Penerapan CNN Pada Klasifikasi Kepribadian Anak Sekolah Dasar Berdasarkan Citra Tulisan Tangan
Abstract
Indonesia has a rich culture. This creates dynamics in personality formation. In schools, teachers' understanding of students' personalities is key. So far, conventional methods such as observation, interviews and graphology have been used to classify children's personalities, which are less efficient. This study uses the CNN algorithm with the Mobilenetv2 architecture. Dataset was taken from 5th grade students from 3 SDN Palembang with a total of 246 data divided into 2 classes, namely extrovert 101 data and introvert 145 data. Then grayscale preprocessing, normalization, and augmentation. Ratio of training, validation, and test data is 80:10:10. Model was trained with Adam optimizer, learning rate 0.0001, batch size 20, and epochs of 12. The result is a model accuracy of 69.2% with a tendency for the model to classify images as introverts. This study is expected to help teachers gain insight into the best teaching approach in the classroom.
Keywords: CNN; Graphology; Elementary School
Abstrak
Indonesia memiliki budaya yang kaya. Ini menciptakan dinamika dalam pembentukan kepribadian. Di sekolah, pemahaman guru terhadap kepribadian siswa menjadi kunci. Selama ini untuk mengklasifikasi kepribadian anak, digunakan metode konvensional seperti observasi, wawancara dan ilmu grafologi yang kurang efisien. Penelitian ini menggunakan algoritma CNN dengan arsitektur Mobilenetv2. Dataset diambil dari siswa kelas 5 dari 3 SDN Palembang dengan total 246 data yang dibagi menjadi 2 kelas, yaitu extrovert 101 data dan introvert 145 data. Kemudian dilakukan preprocessing grayscale, normalisasi, dan augmentasi. Rasio data latih, validasi, dan uji adalah 80:10:10. Model dilatih dengan Adam optimizer, learning rate 0,0001, batch size 20, dan epoch sebanyak 12. Hasilnya akurasi model sebesar 69,2% dengan kecenderungan model mengklasifikasi citra sebagai introvert. Penelitian ini diharapkan dapat membantu guru mendapatkan pandangan tentang cara pendekatan mengajar yang terbaik di kelas.
Kata kunci: CNN; Grafologi; Sekolah Dasar
References
Direktorat Statistik Kependudukan dan Ketenagakerjaan, Profil Suku Dan Keragaman Bahasa Daerah Hasil Long Form Sensus Penduduk 2020, 1st ed. Jakarta: Badan Pusat Statistik, 2024.
E. Kurniawan Zebua, N. Waruwu, and M. Santosa, “Pengaruh Nilai-Nilai Kebudayaan terhadap Pembentukan Kepribadian Manusia: Tinjauan Psikologi Perkembangan,” Scientificum Journal, vol. 1, no. 3, pp. 138–149, 2024, doi: 10.37985/sj.v1i3.11.
Meriyati, Memahami Karakteristik Anak Didik, 1st ed. Lampung: Fakta Press, 2015.
M. Astuti et al., “Peran Guru dan Pemahaman Psikologi Anak dalam Pembelajaran,” Jurnal Visionary, vol. 12, no. 1, pp. 49–57, 2024, [Online]. Available: https://e-journal.undikma.ac.id/index.php/visionary
G. Sutrisna and G. S. Artajaya, “Problematika Kompetensi Kepribadian Guru Yang Memengaruhi Karakter Peserta Didik,” Stilistika, vol. 11, no. 1, pp. 1–14, 2022, doi: 10.5281/zenodo.7416908.
L. Ilham, “Dampak Pola Asuh Otoriter Terhadap Pekembangan Anak,” Islamic EduKids, vol. 4, no. 2, pp. 63–73, 2022.
T. F. A. Fauzian and R. Rachman, “Implementasi Metode Support Vector Machine Dalam Mendeteksi Kepribadian Melalui Tulisan Tangan,” JURNAL RESPONSIF, vol. 4, no. 2, pp. 196–203, 2022, [Online]. Available: https://ejurnal.ars.ac.id/index.php/jti
H. Hasanah, “TEKNIK-TEKNIK OBSERVASI (Sebuah Alternatif Metode Pengumpulan Data Kualitatif Ilmu-ilmu Sosial),” Jurnal at-Taqaddum, vol. 8, no. 1, pp. 21–46, 2016.
T. Zhang, “The Impact of Observers on People’s Behavior,” Lecture Notes in Education Psychology and Public Media, vol. 50, no. 1, pp. 243–248, Apr. 2024, doi: 10.54254/2753-7048/50/20240957.
