Garuda - Garba Rujukan Digital

p-Index From 2021 - 2026

0.23

P-Index

This Author published in this journals

All Journal International Journal of Electrical and Computer Engineering Jurnal Ilmu Komputer dan Informasi Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) Makara Journal of Science Makara Journal of Technology

T. Basaruddin

Fakultas Ilmu Komputer, Universitas Indonesia, Depok 16424, Indonesia

Author-ID : 399817

Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Library & Information Science Materials Science & Nanotechnology Mechanical Engineering

Published : 6 Documents Claim Missing Document

Claim Missing Document

Articles

Dataset Suara dan Teks Berbahasa Indonesia Pada Rekaman Podcast dan Talk show Martin Novela; T. Basaruddin
JURNAL FASILKOM (teknologi inFormASi dan ILmu KOMputer) Vol 11 No 2 (2021): Jurnal Fasilkom
Publisher : Fakultas Ilmu Komputer, Unversitas Muhammadiyah Riau

Salah satu faktor keberhasilan suatu model pembelajaran dalam machine learning atau deep learning adalah dataset yang digunakan. Pada tulisan ini menyajikan dataset suara dari rekaman podcast dan talk show beserta transkripsi berbahasa Indonesia. Dataset ini disajikan karena belum adanya ketersediaan dataset berbahasa Indonesia yang dapat diakses secara publik untuk digunakan pada pembelajaran model Text-to-Speech ataupun Audio Speech Recognition. Dataset terdiri dari 3270 rekaman yang diproses untuk mendapatkan transkripsi berupa teks atau kalimat berbahasa Indonesia. Dalam pembuatan dataset ini dilakukan beberapa tahapan seperti pra-pemrosesan, tahapan translasi, tahapan validasi pertama dan tahapan validasi kedua. Dataset dibuat dengan format yang mengikuti format dari dataset LJSpeech untuk memudahkan pemrosesan dataset ketika digunakan dalam suatu model sebagai input. Dataset ini diharapkan dapat membantu meningkatkan kualitas pembelajaran untuk pemrosesan Text-to-Speech seperti pada model Tacotron2 ataupun pada pemrosesan Audio Speech Recognition untuk bahasa Indonesia.

Text Preprocessing using Annotated Suffix Tree with Matching Keyphrase Ionia Veritawati; Ito Wasito; T Basaruddin
International Journal of Electrical and Computer Engineering (IJECE) Vol 5, No 3: June 2015
Publisher : Institute of Advanced Engineering and Science

Text document is an important source of information and knowledge. Most of the knowledge needed in various domains for different purposes is in form of implicit content. Content of text is represented by keyphrases, which consist of one or more meaningful words. Keyphrases can be extracted from text through several steps of processing, including text preprocessing. Annotated Suffix Tree (AST) built from the documents collection itself is used to extract the keyphrase, after basic text preprocessing that includes removing stop words and stemming are applied. Combination of four variations of preprocessing is used. Two words (bi-words) and three words of phrases extracted are used as a list of keyphrases candidate which can help user who needs keyphrase information to understand content of documents. The candidate of keyphrase can be processed further by learning process to determine keyphrase or non keyphrase for the text domain with manual validation. Experiments using simulation corpus which keyphrases are determined from it show that keyphrases of two and three words can be extracted more than 90% and using real corpus of economy, keyphrases or meaning phrases can be extracted about 70%. The proposed method can be an effective ways to find candidate keyphrases from collection of text documents which can reduce non keyphrases or non meaning phrases from list of keyphrases candidate and detect keyphrases which are separated by stop words.

KLASIFIKASI BEAT ARITMIA PADA SINYAL EKG MENGGUNAKAN FUZZY WAVELET LEARNING VECTOR QUANTIZATION Elly Matul Imah; T. Basaruddin
Jurnal Ilmu Komputer dan Informasi Vol 4, No 1 (2011): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Information)
Publisher : Faculty of Computer Science - Universitas Indonesia

