Claim Missing Document
Check
Articles

Found 15 Documents
Search

APLIKASI DATA MINING UNTUK PENILAIAN KREDIT MENGGUNAKAN DECISION TREE ALGORITMA ID3 STUDI KASUS PT. MANDALA MULTI FINANCE CABANG KENDARI Ilayani, Ilayani; Nangi, Jumadil; Pasrun, Yuwanda Purnamasari
semanTIK Vol 4, No 1 (2018): semanTIK
Publisher : Informatics Engineering Department of Halu Oleo University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2928.389 KB)

Abstract

Credit is one of the most common payment mechanisms in the community. Data mining can search the pattern and new knowledge of these data so that it can facilitate in determination of debtor candidate. For that required a data mining applications that can process and provide the decision of the prospective debtor's eligibility status automatically. One method of data mining used for the classification of prospective borrowers is the decision tree using Iterative Algorithm Dichotomiser 3 (ID3).ID3 is one of the most popular types of Decision trees that attempt to build a decision tree top-down, starting with the first attribute to be checked and placed as root. The ID3 or Iterative Dichotomiser 3 algorithm is a method used to produce decision trees that are able to classify an object. Attributes used are file, job, character, address, pay slip, and motor price.Based on the test results, ID3 method can be implemented in credit appraisal application for the determination of eligibility with 100% accuracy value for 10 data testing from 100 training data and 30 data testing from 60 training data.Keywords—Credit, Data Mining, Decision Tree, ID3 DOI : 10.5281/zenodo.1402830
Penggabungan Fitur Bentuk dan Fitur Tekstur yang Invariant terhadap Rotasi untuk Klasifikasi Citra Pap Smear Pasrun, Yuwanda Purnamasari; Fatichah, Chastine; Suciati, Nanik
Jurnal Buana Informatika Vol 7, No 1 (2016): Jurnal Buana Informatika Volume 7 Nomor 1 Januari 2016
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (714.041 KB) | DOI: 10.24002/jbi.v7i1.479

Abstract

Abstract. Pap test is a cervical cancer screening manually and requires a long time that it needs an exact cell classification system based computers. Features determination by observation in characteristic differences between the datasets visually betweenclass will help a cell classification results which has relevant characteristics between classes. In addition, the change in orientation of the cells at the time of the acquisition will affect the value of the generated feature so extraction method that is rotation invariant is needed to overcome that problem. This research proposes the combination of simple shapes feature and the texture feature from extraction Local Binary Pattern Histogram Fourier (LBP-HF) that invariant to rotation as additional features to classify pap smear images. The result show that the proposed feature combination yield good performance with accuracy 92.44% for two category cell and 70.06% for seven class cell.Keywords: classification, lbp-hf,  pap smear image, shape feature.Abstrak. Pap test adalah pemeriksaan kanker serviks secara manual yang membutuhkan waktu yang lama sehingga dibutuhkan sistem klasifikasi sel berbasis komputer yang tepat. Penentuan fitur melalui observasi pada perbedaan ciri antarkelas secara visual pada dataset akan membantu hasil klasifikasi sel untuk mendapatkan ciri yang relevan antarkelas. Selain itu, adanya perubahan orientasi sel pada saat akuisisi akan mempengaruhi nilai fitur yang dihasilkan sehingga dibutuhkan metode ekstraksi fitur yang invariant terhadap rotasi. Penelitian ini mengusulkan penggabungan fitur bentuk sederhana dan fitur tekstur dengan ekstraksi fitur Local Binary Pattern –Histogram Fourier yang invariant terhadap rotasi sebagai ciri tambahan dalam mengklasifikasikan citra pap smear. Hasilnya menunjukkan bahwa kombinasi fitur menghasilkan performa yang baik dengan akurai 92,44% untuk dua kategori sel dan 70,06% untuk tujuh kelas sel.Kata Kunci: klasifikasi, lbp-hf, citra pap smear, fitur bentuk.
IT governance evaluation at the population and civil registry office in Kolaka district using COBIT 5 framework Zainuddin, Noorhasanah; Winarno, Wing Wahyu; Ningsi, Nurfitria; Pasrun, Yuwanda Purnamasari; Muliyadi, Muliyadi
Register: Jurnal Ilmiah Teknologi Sistem Informasi Vol 6, No 2 (2020): July
Publisher : Information Systems - Universitas Pesantren Tinggi Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26594/register.v6i2.1728

