Articles
<![CDATA[PENERAPAN SISTEM DATA MINING UNTUK DIAGNOSIS PENYAKIT KANKER PAYUDARA MENGGUNAKAN CLASSIFICATION BASED ON ASSOCIATION ALGORITHM ]]>
<![CDATA[Herwanto, Herwanto]]>;
<![CDATA[Arymurthy, Aniati Murni]]>
<![CDATA[ JUTI: Jurnal Ilmiah Teknologi Informasi Vol 8, No 2, Juli 2010 ]]>
Publisher : <![CDATA[Department of Informatics, Institut Teknologi Sepuluh Nopember ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (19168.544 KB)
|
DOI: 10.12962/j24068535.v8i2.a312
<![CDATA[Aplikasi system data mining untuk mengidentifikasi atribut-atribut penting yang berguna membantu pengambilan keputusan dari basis data rumah sakit akan dibahas dalam paper ini. Data-data medis pasien yang beresiko menderita penyakit kanker payudara dimasukkan ke dalam data warehouse. Metodologi model klasifikasi didasarkan pada tiga tahapan, yaitu a) menangani data yang tidak lengkap melalui ekstraksi, b) merubah data yang bernilai kontinyu menjadi data yang bernilai diskrit serta c) rule mining dan klasifikasi. Algoritma yang digunakan untuk proses data mining adalah Classification Based on Predictive Association Rule (CPAR). Pada tahapan diskritisasi, terdapat masalah yang dikenal dengan istilah "sharp boundary". Paper ini mengusulkan proses optimalisasi menggunakan soft discretization, di mana fuzzy logic digunakan untuk mempartisi data. Ada 2.767 pasien yang terpilih, masing-masing diambil 8 atribut: sex, umur dan hasil pemeriksaan laboratorium yaitu Hemoglobin (HB), Lekosit (Leko), Trombosit (Tromb), Hemotokrit (HCT), Red blood cell distribution width (RDW) dan RDW-SD. Tingkat akurasi maksimum untuk positif kanker payudara adalah 67% dan negatif kanker payudara 97%.]]>
<![CDATA[ Classification of LiDAR Images Fused With Aerial Optical Images Using Ensemble Classifier AdaBoost.MH and Post-processing BFS ]]>
<![CDATA[Prasvita, Desta Sandya]]>;
<![CDATA[Arymurthy, Aniati Murni]]>
<![CDATA[ International Journal of Technology And Business Vol 1 No 1 (2017): IJTB|International Journal of Technology And Business ]]>
Publisher : <![CDATA[LPPM of STIMIK ESQ ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[The objective of this research is to propose a method in order to increase classification performance of LiDAR images fused with aerial optical images. Classification method in use is popular multiclass ensemble classifier method, AdaBoost.MH. The Weak classifier in use of AdaBoost.MH is Hamming Trees. Then, the post-processing method is conducted to remove the noise with Breadth First Search (BFS) algorithm. Post-processing increase the accuracy to 0.96% and able to reduce the noise of classification result. This research is able to increase the accuracy on previous research by 94.96%]]>
<![CDATA[ Classification of LiDAR Images Fused With Aerial Optical Images Using Ensemble Classifier AdaBoost.MH and Post-processing BFS ]]>
<![CDATA[Prasvita, Desta Sandya]]>;
<![CDATA[Arymurthy, Aniati Murni]]>
<![CDATA[ IJTB (International Journal of Technology And Business) Vol 1 No 1 (2017): IJTB (International Journal Of Technology And Business) ]]>
Publisher : <![CDATA[LPPM of STIMIK ESQ ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[The objective of this research is to propose a method in order to increase classification performance of LiDAR images fused with aerial optical images. Classification method in use is popular multiclass ensemble classifier method, AdaBoost.MH. The Weak classifier in use of AdaBoost.MH is Hamming Trees. Then, the post-processing method is conducted to remove the noise with Breadth First Search (BFS) algorithm. Post-processing increase the accuracy to 0.96% and able to reduce the noise of classification result. This research is able to increase the accuracy on previous research by 94.96%]]>
<![CDATA[CIELab Color Moments: Alternative Descriptors for LANDSAT Images Classification System ]]>
<![CDATA[Kusumaningrum, Retno]]>;
<![CDATA[Manurung, Hisar Maruli]]>;
<![CDATA[Arymurthy, Aniati Murni]]>
<![CDATA[ INKOM Journal Vol 8, No 2 (2014) ]]>
Publisher : <![CDATA[Pusat Penelitian Informatika - LIPI ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (251.469 KB)
|
DOI: 10.14203/j.inkom.409
<![CDATA[This study compares the image classification system based on normalized difference vegetation index (NDVI) and Latent Dirichlet Allocation (LDA) using CIELab color moments as image descriptors. Â It was implemented for LANDSAT images classification by evaluating the accuracy values of classification systems. The aim of this study is to evaluate whether the CIELab color moments can be used as an alternatif descriptor replacing NDVI when it is implemented using LDA-based classification model. Â The result shows that the LDA-based image classification system using CIELab color moments provides better performance accuracy than the NDVI-based image classification system, i.e 87.43% and 86.25% for LDA-based and NDVI-based respectively. Â Therefore, we conclude that the CIELab color moments which are implemented under the LDA-based image classification system can be assigned as alternative image descriptors for the remote sensing image classification systems with the limited data availability, especially when the data only available in true color composite images.]]>
