Abstract
Now-a-days Skin disease is very common worldwide problem. We have preset this study for the prediction of skin disease. Based on data from UCI data set, there are 34 attributes which plays a vital role in the skin disease diagnosis but all are not important. In this paper we have analyzed only those important attributes which give best accuracy in prediction of skin disease. To select important attributes, we have applied a new hybrid approach using three feature extraction techniques Chi Square, Information Gain and Principle Component Analysis (PCA) and then combining them to select the best possible data subset of skin disease data set. Six base learners Gaussian Naïve Bayesian (NB), K-Nearest Neighbour (KNN), Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF) and Multilayer Perceptron (MLP) are used to evaluate the prediction performance of base learners. Boosting, Bagging and Stacking ensemble techniques are applied on base learners to enhance the results of the proposed model. In this paper, a new proposed method of hybrid feature selection technique is used for evaluating the performance of base learners and we find that reduced data subset performed is higher as compared to whole data set. The metrics are necessary to evaluate the model and calculated to illustrate the performance of prediction. Hybrid feature selection technique along with base learners are then applied on Bagging, Boosting and Staking ensemble techniques to enhance the results. These results are compared with individual base learners. The result obtained in this research paper is higher than previous studies.
Similar content being viewed by others
References
Güvenir, H.A., Demiröz, G., Ilter, N.: Learning differential diagnosis of erythemato-squamous diseases using voting feature intervals. Artif. Intell. Med. 13(3), 147–165 (1998)
Barati, E., Saraee, M., Mohammadi, A., Adibi, N., Ahamadzadeh, M.R.: A survey on utilization of data mining approaches for dermatological (skin) diseases prediction. J. Sel. Areas Heal. Inf. 2(3), 1–11 (2011)
Chang, C.L., Chen, C.H.: Applying decision tree and neural network to increase quality of dermatologic diagnosis. Expert Syst. Appl. 36(2), 4035–4041 (2009)
Yadav, D.C., Pal, S.: Decision tree ensemble techniques to predict thyroid disease. Int. J. Recent Technol. Eng. 8(3), 8242–8246 (2019)
Elsayad, A.M., Dhaifallah, M.A., Nassef, A.M.: Analysis and diagnosis of erythemato-squamous diseases using CHAID decision trees. In: 2018 15th Int. Multi-Conference Syst. Signals Devices, SSD 2018, pp. 252–262 (2018)
Oladele, T.O., Olarinoye, D.R., Adebisi, S.S.: Artificial neural network(ANN). Anal. Ser. Inf. 16, 189–193 (2018)
Maghooli, K., Langarizadeh, M., Shahmoradi, L., Habibi-Koolaee, M., Jebraeily, M., Bouraghi, H.: Differential diagnosis of erythmato-squamous diseases using classification and regression tree. Acta Inform. Med. 24(5), 338–342 (2016)
Kabari, L.G., Bakpo, F.S.: Diagnosing skin diseases using an artificial neural network. ICAST 2009—2nd Int. Conf. Adapt. Sci. Technol., pp. 187–191 (2009)
Amarathunga, A.A.L.C., Ellawala, E.P.W.C., Abeysekara, G.N., Amalraj, C.R.J.: Expert system for diagnosis of skin diseases. Int. J. Sci. Technol. Res. 4(1), 174–178 (2015)
Kanaan, K.Q.: Classification of human skin diseases using data mining. Int. J. Adv. Eng. Res. Sci. 4(1), 159–163 (2017)
Zhang, X., Wang, S., Liu, J., Tao, C.: Towards improving diagnosis of skin diseases by combining deep neural network and human knowledge. BMC Med. Inform. Decis. Mak. 18(S2), 59 (2018)
Çataloluk, H., Kesler, M.: A diagnostic software tool for skin diseases with basic and weighted K-NN. INISTA 2012 Int. Symp. Innov. Intell. Syst. Appl., pp. 0–3 (2012)
Kolkur, M.S., Kalbande, D.R., Kharkar, V.: Machine learning approaches to multi-class human skin disease detection. Int. J. Comput. Intell. Res. 14(1), 29–39 (2018)
Olatunji, S.O., Arif, H.: Identification of erythemato-squamous skin diseases using extreme learning machine and artificial neural network. ICTACT J. Soft Comput. 4(1), 627–632 (2013)
Olatunji, S., Arif, H.: Identification of erythemato-squamous skin diseases using support vector machines and extreme learning machines: a comparative study towards effective diagnosis. Trans. Mach. Learn. Artif. Intell. 2, 6 (2014)
