Selection of Specialization Class Using Support Vector Machine Method in SMA Negeri 1 Ambon CAUCHY –Jurnal Matematika Murni dan Aplikasi Volume 6(4) (2021), Pages 162-168 p-ISSN: 2086-0382; e-ISSN: 2477-3344 Submitted: February 26, 2020 Reviewed: November 10, 2020 Accepted: March 25, 2021 DOI: http://dx.doi.org/10.18860/ca.v6i4.8882 Selection of Specialization Class Using Support Vector Machine Method in SMA Negeri 1 Ambon Stevanny Tamaela1, Yopi Andry Lesnussa2, Venn Yan Ishak Ilwaru3 1Mathematics Department, Pattimura University Email: annytamaela@gmail.com, yopi_a_lesnussa@yahoo.com, vennilwaru007@gmail.com ABSTRACT The curriculum is a system or education plan that is made by a government to form the abilities and character of children based on a standard, one of its forms is the division of specialization classes at the senior high school level. The 2013 curriculum emphasizes that all students in Indonesia can practice their abilities based on their interests and talents, therefore students no longer choose majors but choose abilities (interests) they specialize in. This research uses the Support Vector Machine (SVM) method in the Decision Making System (DMS) of specialization classes at SMA Negeri 1 Ambon. Using the factors driving student acceptance and selection as input data, the SVM method is processed with MATLAB Software and produces a classification of interest class with an accuracy rate of 100%. Keywords: 2013 Curriculum; Classification; Support Vector Machine INTRODUCTION The curriculum is a plan about forming the abilities and character of children based on a standard [1], The 2013 curriculum is a curriculum that simplification [2] and thematic-integrative, adding rainy learning hours to encourage students or students, one of the forms is the division of specialization classes at the High School level (SMA)[3]. Specialization aims to provide opportunities for students to develop their interests in a group of subjects by their scientific interests in tertiary institutions [4] and developing their interest in a particular discipline or skill [5]. Decision Making System is the process of choosing between two or more alternative actions to achieve goals or objectives. Several studies have concluded that there are various decision-making methods can determine reliable results. In this case, the method to be applied is the Support Vector Machine (SVM) algorithm, the SVM method is a technique for making predictions, both in the case of classification and regression [6][7][8]. SVM was introduced by Boser, Guyon, Vanpik, dan first presented in 1992 [9][10] at the Annual Workshop on Computational Learning Theory. The basic concept of SVM is a harmonization of computation theories that have existed tens of years before, such as the Hyperplane margin introduced by Aronszajn in 1950 [11]. However, until 1992 there had never been an effort to assemble these components. The basic principle of SVM is linear classifier [12], and further developed to be able to work on non-linear problems by incorporating the concept of kernel tricks in high- http://dx.doi.org/10.18860/ca.v6i4.8882 mailto:annytamaela@gmail.com mailto:yopi_a_lesnussa@yahoo.com mailto:vennilwaru007@gmail.com Selection of Specialization Class Using Support Vector Machine Method in SMA Negeri 1 Ambon Stevanny Tamaela 163 dimensional space [13]. SVM is a classification method with a relatively fast computative time and several studies have shown that SVM is superior in classifying. In Addition, There is a research about the classification of acoustic events using SVM-based clustering schemes. Several Classifiers Based On Support Vector Machines (SVM) Are Developed Using Confusion Matrix Based Clustering Schemes To Deal With The Multi- Class Problem [14][15]. The main purpose of SVM is to increase the speed of training and testing, meaning that SVM can be used for large data [16]. Support Vector Machine (SVM) is used along with continuous wavelet transform (CWT), an advanced signal- processing tool, to analyze the frame vibrations during start-up [17]. METHODS This type of research is a case study. Namely, the SVM method determines the choice of interest in tenth-grade students. The material used in this study is secondary data obtained from the Sekolah Menengah Atas (SMA) Negeri 1 Ambon. Secondary data taken from SMA Negeri 1 Ambon is in the form of a value criterion as a measure of interest selection include