Oky Dwi Nurhayati
Program Studi Sistem Komputer, Fakultas Teknik, Universitas Diponegoro

Published : 59 Documents
Articles

Ektraksi Ciri Citra Termogram Payudara Berbasis Dimensi Fraktal Nurhayati, Oky Dwi; Widodo, Thomas Sri; Susanto, Adhi; Tjokronagoro, Maesadji
Majalah Forum Teknik UGM Vol 3, No 2 (2010)
Publisher : Majalah Forum Teknik UGM

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (71.575 KB)

Abstract

AbstractThe primary purpose of infrared thermography is the locating of thermal differences and anomalies.  Infrared thermography can  detect  numerous  conditions  in  which  an  anomaly is characterized by an increase or decrease in surface temperature. In this research, we specifically applied calculation of fractal dimension method to a total of20 thermograms of normal breasts as well as of those in advanced breast cancer. In addition standard  image  pre-processing  were  also  used  to  enhance  the  detection capabilitity.  Severalmethods in image processing which are pre-processing with canny edge detection, thresholding, calculation of fractal dimension use box-counting and Hausdorff dimension.The results of this research are shown that Hausdorff dimension in the normal thermogramshave range value 0,4 – 0,95 smaller than the advanced thermograms which have value more than  1,26.Finally  this  results  show  that  the  difference  of  fractal dimension  can  be  used  todistinguish between normal and advanced thermograms.Keywords: canny edge detection, thresholding, fractal dimension, box-counting, Hausdorff
PENGGUNAAN APLIKASI BANTUAN (SAKPA) DALAM MEMPERMUDAH PEMBUATAN LAPORAN KEUANGAN nurhayati, oky dwi; Ningrum, Alifvia Arvi
Jurnal Sistem Komputer Vol 2, No 2 (2012)
Publisher : Jurnal Sistem Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | http://jsiskom.undip.ac.id/index.php/jsk/article/view/39

Abstract

Financial treasure at each agency is required to prepare financial statements which will be reconciled with the KPPN (Office of the State Treasury). The Treasurer shall make an accurate and in accordance with the provisions, it is necessary to review and analysis prior to the report. The reconciliation process must be manually where satker come back and forth to merekon KPPN same data that is not very efficient for satker less far away. So KPPN has done groundbreaking steps to overcome that is through the internet and applications prarekonsiliasi help the SAKPA. SAKPA application is an application used to process data in the User Authorization Budget Accounting System (SAKPA). SAKPA application developed by the Directorate of Treasury Systems as one of the Directorate under the auspices of the Directorate General of Treasury application was developed with the aim Provides ease of the Government Accounting Standard Reporting on Budget User Authorization unit.
Peningkatan Citra Termogram untuk Klasifikasi Kanker Payudara berbasis Adaptive Neuro Fuzzy Inference System (ANFIS) Nurhayati, Oky Dwi; Widodo, Thomas Sri; Susanto, Adhi; T, Maesadji
Electrician Vol 4, No 1 (2010)
Publisher : Department of Electrical Engineering, Faculty of Engineering, Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (211.929 KB)

Abstract

The application of pattern recognition is related to bioinformatics of medicine, image pattern recognition of illness or analysis of disease. The aim of this study is to measure the accuracy of thermogram images using Adaptive Neuro Fuzzy Inference System (ANFIS) method with and without image processing. Image processing has several steps technique. First step is image pre-processing with wiener filter, histogram equalization, and region growing methods. The second step of image processing is statistical feature extraction. Several values extracted from thermograms. The last step is classification by ANFIS method. This study uses 60 breast thermogram samples with Fluke Ti20 Thermal Camera as acquisition. These samples divided into three classes that are normal thermogram, early breast cancer thermogram, and advanced breast cancer thermogram. From this research that has been done can be proved that ANFIS method without image processing giving an error value 0,6395 in the influence range 0.5 and decreased error value 0,4199 with image processing method in the same influence range.
Analisis Regresi dan Analisis Diskriminan untuk Mengukur Tingkat Akurasi Feature Citra Termogram Nurhayati, Oky Dwi
Electrician Vol 8, No 2 (2014)
Publisher : Department of Electrical Engineering, Faculty of Engineering, Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (218.845 KB)