Abstract

The implementation of information technology is compulsory to fit organizational goals. This research aims to evaluate the quality of information technology services at the Population and Civil Registry Office at Kolaka District based on COBIT 5 Framework that focused on DSS (deliver, service and support) domain by measuring the Maturity Level using Process Assessment Model (PAM). The Population and Civil Registry Office is under the local government ‘s auspices which is essential in managing the population. The data collection method was done by distributing questionnaires and conducting interviews. This study used 8 (eight) respondents based on the RACI chart. This research was expected to reach level 3 (established process) to create IT governance that fits organizational goals and international standards. From the research result, it is known that the maturity level from the evaluation process conducted by COBIT 5 using the processes DSS-01, DSS-02, DSS-03, DSS-04, DSS-05, and DSS-06 were as follows: 2 processes were at level 1 (performed process), namely the DSS-05 and DSS-06 while the others (DSS-01, DSS-02, DSS-03, and DSS-04) were at level 2 (managed process).
MACULAR EDEMA CLASSIFICATION USING SELF-ORGANIZING MAP AND GENERALIZED LEARNING VECTOR QUANTIZATION Rizal Adi Saputra; Yuwanda Purnamasari Pasrun; Amaliya Nurani Basyarah
Jurnal Ilmu Komputer dan Informasi Vol 7, No 2 (2014): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Information)
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (294.548 KB) | DOI: 10.21609/jiki.v7i2.257

Abstract

Abstract Macular edema is a kind of human sight disease as a result of advanced stage of diabetic retinopathy. It affects the central vision of patients and in severe cases lead to blindness. However, it is still difficult to diagnose the grade of macular edema quickly and accurately even by the medical doctor's skill. This paper proposes a new method to classify fundus images of diabetics by combining Self-Organizing Maps (SOM) and Generalized Vector Quantization (GLVQ) that will produce optimal weight in grading macular edema disease class. The proposed method consists of two learning phases. In the first phase, SOM is used to obtain the optimal weight based on dataset and random weight input. The second phase, GLVQ is used as main method to train data based on optimal weight gained from SOM. Final weights from GLVQ are used in fundus image classification. Experimental result shows that the proposed method is good for classification, with accuracy, sensitivity, and specificity at 80%, 100%, and 60%, respectively.
Penggabungan Fitur Bentuk dan Fitur Tekstur yang Invariant terhadap Rotasi untuk Klasifikasi Citra Pap Smear Yuwanda Purnamasari Pasrun; Chastine Fatichah; Nanik Suciati
Jurnal Buana Informatika Vol. 7 No. 1 (2016): Jurnal Buana Informatika Volume 7 Nomor 1 Januari 2016
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/jbi.v7i1.479

Abstract

Abstract. Pap test is a cervical cancer screening manually and requires a long time that it needs an exact cell classification system based computers. Features determination by observation in characteristic differences between the datasets visually betweenclass will help a cell classification results which has relevant characteristics between classes. In addition, the change in orientation of the cells at the time of the acquisition will affect the value of the generated feature so extraction method that is rotation invariant is needed to overcome that problem. This research proposes the combination of simple shapes feature and the texture feature from extraction Local Binary Pattern Histogram Fourier (LBP-HF) that invariant to rotation as additional features to classify pap smear images. The result show that the proposed feature combination yield good performance with accuracy 92.44% for two category cell and 70.06% for seven class cell.Keywords: classification, lbp-hf,  pap smear image, shape feature.Abstrak. Pap test adalah pemeriksaan kanker serviks secara manual yang membutuhkan waktu yang lama sehingga dibutuhkan sistem klasifikasi sel berbasis komputer yang tepat. Penentuan fitur melalui observasi pada perbedaan ciri antarkelas secara visual pada dataset akan membantu hasil klasifikasi sel untuk mendapatkan ciri yang relevan antarkelas. Selain itu, adanya perubahan orientasi sel pada saat akuisisi akan mempengaruhi nilai fitur yang dihasilkan sehingga dibutuhkan metode ekstraksi fitur yang invariant terhadap rotasi. Penelitian ini mengusulkan penggabungan fitur bentuk sederhana dan fitur tekstur dengan ekstraksi fitur Local Binary Pattern –Histogram Fourier yang invariant terhadap rotasi sebagai ciri tambahan dalam mengklasifikasikan citra pap smear. Hasilnya menunjukkan bahwa kombinasi fitur menghasilkan performa yang baik dengan akurai 92,44% untuk dua kategori sel dan 70,06% untuk tujuh kelas sel.Kata Kunci: klasifikasi, lbp-hf, citra pap smear, fitur bentuk.
Perancangan e-Jaminan Mutu Perguruan Tinggi Baru menggunakan metode Waterfall Nurfitria Ningsi; Yuwanda Purnamasari Pasrun
JUPITER (Jurnal Penelitian Ilmu dan Teknologi Komputer) Vol 14 No 1 (2022): jupiter April 2022
Publisher : Teknik Komputer Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281./4609/5.jupiter.2022.04