M. Fadhilla, M. Ro’is, A. Saf, D. Syarif, and S. Sahid, “Pengenalan Kepribadian Seseorang Berdasarkan Pola Tulisan Tangan Menggunakan Jaringan Saraf Tiruan,” JNTETI, vol. 6, no. 3, pp. 365–373, 2017.
A. G. Purwanto, R. Y. Wijaya, T. Timotius, I. J. Agustian, and I. B. Trisno, “Analisis dan Desain Intelligent Agent Menentukan Kepribadian Berdasarkan Tulisan Tangan,” Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI), vol. 5, no. 2, pp. 243–247, Apr. 2022, doi: 10.32672/jnkti.v5i2.4176.
Y. V. Guntara, Syamsuryadi, and Sukemi, “Pengenalan Kepribadian Melalui Tulisan Tangan Menggunakan Convulutional Neural Network Dengan LS Classifiers,” Digital Zone: Jurnal Teknologi Informasi dan Komunikasi, vol. 14, no. 2, pp. 151–167, Nov. 2023, doi: 10.31849/digitalzone.v14i2.15193.
G. Chaubey and S. K. Arjaria, Personality Prediction Through Handwriting Analysis Using Convolutional Neural Networks, 1st ed. Singapore: Springer Nature, 2022. doi: 10.1007/978-981-16-3802-2_5.
H. A. Abdo, A. Abdu, R. R. Manza, and S. Bawiskar, “ArabicWordNet: fine-tuning MobileNetV2-based model for Arabic handwritten words recognition,” IRJET, vol. 10, no. 12, pp. 337–345, 2023, [Online]. Available: www.irjet.net
G. S. Nugraha, M. I. Darmawan, and R. Dwiyansaputra, “Comparison of CNN’s Architecture GoogleNet, AlexNet, VGG-16, Lenet -5, Resnet-50 in Arabic Handwriting Pattern Recognition,” Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, vol. 8, no. 2, pp. 545–554, May 2023, doi: 10.22219/kinetik.v8i2.1667.
N. Aneja and S. Aneja, “Transfer Learning using CNN for Handwritten Devanagari Character Recognition,” in 2019 1st International Conference on Advances in Information Technology (ICAIT), Chikmagalur: IEEE, 2019, pp. 293–296. doi: 10.1109/ICAIT47043.2019.8987286.
S. Agduk and E. Aydemir, “Classification of Handwritten Text Signatures by Person and Gender: A Comparative Study of Transfer Learning Methods,” Acta Informatica Pragensia, vol. 11, no. 3, pp. 324–347, 2022, doi: 10.18267/j.aip.197.
M. Arsal, B. Agus Wardijono, and D. Anggraini, “Face Recognition Untuk Akses Pegawai Bank Menggunakan Deep Learning Dengan Metode CNN,” Jurnal Nasional Teknologi dan Sistem Informasi, vol. 6, no. 1, pp. 55–63, Jun. 2020, doi: 10.25077/teknosi.v6i1.2020.55-63.
N. Kasim and G. Satya Nugraha, “Pengenalan Pola Tulisan Tangan Aksara Arab Menggunakan Metode Convolution Neural Network (Handwritten Arabic Script Recognition Using Convolution Neural Network ),” JTIKA, vol. 3, no. 1, pp. 85–95, 2021, doi: https://doi.org/10.29303/jtika.v3i1.136.
K. R. R. Wardani and L. Leonardi, “Klasifikasi Penyakit pada Daun Anggur menggunakan Metode Convolutional Neural Network,” Jurnal Tekno Insentif, vol. 17, no. 2, pp. 112–126, Oct. 2023, doi: 10.36787/jti.v17i2.1130.
J. A. AYENI, “Convolutional Neural Network (CNN): The architecture and applications,” Applied Journal of Physical Science, vol. 4, no. 4, pp. 42–50, Dec. 2022, doi: 10.31248/AJPS2022.085.
M. Krichen, “Convolutional Neural Networks: A Survey,” Computers, vol. 12, no. 8, pp. 1–41, Jul. 2023, doi: 10.3390/computers12080151.
X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, and M. Parmar, “A review of convolutional neural networks in computer vision,” Artif Intell Rev, vol. 57, no. 4, p. 99, Mar. 2024, doi: 10.1007/s10462-024-10721-6.
How To Cite This :
Refbacks
- There are currently no refbacks.