Abstract

Intisari — Analisis diskriminan adalah analisis multivariat yang diterapkan untuk memodelkan hubungan antara satu variabel respon yang bersifat kategori dengan satu atau lebih variabel prediktor yang bersifat kuantitatif. Sedangkan analisis regresi bertujuan untuk membentuk sebuah fungsi yang dapat menjelaskan hubungan dua variabel, yaitu variabel penjelas/prediktor (x) dan variabel respon (y). Banyak aplikasi pada bidang kedokteran atau industri yang berhubungan dengan data mining salah satunya untuk pengenalan pola pada citra termogram. Tujuan dari penelitian ini adalah membandingkan teknik analisis diskriminan atau linear discriminant analysis (LDA) dan analisis regresi pada tingkat akurasi pengenalan pola citra termogram. Penelitian ini menggunakan sampel citra digital termogram payudara yang diambil dari kamera Fluke Ti20. Jumlah sampel yang digunakan adalah 60 citra termogram yang di bagi masing-masing ke dalam tiga kelas yaitu kelas normal, kelas kanker payudara dini, dan kelas payudara lanjut. Dari penelitian yang telah dilakukan dapat dibuktikan bahwa analisis diskriminan dengan 2 feature (ciri), 3 ciri, dan 5 ciri pada citra termogram memberikan tingkat akurasi 81,7 %. Sedangkan analisis diskriminan dengan 4 ciri pada citra termogram memberikan tingkat akurasi yang paling tinggi yaitu 83,33 %. Kata kunci — termogram, multivariat, kovarian, ciri, analisis diskriminan Abstract — Discriminant analysis is a multivariate analysis applied to model the relationship between the response variable is the category with one or more predictor variables that are quantitative. While regression analysis aims to establish a function that can explain the relationship between two variables, namely the explanatory variables / predictors (x) and the response variable (y). Many applications in the medical field or industry related to one of data mining for pattern recognition in the thermogram image. The aim of this study is to prove the technique of linear discriminant analysis  (LDA) and regression analysis to distinguish the types of thermogram. This study used 60 samples of breast thermograms captured from camera Fluke Ti20. The samples used are images in the thermograms which each classify into three classes, namely breast normal thermogram, early breast cancer thermogram, and advanced breast cancer thermogram. The result of research, discriminant analysis with  two features, three features, and five features give 81.7% accuracy rate. While discriminant analysis with four features have the highest accuracy rate is 83.33%. Final results of the regression analysis is able to significantly separate the three types of normal, early, and advanced thermogram. Keywords —  thermogram, multivariate, covarian, feature, discriminat analysis, regression analysis
Analisis Sentimen Berbasis Ontologi di Level Kalimat untuk Mengukur Persepsi Produk Akbar, Agus Subhan; Sediyono, Eko; Nurhayati, Oky Dwi
JURNAL SISTEM INFORMASI BISNIS Vol 5, No 2 (2015): Volume 5 Nomor 2 Tahun 2015
Publisher : Magister Sistem Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1207.424 KB) | DOI: 10.21456/vol5iss2pp84-97

