Article Per Year (5 Year)
p-Index From 2021 - 2026
2.863
P-Index
This Author published in this journals
All Journal Media Teknik Sipil TEKNIK INFORMATIKA Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) Journal of ICT Research and Applications Indonesian Journal of Artificial Intelligence and Data Mining JURNAL NUSANTARA APLIKASI MANAJEMEN BISNIS Jurnal Telematika Building of Informatics, Technology and Science ACADEMICS IN ACTION Journal of Community Empowerment JISA (Jurnal Informatika dan Sains) International Journal of Advances in Data and Information Systems Jurnal Sains Indonesia IT For Society : Journal of Information Technology SENMEA
Tjong Wan Sen
Universitas Presiden
Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Mathematics Social Sciences Other

Published : 27 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 27 Documents
Search

 1   2   3 
ROBUST AUTOMATIC PHONEME RECOGNITION FEATURES USING COMPLEX WAVELET PACKET TRANSFORM COEFFICIENTS Sen, Tjong Wan
Jurnal Telematika Vol. 6 No. 1 (2010)
Publisher : Yayasan Petra Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61769/telematika.v6i1.41

Abstract

Untuk meningkatkan kinerja sistem pengenalan fonem otomatis pada saat dioperasikan pada lingkungan berderau, kami mengembangkan teknik baru yang dapat melakukan estimasi terhadap suatu fitur fonem bersih dari bentuk berderaunya. Fitur-fitur kokoh tersebut diperoleh dari koefisien transformasi paket wavelet kompleks (ComplexWavelet Packet Transform/CWPT). Karena koefisien CWPT merepresentasikan semua pita frekuensi yang berbeda dari suatu sinyal masukan, mendekomposisi sinyal masukan tersebut ke dalam pohon CWPT yang lengkap akan mencakup semua frekuensi yang terlibat dalam proses pengenalan. Setiap komponen frekuensi dalam sinyal masukan akan ditempatkan pada tepat satu pita frekuensi yang spesifik. Untuk suatu campuran sinyal domain waktu dengan frekuensi yang berbedabeda, misalnya sinyal fonem dengan derau, semua koefisien fonem dalam pita frekuensi yang sama, yaitu semua koefisienyang melewati jalur filter bank wavelet yang sama, akan berubah sesuai dengan magnituda komponen frekuensi derau. Oleh karena itu, jika ada sebuah pita frekuensi yang tidak mengandung derau sama sekali, seluruh koefisien fonem pada pita frekuensi tersebut tidak akan mengalami perubahan. Informasi dari semua koefisien yang dikandung oleh pita frekuensi tersebut kemudian dapat dimanfaatkan untuk melakukan estimasi terhadap kemungkinan fonem bersihnya. Karena jumlah fonem dalam suatu bahasa adalah terbatas dan relatif kecil dan sudah diketahui dengan baik sebelumnya, teknik yang dikembangkan ini fisibel secara komputasi. Hasil-hasil simulasi menunjukkan bahwa teknik baru yang dikembangkan ini merupakan pengekstrak fitur yang efisien dan tidak hanya dapat meningkatkan kekokohan sistem pengenal fonem otomatis jika dioperasikan pada berbagai macam lingkungan yang berderau tetapi juga tetap memelihara kinerja baiknya pada lingkungan yang bersih.To improve the performance of Automatic Phoneme Recognition in noisy environment, we developed a new technique that could estimate clean phoneme feature from its noisy one. These robust features are obtained from Complex Wavelet Packet Transform (CWPT) coefficients. Since the CWPT coefficients represent all different frequency bands of the input signal, decomposing the input signal into complete CWPT tree would covered all frequencies that involved in recognitionprocess. Each frequency would be placed into exactly one of its frequency bands. For time overlapping signals with different frequency contents, e. g. phoneme with noises, all coefficientsbelongs to the same frequency band, which is coming through the same wavelet filter banks path, would be changed according to noise frequencies magnitude. Thus, if there is one frequency band which contain no noises at all, all coefficients belongs to that frequency band would not change. Information from all coefficients belongs to that frequency band could be used then to estimate the clean phonemes. Since the numbers of phonemes are limited and already well known, this technique is computationally feasible. Simulation results showed that this new technique is an efficient features extractor that improves the robustness of the systems in various adverse noisy conditions but still reserve the good performance in clean environments.
License Plate Localization for Low Computation Resources Systems Using Raw Image Input and Artificial Neural Network Wan Sen, Tjong; Suakanto, Sinung; Siregar, Amril Mutoi
Jurnal Telematika Vol. 15 No. 1 (2020)
Publisher : Yayasan Petra Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61769/telematika.v15i1.349