Parikh, K.S., Shah, T.P., Kota, R.K., Vora, R.: Diagnosing common skin diseases using soft computing techniques. Int. J. Bio-Sci. Bio-Technol. 7(6), 275–286 (2015)
Putatunda, S.: A hybrid deep learning approach for diagnosis of the erythemato-squamous disease. arxiv:1909.07587v1, pp. 1–13 (2019)
Ahmed, K.: Early prevention and detection of skin cancer risk using data mining. Int. J. Comput. Appl. 62(4), 1–6 (2013)
Giveki, D.: Detection of erythemato-squamous diseases using AR-CatfishBPSO-KSVM. Signal Image Process. An Int. J. 2(4), 57–72 (2012)
Güvenir, H.A., Emeksiz, N.: Expert system for the differential diagnosis of erythemato-squamous diseases. Expert Syst. Appl. 18(1), 43–49 (2000)
Sudha, M., Poorva, B.: Predictive tool for dermatology disease diagnosis using machine learning techniques. Int. J. Inno. Technol. Explor. Eng. 8(9), 355–360 (2019)
Idoko, J. B., Arslan, M., Abiyev, R.: Fuzzy neural system application to differential diagnosis of erythemato-squamous diseases. Cyprus J. Med. Sci., pp. 90–97 (2018)
Ravichandran, K.S., Narayanamurthy, B., Ganapathy, G., Ravalli, S., Sindhura, J.: An efficient approach to an automatic detection of erythemato-squamous diseases. Neural Comput. Appl. 25(1), 105–114 (2014)
Übeyli, E.D., Doǧdu, E.: Automatic detection of erythemato-squamous diseases using κ-means clustering. J. Med. Syst. 34(2), 179–184 (2010)
Sharma, D., Hota, H.: Data mining techniques for prediction of different categories of dermatology diseases. J. Manag. Inf. Decis. Sci. 16(2), 103 (2013)
Verma, A.K., Pal, S.: Prediction of skin disease with three different feature selection techniques using stacking ensemble method. Appl. Biochem. Biotechnol. (2019). https://doi.org/10.1007/s12010-019-03222-8
Verma, A.K., Pal, S., Kumar, S.: Classification of skin disease using ensemble data mining techniques. Asian Pac. J. Cancer Prev. 20(6), 1887–1894 (2019)
Aruna, S., Nandakishore, L.V., Rajagopalan, S.P.: A hybrid feature selection method based on IGSBFS and naive bayes for the diagnosis of erythemato-squamous diseases. Int. J. Comput. Appl. 41(7), 13–18 (2012)
Kamala, F.R., Thangaiah, P.R.J., Info, A.: An improved hybrid feature selection method for huge dimensional datasets. IAES Int. J. Artif. Intell. 8(1), 77–86 (2019)
Ozcift, A., Gulten, A.: A robust multi-class feature selection strategy based on rotation forest ensemble algorithm for diagnosis of erythemato-squamous diseases. J. Med. Syst. 36(2), 941–949 (2012)
Pattanshetti, T., Attar, V.: Performance evaluation and analysis of feature selection algorithms. Adv. Intell. Syst. Comput. 808, 47–60 (2019)
Xie, J., Lei, J., Xie, W., Shi, Y., Liu, X.: Two-stage hybrid feature selection algorithms for diagnosing erythemato-squamous diseases. Heal. Inf. Sci. Syst. 1(1), 1–14 (2013)
Verma, A.K., Pal, S., Kumar, S.: Prediction of skin disease using ensemble data mining techniques and feature selection method—a comparative study. Appl. Biochem. Biotechnol. (2019). https://doi.org/10.1007/s12010-019-03093-z
Badrinath, N., Gopinath, G., Ravichandran, K.S., Soundhar, R.G.: Estimation of automatic detection of erythemato-squamous diseases through AdaBoost and its hybrid classifiers. Artif. Intell. Rev. 45(4), 471–488 (2016)
Chaurasia, V., Pal, S.: Skin diseases prediction: binary classification machine learning and multi model ensemble techniques. Res. J. Pharm. Technol. 12(8), 3829–3832 (2019)
Maryam, N.A., Setiawan, Wahyunggoro, O.: A hybrid feature selection method using multiclass SVM for diagnosis of erythemato-squamous disease. AIP Conf. Proc. 1867, (2017)
Xie, J., Wang, C.: Using support vector machines with a novel hybrid feature selection method for diagnosis of erythemato-squamous diseases[1] J. Xie and C. Wang, “Using support vector machines with a novel hybrid feature selection method for diagnosis of erythemato-squamou. Expert Syst. Appl. 38(5), 5809–5815 (2011)
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Verma, A.K., Pal, S. & Tiwari, B.B. Skin disease prediction using ensemble methods and a new hybrid feature selection technique. Iran J Comput Sci 3, 207–216 (2020). https://doi.org/10.1007/s42044-020-00058-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42044-020-00058-y