Claim Missing Document
Check
Articles

Found 18 Documents
Search

Instrumental Music Emotion Recognition with MFCC and KNN Algorithm Santoso, Tri Budi; Dutono, Titon
The Indonesian Journal of Computer Science Vol. 12 No. 1 (2023): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v12i1.3152

Abstract

Every piece of music contains emotion in every sound presented. Detection of the music emotion is quite difficult to do because the emotions felt are subjective. Based on this problem, it is necessary to have an automatic classification system to detect the emotions produced in music. In this paper, an explanation of the result to develop an emotional classification system of instrumental music. This system described the process starting with the receiving an input in the form of a music file in the format wav. Furthermore, the feature extraction process is carried out using Mel-Frequency Cepstral Coefficients (MFCC). The result of the extraction of such features are used in the classification process using the K-Nearest Neighbor (K-NN). The system produced output in the form of happy, relaxed, and sad emotions. The output of the system has a classification achieved an accuracy of 97.5% for the value of k = 1, reaching an accuracy of 95% for the value of k = 2.95% and for k = 3, reaching an accuracy of up to 90%.
Analisis Kompatibilitas Sederhana Terhadap Kemungkinan Layanan Komunikasi Radio Nelayan Tradisional di Laut Jawa dengan Layanan Komunikasi Radio Lain pada Pita Frekuensi 5,2 MHz: A Simple Compatibility Analysis of Possible Traditional Fishermen Radio Communication Across Java Sea with Existing Radio Services in The 5.2 MHz Frequency Band Dutono, Titon
The Indonesian Journal of Computer Science Vol. 12 No. 2 (2023): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v12i2.3193

Abstract

Interferensi pada pita frekuensi sub-10 MHz yang disebabkan oleh pancaran ilegal oleh nelayan tradisional di sepanjang laut Jawa merupakan masalah kronis yang memerlukan penanganan mendasar untuk memitigasinya. Fihak berwenang kesulitan melokalisasi posisi emisi pancaran ilegal karena selalu bergerak di tengah laut. Oleh karena itu, fihak berwenang sedang mempertimbangkan untuk mencari pita frekuensi yang memungkinkan untuk ditetapkan sebagai alokasi frekuensi baru bagi nelayan tradisional, khususnya di wilayah Laut Jawa. Kami menawarkan segmen pita frekuensi 5,2 MHz untuk menjadi alokasi frekuensi baru ini. Untuk tujuan ini, kami melakukan analisis kompatibilitas sederhana dari pita frekuensi ini. Analisis dilakukan dengan menggunakan dua tahap. Tahap pertama dengan mempelajari regulasi telekomunikasi terkini, kemudian dilanjutkan dengan pemantauan selama satu tahun terhadap kondisi pita frekuensi tersebut. Pemantauan dilakukan pada periode aktifitas matahari minimum dengan memanfaatkan sistem WSPR yang hasilnya akan dibandingkan dengan hasil prediksi dari program aplikasi VOACAP. Hasil analisis dapat disimpulkan bahwa pita 5,2 MHz dapat digunakan oleh masyarakat nelayan tradisional di wilayah Laut Jawa. Oleh karena itu, regulator telekomuniksi dapat mempertimbangkan untuk menetapkan alokasi khusus bagi nelayan lokal di Laut Jawa untuk memanfaatkan pita frekuensi ini.
Indonesian speech emotion recognition: feature extraction and neural network approaches Afifah, Izza Nur; Santoso, Tri Budi; Dutono, Titon
International Journal of Electrical and Computer Engineering (IJECE) Vol 15, No 4: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v15i4.pp3769-3778

