species” PLoS ONE 8(3): e57669
Van Dijck G, Seidl K, Paul O, Ruther P, Van Hulle MM, Maex R (2012), “Enhancing the Yield of High-Density Electrode Arrays through Automated Electrode Selection” Int J Neural Syst 22(1): 1-19
Van Dijck G, Van Hulle MM (2011), “Genetic Algorithm for Informative Basis Function Selection from the Wavelet Packet Decomposition with Application to Corrosion Identification using Acoustic Emission” Chemometrics Intell. Lab. Syst. 107(2): 318-332
Publications
2011
Van Dijck G, Van Hulle MM (2011), “Information Theory Filters for Wavelet Packet Coefficient Selection with Application to Corrosion Type Identification from Acoustic Emission Signals.” Sensors (Basel) 11(6):5695-5715 Details
Van Dijck G, Van Hulle MM (2011), “Joint Markov Blankets in Feature Sets Extracted from Wavelet Packets” Entropy 13(7): 1403-1424
2010
Seidl K, Torfs T, De Mazière PA, Van Dijck G, Csercsa R, Dombovari B, Nurcahyo Y, Ramirez H, Van Hulle MM, Orban GA, Paul O, Ulbert I, Neves H, Ruther P (2010), “Control and data acquisition software for high-density CMOS-based microprobe arrays implementing electronic depth control.” Biomed Tech (Berl) 55(3):183-91 Details
Van Dijck G, Jezzini A, Herwik S, Kisban S, Seidl K, Paul O, Ruther P, Serventi F, Fogassi L, Van Hulle M, Umiltà M (2010), “Toward Automated Electrode Selection in the Electronic Depth Control Strategy for Multi-unit Recordings.” Lecture Notes in Computer Science: Neural Information Processing, Models and Applicationsn, Part II 6444: 17-25.
Van Dijck G, Van Hulle MM (2010), “Increasing and Decreasing Returns and Losses in Mutual Information Feature Subset Selection” Entropy 12(10): 2144-2170
2009
Van Dijck G, Van Vaerenbergh J, Van Hulle MM (2009), “Posterior probability profiles for the automated assessment of the recovery of patients with stroke from activity of daily living tasks.” Artif Intell Med 46(3):233-49 Details
Van Dijck G, Wevers M, Van Hulle MM (2009), “Wavelet Packet Decomposition for the Identification of Corrosion Type from Acoustic Emission Signals. ” Int. J. Wavelets Multiresolut. Inf. Process. 7(4): 513-534
2007
Van Dijck G, Van Hulle MM (2007), “Speeding Up Feature Subset Selection through Mutual Information Relevance Filtering” European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD 2007). Lecture Notes in Computer Science 4702: 277-287
Van Dijck G, Van Hulle MM, Van Vaerenbergh J (2007), “A Novel Criterion for Onset Detection: Differential Information Redundancy with Application to Human Movement Initiation” Proceedings of the 7th IEEE International Conference on Data Mining (ICDM 2007) 673-678
Van Dijck G, Van Vaerenbergh J, Van Hulle MM (2007), “Information Theoretic Derivations for Causality Detection: Application to Human Gait” Proceedings of the 17th International Conference on Artificial Neural Networks (ICANN 2007). Springer, Lecture Notes in Computer Science 4669: 159-168
Van Dijck G, Van Vaerenbergh J, Van Hulle MM (2007), “Posterior Probability Profiles for the Automated Assessment of the Recovery of Stroke Patients.” Proceedings of the Twenty-Second AAAI Conference on Artificial Intelligence (AAAI 2007) 347-353.
2006
Van Dijck G, Van Hulle MM (2006), “Speeding up the Wrapper Feature Subset Selection in Regression by Mutual Information Relevance and Redundancy Analysis” 16th International Conference on Artificial Neural Networks (ICANN 2006). Lecture Notes in Computer Science 4131: 31-40.
Van Dijck G, Van Hulle MM (2006), “Onset Detection through Maximal Redundancy Detection” Proceedings of the 18th International Conference on Pattern Recognition (ICPR 2006) 945-949
Van Dijck G, Van Hulle MM, Van Vaerenbergh J (2006), “Hybrid feature subset selection for the quantitative assessment of skills of stroke patients in activity of daily living tasks.” Conf Proc IEEE Eng Med Biol Soc 1:5699-703 Details
Van Dijck G, Van Hulle MM, Van Vaerenbergh J (2006), “Statistically rigorous human movement onset detection with the maximal information redundancy criterion.” Conf Proc IEEE Eng Med Biol Soc 1:2474-7 Details
2005
Van Dijck G, Van Hulle MM (2005), “Hierarchical Feature Subset Selection for Features Computed from the Continuous Wavelet Transform” Proceedings of IEEE Machine Learning for Signal Processing Workshop XV 81-86


