Semi-supervised learning with the clustering and Decision Trees classifier for the task of cognitive workload study


Abstract

The paper is focused on application of the clustering algorithm and Decision Tress classifier (DTs) as a semi-supervised method for the task of cognitive workload level classification. The analyzed data were collected during examination of Digit Symbol Substitution Test (DSST) with use of eye-tracker device. 26 participants took part in examination as volunteers. There were conducted three parts of DSST test with different levels of difficulty. As a results there were obtained three versions of data: low, middle and high level of cognitive workload. The case study covered clustering of collected data by using k-means algorithm to detect three clusters or more. The obtained clusters were evaluated by three internal indices to measure the quality of clustering. The David-Boudin index detected the best results in case of four clusters. Based on this information it is possible to formulate the hypothesis of the existence of four clusters. The obtained clusters were adopted as classes in supervised learning and have been subjected to classification. The DTs was applied in classification. There were obtained the 0.85 mean accuracy for three-class classification and 0.73 mean accuracy for four-class classification.  


Keywords

clustering; semi-supervised learning; eye-tracker

T. Urruty, S. Lew, N. Ihadaddene and D. A. Simovici, Detecting eye fixations by projection clustering. ACM Transaction on Multimedia Computing, Communications and Application, 3 (4), 5:1–5:20, 2007

N. Flad, T. Fomina, H. H. Buelthoff and L. L. Chuang, Unsupervised Clustering of EOG as a Viable Substitute for Optical Eye Tracking. Eye Tracking and Visualization, Cham, 2017, 151–167

R. S. Hessels, D. C. Niehorster, C. Kemner and I. T. C. Hooge Noise-robust fixation detection in eye movement data: Identification by two-means clustering (I2MC). Behaviour Research Methods, 49 (5), 1802–1823, 2017

J. Otero-Millan, J. L. A. Castro, S. L. Macknik and S. Martinez-Conde Unsupervised clustering method to detect microsaccades. Journal of Vision, 14 (2), 18–18, 2014

A. Santella and D. DeCarlo Robust clustering of eye movement recordings for quantification of visual interest. Proceedings of the 2004 symposium on Eye tracking research & applications, San Antonio, Texas, 2004, 27–34

P. K. Mital, T. J. Smith, R. L. Hill and J. M. Henderson, Clustering of Gaze During Dynamic Scene Viewing is Predicted by Motion. Cognitive Computation, 3 (1), 5–24, 2011

Z. Kang and S. J. Landry An Eye Movement Analysis Algorithm for a Multielement Target Tracking Task: Maximum Transition-Based Agglomerative Hierarchical Clustering. IEEE Transactions on Human-Machine Systems, 45 (1), 13–24, 2015

M. Aamir and S. M. A. Zaidi Clustering based semi-supervised machine learning for DDoS attack classification. Journal of King Saud University - Computer Information Sciences, 2019

K. Liang, Y. Chahir, M. Molina, C. Tijus and F. Jouen Appearance-based gaze tracking with spectral clustering and semi-supervised Gaussian process regression. Proceedings of the 2013 Conference on Eye Tracking South Africa, Cape Town, South Africa, 2013, 17–23

K. Wang, B. Wang and L. Peng CVAP: Validation for Cluster Analyses. Data Science Journal, 8 (0), 88–93, 2009

A. Thalamuthu, I. Mukhopadhyay, X. Zheng and G. C. Tseng Evaluation and comparison of gene clustering methods in microarray analysis. Bioinformatics (Oxford, England), 22 (19), 2405–2412, 2006

S. Dudoit and J. Fridlyand A prediction-based resampling method for estimating the number of clusters in a dataset. Genome Biology, 3 (7), 2002

T. Caliński and J. Harabasz A dendrite method for cluster analysis. Communications in Statistic, 3 (1), 1–27, 1974

P. J. Rousseeuw Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20, 53–65, 1987

D. L. Davies and D. W. Bouldin A Cluster Separation Measure. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-1 (2), 224–227, 1979

C. Boake From the Binet-Simon to the Wechsler-Bellevue: tracing the history of intelligence testing. Journal of Clinical and Experimental Neuropsychology, 24 (3), 383–405, 2002

V. Sicard, R. D. Moore, i D. Ellemberg Sensitivity of the Cogstate Test Battery for Detecting Prolonged Cognitive Alterations Stemming From Sport-Related Concussions. Clinical Journal of Sport Medicine: Official Journal Canadian Academy Sport Medicine,29 (1), 62–6

Download

Published : 2020-06-30


Wawrzyk, M. (2020). Semi-supervised learning with the clustering and Decision Trees classifier for the task of cognitive workload study. Journal of Computer Sciences Institute, 15, 214-218. https://doi.org/10.35784/jcsi.1725

Martyna Wawrzyk  martyna.wawrzyk@pollub.edu.pl
  Poland