the initial test scores in SMA 1 or a comparison score to determine the choice of interest in tenth-grade students. In detail, the flowchart diagram of the Support Vector Machine (SVM) can be seen in the following Figure 1: Figure 1. Flowchart Diagram of Support Vector Machine (SVM) This research uses the linear SVM method with MATLAB software to analyze data. The Ratio of training and testing data used is 7:3 from each grouping that has been determined. START Grouping Data Dividing Data for Training and for Testing Classification SVM Score > 0 Science Major Classification Results No FINISH Social Major Yes Selection of Specialization Class Using Support Vector Machine Method in SMA Negeri 1 Ambon Stevanny Tamaela 164 For this research method the variables used for data are the National Exam Score (𝑋1), Initial Test Score (𝑋2), Psychology Score (𝑋3). While the target or output is Major/ Interest (𝑌). Data obtained as follows: Table 1. SVM Method Data NO NATIONAL EXAM SCORE (REC) INITIAL TEST SCORE PSYCHOLOGY SCORE FINAL SCORE MAJOR/ INTEREST 1 82 35 106.7 74.57 SCIENCE 2 80.2 34 86.2 66.8 SOCIAL 3 80 34 100 71.33 SCIENCE 4 81.5 34 94.4 69.97 SOCIAL 5 80 34 93.9 69.30 SOCIAL 6 85.5 33 111.8 76.77 SCIENCE 7 84.5 33 111.9 76.47 SCIENCE 8 80 33 86.1 66.37 SOCIAL 9 81.5 33 109.6 74.70 SCIENCE 10 80.8 32 106.3 73.03 SCIENCE 11 80 32 97 69.67 SOCIAL 12 83 32 106.7 73.90 SCIENCE 13 82.5 32 92.6 69.03 SOCIAL 14 81.9 31 107.7 73.53 SCIENCE 15 80.5 31 92.6 68.03 SOCIAL 16 80 31 98.7 69.90 SOCIAL 17 81.5 31 83.3 65.27 SOCIAL 18 80 31 91.3 67.43 SOCIAL 19 85.5 30 90.6 68.70 SOCIAL 20 84.5 30 101.3 71.93 SCIENCE 21 80 30 89.7 66.57 SOCIAL 22 80 30 93.6 67.87 SOCIAL 23 83 30 88.3 67.10 SOCIAL 24 82.5 30 111.4 74.63 SCIENCE 25 81.9 30 97.7 69.87 SOCIAL 26 80.5 30 109.6 73.37 SCIENCE 27 80 30 104.5 71.50 SCIENCE 28 81.5 30 100 70.50 SCIENCE 29 83 30 91.1 68.03 SOCIAL 30 82.5 30 103.9 72.13 SCIENCE 31 81.9 30 100 70.63 SCIENCE 32 80.5 28 104.2 70.90 SCIENCE 33 83.9 28 106 72.63 SCIENCE 34 84 28 92.9 68.30 SOCIAL 35 80.5 28 87.7 65.40 SOCIAL 36 80.4 28 86.9 65.10 SOCIAL 37 81.3 28 111.9 73.73 SCIENCE Selection of Specialization Class Using Support Vector Machine Method in SMA Negeri 1 Ambon Stevanny Tamaela 165 NO NATIONAL EXAM SCORE (REC) INITIAL TEST SCORE PSYCHOLOGY SCORE FINAL SCORE MAJOR/ INTEREST 38 81.9 28 92.5 67.47 SOCIAL 39 81 28 86.8 65.27 SOCIAL 40 80.2 28 105 71.07 SCIENCE 41 82 27 109.9 72.97 SCIENCE 42 83.6 27 110.5 73.70 SCIENCE 43 80 27 93.8 66.93 SOCIAL 44 82.5 27 94.9 68.13 SOCIAL 45 81.6 27 91.3 66.63 SOCIAL 46 85 27 106.6 72.87 SCIENCE 47 82.9 27 106 71.97 SCIENCE 48 83.5 27 94.7 68.40 SOCIAL 49 80 27 93.3 66.77 SOCIAL 50 80 27 111.1 72.70 SCIENCE The amount of data in this study amounted to 50 data that will be divided into data testing and training. The target data of the Department is divided into 3 groups with the following conditions: Science Major for y > 80 with the very smart requirement Neutral Major for 70 ≤ y ≤ 80 with the average requirement Social Major for y < 70 Hint: y = Major RESULTS AND DISCUSSION SVM linear search for hyperplane with the largest margin, known as Maximum Marginal Hyperplane (MMH). Based on the Lagrangian formulation mentioned, MMH can be rewritten as a boundary decision: 𝑑(𝑋𝑇) = ∑ 𝑦𝑖𝛼𝑖𝑋𝑖𝑋 𝑇 + 𝑏0 𝑙 𝑖=1 (1) Where 𝑦𝑖 is the label of support vector classes 𝑋𝑖. 𝑋 𝑇 is the tuple; 𝛼𝑖 and 𝑏0 are the numerical parameter determined automatically by the SVM optimization algorithm, and l is the number of Support Vector. The results of the program for the grouping of testing data are as follows: Table 2. Software Processing Results for Testing Data No Original Data svmStruct1 svmStruct2 svmStruct3 Software Results 1 0 0 0 0 0 2 0 1 0 0 0 3 0 1 0 0 0 4 0 0 0 0 0 5 0 0 0 0 0 6 0 0 0 0 0 7 0 0 0 0 0 8 0 1 0 0 0 Selection of Specialization Class Using Support Vector Machine Method in SMA Negeri 1 Ambon Stevanny Tamaela 166 No Original Data svmStruct1 svmStruct2 svmStruct3 Software Results 9 1 1 1 1 1 10 1 1 1 1 1 11 1 1 1 1 1 12 1 1 1 1 1 13 1 0 1 1 1 14 1 1 1 1 1 15 1 0 1 1 1 16 1 1 1 1 1 From Table 2 above it can be seen, the SVM method classification shows the output with 99% accuracy for testing data. This can be seen from the comparison between the target data and the output target. With Hyperplane obtained from each class as follows: Figure 2. Hyperplane for svmStruct1 Based on Figure 2 above it can be explained that the svmStruct1 data shows