Support Vector Machines (SVMs) in classification.

Support Vector Machines (SVMs) Compulsory part of the HW: (a) Writing a technical report on Support Vector Machines (SVMs) in classification. Write a technical report on Support Vector Machines (SVMs) in classification. In this technical report, introduction of SVMs, applications of SVMs, theoretical background of SVMs, important points on implementation of SVM coding, available SVM libraries in the literature may be given. In the text, references must be given in IEEE format. References must be included in the report (Please learn how to give references in IEEE format). Similarity score of your report must be less than 20%. (b) Preparing presentation on Support Vector Machine (SVMs). Presentation of the technical report on Support Vector Machine must be prepared, Deliveries: Both the Technical report and the presentation. Optional part of the HW: Application of SVM for classification Use LIBSVM — A Library for Support Vector Machines (https://www.csie.ntu.edu.tw/~cjlin/libsvm/) in SVM classification of Camarg data which has already given in HW8. Data must be normalized between 0 and 1. Normalization must be performed based on min and max values of training data. In the application use SVM Type “C-SVM” and use “linear SVM” and “Radial Basis Function (RBF-SVM) SVM” as Kernel Types. You should use proper version of the Matlab executables (MEX) which are in Windows folder of LIBSVM toolbox. The older version of the LIBSVM can be found in https://www.csie.ntu.edu.tw/~cjlin/libsvm/oldfiles/ For instance if your Matlab version is 2014 then you can use MEX files given in windows folder of libsvm-3.20.zip, If your Matlab version is 2019 then you can use current version of LIBSVM which is libsvm-3.24.zip. Deliveries: Matlab code and a brief report on Overall accuracy, average accuracy, Confusion Matrix and kappa statistics for training and testing data. Classification map is also generated.