Document Type: Original Research

Authors

1 CSE & IT Dept., School of Electrical and Computer Engineering, Shiraz University, Shiraz, Iran

2 Department of Clinical Psychology, Faculty of Education and Psychology, Shiraz University, Shiraz, Iran

Abstract

Background: Since psychological tests such as questionnaire or drawing tests are almost qualitative, their results carry a degree of uncertainty and sometimes subjectivity. The deficiency of all drawing tests is that the assessment is carried out after drawing the objects and lots of information such as pen angle, speed, curvature and pressure are missed through the test. In other words, the psychologists cannot assess their patients while running the tests. One of the famous drawing tests to measure the degree of Obsession Compulsion Disorder (OCD) is the Bender Gestalt, though its reliability is not promising.Objective: The main objective of this study is to make the Bender Gestalt test quantitative; therefore, an optical pen along with a digital tablet is utilized to preserve the key drawing features of OCD patients during the test.Materials and Methods: Among a large population of patients who referred to a special clinic of OCD, 50 under therapy subjects voluntarily took part in this study. In contrast, 50 subjects with no sign of OCD performed the test as a control group. This test contains 9 shapes and the participants were not constraint to draw the shapes in a certain interval of time; consequently, to classify the stream of feature vectors (samples through drawing) Hidden Markov Model (HMM) is employed and its flexibility increased by incorporating the fuzzy technique into its learning scheme.Results: Applying fuzzy HMM classifier to the data stream of subjects could classify two groups up to 95.2% accuracy, whereas the results by applying the standard HMM resulted in 94.5%. In addition, multi-layer perceptron (MLP), as a strong static classifier, is applied to the features and resulted in 86.6% accuracy.Conclusion: Applying the pair of T-test to the results implies a significant supremacy of the fuzzy HMM to the standard HMM and MLP classifiers.

