TY - JOUR ID - 43249 TI - Diagnosis of OCD Patients Using Drawing Features of Bender Gestalt Shapes JO - Journal of Biomedical Physics and Engineering JA - JBPE LA - en SN - AU - Boostani, R AU - Asadi, F AU - Mohammadi, N AD - CSE & IT Dept., School of Electrical and Computer Engineering, Shiraz University, Shiraz, Iran AD - Department of Clinical Psychology, Faculty of Education and Psychology, Shiraz University, Shiraz, Iran Y1 - 2017 PY - 2017 VL - 7 IS - 1 SP - 59 EP - 68 KW - Bender Gestalt KW - Optical Pen KW - Fuzzy HMM KW - OCD KW - Psychology DO - N2 - 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. UR - https://jbpe.sums.ac.ir/article_43249.html L1 - https://jbpe.sums.ac.ir/article_43249_b6b95a347dd937a93fc4a1c991ba249f.pdf ER -