<![CDATA[Combining Deep Belief Networks and Bidirectional Long Short-Term Memory ]]>
<![CDATA[Nurma Yulita, Intan]]>;
<![CDATA[Ivan Fanany, Mohamad]]>;
<![CDATA[Murni Arymurthy, Aniati]]>
<![CDATA[ Proceeding of the Electrical Engineering Computer Science and Informatics Vol 4: EECSI 2017 ]]>
Publisher : <![CDATA[IAES Indonesia Section ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (307.775 KB)
|
DOI: 10.11591/eecsi.v4.1051
<![CDATA[This paper proposes a new combination of Deep Belief Networks (DBN) and Bidirectional Long Short-Term Memory (Bi-LSTM) for Sleep Stage Classification. Tests were performed using sleep stages of 25 patients with sleep disorders. The recording comes from electroencephalography (EEG), electromyography (EMG), and electrooculography (EOG) represented in signal form. All three of these signals processed and extracted to produce 28 features. The next stage, DBN Bi-LSTM is applied. The analysis of this combination compared with the DBN, DBN HMM (Hidden Markov Models), and Bi-LSTM. The results obtained that DBN Bi-LSTM is the best based on precision, recall, and F1 score.]]>
<![CDATA[Face Recognition Based on Symmetrical Half-Join Method using Stereo Vision Camera ]]>
<![CDATA[Edy Winarno]]>;
<![CDATA[Agus Harjoko]]>;
<![CDATA[Aniati Murni Arymurthy]]>;
<![CDATA[Edi Winarko]]>
<![CDATA[ International Journal of Electrical and Computer Engineering (IJECE) Vol 6, No 6: December 2016 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (435.818 KB)
|
DOI: 10.11591/ijece.v6i6.pp2818-2827
<![CDATA[The main problem in face recognition system based on half-face pattern is how to anticipate poses and illuminance variations to improve recognition rate. To solve this problem, we can use two lenses on stereo vision camera in face recognition system. Stereo vision camera has left and right lenses that can be used to produce a 2D image of each lens. Stereo vision camera in face recognition has capability to produce two of 2D face images with a different angle. Both angle of the face image will produce a detailed image of the face and better lighting levels on each of the left and right lenses. In this study, we proposed a face recognition technique, using 2 lens on a stereo vision camera namely symmetrical half-join. Symmetrical half-join is a method of normalizing the image of the face detection on each of the left and right lenses in stereo vision camera, then cropping and merging at each image. Tests on face recognition rate based on the variety of poses and variations in illumination shows that the symmetrical half-join method is able to provide a high accuracy of face recognition and can anticipate variations in given pose and illumination variations. The proposed model is able to produce 86% -97% recognition rate on a variety of poses and variations in angles between 0 °- 22.5 °. The variation of illuminance measured using a lux meter can result in 90% -100% recognition rate for the category of at least dim lighting levels (above 10 lux).]]>
<![CDATA[A non-negative matrix factorization based clustering to identify potential tuna fishing zones ]]>
<![CDATA[Devi Fitrianah]]>;
<![CDATA[Hisyam Fahmi]]>;
<![CDATA[Achmad Nizar Hidayanto]]>;
<![CDATA[Pang Ning-Tan]]>;
<![CDATA[Aniati Murni Arymurthy]]>
<![CDATA[ International Journal of Electrical and Computer Engineering (IJECE) Vol 11, No 6: December 2021 ]]>
Publisher : <![CDATA[Institute of Advanced Engineering and Science ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijece.v11i6.pp5458-5466
<![CDATA[Many nonnegative matrix factorization based clusterings are employed in discovering pattern and knowledge. Considering the sparseness nature of our data set about the daily tuna fishing data, we attempted to utilize a clustering approach, which is based on non-negative matrix factorization. Adding sparseness constraint and assigning good initial value in the modified NMF method, a proposed algorithm Direct-NMFSC yielded better result cluster compared to other methods which are also utilizing sparse constraint to their approaches, SNMF and NMFSC. The result of this study shows that Direct-NMFSC has 5.376 times of iteration number less than NMFSC in average with 531.97 as the CH index result. The determination of potential fishing zones is one of the essential efforts in the potential fishing zone mapping system for tuna fishing. By means of this novel data-driven study to construct the information and to identify the potential tuna fishing zones is done. We also showed that utilizing the Direct-NMFSC can spot and identify the potential tuna fishing zones presented in red cluster that covers both the spatial and temporal information.]]>