Abstract

The purpose of this research is to do sentiment analysis on tweets data retrieved using ontology framework and using naïve bayes classifier algorithm for classification process. This study is based on the habits of twitter users who frequently writes opinion, expression, or sentiment on a specific product, especially smartphones. These tweets can be used as a basis for sentiment analysis on a particular product. The method used in this study include the use of ontology framework for tweets retrieval that match the domain of the discussion and the use of naïve bayes classification algorithm for data classification. Classification process carried past the 3 pieces of layer classification to fine tune the final result of classification. Three layers of classification used include buzz/promo classification (classifying tweets into buzz and not-buzz tweets), subjectivity classification (classifying not-buzz tweets into subjective and objective tweets), and sentiment classification (classifying subjective tweets into positive, negative, or neutral tweets). The resulted software can classify tweets with high accuracy. This software was trained and tested with the composition of 25:75, 50:50, 75:25 from sample data and tested 10 times for each composition. Average accuracy of the system reached 84.16%, 86.15%, and 87.54% for each composition. The result showed that by employing this system, product marketing stakeholders can determine the level of user sentiment expressed in the form of tweets. The method used in this study could be developed to improve the accuracy of classification systems. Keywords: Sentence Level Sentiment Analysis; Ontology; Naïve Bayes, Classification
Penerapan Cutomer Relationship Management (CRM) Dengan Menggunakan Metode Analytic Network Process (ANP) Pada Perusahaan Ritel Nofiyati, Nofiyati; Sediyono, Eko; Nurhayati, Oky Dwi
JURNAL SISTEM INFORMASI BISNIS Vol 3, No 3 (2013): Volume 3 Nomor 3 Tahun 2013
Publisher : Magister Sistem Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (71.575 KB)

Abstract

Retail industry or retail business is a fast-growing business in the midst of global competition conditions. One strategy to attract more consumers are Customer Relationship Management (CRM). The successful implementation of CRM in the enterprise is influenced by several environmental perspectives, strategies, customers and products / services, processes, participants, infrastructure, and information technology are integrated in the framework of Work System (WS). This research was carried out by applying the method of Multiple Criteria Decision Making (MCDM) that is able to accommodate the outer and inner linkage from multiple nodes / indicators are considered, namely the Analytical Network Process (ANP) to rank the quality of implementation CRM in retail companies and strong influential node / indicator of the best retail among three alternative the consisting of Alfamart, Indomaret and Smesco mart. From the results of application ANP method, obtained the rank quality of implementation CRM in retail companies with first rank is Indomaret the value of 1.0000; and the second is Alfamart with a value 0.9575; and the third is Smesco mart with a value of 0.8034. While node / indicator strong influence on the the best retail is level of chaos, long and short term planning, customer service, system integration, appropriate skills, technical infrastructure, easily of use and accessibility of information.   Keywords: Ritel, Customer Relationship Management (CRM), Analytic Network Process (ANP), Kerangka Work System (WS).
Pendekatan Metode Pohon Keputusan Menggunakan Algoritma ID3 Untuk Sistem Informasi Pengukuran Kinerja PNS Sidette, Julce Adiana; Eko, Eko; Nurhayati, Oky Dwi
JURNAL SISTEM INFORMASI BISNIS Vol 4, No 2 (2014): Volume 4 Nomor 2 Tahun 2014
Publisher : Magister Sistem Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1049.686 KB) | DOI: 10.21456/vol4iss2pp75-86

Abstract

Decision tree method is a classification method that has been widely used for the solution of problems of classification. Decision tree classification provides a rapid and effective method. The approach has been proven decision tree method can be applied in various fields of life. Capability classification is indicated by the decision tree method is what encourages authors to use decision tree methods approach to measure the performance of civil servants. To build a decision tree induction algorithms used. In this study, the ID3 algorithm method is used to construct a decision tree. Starting with the data collecting training samples and then measuring the entropy and information gain. Information Gain value will be used as the root of a decision tree. And translates it into a decision tree classification rules. The results show that the decision tree method is used to produce classification rules into groups employee performance Good and Bad. The resulting rules are used to measure the performance of employees and classifying employees into two groups above are constructed in an information system. Information system built to assist management in making more objective assessment process.    *) Penulis korespondensi: utje_caem@yahoo.com   Keywords: ID3 Algorithm; Decision tree; Employee performance
Implementasi Adaptive Neuro Fuzzy Inference System untuk Penentuan Status Gizi Balita Baun, Hanna Mariana; Nurhayati, Oky Dwi
JURNAL SISTEM INFORMASI BISNIS Vol 3, No 2 (2013): Volume 3 Nomor 2 Tahun 2013
Publisher : Magister Sistem Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (629.092 KB) | DOI: 10.21456/vol3iss2pp116-125