Abstract

License Plate localization using Computer Vision needs a lot of computation resources. Thus, it is hard to deploy it on small systems. This paper presents an efficient license plate localization method using raw image input and artificial neural network. This is achieved by eliminating feature extraction stage and try to use as minimum as possible neural network architecture. Raw image input in dataset is cropped and labelled manually from random car images and video frames. The minimum architecture of the model has only three layers and 32,770 neurons. This is feasible to be deployed in today most single chip systems. The results, from various experiments, yield more than 90% of localization accuracy. Nomor plat kendaraan bermotor yang diperoleh dengan menggunakan Computer Vision membutuhkan banyak daya komputasi. Hal ini menyebabkan implementasinya ke dalam sistem minimum yang sederhana menjadi tidak mudah. Dalam penelitian ini, dikembangkan sebuah metoda untuk mendapatkan plat nomor kendaraan bermotor yang effisien menggunakan masukan langsung tanpa ektraksi ciri dan jaringan saraf tiruan. Penghematan daya komputasi dicapai dengan cara menghilangkan tahap ekstraksi ciri dan penggunaan arsitektur jaringan saraf tiruan yang seminimum mungkin. Citra masukan diperoleh dengan cara memotong dan memberi label gambar mobil dan frame video yang diperoleh secara acak. Arsitektur minimum yang dihasilkan berupa model yang hanya terdiri dari tiga lapisan dan 32,770 neuron. Model ini cukup fisibel untuk diterapkan pada kebanyakan system on a chip yang ada pada saat ini. Tingkat akurasi model dalam menemukan lokasi nomor kendaraan dari berbagai eksperimen berhasil mencapai lebih dari 90%. 
Optimization in Time and Score using IID Algorithm for K-Modes Clustering Yulianti, Farah; Sen, Tjong Wan
Building of Informatics, Technology and Science (BITS) Vol 4 No 4 (2023): March 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v4i4.2791

Abstract

Nowadays, there are numerous methods for analyzing data, one of which is cluster analysis. Because most practical data in today's analysis contains categorical attributes, categorical data clustering has recently received a lot of attention. To cluster categorical data, unsupervised machine learning techniques, which used frequency-based method, such as K-Mode’s clustering are used. The K-Modes algorithm takes advantage of the differences between the data points (total mis-matches or dissimilarities). The lower the dissimilarities, the more similar the data points, and thus the better the cluster. This paper aims to improve K-Mode’s clustering performance by incorporating the intercluster and intracluster dissimilari-ty measure, or IID measure, into the K-Modes algorithm rather than just using the standard simple-matching method to increase the algorithm's accuracy and execution time. This combined algorithm improves accuracy and execution time of the K-Modes algorithm. As a result, this algorithm can be used as an alternative to better cluster categorical data.
Machine Learning Algorithms for Prediction of Boiler Steam Production Lianzhai, Duan; Roestam, Rusdianto; Sen, Tjong Wan; Fahmi, Hasanul; ChungKiat, Ong; Hariyanto, Dian Tri
International Journal of Advances in Data and Information Systems Vol. 5 No. 2 (2024): October 2024 - International Journal of Advances in Data and Information System
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v5i2.1339

Abstract

The continuous increase in global electricity demand has resulted in boiler power plants becoming a significant energy source. The production of steam is a principal indicator of boiler efficiency, and the accurate prediction of steam production is paramount importance for the enhancement of boiler efficiency and the reduction of operational costs. In this study employs a boiler dataset with a steam production capacity of 420 tons per hour. A total of 25 independent variables were extracted from the original 39 variables through data processing and feature engineering for the purpose of prediction analysis. Subsequently, 8 machine learning models were used for modeling predictions. Grid search cross-validation was employed in order to optimise the performance of the model. The models were analysed and assessed using the Mean Squared Error (MSE) metrics. The results show that random forest achieves the highest accuracy among the 8 single models. Based on 8 models, New Bagging ensemble model is proposed, which combined predictions from 8 single models, demonstrated the optimal overall fit and the lowest MSE, achieved the purpose of the research. The present study demonstrates the ability to analyse and predict complex industrial systems with machine learning algorithms, and provides insights into the use of machine learning algorithms for industrial big data analytics and Industry 4.0. Further work could explore using larger datasets and deep learning to make predictions more accurate.
SENTIMENT ANALYSIS OF STUDENT SATISFACTION TOWARDS DISTANCE LEARNING USING MACHINE LEARNING METHOD Andres, M; WanSen, Tjong; Roestam, Rusdianto
IT for Society Vol 9, No 1 (2024): Vol 9, No 1
Publisher : President University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33021/itfs.v9i1.5073

