Claim Missing Document
Check
Articles

Found 37 Documents
Search

Detection of the Breast Cancer from Thermal Infrared Images Dwi Nurhayati, Oky; Sri Widodo, Thomas; Susanto, Adhi
Jurnal Sistem Komputer Vol 1, No 2 (2011)
Publisher : Jurnal Sistem Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jsk.v1i2.14

Abstract

Thermography can be used as part of an earlydetection tool which gives women of all ages the opportunityto increase their chances of detecting breast diseases at avery early stage. Breast thermography is a noninvasiveprognostic procedure which can predict a tumor growth ratein breast cancer patients. The objective of this research is toacquire the potential of the statistical characteristics of thebreast thermogram images for the detection of the breastcancer.For this research we use thermal data images fromSardjito hospital at Yogyakarta, from normal and abnormalbreast (detected breast cancer). Firstly, download the breastimage thermograms from the InsideIR software of FlukeTi20 and save them as the inputs to our image processingprogram. Then adjust the format of the images, convert tograyscale images, and crop them to separate the suspectedobjects from the background. Finally we tabulated thestatistical characteristics of the objects which are the means,standard deviations, and entropy to reveal the abnormalitiesof breast thermograms.The results show that the method are promising todetect the abnormality on the breast thermogram images.The normal breast thermograms have minimum entropieswhich differ from those abnormal thermograms in the earlystage of breast cancer and thesignificantly from the moreadvanced of breast cancer.
Sistem Pengenalan Iris Mata Berdasar Tekstur Menggunakan Ekstraksi Ciri Energi pada Alihragam Wavelet Haar Isnanto, R. Rizal; Santoso, Imam; Dwi Prihartono, Teguh; Sri Widodo, Thomas; Suhardjo, Suhardjo; Susanto, Adhi
Jurnal Sistem Komputer Vol 2, No 1 (2012)
Publisher : Jurnal Sistem Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/jsk.v2i1.28

Abstract

Human iris has a very unique pattern which is different for each person so it is possible to use it as a basic of biometric recognition. To identify texture in an image, texture analysis method can be used. There is some texture analysis method, one of them is wavelet that extract the feature of image based on energy. The texture analysis using energy features which are in the wavelet transform. Based on that reason, in this research made a simulation to identified eyes iris based on Haar wavelet transform. First, the image of iris is segmented from eye image then enhanced with histogram equalization. The method used to extract the feature is Haar wavelet transform. The features obtained is energy value. The next step is recognition using normalized Euclidean distance. Four experiments are done in the research, those are influence of number of sample in database, influence of Haar wavelet transform level, influence of different input image format and testing on eye images which are not in database. As the result, the highest accuration is achieved using Haar wavelet transform level 4 with two samples iris image saved is 85,58%. The lowest accuration is achieved using Haar wavelet transform level 1 with one sample iris image saved is 65,27%. Then, from the test result for the influence of different input image format, the .bmp input image format is better than .jpg input image format. Whereas, from the test result for eye images which are not in database with threshold 2,3653, the recognition level is 81,48%Permalink: http://jsiskom.undip.ac.id/index.php/jsk/article/view/28
STUDI KOMPARASI ALGORITMA HIERARCHICAL DAN PARTITIONAL UNTUK CLUSTERING DOKUMEN TEKS BERBAHASA INDONESIA Hamzah, Amir; Susanto, Adhi; Soesianto, F; Istiyanto, Jazi Eko
JURNAL TEKNOLOGI TECHNOSCIENTIA Academia Ista Vol 12 No 01 Agustus 2007
Publisher : Lembaga Penelitian & Pengabdian Kepada Masyarakat (LPPM), IST AKPRIND Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34151/technoscientia.v0i0.1972

Abstract

Text document clustering is a technique which has been intensively studied be-cause of its important role in the text-mining and information retrieval. In the vector spa-ce model it is typically known two main clustering approaches,i.e. hierachical algorithm and partitional algorithm. The hierarchical algorithm produces deterministic result known as a dendogram, but its weakness is high complexity in time and memory. On the other hand, partitiaonal algorithm has linear time and memory complexity although its clustering result is not independent from its initial cluster. The aim of this research was to study experimentally to compare the perfor-mances of several techniques of hierarchical algorithms and partitional algorithms applied to text documents written in Bahasa Indonesia. The five similarity techniques i.e. UPGM-A, CSI, IST,SL and CL were chosen from hierarchical, whereas K-Means, Bisecting K-Mean and Buckshot are chosen for partitonal ones. The documents were collected from 200 to 800 Indonesian news text that have been categorized manually and used to test these algorithms using F-measure for clustering performance. This value was derived from Recall and Precision and can be used to measure the performance of the algorithms to correctly classify the collections. Results showed that Bisecting K-Mean as a variant of partitional algorithm performed comparably with the two best hierarchical techniques,i.e. UPGMA and CL but with much lower time complexity.
Students' Mathematical Critical Thinking Ability with Project Based Learning (PjBL) Model Based on Local Culture Susanto, Adhi; Zaenuri, Zaenuri; Rachmani Dewi, Nuriana
Journal of Primary Education Vol 10 No 4 (2021): December 2021
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/jpe.v10i4.55932