Abstract

This study explored the challenges of emotion recognition in Indonesian speech using deep learning techniques, addressing the complex nuances of emotional expression in spoken language that posed significant difficulties for automatic recognition systems. The research focused on the application of feature extraction methods and the implementation of convolutional neural networks (CNN) and a hybrid convolutional neural networks-long short-term memory (CNN-LSTM) model to identify emotional states from speech data. By analyzing key features of speech signals, including mel frequency cepstral coefficient (MFCC), zero crossing rate (ZCR), root mean square energy (RMSE), pitch, and spectral centroid, the study evaluated the models’ ability to capture both spatial and temporal patterns in the data. Testing was conducted using an Indonesian dataset comprising 200 samples. The CNN model, utilizing four features (MFCC, ZCR, RMSE, and pitch), and the CNN-LSTM model, which used three features (MFCC, ZCR, and RMSE), both achieved an emotion classification accuracy of approximately 88%. The result showed that the CNN-LSTM model achieved comparable performance with a simpler feature set compared to the CNN model. This highlighted the significance of choosing the appropriate techniques in feature extraction and classification to enhance the accuracy of identifying emotions from speech data while also managing computational complexity.
Sistem Deteksi Dini Bencana Banjir di Lingkungan Masyarakat Keputih Surabaya Lestari, Paramita; Darwito, Haryadi Amran; Muna, Nailul; Dutono, Titon; Arifin, Arifin; Syahroni, Nanang; Rizki, Aris Bahari; Suparno, Hari Wahyuningrat; Supriyanto, Eko; Hakum, Fadhil Ahnaf Taufiqul; Arifin, M. Zainul; Wicaksono, Syahrul; Christinanda, Mitchell Onesimus; Rizqi, Karisma Nur
Sewagati Vol 9 No 4 (2025)
Publisher : Pusat Publikasi ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j26139960.v9i4.6549

Abstract

Banjir adalah bencana alam yang sering melanda Indonesia, termasuk wilayah Keputih, Surabaya, yang mengalami genangan akibat tingginya curah hujan dan aliran air yang tidak lancar. Penyebab banjir di daerah ini meliputi intensitas hujan yang tinggi, terbatasnya daerah resapan, saluran sungai yang tersumbat sampah, dan tata ruang kota yang kurang mendukung sistem drainase yang optimal. Untuk mengatasi masalah ini, telah dikembangkan sistem deteksi dini banjir yang terintegrasi dengan smart PJU (Penerangan Jalan Umum). Sistem ini memanfaatkan data curah hujan dan ketinggian air yang dipantau di sejumlah ruas jalan di kawasan Keputih, beroperasi secara real-time, dan melaporkan hasil pemantauan melalui platform website monitoring. Selain itu, sistem ini dilengkapi dengan aktivasi sirine buzzer saat potensi banjir terdeteksi. Aplikasi website monitoring dapat diakses melalui perangkat ponsel, sehingga masyarakat dapat memantau situasi banjir kapan saja dan di mana saja. Sistem ini sangat membantu warga sekitar keputih untuk lebih antisipasi akan bencana banjir ketika curah hujan di wilayah tersebut sedang tinggi dan pengembangan kedepannya dilakukan analisis dan klasifikasi curah hujan untuk meningkatkan keberlanjutan pengembangan dan pengelolaan di lingkungan Kelurahan Keputih.
Aplikasi Terapi Digital Anak Penyandang Autism di Komunitas Forkesi Chapter Surabaya Mahmudah, Hani'ah; Pratiarso, Aries; Saleh, Akuwan; Yuliana, Mike; Kristalina, Prima; Samsono Hadi, Moch. Zen; Dutono, Titon; Anisah, Ida; Sa’adah, Nihayatus
BUDIMAS : JURNAL PENGABDIAN MASYARAKAT Vol. 4 No. 2 (2022): BUDIMAS : VOL. 04 NO. 02, 2022
Publisher : LPPM ITB AAS Indonesia Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Many parents in the Surabaya Chapter Forkesi Community (Indonesian Special Children's Parents Communication Forum) do not understand how to care for and teach children with autism, despite the fact that 50 percent of the members of this community are parents of children with autism. This service aims to assist parents in dealing with their autistic children on a daily basis. Furthermore, to address the issue of disadvantaged children with autism who are unable to participate in therapy or seek treatment from psychologists on a regular basis due to the high expense of doing so. The development of an augmented reality-based android mobile application using the marker method will include learning materials for build a match and WH questions, as well as games to help deepen learning, and will be used in conjunction with the ABA method and DTT technique. In May-July 2021, this service activity was carried out in the Surabaya Chapter Forkesi community. Data collecting, interactions with community members, and direct implementation were the strategies used in this service. According to the findings of the Usability Testing, which received a score of 54.6, parents of children with autism agree on the use of digital therapy via Android mobile app.
Speech Emotion Recognition of Indonesian Movies by Using Convolutional Neural Network Santoso, Tri Budi; Khoirotul Aini, Yulistia; Dutono, Titon
JOIV : International Journal on Informatics Visualization Vol 9, No 6 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.6.3552