Abstract

The Covid-19 pandemic forces the entire societyto change their way of life. One of them is the process of face-to-face learning changing into distant learning. Various responsesarise from students during the implementation of this newsystem, both positive and negative, indicating the level of studentsatisfaction. The sentiment analysis of students' commentsduring distance learning was conducted using machine learningalgorithms and tools Rapid miner. Literature study shows thatthe Naive Bayes, K-NN, and Decision Tree algorithms have veryhigh accuracy, so this research uses those methods to get high-accuracy results. The research shows the following results;Naive Bayes is 93.80% and class precision for pred. Positive93.80% and pred. negative 100.00%. The K-NN algorithm is92.49% and class precision for pred. positive is 92.37%, pred.negative 100%. The Decision Tree method is 90.81% with astandard deviation of (+-) 0.58 and class precision for pred.positive 90.81% and class pred. negative 0.00%.
Tomato Pest and Disease Identification Based on Improved Deep Residual Network and Transfer Learning Linli, Peng; Sen, Tjong Wan; Fahmi, Hasanul; Roestam, Rusdianto
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 1 (2025): March 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i1.34038

Abstract

Tomatoes are a vital global crop, but their yield can be severely impacted by various diseases like leaf mold and spotted wilt. Early and accurate diagnosis of these diseases is crucial for implementing timely treatments, thereby reducing crop loss. Traditional manual diagnosis often suffers from low accuracy, high costs, and time consumption. To address these issues, this study introduces a method for identifying tomato pests and diseases using an improved residual network and transfer learning. A dataset comprising images of seven common tomato diseases and healthy leaves was created. This study introduces an improved residual network and transfer learning method to accurately identify tomato pests and diseases. The enhanced ResNet50 model, with an attention mechanism and focal loss, achieved 98.10% recognition accuracy. This research not only facilitates early disease detection, reducing crop loss but also minimizes pesticide use, thereby enhancing environmental sustainability and agricultural productivity worldwide.
Enhancing Stego Image Quality With SIUN Post-Processing of Image Steganography Without Embedding DCGAN Outputs Forenziana, Jessica; Sen, Tjong Wan
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 1 (2025): March 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i1.35640

Abstract

In digital steganography, hiding information seamlessly within images is key. This study merges Deep Convolutional Generative Adversarial Networks (DCGAN) with Scale-Iterative Upscaling Networks (SIUN) to craft high-quality stego images swiftly and enhance the DCGAN image training period. Eschewing length DCGAN training, SIUN refines post-generation images, ensuring detailed visuals and increased data storage. Using the MNIST dataset, findings show that SIUN not only accelerates the process but also improves the stego image quality, suggesting a significant leap forward for secure communication efficiency. This research found that by using SIUN can enhance the quality of stego images with just 50 epochs of DCGAN training. After this initial training, the images are sent to SIUN for further quality upgrades with more efficient time.
Optimization of Machine Learning Models with Segmentation to Determine the Pose of Cattle Siregar, Amril Mutoi; Hartono Wijaya, Sony; Fauzi, Ahmad; Sen, Tjong Wan; Faisal, Sutan; Tukino, Tukino; Cahyana, Yana
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 3 (2023): September
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i3.26750