Abstract

Students' mathematical critical thinking skills are still low, this is because the learning is still monotonous. Therefore, it is necessary to implement student-based learning. The purpose of this study was to analyze the effectiveness of the local culture-based Project Based Learning model in improving the critical thinking skills of class VIII students. This study uses a quantitative research approach. This design involved two groups of subjects, the experimental class was given treatment in the form of giving a Project Based Learning model with ethnomathematical nuances based on local wisdom, while the control class was taught using conventional learning. The sample in this study were 30 students in the experimental class and 30 students in the control class. The results of this study are the effectiveness of learning using the PjBL model with an ethnomathematical nuance based on local culture in improving the critical thinking skills of eighth grade students. Value of Sig. in the experimental class, the results of 0.05 it means that H0 is rejected, in other words that the average posttest result of students' critical thinking skills classically has reached the minimum criteria completeness so that it can be said to be effective. The mean of the experimental class showed a result of 82.50, while the control class showed a result of 71.09. This shows that the average critical thinking ability of students in the experimental class is higher than the average critical thinking ability of students in the control class. The conclusion of this research is that the Project Based Learning (PjBL) Model Based on Local Culture is effective in improving the critical thinking skills of eighth grade students.
TRANSFORM FOURIER CEPAT MATEMATIS UNTUK MENGANALISIS SPEKTRUM FREKUENSI LINIER SINYAL TUTUR Salman Abd. Cadum; Prayoto Prayoto; Adhi Susanto; Kirbani Sri Brotopuspito
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 2, No 1: April 2004
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v2i1.1752

Abstract

Spektrum menggunakan transform Fourier cepat FFT matematis dimaksudkan untuk melakukan analisis frekuensi. Resolusi frekuensi spektrum tergantung nilai-nilai cuplikan sinyal audio/tutur digital, yang terbagi dalam sejumlah poin data FFT, yaitu semakin besar jumlah poin data, semakin baik resolusi frekuensi spektrum. Skala frekuensi pada spektrum ini menggunakan skala frekuensi linier yang menyebarkan komponen frekuensi secara merata pada tampilan spektrum secara keseluruhan. Penanganan terhadap berkas gelombang tutur, atau masukan audio, dapat berjalan lebih cepat ketika menggunakan skala frekuensi linier daripada menggunakan skala frekuensi logaritmis. Penerapan fungsi berbagai window terhadap data dapat membantu mengurangi efek kebocoran yang terjadi pada spektrum frekuensi.
ANALISIS SPEKTRUM FREKUENSI NON-LINEAR SINYAL TUTUR DENGAN ALIH RAGAM FOURIER CEPAT Salman Abd. Cadum; Prayoto Prayoto; Adhi Susanto; Kirbani Sri Brotopuspito
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 5, No 1: April 2007
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v5i1.1336

Abstract

            Pada penelitian ini akan diteliti analisis spektrum frekuensi non-linear sinyal tutur dengan menggunakan alih ragam Fourier cepat (Fast Fourier Transform, FFT). Hasil penelitian menunjukkan bahwa: suatu skala logaritmis akan memperluas daerah frekuensi yang rendah dari spektrum dan mempersempit daerah frekuensi yang tinggi pada tampilan, dibutuhkan suatu FFT yang jauh lebih besar guna mendapatkan resolusi frekuensi yang sangat tinggi pada frekuensi yang rendah, penerapan fungsi berbagai window terhadap data dapat membantu mengurangi efek kebocoran yang terjadi pada spektrum frekuensi, metode ini berjalan lebih cepat jika jumlah point data merupakan kelipatan dua (128, 256, 1024, 2048, atau 4096, dan seterusnya) dan memilih suatu resolusi frekuensi yang tepat serta resolusi waktu yang sesuai menjadi suatu kesesuaian antara kebutuhan untuk mengamati detail frekuensi yang baik dalam spektrum dengan kebutuhan untuk mengamati variasi waktu yang cepat dalam spektrum.
An Explicit Wavelet-Based Finite Difference Scheme for Solving One-Dimensional Heat Equation Mahmmod Aziz Muhammed; Adhi Susanto; F. Soesianto F. Soesianto; Soetrisno Soetrisno
Teknoin Vol. 10 No. 1 (2005)
Publisher : Faculty of Industrial Technology Universitas Islam Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20885/.v10i1.695