Abstract

Penentuan status gizi balita dilakukan untuk mengatasi permasalahan yang sangat penting dan mendasar dari kesehatan masyarakat karena jika terjadi permasalahan status gizi pada balita, hal ini akan sangat berpengaruh pada tumbuh kembangnya dan bersifat irreversible (tidak dapat pulih). Untuk mengatasi permasalahan tersebut dibuat suatu sistem yang mempunyai kemudahan komputasi dalam pengklasifikasian status gizi. Data dianalisis dengan menggunakan metode Adaptive Neuro Fuzzy Inference System (ANFIS) dengan algoritma hibryda yang melakukan pembelajaran dengan metode Least Square Estimator dan Backpropagation dan pengklusteran dengan menggunakan fuzzy C-means. Tujuan penelitian ini adalah untuk membuat suatu sistem pengukuran dengan menggunakan metode ANFIS untuk penentuan status gizi balita sehingga pengguna dapat dengan mudah untuk melakukan pengukuran status gizi. Hasil evaluasi menunjukan bahwa hasil klasifikasi lebih akurat dibandingkan menggunakan perhitungan manual karena dengan perhitungan ANFIS, kecenderungan nilai rata-rata error dan rata-rata RMSE semakin kecil pada saat jumlah iterasi bertambah dari 200 ke 5000 dengan nilai jumlah input membership function sama dengan 9 dan nilai target error sama dengan 0,1, RMSE dan rata-rata error bernilai 0 dan akurasi total menjadi 81.15% dari 138 total data yang dilatih dan diuji. Penelitian ini menghasilkan tools program untuk penentuan status gizi balita dengan menggunakan metode ANFIS untuk mempermudah pengklasifikasian status gizi balita. Studi kasus yang dilakukan pada Rumah Sakit Umum W.Z. Yohannes Kupang.   Kata kunci : Status gizi; Metode ANFIS; Algoritma hibryda; Fuzzzy C-means
EVALUASI KINERJA ORGANISASI PUBLIK DENGAN MENGGUNAKAN PENDEKATAN BALANCED SCORECARD DAN ANALYTIC NETWORK PROCESS Tunggul, Adi Mora; Isnanto, Rizal; Nurhayati, Oky Dwi
JURNAL SISTEM INFORMASI BISNIS Vol 6, No 2 (2016): Volume 6 Nomor 2 Tahun 2016
Publisher : Magister Sistem Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (71.575 KB) | DOI: 10.21456/vol6iss2pp%p

Abstract

Balanced scorecard is a strategic business management method that links performance evaluation to vision and strategies using a multidimensional set of financial and nonfinancial performance metrics. This study examined both quantitative data for the proposed Analytic Network Process method. The purpose of this research is to build a model that combines the Balanced Scorecard approach and Analytical Network Process to assist in the performance evaluation of public organizations tax services. Balanced Scorecard concept is applied to determine the hierarchy of the financial perspective, customer perspective, internal business processes, and learning and growth perspective as well as their respective performance indicators of public organizations and then Analytical Network Process used to tolerate vagueness and ambiguity of information and built an information system that is applied to facilitate the performance evaluation process. The study provides recommendations to the management of public organizations regarding the tax service strategy to improve the performance of public organizations.
Implementasi Metode Dempster Shafer Analytic Hierarchy Process Untuk Pemilihan Program Studi Calon Mahasiswa Pangestika, Menur Wahyu; Nurhayati, Oky Dwi; Suryono, Suryono
JURNAL SISTEM INFORMASI BISNIS Vol 6, No 1 (2016): Volume 6 Nomor 1 Tahun 2016
Publisher : Magister Sistem Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1080.968 KB) | DOI: 10.21456/vol6iss1pp11-20