<![CDATA[EKSTRAKSI FITUR FRAKTAL DAN MORFOLOGI SINYAL ELEKTROKARDIOGRAM DAN PEMANFAATANNYA DALAM KLASIFIKASI DEEP SLEEP ]]>
<![CDATA[Aniati Murni Arymurthy]]>;
<![CDATA[Edward Citrahadi]]>;
<![CDATA[Tieta Antaresti]]>
<![CDATA[ Jurnal Ilmu Komputer dan Informasi Vol 4, No 2 (2011): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Information) ]]>
Publisher : <![CDATA[Faculty of Computer Science - Universitas Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (821.551 KB)
|
DOI: 10.21609/jiki.v4i2.169
<![CDATA[Detak jantung manusia dapat memberikan informasi yang berguna tentang aktivitas yang terjadi di dalam tubuh. Salah satu informasi yang dapat diperoleh dari rekaman detak jantung atau elektrokardiogram adalah tingkat keterlelapan tidur seseorang (sleep stages). Dari sinyal elektrokardiogram seseorang, tingkat keterlelapan tidurnya dapat dikenali dengan terlebih dahulu mengekstrak fitur yang merepresentasikan sinyal elektrokardiogram tersebut secara keseluruhan. Ekstraksi dilakukan agar dimensi data dapat tereduksi sehingga proses klasifikasi dapat lebih mudah dilakukan. Penelitian ini melakukan ekstraksi fitur fraktal dan morfologi dari sinyal elektrokardiogram yang diperoleh dari PhysioNet. Sebelum melakukan ekstraksi fitur morfologi dari sinyal elektrokardiogram, terlebih dahulu dilakukan “Wavelet Denoising†untuk menghilangkan noise yang terdapat pada sinyal. Human heart rate can provide useful information about the activities that occur in the body. One of information which may be obtained from recording the heart rate or electrocardiogram is commonly called a person's level of deep sleep (sleep stages). From a person's electrocardiogram signal, the level of deep sleep recognizable by extracting features that represent the electrocardiogram signal as a whole. Extraction is done so that the dimension of the data can be reduced so that the classification process can be more easily done. This study aims to extract fractal features and morphology of the electrocardiogram signal obtained from PhysioNet. Prior to the extraction of morphological features of the electrocardiogram signal, first performed “Wavelet Denoising†to remove the noise contained in the signal.]]>
<![CDATA[Batik Classification using Deep Convolutional Network Transfer Learning ]]>
<![CDATA[Yohanes Gultom]]>;
<![CDATA[Aniati Murni Arymurthy]]>;
<![CDATA[Rian Josua Masikome]]>
<![CDATA[ Jurnal Ilmu Komputer dan Informasi Vol 11, No 2 (2018): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Information ]]>
Publisher : <![CDATA[Faculty of Computer Science - Universitas Indonesia ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (504.497 KB)
|
DOI: 10.21609/jiki.v11i2.507
<![CDATA[Batik fabric is one of the most profound cultural heritage in Indonesia. Hence, continuous research on understanding it is necessary to preserve it. Despite of being one of the most common research task, Batik’s pattern automatic classification still requires some improvement especially in regards to invariance dilemma. Convolutional neural network (ConvNet) is one of deep learning architecture which able to learn data representation by combining local receptive inputs, weight sharing and convolutions in order to solve invariance dilemma in image classification. Using dataset of 2,092 Batik patches (5 classes), the experiments show that the proposed model, which used deep ConvNet VGG16 as feature extractor (transfer learning), achieves slightly better average of 89 ± 7% accuracy than SIFT and SURF-based that achieve 88 ± 10% and 88 ± 8% respectively. Despite of that, SIFT reaches around 5% better accuracy in rotated and scaled dataset.]]>
<![CDATA[Keyblock for Content-based Image Retrieval (Vector quantization Comparison In Piercing Domain Image) ]]>
<![CDATA[I Gusti Agung Gede Arya Kadyanan]]>;
<![CDATA[Wahyudi -]]>;
<![CDATA[Aniati Murni Arymurthy]]>
<![CDATA[ Jurnal Ilmu Komputer Vol. 5, No. 1 April 2012 ]]>
Publisher : <![CDATA[Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1156.45 KB)
<![CDATA[Keyblock is a generalization of the text-based information retrieval technology in the image domain. The main purpose of this framework is to find the codebook of a given size from a set of training image blocks. This main purpose can be achieved with any Vector quantization algorithm. This paper is an answer to the questions: “Can we use keyblock for piercing pattern?” Which one is the best algorithm between GLA or PNNA for VQ ?” The paper begins by describing some basic theory of Texture Feature, Keyblock-based, Vector quantization, Generalized Lloyd Algorithm (GLA) and Pairwise Nearest Neighbour Algorithm (PNNA). Next, it summarizes the implementation of both algorithm in keyblock framework for piercing pattern. Finally, it describes the experimental result of this research.]]>