Abstract

Metode finite difference eksplisit adalah metode yang mudah diprogram dibandingkan metode finite difference implicit atau metode-metode numerik lainnya. Selain itu, metode eksplisit itu dapat digunakan untuk menyelesaikan persamaan panas (heat equation) linear dalam satu dimensi. Akan tetapi, metode eksplisit itu mempunyai sebuah kekurangan yaitu keterbatasan stabilitas dari penyelesaian numerik adalah sangat ketat. Oleh sebab itu, metode eksplisit itu tidak lagi termasuk daftar metode-metode numerik yang handal yang dapat digunakan untuk menyelesaikan persamaan-persamaan diferensial parsial.Oleh karena itu, maka diusulkan untuk menggunakan analisis wavelet Haar di dalam skema numerik dari metode eksiplisit untuk mengatasi kekurangan metode itu, yaitu keterbatasan stabilitas, dengan menjaga diskretisasi dari metode eksplisit agar tidak berubah. Kekurangan dari metode finite difference eksiplisit itu sudah dapat diatasi secara signifikan oleh analisis Haar wavelet yang tidak mempengaruhi logika metode asli yatiu metode eksiplisit. Kata kunci: metode finite difference eksplisit, persamaan panas
Identifikasi Citra Massa Kistik Berdasar Fitur Gray-Level Co-Occurrence Matrix Hari Wibawanto; Adhi Susanto; Thomas Sri Widodo; S. Maesadji Tjokronegoro
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2008
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

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

Abstract

We have studied the effectiveness of using texture features derived from gray-level co-occurrence matrix(GLCM) matrices for classification of cystic mass and non-cystic mass in ultra sonograms. Twenty-three (23)region of interest (ROIs) containing cystic masses and fifty-five (55) non-cystic masses were extracted from ultrasonogram for this study. For each ROI of 50x50 pixels, seven features (energy, inertia, entropy, homogeneity,maximum probability, inverse difference moment, and correlation) were calculated. The importance of eachfeature in distinguishing cystic masses from non-cystic masses was determined by linear discriminant analysiswith SPSS version 11.5 program. As a result of a study, it was found that all seven features can distinguishingcystic masses from non-cystic masses with an accuracy about 91 %-92.3%. Those levels of accuracy also foundwhen two features (energy and inverse difference moment) was excluded from analysis. The result demonstratethe feasibility of using texture features based on GLCM for distinguishing cystic masses from non-cystic massesof ultra sonogram .Keywords: Gray-level Co-occurrence Matrix Ultrasonografi, massa kistik, fitur tekstur, analisis tekstur, analisisdiskriminan
Identifikasi Citra Massa Kistik Berdasar Fitur Graylevel Co Occurrence Matrix Hari Wibawanto; Adhi Susanto; Thomas Sri Widodo; S. Maesadji Tjokronegoro
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2009
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

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

Abstract

We have studied the effectiveness of using texture features derived from gray-level co-occurrence matrix(GLCM) matrices for classification of cystic mass and non-cystic mass in ultra sonograms. Twenty-three (23)region of interest (ROIs) containing cystic masses and fifty-five (55) non-cystic masses were extracted from ultrasonogram for this study. For each ROI of 50x50 pixels, seven features (energy, inertia, entropy, homogeneity,maximum probability, inverse difference moment, and correlation) were calculated. The importance of eachfeature in distinguishing cystic masses from non-cystic masses was determined by linear discriminant analysiswith SPSS version 11.5 program. As a result of a study, it was found that all seven features can distinguishingcystic masses from non-cystic masses with an accuracy about 91 %-92.3%. Those levels of accuracy also foundwhen two features (energy and inverse difference moment) was excluded from analysis. The result demonstratethe feasibility of using texture features based on GLCM for distinguishing cystic masses from non-cystic massesof ultra sonogram .Keywords: Gray-level Co-occurrence Matrix Ultrasonografi, massa kistik, fitur tekstur, analisis tekstur, analisisdiskriminan
Perbandingan Feature Kata dan Frasa dalam Kinerja Clustering Dokumen Teks Berbahasa Indonesia Amir Hamzah; Adhi Susanto; F. Soesianto; Jazi Eko Istyanto
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2007
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

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

Abstract

Text document clustering has been intensively studied because of its important role in text-mining andinformation retrieval. High dimensionality problem caused by high number of words is always happened inword-based clustering technique using vector space model. Although extracting words in the preprocessingphase is simple, the collection itself is not only can be viewed as a set of words but also a set of partly more thanone word phrase. Separating a phrase into its parts can eliminate the actual meaning of phrase. Therefore inorder to maintain the context of words a phrase must be maintain as a phrase. It is assumed that by addingphrases to words as features in clustering will improve the performance. This paper will study the comparison ofword-base and phrase-based clustering. Three clustering models was chosen i.e. hierachical, partional andhybrid model. Four similarity technique i.e. GroupAverage, CompleteLink, SingleLink, and ClusterCenter wastried for hierarchical, K-Means and Bisecting K-Mean for partitonal and buckshot for hybrid. Documentcollections from 200-800 news text that has been categorized manually was used to test these algorithms byusing F-measure as criteria of clustering performance. This value was derived from Recall and Precision andcan be used to measure the performance of the algorithms to correctly classify the collections. Results show thatby adding phrases or simply word pair, although it’s still not statistically significant, it slightly improves theperformance of clustering.Keywords: word-base document clustering, phraset-based document clustering, clustering performance