Fan Speed Level Control Using Three-Language Voice Commands Based on YAMNet Audio Classification in Deep Learning

Heri Pratikno; Giga Razki Arianda; Pauladie Susanto; Musayyanah

doi:10.52435/complete.v6i2.725

Authors

Heri Pratikno Computer Engineering, Faculty of Technology and Informatics, Universitas Dinamika, Surabaya, Indonesia
Giga Razki Arianda Computer Engineering, Faculty of Technology and Informatics, Universitas Dinamika, Surabaya, Indonesia
Pauladie Susanto Computer Engineering, Faculty of Technology and Informatics, Universitas Dinamika, Surabaya, Indonesia
Musayyanah Politeknik Elektronika Negeri Surabaya

DOI:

https://doi.org/10.52435/complete.v6i2.725

Keywords:

artificial intelligence, audio classification, arduino uno, deep learning, voice recognition

Abstract

The process of interaction between humans, computers, and electronic equipment can now be made more interactive, natural, and intuitive. In several previous studies, this interactive process was carried out through sensors or detection of finger gestures using computer vision based on MediaPipe. In this research, we designed and built a system that can control the fan rotation speed level using voice commands from three languages, namely Indonesian, English, and Javanese in real time through an audio classification process with YAMNet. The research results in the training process with 15 epochs had 100% accuracy, loss 0.46, ROC curve class 0 (fan off) was 100%, class 1 (low rotation fan) was 100%, class 2 (medium rotation fan) was 99%, and class 3 (high rotation fan) was 100%. Meanwhile, the results of testing the subset test dataset model using 15 epochs for all commands produced a percentage value of 97.5%.

References

A. Hanafie, Kamal, and R. Ramadhan, "Perancangan Alat Pendeteksi Gerak Sebagai Sistem Keamanan Menggunakan ESP32 CAM Berbasis IoT," J. Teknol. dan Komput., vol. 2, pp. 142-148, 2022, doi: 10.56923/jtek.v2i02.101.

A. A. Syukron and Isnaini Lilis Elviyanti, "Pembuatan Sensor Cahaya dengan Memanfaatkan LED dan LDR Berbasis Arduino Uno," J. Kridatama Sains Dan Teknol., vol. 3, no. 02, pp. 161-169, 2021, doi: 10.53863/kst.v3i02.435.

Budy and T. Radillah, "Sistem Kontrol Menghidupkan Lampu Otomatis Menggunakan Sensor Suara FC-04 Berbasis Arduino Uno," Indones. J. Comput. Sci., vol. 12, 2023, doi: 10.33022/ijcs.v12i1.3121.

N. K. Daulay, N. Lestari, and A. Armanto, "SIMULASI MONITORING PENGATUR KECEPATAN KIPAS ANGIN MENGGUNAKAN SISTEM FUZZY BERBASIS WEB," 2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:225411605

M. A. Fakhruddin, "TA: Sistem Deteksi Gestur Jari Tangan menggunakan Mediapipe dan Faster-RCNN untuk Mengontrol Kecepatan Kipas Angin," Universitas Dinamika, 2023.

H. Wicaksono, L. Liliana, and A. N. Tjondrowiguno, "Pemodelan Lip Reading Bahasa Indonesia Berbasis Visem Menggunakan VGG16 serta Jaro-Winkler Similarity dan Bigram," J. Infra, 2022. [Online]. Available: https://publication.petra.ac.id/index.php/teknik-informatika/article/view/12513

M. Irwanto, F. Bachtiar, and N. Yudistira, "Klasifikasi Aktivitas Manusia Menggunakan Algoritme Computed Input Weight Extreme Learning Machine dengan Reduksi Dimensi Principal Component Analysis," J. Teknol. Inf. dan Ilmu Komput., vol. 9, p. 1195, 2022, doi: 10.25126/jtiik.2022965504.

F. D. Tanugraha, "TA: Sistem Pengenalan Aktivitas Manusia Menggunakan Long Short-Term Memory dan Mediapipe," Universitas Dinamika, 2022.

Y. R. B. Edowai, "TA: Sistem Automatic Feature Selection Berbasis Deteksi Gestur Kedua Jari Tangan untuk Mengontrol Level Kecepatan Putaran 2 Kipas Angin menggunakan Mediapipe," Universitas Dinamika, 2023.

F. Wakerkwa, "TA: Kontrol Level Kecepatan Putaran Kipas Angin melalui Deteksi Bentuk Gestur Jari Tangan Berbasis IoT," Universitas Dinamika, 2023.

M. R. P. Nautica, "TA: Hand Gesture Detection sebagai Alat Bantu Ajar Berhitung menggunakan Mediapipe dan Convolutional Neural Network secara Realtime," Universitas Dinamika, 2022.

A. A. Firmansyah, "Rancang Bangun Alat Bantu Penyandang Disabilitas Tangan Untuk Menghidupkan dan Mematikan Perangkat Elektronik Menggunakan Voice Recognition Module V3," J. Telecommun. Netw., vol. 3, no. 2, pp. 47-52, 2016, doi: 10.33795/jartel.v3i2.220.

C. Malmberg, "Real-time Audio Classification on an Edge Device-Using YAMNet and TensorFlow Lite," 2021.

Z. Fadilah and A. W. Wijayanto, "Perbandingan Metode Klasterisasi Data Bertipe Campuran: One-Hot-Encoding, Gower Distance, dan K-Prototype Berdasarkan Akurasi," J. Appl. Informatics Comput., vol. 7, pp. 57-67, 2023, doi: 10.30871/jaic.v7i1.5857.

F. X. L. Riberu, "TA: Sistem Deteksi Simbol pada SIBI secara Real Time menggunakan Mediapipe dan LSTM," Universitas Dinamika, 2023.

B. G. Permana, "TA: Sign Language Detection sebagai Alat Bantu Survey Pelayanaan Publik Menggunakan Long Short Term Memory Secara Realtime," Universitas Dinamika, 2023.

D. I. Puteri, "Implementasi Long Short Term Memory (LSTM) dan Bidirectional Long Short Term Memory (3BiLSTM) Dalam 4Prediksi Harga Saham Syariah," Euler J. Ilm. Mat. Sains dan Teknol., vol. 11, no. 1, pp. 35-43, 2023, doi: 10.34312/euler.v11i1.19791.

Z. Cui, R. Ke, Z. Pu, and Y. Wang, "Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction," pp. 1-11, 2018. [Online]. Available: http://arxiv.org/abs/1801.02143