Abstract

This study is focused on designing e-quality assurance services to improve the performance of the USN Kolaka FTI Quality Assurance group, which during the COVID-19 pandemic was still applying manual SOP submissions and approvals. the importance of designing e-quality assurance considering the magnitude of its support in academic policy making during the new normal adaptation period in order to support the implementation of quality education in accordance with expectations. the results of this study indicate that 95% of users agree that the faculty's e-quality assurance is able to encourage increased work productivity of GJM FTI through the use of the online SOP draft submission feature to approval and automatic review. The importance of adding MONEV and Internal Audit features will maximize the performance of GJM FTI in the future.
PENERAPAN METODE CBA (CLASSIFICATION BASED ON ASSOSIATION RULE ) MENGGUNAKAN ALGORITMA APRIORI UNTUK KLASIFIKASI PENYAKIT ISPA (INFEKSI SALURAN PERNAPASAN AKUT) Haryati Haryati; Natalis Ransi; Yuwanda Purnamasari Pasrun
semanTIK Vol 3, No 2 (2017): semanTIK
Publisher : Informatics Engineering Department of Halu Oleo University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (898.664 KB) | DOI: 10.55679/semantik.v3i2.3149

Abstract

Infeksi pada saluran pernapasan merupakan penyakit yang umum terjadi pada masyarakat. Dari hasil rekapitulasi dan laporan medis UPT Puskesmas Lepo-Lepo, ISPA (Infeksi Saluran Pernapasan Akut) adalah salah satu penyakit yang sering diderita. Hasil diagnosis yang yang diberikan hanya berupa keterangan positif atau negatif, belum ada keterangan kategori ISPA. Dalam menemukan pola penyakit ISPA diperlukan analisis terhadap pola data. Pencarian pola atau hubungan asosiatif dari data yang berskala besar sangat erat kaitannya dengan data mining. Metode yang digunakan adalah metode CBA (Classification Based on Assosiation ) dengan algoritma apriori untuk klasifikasi pola penyakit ISPA. Metode CBA mengintegrasikan teknik klasifikasi dengan teknik asosiasi data mining untuk menemukan rule. Banyak rule yang ditemukan tergantung pada minimum support dan minimum confidence. Informasi yang dihasilkan untuk selanjutnya bisa digunakan oleh dokter sebagai dasar untuk melakukan tindakan – tindakan yang diperlukan dalam menangani penyakit ISPA.Kata kunci— ISPA (Infeksi Saluran Pernapasan Akut), Data Mining, CBA (Classification Based on Assosiation ), Algoritma Apriori
Penerapan Metode Naïve Bayes Clasification Dalam Klasifikasi Jenis Penyakit ISPA Yuwanda Purnamasari Pasrun
semanTIK Vol 5, No 2 (2019): semanTIK
Publisher : Informatics Engineering Department of Halu Oleo University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2154.732 KB) | DOI: 10.55679/semantik.v5i2.8588