Abstract

Image pattern recognition poses numerous challenges, particularly in feature recognition, making it a complex problem for machine learning algorithms. This study focuses on the problem of cow pose detection, involving the classification of cow images into categories like front, right, left, and others. With the increasing popularity of image-based applications, such as object recognition in smartphone technologies, there is a growing need for accurate and efficient classification algorithms based on shape and color. In this paper, we propose a machine learning approach utilizing Support Vector Machine (SVM) and Random Forest (RF) algorithms for cow pose detection. To achieve an optimal model, we employ data augmentation techniques, including Gaussian blur, brightness adjustments, and segmentation. The proposed segmentation methods used are Canny and Kmeans. We compare several machine learning algorithms to identify the optimal approach in terms of accuracy. The success of our method is measured by accuracy and Receiver Operating Characteristic (ROC) analysis. The results indicate that using the Canny segmentation, SVM achieved 74.31% accuracy with a testing ratio of 90:10, while RF achieved 99.60% accuracy with the same testing ratio. Furthermore, testing with SVM and K-means segmentation reached an accuracy of 98.61% with a test ratio of 80:20. The study demonstrates the effectiveness of SVM and Random Forest algorithms in cow pose detection, with Kmeans segmentation yielding highly accurate results. These findings hold promising implications for real-world applications in image-based recognition systems. Based on the results of the model obtained, it is very important in pattern recognition to use segmentation based on color even though shape recognition.
Syllable-Based Javanese Speech Recognition Using MFCC and CNNs: Noise Impact Evaluation Hermanto, Hermanto; Sen, Tjong Wan
JURNAL TEKNIK INFORMATIKA Vol. 18 No. 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v18i1.41067

Abstract

Javanese, a regional language in Indonesia spoken by over 100 million people, is classified as a low-resource language, presenting significant challenges in the development of effective speech recognition systems due to limited linguistic resources and data. Furthermore, the presence of noise is a significant factor that impacts the performance of speech recognition systems. This study aims to develop a speech recognition model for the Javanese language, focusing on a syllable-based approach using Mel Frequency Cepstral Coefficients (MFCC) for audio feature extraction and Convolutional Neural Networks (CNNs) methods for classification. Additionally, it will analyze how different types of colored noise: white gaussian, pink, and brown, when added to the audio, impact the model's accuracy. The results showed that the proposed method reached a peak accuracy of 81% when tested on the original audio (audio without any synthetic noise added). Moreover, in noisy audio, model accuracy improves as noise levels decrease. Interestingly, with brown noise at a 20 dB SNR, the model's accuracy slightly increases to 83%, representing a 2.47% improvement over the original audio. These results demonstrate that the proposed syllable-based method is a promising approach for real-world applications in Javanese speech recognition, and the slight accuracy improvement in noisy conditions suggests potential regularization effects
Aplikasi Mobile Untuk Menekan Biaya Penjualan Produk Pertanian Lokal Tjong, Wan Sen
Jurnal Nusantara Aplikasi Manajemen Bisnis Vol 8 No 1 (2023): Jurnal NUSAMBA
Publisher : UNIVERSITAS NUSANTARA PGRI KEDIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29407/nusamba.v8i1.18725

Abstract

Research aim: This mobile application development aims to directly connect local agricultural producers to their buyers without any intermediary party in order to keep the selling costs minimum. Design/Methode/Approach: Rapid Application Development method with User Oriented are used in this research, which allows a relatively short development time and supports a more intense interaction with the related stakeholders. Research Finding: This research finds that simplification of transactions and more exposure through this application is very important. Theoretical contribution/Originality: This application has unique functions and interfaces that are designed as simple as possible to be easily operated by local agricultural producers, even with minimum digital literacy level. Practitionel/Policy implication: This implicated on application speed factor, data transmission size, and minimum hardware requirements are also the main criterias on which this application development is based. The result is a new and unique mobile application which is easy to use, does not consume too much internet quota, and supports older smartphones which are very beneficial for stakeholder. Research limitation: However system limitations such as integration with digital payment, rating systems, and recommendation systems still not covered yet.
Co-Authors Abdul Ghofir Andres, M Arry Akhmad Arman Bambang Riyanto Trilaksono ChungKiat, Ong Darien Daud Earlliawand Diky Djafar Sidik EKO WAHYUDI Fahmi, Hasanul Faisal, Sutan Fauzi Ahmad Muda Forenziana, Jessica Ghofur, Muhamad Hariyanto, Dian Tri Hartono Wijaya, Sony Hermanto Hermanto Lianzhai, Duan Linli, Peng Muhamad Muhaimin Mutia, Siti Aisyah Naili Rachma Oktari Riady, Sasmitoh Rahmad Rila Mandala Riyanto Adji Rosalina Rosalina Rusdianto Roestam Sahuri, Genta Sahuri Sinung Suakanto Siregar, Amril Mutoi Suryana, Yahya Sutisna, Nanang Ali Tukino, Tukino Yana Cahyana Yonata, Yosi Yulianti, Farah