Sistem Klarifikasi Bahasa Isyarat Indonesia (Bisindo) Dengan Menggunakan Algoritma Convolutional Neural Network

Arisandi, Lukman; Satya, Barka

doi:10.37396/jsc.v5i3.262

Cited by 6 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Dalam pelatihan model, penggunaan callback sangat penting untuk memantau dan mengontrol proses agar menghindari overfitting dan meningkatkan kualitas model secara keseluruhan, sebagaimana dijelaskan oleh (Arisandi & Satya, 2022). Salah satu callback yang berguna adalah Early Stopping, yang memungkinkan proses pelatihan dihentikan secara otomatis jika akurasi data telah mencapai nilai tertentu, sehingga menghindari overfitting.…”

Section: Penerapan Callbackunclassified

Klasifikasi Gambar Batu-Kertas-Gunting Menggunakan Convolutional Neural Network dengan Fungsi Callback untuk Mencegah Overfitting

Samidin,

Fadjeri

2024

Jur. Penel. Inov.

View full text Add to dashboard Cite

Dalam era modern, kecerdasan buatan (AI) dan machine learning, khususnya teknik machine learning, telah menjadi integral dalam perkembangan teknologi. Implementasi Convolutional Neural Network (CNN) dalam klasifikasi gambar sering mengalami masalah overfitting, di mana model terlalu beradaptasi dengan data latih dan kurang mampu menggeneralisasi data uji. Untuk mencegah overfitting, penelitian ini menggunakan callback, seperti Early Stopping, Model Checkpointing, dan CSV Logging. Dataset gambar batu-kertas-gunting diperoleh dari Github Dicoding dan diproses dengan pembagian subset, augmentasi data, dan generator data. Model CNN dirancang dengan lapisan konvolusi, lapisan pooling, dan lapisan Dense. Optimizer, fungsi loss, dan metrik evaluasi dipilih sesuai tugas klasifikasi gambar. Melalui pelatihan model, akurasi meningkat dari 48.75% menjadi 98.75%, sementara loss menurun dari 0.9794 menjadi 0.0448. Evaluasi pada data validasi juga menunjukkan peningkatan konsisten. Pelatihan dihentikan pada epoch ke-18 setelah mencapai akurasi di atas 98%, untuk mencegah overfitting dan mengoptimalkan waktu pelatihan. Kesimpulan menunjukkan bahwa penggunaan callback efektif dalam mencegah overfitting dan meningkatkan akurasi model CNN dalam klasifikasi gambar batu-kertas-gunting. Ini menjadi strategi penting dalam meningkatkan kualitas hasil akhir model.

show abstract

Section: Penerapan Callbackunclassified

Klasifikasi Gambar Batu-Kertas-Gunting Menggunakan Convolutional Neural Network dengan Fungsi Callback untuk Mencegah Overfitting

Samidin,

Fadjeri

2024

Jur. Penel. Inov.

View full text Add to dashboard Cite

show abstract

“…Proses ini menggunakan prediksi secara acak, yang merupakan salah satu subclass dari perpustakaan Keras. Tujuannya adalah untuk meningkatkan efisiensi analisis gambar [23]. Berikut ini adalah hasil klasifikasi yang diperoleh dari arsitektur CNN Xception tersebut.…”

Section: Hasil Klasifikasi Citraunclassified

Klasifikasi Hama Serangga pada Pertanian Menggunakan Metode Convolutional Neural Network

Akram,

Fayakun,

Ramza

2023

bits

View full text Add to dashboard Cite

Insect pest attacks pose a serious threat that can potentially cause significant losses in agricultural production. Therefore, the effective recognition and control of insect pests are crucial for maintaining agricultural productivity and quality of yields. With the advancement of computer technology and artificial intelligence, computer technology can be utilized to automatically recognize images in object recognition, particularly for insect pest classification using the Convolutional Neural Network (CNN) method with the Xception architecture. CNN is one of the types of deep feed-forward artificial neural networks widely used in digital image analysis and can process data in the form of grid patterns. CNN consists of three types of layers: convolutional layer, pooling layer, and fully connected layer. The use of CNN in this research aims to facilitate the classification of insect pests. The CNN process involves stages of training, testing, and validation on insect pests to determine the classification of images of various insect pest species. This research utilizes 1363 image samples with 13 classes of insect pests. The training process of CNN involves several parameters such as batch size, number of epochs, learning rate, and optimizer. The experiment's results indicate that the best accuracy achieved by this model is 93.81% during the training phase and 81.75% during the validation phase. This demonstrates that the model successfully performs insect pest classification using the CNN method.

show abstract

“…However, those who possess physical impairments may resort to nonverbal means of communication, such as sign language, to convey their messages. In March 2022, the number of individuals who are deaf and speech impaired in Indonesia will reach 19,392 people, which is equivalent to 9.14% of the total number of people with disabilities in Indonesia (Arisandi & Satya, 2022).…”

Section: Introductionmentioning

confidence: 99%

“…Sign language is used to overcome limitations associated with being deaf and speech impairment. In the context of Indonesia, it is common to observe the utilization of two distinct sign languages, specifically Indonesian Sign Language (BISINDO) and Indonesian Sign Language System (SIBI) (Arisandi & Satya, 2022). BISINDO, the Indonesian Sign Language, was established by the deaf community and exhibits regional variances that reflect the many origins of the community.…”

Section: Introductionmentioning

confidence: 99%

Deep Transfer Learning for Sign Language Image Classification: A Bisindo Dataset Study

Rachmawati,

Yunanda,

Hidayat

et al. 2023

EMACS Journal

View full text Add to dashboard Cite

This study aims to identify and categorize the BISINDO sign language dataset, primarily consisting of image data. Deep learning techniques are used, with three pre-trained models: ResNet50 for training, MobileNetV4 for validation, and InceptionV3 for testing. The primary objective is to evaluate and compare the performance of each model based on the loss function derived during training. The training success rate provides a rough idea of the ResNet50 model's understanding of the BISINDO dataset, while MobileNetV4 measures validation loss to understand the model's generalization abilities. The InceptionV3-evaluated test loss serves as the ultimate litmus test for the model's performance, evaluating its ability to classify unobserved sign language images. The results of these exhaustive experiments will determine the most effective model and achieve the highest performance in sign language recognition using the BISINDO dataset.

show abstract

Sistem Klarifikasi Bahasa Isyarat Indonesia (Bisindo) Dengan Menggunakan Algoritma Convolutional Neural Network

Cited by 6 publications

References 8 publications

Klasifikasi Gambar Batu-Kertas-Gunting Menggunakan Convolutional Neural Network dengan Fungsi Callback untuk Mencegah Overfitting

Klasifikasi Gambar Batu-Kertas-Gunting Menggunakan Convolutional Neural Network dengan Fungsi Callback untuk Mencegah Overfitting

Klasifikasi Hama Serangga pada Pertanian Menggunakan Metode Convolutional Neural Network

Deep Transfer Learning for Sign Language Image Classification: A Bisindo Dataset Study

Contact Info

Product

Resources

About