Abstract

ARI is the leading cause of infectious disease morbidity and mortality in the world. Nearly four million people die from ARI each year, 98% of which are caused by lower respiratory tract infections. Mortality rates are very high in infants, children and the elderly, especially in countries with low and medium per capita incomes. Likewise, ARI is one of the main causes of consultation or hospitalization in health care facilities, especially in the child care department. Lepo-Lepo is one of the health service units in the Lepo-Lepo sub-district of Kendari, which has data on patients with ARI. From the recapitulation results and medical reports of UPT Lepo-Lepo Puskesmas, ISPA is one of the diseases that is often suffered by patients in the Lepo-Lepo Puskesmas. The diagnosis results given are only in the form of positive or negative information, there is no information on the category of ARI suffered by patients including ISPaA or ISPbA so it is necessary to recognize patterns. One of the tasks of Data Mining is data classification, which is mapping (classifying) data into one or several classes that have been previously defined. From the research results obtained, from 50 data of ISPA patients tested, the results obtained using the naïve bayes method, using cross validation with 10 training data from 50 data, 96% correct and 4% wrong so that the application of the naïve bayes method in the type classification ARI can be applied ..
IMPLEMENTASI METODE ENKRIPSI ADVANCE VIGENERE CIPHER DALAM PENGAMANAN SISTEM TRANSAKSI PAYMENT POINT ONLINE BANK Muh Iskandar Z. A; Sutardi Sutardi; Yuwanda Purnamasari Pasrun
semanTIK Vol 3, No 2 (2017): semanTIK
Publisher : Informatics Engineering Department of Halu Oleo University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (232.381 KB) | DOI: 10.55679/semantik.v3i2.3758

Abstract

Advance vigenere cipher merupakan suatu modifikasi vigenere cipher yang memungkinkan metode enkripsi vigenere untuk tidak hanya mampu menyandikan karakter abjad, namun juga mampu menyandikan seluruh karakter yang ada termasuk angka dan simbol-simbol. Tujuan dari penelitian ini adalah membangun sistem transaksi Payment Point Online Bank (PPOB) yang aman dengan mengimplementasikan metode Advance Vigenere Cipher dalam pengamanan sistemnya.Dalam penelitian ini, sistem pengamanan transaksi PPOB dibagi menjadi dua tahapan utama yaitu tahapan enkripsi dan tahapan dekripsi. Data yang dienkripsi menggunakan metode Advance Vigenere Cipher merupakan detail data tagihan dari transaksi yang akan dilakukan. Hasil dari enkripsi menghasilkan ciphertext yang akan dikirimkan dan didekripsi oleh pihak penyedia layanan PPOB.Hasil dari penelitian ini menunjukkan karakteristik dari ciphertext yang dihasilkan sangat rumit, sehingga akan sulit bagi pihak luar untuk melakukan intervensi dan mengelola informasi yang dikirimkan dari pihak penyedia layanan PPOB kepada pengguna layanan PPOB.Kata Kunci—Enkripsi advance vigenere cipher, sistem transaksi Payment Point Online Bank  (PPOB)
PERAMALAN JUMLAH PRODUKSI PADI DI SULAWESI TENGGARA MENGGUNAKAN METODE FUZZY TIME SERIES Djafar Djafar; Muh. Ihsan Sarita; Yuwanda Purnamasari Pasrun
semanTIK Vol 3, No 2 (2017): semanTIK
Publisher : Informatics Engineering Department of Halu Oleo University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (257.734 KB) | DOI: 10.55679/semantik.v3i2.3482

Abstract

Padi merupakan tanaman pangan yang sangat penting di dunia setelah gandum dan jagung. Padi merupakan tanaman pangan yang sangat penting karena beras masih digunakan sebagai makanan pokok serta merupakan komoditas strategis di Indonesia. Terkhusus untuk Sulawesi tenggra, produksi padi terus mengalami peningkatan dari tahun ke tahun, namun tidak diketahui perkiraan peningkatan produksi padi pada tahun berikutnya sehingga tidak terdapat gambaran mengenai peningkatan produksi padi tersebut. Perkiraan ini dapat dilakukan menggunakan Metode peramalan Fuzzy Time Series. Sistem peramalan dengan Fuzzy Time Series menggunakan prinsip-prinsip fuzzy sebagai dasarnya dan menangkap pola dari data yang telah lalu kemudian digunakan untuk memproyeksikan data yang akan datang. Prosesnya juga tidak membutuhkan suatu sistem pembelajaran yang rumit.Metode Fuzzy Time Series  yang digunakan untuk meramalkan jumlah produksi padi di Sulawesi Tenggara. Data yang digunakan pada peramalan ini yaitu data tahun 1974 sampai dengan 2014 dan menghasilkan peramalan produksi padi pada tahun 2015 sebesar 657768.25191 Ton dengan MAPE sebesar 5.51%.Toleransi kesalahan peramalan yaitu sebesar 10% sehingga prediksi jumlah produksi padi di Sulawesi Tenggara berada di bawah batas toleransi kesalahan.Kata kunci—Padi, Fuzzy Time Series, Produksi