COMPARISON OF THE CLASSIFICATION PERFORMANCES OF CRIMINAL TENDENCIES OF SCHIZOPHRENIC PATIENTS BY ARTIFICIAL NEURAL NETWORKS AND SUPPORT VECTOR MACHINE

Abstract

 In this study, a new approach based on Artificial Neural Networks (ANN) and Support Vector Machine (SVM) classifiers has been proposed in the determination of criminal tendency with biochemical data of schizophrenia patients. Classification was performed using the biochemical data of the offender and control group schizophrenic patients. The data were obtained from 100 schizophrenic inpatients in Elazığ mental and Neurological Disorders Hospital. The biochemical data used for the examination and classification of the criminal tendencies of schizophrenic patients were Triglycerides, Total Cholesterol, High Density Lipoproteins (HDL), Low Density Lipoproteins (LDL), Very Low Density Lipoproteins (VLDL), Sex Hormone Binding Globulin (SHBG), Oestradiol, Free Testosterone, Total Testosterone, Ghrelin, Copper (Cu) and Zinc (Zn). Biochemical data were classified using ANN and SVM.  All data were normalized to before classification. In addition, classifier results were evaluated using cross-validation method. As a result of the classification performed, 87% accuracy and 89% accuracy were achieved by ANN and SVM, respectively. In the determination of the criminal tendencies of schizophrenic patients using their biochemical data, SVM classifier performed a more effective classification compared to ANN classifier. According to classification results, it was seen that the biochemical data used could be useful features in the determination of the criminal tendencies of schizophrenic patients.

Keywords

• Schizophrenia,Artificial neural network,Support vector machine,Classification,Criminal tendency

References

1. A. Türkoğlu, “Suç İşlemiş ve İşlememiş Şizofrenik Hastalarda Bazı Biyokimyasal Parametrelerin Karşılaştırılması,” Fırat Üniversitesi, Tıp Fakültesi Adli Tıp Anabilim Dalı, Uzmanlık Tezi, Elazığ, 2008.
2. E. Köroğlu and C. Güleç, Psikiyatri Temel Kitabı. Ankara: Hekimler Yayın Birliği, 1997.
3. E. Belene, “Şizofreni’de Anksiyete Belirtilerinin, Pozitif, Negatif ve Depresif Belirtiler, İntihar Düşüncesi, İçgörü ve Yaşam Kalitesi Açısından İncelenmesi,” Sağlık Bakanlığı, Bakırköy Ord. Prof. Mazhar Osman Ruh Sağlığı ve Sinir Hastalıkları Eğitim Ve Araştırma Hastanesi, 2009.
4. İ. Akdaş, “Şizofreni, Bipolar Affektif Bozukluk ve Anksiyete Tanısı Almış Hastalarda Toxoplasma Gondii Prevalansının Serolojik ve Moleküler Yöntemlerle Araştırılması,” Eskişehir Osmangazi Üniversitesi, Sağlık Bilimleri Enstitüsü, Yüksek Lisans Tezi, Eskişehir, 2013.
5. A. Türkoğlu, M. Tokdemir, M. Atmaca, N. Mustafa, and B. Üstündağ, “Serum Cholesterol, Triglyceride, and Ghrelin Levels in Criminal and Non-criminal Schizophrenia Patients,” Bull. Clin. Psychopharmacol., vol. 19, no. 4, pp. 353–358, 2009.
6. Ö. O. Dursun, S. Toraman, and A. Türkoğlu, “Determination Of The Crime Status Of Schizophrenia Patients With Sequential Backward Selection Algorithm,” in International Conference on Natural Science and Engineering (ICNASE’16), 2016, pp. 2347–2353.
7. S. K. Bose, F. E. Turkheimer, O. D. Howes, M. A. Mehta, R. Cunliffe, P. R. Stokes, and P. M. Grasby, “Classification of schizophrenic patients and healthy controls using [18F] fluorodopa PET imaging,” Schizophr. Res., vol. 106, no. 2–3, pp. 148–155, 2008.
8. R. C. W. Mandl, R. M. Brouwer, W. Cahn, R. S. Kahn, and H. E. Hulshoff Pol, “Family-wise automatic classification in schizophrenia,” Schizophr. Res., vol. 149, no. 1–3, pp. 108–111, 2013.

