Klasifikasi Label Gambar Soal Matematika Menggunakan Convolutional Neural Network

Azhar, Fadhli (2023) Klasifikasi Label Gambar Soal Matematika Menggunakan Convolutional Neural Network. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 06211640000049-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (1MB) | Request a copy

Abstract

Pemahaman learner-centered merupakan pemahaman yang mendorong pelajar untuk berkontribusi secara aktif pada proses pembelajaran. Proses belajar aktif terdistribusi merupakan salah satu Teknik yang dapat diterapkan pada pemahaman learner-centered. Infrastruktur dalam menerapkan proses belajar aktif terdistribusi dibutuhkan agar memudahkan pelajar dalam melaksanakan proses belajar aktif terdistribusi seperti sistem rekomendasi. Sistem rekomendasi yang dapat dibuat untuk membantu pengalaman belajar pelajar lebih menarik antara lain pengenal soal, rekomendasi materi belajar dan sebagainya. Sistem rekomendasi seperti pengenal soal dapat dibuat dengan bantuan model deep learning seperti Convolutional Neural Network. Model convolutional neural network mampu mempelajari pola yang ada pada label soal matematika. Model terbaik yang didapatkan pada hasil penerapan convolutional neural network adalah model convolutional neural network dengan 2 convolutional kernel dan 3 convolutional layer. Model tersebut mamput mendapatkan nilai kebaikan klasifikasi sebesar 0,9453 pada data training dan 0,9375 pada data testing.
=================================================================================================================================
Learner-centered understanding is an understanding that encourages students to actively contribute to the learning process. Distributed active learning is a technique that can be applied to learner-centered understanding. Infrastructure in implementing a distributed active learning process is needed to make it easier for students to carry out a distributed active learning process such as a recommendation system. Recommendation systems that can be made to help students' learning experiences be more interesting include question identifiers, study material recommendations and so on. Recommendation systems such as question identifiers can be made with the help of deep learning models such as Convolutional Neural Networks. The convolutional neural network model is able to study patterns in mathematics problem labels. The best model obtained from the results of implementing a convolutional neural network is a convolutional neural network model with 2 convolutional kernels and 3 convolutional layers. The model is able to get a good classification value of 0.9453 on the training data and 0.9375 on the testing data.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Convolutional Neural Network, Convolutional Kernel, Convolutional Layer, Learner-Centered, Distributed Active Learning
Subjects:	Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Fadhli Azhar
Date Deposited:	05 Oct 2023 05:22
Last Modified:	05 Oct 2023 05:22
URI:	http://repository.its.ac.id/id/eprint/104250

Actions (login required)

View Item