Abstract

Speech emotional recognition (SER) is one of the interesting research areas of human-computer interaction (HCI) systems. The objective of this study is to provide a basis for a basic model of Indonesian-language speech emotional recognition, which is achieved by utilizing dialogues from an Indonesian-language movie.  The process began by developing a dataset from film dialogue and grouping it into four emotion classes: angry, happy, neutral, and sad. The development of the datasheet produced 5049 data points consisting of 1202 for anger, 1228 for happy, 2075 for neutral, and 899 for sad. This study uses the Mel-frequency cepstral coefficients (MFCC) method to analyze audio features from Indonesian-language movies and employs a Convolutional Neural Network (CNN) for clustering. The process began with MFCC feature extraction. During training, an accuracy of 85.85% was achieved, and during testing, 83.35%. Based on a series of tests carried out with various improvements to the previous process, a description of this system's behavior is obtained from a confusion matrix. Angry, happy, and sad expressions are easier to recognize than neutral expressions. The behavior of neutral expressions is flat in energy levels and other features. In the future, we hope it can be developed into a cross-corpus model and applied to speakers from various cultures.
A Simplified Sounding System for Finding NVIS Channel Availability to Support Government Radio Networks in Indonesia Dutono, Titon; Zakariyah, Zulmi; Santoso, Tribudi; Setiawan, Denny
EMITTER International Journal of Engineering Technology Vol 7 No 1 (2019)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (16.57 KB) | DOI: 10.24003/emitter.v7i1.388

Abstract

Mostly  natural disasters in Java Island such as landslides are within the vicinity of not more than 200 Km from the district capital. Cellular communications require complex systems and rather vulnerable  to cope with disasters. NVIS mode is considered as a simple radio link during disaster mitigation initiation process. It needs a valid estimation to figure out the condition of the ionosphere. There are two purposes of this study, the first of which is an attempt to find out a fact the existences of authorized HF users who still work in the band of 3 MHz – 10 MHz.  The second is to integrate low cost HF radio communication, commonly available small single board computer hardware, and opensource software, to build a sounding system to evaluate the quality of NVIS channels. Prediction system such VOACAP give hourly prediction data, however it has an inherent limitation because of   nature the underlying databases is monthly average based, therefore, the estimation could not be made in a daily bases. However, a real-time channel evaluation (RTCE)  able to purify maximum observed frequency (MOF) estimation, and consequently, its able to select the best available frequency for short term  and real time operation. In this study, we used WSPR to perform a simple RTCE technique. Furthermore, we also reviewed the current regulatory status regarding  the availability of sub-10 MHz band for NVIS radio operation. The results show that discrepancies between simulation and measurement are occurred mainly because of sporadic data in the band of 60m and 80m. However, all of the measurement results and simulations almost have the same agreement regarding the quiet period between local midnight and local sunrise. The results of measurements show that 60m band is the most reliable NVIS channel between local sunrise and local midnight. Furthermore, 100 watts is a proper transmitter power to reach the required SNR for reliable voice communication. 
Secure Data Travelling User using Hybrid Cryptosystem with User Privacy Protection Anindya Dwi Putri Islamidina; Amang Sudarsono; Titon Dutono
EMITTER International Journal of Engineering Technology Vol 8 No 1 (2020)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24003/emitter.v8i1.486

Abstract

Nowadays traveling is the activity that everyone likes the most, but sometimes there is one traveling member who is lost and confused looking for the location of the other members. When traveling, they must bring a smartphone because of its small size and easy to carry anywhere. For this reason, an Android-based smartphone application that is able to send GPS data to all travelling members is proposed. In order to secure data transmission, cryptography and group signature to ensure that only traveling members could find out the location are applied. We use hybrid cryptography, which is a combination of symmetric cryptography using AES and asymmetric cryptography using IB-mRSA. We also add group signature as verification that members are in the same traveling group. The test result showed that the proposed method is safer than the comparison method because the symmetric key is encrypted before the key is distributed, so the attacker can not know the key. The total processing time needed to send data until member get data is 2.01 s.