Keywords

  1. Özer S. A comparison of clinical and nonclinical groups of children on the Bender-Gestalt and Draw a Person Tests. Procedia-Social and Behavioral Sciences. 2010;5:449-54. doi.org/10.1016/j.sbspro.2010.07.121.
  2. Brannigan GG. Bender Visual-Motor Gestalt Test: Wiley Online Library; 2003.
  3. Bender L. A visual motor Gestalt test and its clinical use. Research Monographs, American Orthopsychiatric Association. 1938.
  4. Fierrez J, Ortega-Garcia J, Ramos D, Gonzalez-Rodriguez J. HMM-based on-line signature verification: Feature extraction and signature modeling. Pattern recognition letters. 2007;28:2325-34. doi.org/10.1016/j.patrec.2007.07.012.
  5. Boscaglia NS, Gaudio LA, Ribeiro MR, editors. A low cost prototype for an optical and haptic pen. ISSNIP Biosignals and Biorobotics Conference 2011; 2011: IEEE.
  6. Scheidat T, Vielhauer C, Dittmann J, editors. Study of Possibility of On-pen Matching for Biometric Handwriting Verification. Signal Processing Conference, 2007 15th European; 2007: IEEE.
  7. Seeliger I, Schwanecke U, Barth P, editors. An optical pen tracking system as alternative pointing device. IFIP Conference on Human-Computer Interaction: Springer; 2009.
  8. Razzak MI, Anwar F, Husain SA, Belaid A, Sher M. HMM and fuzzy logic: a hybrid approach for online Urdu script-based languages’ character recognition. Knowledge-Based Systems. 2010;23:914-23. doi.org/10.1016/j.knosys.2010.06.007.
  9. Suliman A, Shakil A, Sulaiman MN, Othman M, Wirza R, editors. Hybrid of HMM and Fuzzy Logic for handwritten character recognition. 2008 International Symposium on Information Technology; 2008: IEEE.
  10. Bhattacharya U, Das TK, Datta A, Parui SK, Chaudhuri BB. A hybrid scheme for handprinted numeral recognition based on a self-organizing network and MLP classifiers. International journal of pattern recognition and artificial intelligence. 2002;16:845-64. doi.org/10.1142/S0218001402002027.
  11. Du W, Dyson N. The role of RBF in the introduction of G1 regulation during Drosophila embryogenesis. EMBO J. 1999;18:916-25. doi.org/10.1093/emboj/18.4.916. PubMed PMID: 10022834. PubMed PMCID: 1171184.
  12. Bottou L, Cortes C, Denker JS, Drucker H, Guyon I, Jackel LD, et al., editors. Comparison of classifier methods: a case study in handwritten digit recognition. International conference on pattern recognition; 1994: IEEE Computer Society Press.
  13. Leslie C, Eskin E, Noble WS. The spectrum kernel: a string kernel for SVM protein classification. Pac Symp Biocomput. 2002:564-75. PubMed PMID: 11928508.
  14. Rezaei M, Boostani R, editors. Fuzzy rule weights optimization based on Imperialist Competitive Algorithm. Intelligent Systems (ICIS), 2014 Iranian Conference on; 2014: IEEE.
  15. Herrera F. Genetic fuzzy systems: taxonomy, current research trends and prospects. Evolutionary Intelligence. 2008;1:27-46. doi.org/10.1007/s12065-007-0001-5.
  16. Lang KJ, Waibel AH, Hinton GE. A time-delay neural network architecture for isolated word recognition. Neural networks. 1990;3:23-43. doi.org/10.1016/0893-6080(90)90044-L.
  17. Sejnowski TJ, Rosenberg CR. Parallel networks that learn to pronounce English text. Complex systems. 1987;1:145-68.
  18. Goodman WK, Price LH, Rasmussen SA, Mazure C, Fleischmann RL, Hill CL, et al. The Yale-Brown obsessive compulsive scale: I. Development, use, and reliability. Arch Gen Psychiatry. 1989;46:1006-11. doi.org/10.1001/archpsyc.1989.01810110048007. PubMed PMID: 2684084.
  19. Deacon BJ, Abramowitz JS. The Yale-Brown Obsessive Compulsive Scale: factor analysis, construct validity, and suggestions for refinement. J Anxiety Disord. 2005;19:573-85. doi.org/10.1016/j.janxdis.2004.04.009. PubMed PMID: 15749574.
  20. Baum LE, Petrie T, Soules G, Weiss N. A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains. The annals of mathematical statistics. 1970;41:164-71. doi.org/10.1214/aoms/1177697196.
  21. Huang Z, Chang Y, Long B, Crespo J-F, Dong A, Keerthi S, et al., editors. Iterative Viterbi A* algorithm for k-best sequential decoding. Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers-Volume 1; 2012: Association for Computational Linguistics.
  22. Taheri A, Tarihi MR, editors. Fuzzy hidden Markov models for speech recognition on based FEM Algorithm. WEC’05: The Second World Enformatika Conference; 2005.
  23. Li C, Ji H, Pei J, editors. Multilayer fuzzy HMM for online handwriting shape recognition. Signal Processing, 2004. Proceedings. ICSP’04. 2004 7th International Conference on; 2004: IEEE.
  24. Zeng J, Liu Z-Q. Type-2 fuzzy hidden Markov models and their application to speech recognition. IEEE Transactions on Fuzzy Systems. 2006;14:454-67. doi.org/10.1109/TFUZZ.2006.876366.
  25. Hassan R, Nath B, Kirley M, editors. HMM based fuzzy model for time series prediction. 2006 IEEE International Conference on Fuzzy Systems; 2006: IEEE.
  26. Hassan MR. A combination of hidden Markov model and fuzzy model for stock market forecasting. Neurocomputing. 2009;72:3439-46. doi.org/10.1016/j.neucom.2008.09.029.
  27. Thangavel K, Pethalakshmi A. Feature selection for medical database using rough system. International Journal on Artificial Intelligence and Machine Learning. 2005;6:11-7.
  28. Morgan N, Bourlard H, editors. Continuous speech recognition using multilayer perceptrons with hidden Markov models. Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on; 1990: IEEE.
  29. Buckley A, LeNir A. QN-like variable storage conjugate gradients. Mathematical programming. 1983;27:155-75. doi.org/10.1007/BF02591943.
  30. In: Mathworks. Neural Network Toolbox Documentation. Available from: https://www.mathworks.com/help/nnet/ref/nprtool.html?requestedDomain=www.mathworks.com#.