9. M. Shim, H. J. Hwang, D. W. Kim, S. H. Lee, and C. H. Im, “Machine-learning-based diagnosis of schizophrenia using combined sensor-level and source-level EEG features,” Schizophr. Res., vol. 176, no. 2–3, pp. 314–319, 2016.
10. L. Squarcina, C. Perlini, D. Peruzzo, U. Castellani, V. Marinelli, M. Bellani, G. Rambaldelli, A. Lasalvia, S. Tosato, K. De Santi, F. Spagnolli, R. Cerini, M. Ruggeri, P. Brambilla, and P.-V. Group, “The use of dynamic susceptibility contrast (DSC) MRI to automatically classify patients with first episode psychosis,” Schizophr. Res., vol. 165, no. 1, pp. 38–44, 2015.
11. M. Takahashi, H. Hayashi, Y. Watanabe, K. Sawamura, N. Fukui, J. Watanabe, T. Kitajima, Y. Yamanouchi, N. Iwata, K. Mizukami, T. Hori, K. Shimoda, H. Ujike, N. Ozaki, K. Iijima, K. Takemura, H. Aoshima, and T. Someya, “Diagnostic classification of schizophrenia by neural network analysis of blood-based gene expression signatures,” Schizophr. Res., vol. 119, no. 1–3, pp. 210–218, 2010.
12. C. G. Cheng, Y. M. Tian, and W. Y. Jin, “A study on the early detection of colon cancer using the methods of wavelet feature extraction and SVM classifications of FTIR,” Spectroscopy, vol. 22, no. 5, pp. 397–404, 2008.
13. S. Ayhan and Şenol Erdoğmuş, “Destek Vektör Makineleriyle Sınıflandırma Problemlerinin Çözümü İçin Çekirdek Fonksiyonu Seçimi,” Eskişehir Osmangazi Üniversitesi İİBF Derg., vol. 9, no. 1, pp. 175–198, 2014.
14. S. Osowski, K. Siwek, and T. Markiewicz, “MLP and SVM networks–a comparative study,” Proc. 6th Nord. Signal Process. Symp., vol. 2004, no. 2, pp. 37–40, 2004.
15. A. T. Özdemir, “Erken Ventriküler Kasılmalarda YSA Tabanlı Bir Sınıflandırıcının Fpga ile Gerçekleştirilmesi,” Erciyes Üniversitesi, Fen Bilimleri Enstitüsü, Doktora Tezi, 2010.
16. C. Öztürk, “Yapay Sinir Ağlarının Yapay Arı Kolonisi Algoritması ile Eğitilmesi,” Erciyes Üniversitesi, Fen Bilimleri Enstitüsü, Doktora Tezi, Kayseri, 2011.
17. A. Şengür, “Endoskopik Görüntülerin Değerlendirilmesinde Görüntü İşleme Temelli Akıllı Karar Destek Sistemi,” Fırat Üniversitesi, Fen Bilimleri Enstitüsü, Doktora Tezi, 2006.
18. A. Khazaee and A. Ebrahimzadeh, “Classification of electrocardiogram signals with support vector machines and genetic algorithms using power spectral features,” Biomed. Signal Process. Control, vol. 5, no. 4, pp. 252–263, 2010.
19. T. Kavzoğlu and İ. Çölkesen, “Destek Vektör Makineleri ile Uydu Görüntülerinin Sınıflandırılmasında Kernel Fonksiyonlarının Etkilerinin İncelenmesi,” Harit. Derg., vol. 144, pp. 73–82, 2010.
20. S. Patidar and T. Panigrahi, “Detection of epileptic seizure using Kraskov entropy applied on tunable-Q wavelet transform of EEG signals,” Biomed. Signal Process. Control, vol. 34, pp. 74–80, 2017.
21. E. Osuna, R. Freund, and F. Girosi, “Support Vector Machines : Training and Applications,” Massachusetts Inst. Technol., vol. 9217041, no. 1602, 1997.
22. A. Akbari and M. K. Arjmandi, “An efficient voice pathology classification scheme based on applying multi-layer linear discriminant analysis to wavelet packet-based features,” Biomed. Signal Process. Control, vol. 10, no. 1, pp. 209–223, 2014.
23. A. Akbari and M. K. Arjmandi, “Employing linear prediction residual signal of wavelet sub-bands in automatic detection of laryngeal pathology,” Biomed. Signal Process. Control, vol. 18, pp. 293–302, 2015.