Pengenalan pola beat dalam analisa rekaman elektrokardiogram (EKG) menjadi bagian yang penting dalam deteksi penyakit jantung terutama aritmia. Banyak metode yang dikembangkan terkait dengan pengenalan pola beat, namun sebagian besar masih mengunakan algoritma klasifikasi klasik di mana masih belum mampu mengenali outlier klasifikasi. Fuzzy Learning Vector Quantization (FLVQ) merupakan salah satu algoritma yang mampu untuk mengenali outlier klasifikasi tetapi juga memiliki kelemahan untuk sistem uji yang bukan data berkelompok. Dalam tulisan ini peneliti mengusulkan Fuzzy Wavelet LearningVector Quantization (FWLVQ), yaitu modifikasi FLVQ sehingga mampu mengatasi data crisp maupun data fuzzy dan juga memodifikasi inferensi sistemnya sebagai perpaduan model fuzzy Takagi Sugeno Kang dengan wavelet. Sinyal EKG diperoleh dari database MIT-BIH. Sistem pengenalan pola beat secara keseluruhan terbagi atas dua bagian yaitu data pra proses dan klasifikasi. Hasil percobaan diperoleh bahwa FWLVQ memiliki akurasi sebesar 90.20% untuk data yang tidak mengandung outlier klasifikasi dan 87.19% untuk data yang melibatkan outlier klasifikasi dengan rasio data uji outlier klasifikasi dengan data non-outlier sebesar 1:1. The recognition of beat pattern in analysis of recording an electrocardiogram (ECG) becomes an important detection of heart disease, especially arrhythmias. Many methods are developed related to the recognition of beat patterns, but most still use the classical classification algorithms which are still not able to identify outlier classification. Fuzzy Learning Vector Quantization (FLVQ) is one of the algorithms that can identify outlier classification but also has a weakness for test systems that are not grouped data. In this paper we propose a Fuzzy Wavelet Quantization Learning Vector (FWLVQ), which is modified so as to overcome FLVQ crisp data and fuzzy data and also modify the inference system as a combination of Takagi Sugeno Kang fuzzy model with the wavelet. ECG signal obtained from the MIT-BIH database. Beat pattern recognition system as a whole is divided into two parts: data pre-processing and classification. The experimental results obtained that FWLVQ has an accuracy 90.20% for data that does not contain outlier classification and 87.19% for the classification of data involving outlier ratio outlier test data classification with non-outlier data of 1:1.

On the Performance of SVD-DWT Based Digital Video Watermarking Technique with Semi-Blind Detector Basaruddin, Tarzan; Maulidiya, Della
Makara Journal of Technology Vol. 13, No. 1
Publisher : UI Scholars Hub

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

On the Performance of SVD-DWT Based Digital Video Watermarking Technique with Semi-Blind Detector. This paper presents a watermarking technique for digital video. The proposed scheme is developed based on the work of Ganic and Chan which took the virtue of SVD and DWT. While the previous works of Chan has the blind detector property, our attempt is to develop a scheme with semi-blind detector, by using the merit of the DWT-SDV technique proposed by Ganic which was originally applied to still image. Overall, our experimental results show that our proposed scheme has a very good imperceptibility and is reasonably robust especially under several attacks such as compression, blurring, cropping, and sharpening.

Particle Filter with Binary Gaussian Weighting and Support Vector Machine for Human Pose Interpretation Agustien, Indah; Widyanto, Muhammad Rahmat; Endah, Sukmawati Nur; Basaruddin, Tarzan
Makara Journal of Technology Vol. 14, No. 1
Publisher : UI Scholars Hub

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

This paper proposes human pose interpretation using particle filter (PF) with Binary Gaussian Weighting and support vector machine (SVM). In the proposed system, particle filter is used to track a human object, then this human object is skeletonized using thinning algorithm and classified using SVM. The classification is to identify human pose, whether it is normal or abnormal behavior. Here particle filter is modified through weight calculation using Gaussian distribution to reduce the computational time. The modified particle filter consists of four main phases. First, particles are generated to predict target’s location. Second, the weight of certain particles is calculated and these particles are used to build Gaussian distribution. Third, the weight of all particles is calculated based on Gaussian distribution. Fourth, particles are updated based on each weight. The modified particle filter could reduce computational time of object tracking since this method does not have to calculate particle’s weight one by one. To calculate weight, the proposed method builds Gaussian distribution and calculates particle’s weight using this distribution. Through an experiment using video data taken in front of the cashier of a convenience store, the proposed method reduced computational time in tracking process until 68.34% in average compared to the conventional one, meanwhile the accuracy of tracking with this new method is comparable with particle filter method, i.e. 90.3%. Combining particle filter with binary Gaussian weighting and support vector machine is promising for advanced early crime scene investigation.

PENYISIPAN TANDA AIR PADA CITRA DIJITAL BERBASIS DEKOMPOSISI NILAI SINGULIR (DNS) Basaruddin, T; Cahyana, Cahyana
Makara Journal of Science Vol. 10, No. 2
Publisher : UI Scholars Hub

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

Imperceptible of Watermarking in Digital Image Based Singular Value Decomposition. Watermarking is a commonly used technique to protect digital image from unintended used such as counterfeiting. This paper will address one of the techniques to embed a watermark to digital image which is based on the singular value decomposition. The primary target to be achieved by a good watermarking technique is that the watermarked image is imperceptible and that the inserted image can still be perfectly retrieved even though various transformations are done to the watermarked image. Our works show that the SVD-based watermarking demonstrates both imperceptibility as well as robustness of the watermarking scheme as indicated by significantly high value of correlation between the inserted and retrieved logo after some transformation such as PSNR, RML and Compression.

Co-Authors Cahyana . Cahyana, Cahyana Della Maulidiya Della Maulidiya Dewi Yanti Liliana Elly Matul Imah Ionia Veritawati Ito Wasito Martin Novela Muhammad Rahmat Widyanto Muhammad Rahmat Widyanto, Muhammad Rahmat Rahmatri Mardiko Siradjuddin, Indah Agustien Sukmawati Endah Sukmawati Endah, Sukmawati Sukmawati Nur Endah

Title

Found 6 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 6 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 6 Documents
Search