62 research outputs found
Kualitas sekolah menengah di Indonesia : potret sesaat dari seleksi penerimaa mahasiswa baru 2005
No full text
Effect of mean stress and amplitude stress on mechanical stress-strain response of chopped strand mat (CSM) composite under cyclic load
No full textDataset Suara dan Teks Berbahasa Indonesia Pada Rekaman Podcast dan Talk show
Get PDFSalah 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
KLASIFIKASI BEAT ARITMIA PADA SINYAL EKG MENGGUNAKAN FUZZY WAVELET LEARNING VECTOR QUANTIZATION
Get PDFPengenalan 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
Imperceptible of Watermarking in Digital Image Based Singular Value Decomposition
No full textWatermarking 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
PENYISIPAN TANDA AIR PADA CITRA DIJITAL BERBASIS DEKOMPOSISI NILAI SINGULIR (DNS)
Get PDFImperceptible 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
PENYISIPAN TANDA AIR PADA CITRA DIJITAL BERBASIS DEKOMPOSISI NILAI SINGULIR (DNS)
No full textImperceptible 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. Keywords: watermarking, singular value, digital image, imperceptibility, robustne
- …