Abstract

Methods Dempster Shafer Analytic Hierarchy Process is used to rank or sort information based on a number of criteria. DS/AHP advantage of Pairwise Comparison, Consistency Ratio, and Dempster Rules of Combination, which is used to generate information systems in the form of a sequence of courses as consideration for the selection of majors for prospective students. The sample used in this study were 29 students of five faculty at the University of Diponegoro. The data used is the standard minimum value of each faculty and the average value of the semester report card 1-5 Mathematics, Indonesian, English, Biology, Chemistry, and Physics. Results of this study was the software selection study program that gives students the value of trust in each department. Testing the validity of the value of the accuracy of the system is done by comparing the majors were chosen with the recommendation majors produced by the system, resulting accuracy of 79.33%.
Co-Authors Adhi Susanto Adi Mora Tunggul Adi, Yudi Restu Agus Subhan Akbar, Agus Subhan Agus Subkhi Hermawan, Agus Subkhi Ahmad Muzami, Ahmad Aji Prajayudha Permana, Aji Prajayudha Alifvia Arvi Ningrum Alim Muadzani, Alim Ambrina Kundyanirum Anggi Anugraha Putra, Anggi Anugraha Anggit Sri Herlambang, Anggit Sri Anggoro Mukti, Anggoro Anisa Eka Utami, Anisa Eka Annisa Hedlina Hendraputri, Annisa Hedlina Arief Puji Eka Prasetya, Arief Puji Eka Aulia Medisina Ramadhan, Aulia Medisina Cerah, Tyas Panorama Nan Damar Wicaksono Danal Meizantaka Daeanza, Danal Meizantaka Dania Eridani Deryan Gelrandy, Deryan Dwiana Okviandini Eggy Listya Sutigno, Eggy Listya Eko Didik Widianto Eko Eko, Eko Eko Sediyono Febi Andrea Renatha, Febi Andrea Galuh Boy Hertantyo, Galuh Boy Hadi Hilmawan, Hadi Hanna Mariana Baun, Hanna Mariana hastuti, Isti Pudji Hendra Pria Utama, Hendra Pria Ike Pertiwi Windasari Imaduddin Abdul Rahim, Imaduddin Abdul Indra Aditia Indra Permana, Indra Julce Adiana Sidette, Julce Adiana Kodrat Iman Satoto Kurniawan Teguh Martono Kusworo Adi Lazuardi Arsy, Lazuardi Lia Dorothy, Lia M. Rizki Kurniawan, M. Rizki Maesadji T Maesadji Tjokronagoro Menur Wahyu Pangestika, Menur Wahyu Mey Fenny Wati Simanjuntak, Mey Fenny Wati Muhammad Naufal Prasetyo, Muhammad Naufal Muhammad Ridwal Asad, Muhammad Ridwal Muhammad Ridwan Asad, Muhammad Ridwan Nofiyati Nofiyati, Nofiyati Nurazizah Nurazizah, Nurazizah Nurhuda Maulana, Nurhuda Nurul Arifa R. Rizal Isnanto Reza Najib Hidayat, Reza Najib Rian Haris Muda Nasution, Rian Haris Muda Rinta Kridalukmana Rismawan Fajril Falah, Rismawan Fajril Riyadhi Sholikhin, Riyadhi Rizal Isnanto Santoso, Nugroho Adhi Satriaji Cahyo Nugroho, Satriaji Cahyo Suryo Mulyawan Raharjo, Suryo Mulyawan Suryono Suryono Teguh Hananto Widodo, Teguh Hananto Thomas Sri Widodo Tristy Meinawati Wijaya Wahyudi Akbar, Wijaya Wahyudi Yessy Kurniasari Yudi Eko Windarto Zaskia Wiedya Sahardevi, Zaskia Wiedya