that the data in the two classes are not completely separate can be seen from several red circles whose distribution is around the green circle area. Figure 3. Hyperplane for svmStruct2 Selection of Specialization Class Using Support Vector Machine Method in SMA Negeri 1 Ambon Stevanny Tamaela 167 Based on Figure 3 above it can be explained that the data in svmStruct2 is properly classified in class 0 (which is the science major group) or class 1 (which is the social major group) while those that are Support Vector are patterns within a circle. Figure 4. Hyperplane for svmStruct3 Based on Figure 4 above it can be explained that all svmStruct3 data is properly classified into class 0 (which is the science major) or class 1 (which is the social major), while those that are Support Vector are patterns within a circle. CONCLUSIONS From the results of the software output that is matched with the real data, it is seen that 100% of the output data is the same as the real data. This shows for the SVM method of class division of interests carried out by the school according to the ability of children. Based on the results of research with the SVM method there is no difference between the results of the assessment using software and real data. In other words the results of the SVM method are said to be perfect. REFERENCES [1] M. Lestari, “Implementation of Citizenship Character Formation by the Study of Civic Education on Senior High School in The District of Bantul,” E-CIVICS, 2016. [2] Suyatmini, “Implementasi Kurikulum 2013 pada Pelaksanaan Pembelajaran Akuntansi di Sekolah Menengah Kejuruan,” J. Pendidik. Ilmu Sos., 2017. [3] Subandi, “Pengembangan Kurikulum 2013,” J. Pendidik. dan Pembelajaran Dasar, 2014. [4] B. L. Julien, L. Lexis, J. Schuijers, T. Samiric, and S. McDonald, “Using capstones to develop research skills and graduate capabilities: A case study from physiology,” J. Univ. Teach. Learn. Pract., 2012. [5] Direktorat Pembinaan SMA, Modul Pelatihan Implementasi Kurikulum 2013 SMA Tahun 2018. 2018. [6] A. S. Nugroho, A. B. Witarto, and D. Handoko, “Application of Support Vector Machine in Bioinformatics,” 2003. [7] A. M. Puspitasari, D. E. Ratnawati, and A. W. Widodo, “Klasifikasi Penyakit Gigi Dan Mulut Menggunakan Metode Support Vector Machine,” J. Pengemb. Teknol. Inf. dan Selection of Specialization Class Using Support Vector Machine Method in SMA Negeri 1 Ambon Stevanny Tamaela 168 Ilmu Komput., vol. 2, no. 2, pp. 802–810, 2018. [8] P. A. Octaviani, Yuciana Wilandari, and D. Ispriyanti, “Penerapan Metode Klasifikasi Support Vector Machine (SVM) pada Data Akreditasi Sekolah Dasar (SD) di Kabupaten Magelang,” J. Gaussian, vol. 3, no. 8, pp. 811–820, 2014, [Online]. Available:http://download.portalgaruda.org/article.php?article=286497&val=47 06&title=Penerapan Metode Klasifikasi Support Vector Machine (Svm) Pada Data Akreditasi Sekolah Dasar (Sd) Di Kabupaten Magelang. [9] Y. Lin, H. Tseng, and C. Fuh, “Using Support Vector Machine,” Image Process., 2003. [10] M. Ichwan, I. A. Dewi, and Z. M. S, “Klasifikasi Support Vector Machine (SVM) Untuk Menentukan TingkatKemanisan Mangga Berdasarkan Fitur Warna,” MIND J., vol. 3, no. 2, pp. 16–23, 2019, doi: 10.26760/mindjournal.v3i2.16-23. [11] Y. Wang, J. Wong, and A. Miner, “Anomaly intrusion detection using one class SVM,” 2004, doi: 10.1109/iaw.2004.1437839. [12] M. A. Oskoei and H. Hu, “Support vector machine-based classification scheme for myoelectric control applied to upper limb,” IEEE Trans. Biomed. Eng., 2008, doi: 10.1109/TBME.2008.919734. [13] S. Vijayakumar and S. Wu, “Sequential Support Vector Classifiers and Regression,” 1999. [14] S. Aprilia, M. T. Furqon, and M. A. Fauzi, “Klasifikasi Penyakit Skizofrenia dan Episode Depresi pada Gangguan Kejiwaan dengan Menggunakan Metode Support Vector Machine (SVM),” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 2, no. 11, pp. 5611–5618, 2018. [15] A. Temko and C. Nadeu, “Classification of acoustic events using SVM-based clustering schemes,” Pattern Recognit., vol. 39, no. 4, pp. 682–694, 2006, doi: 10.1016/j.patcog.2005.11.005. [16] H. Amalia, A. F. Lestari, and A. Puspita, “Penerapan Metode SVM Berbasis PSO Untuk Penentuan Kebangkrutan Perusahaan,” None, 2017. [17] P. Dhanalakshmi, S. Palanivel, and V. Ramalingam, “Classification of audio signals using SVM and RBFNN,” Expert Syst. Appl., vol. 36, no. 3 PART 2, pp. 6069–6075, 2009, doi: 10.1016/j.eswa.2008.06.126.