Article Per Year (5 Year)
p-Index From 2019 - 2024
0.408
P-Index
This Author published in this journals
All Journal Semantik Jurnal Teknologi Informasi Cyberku
Moch Arief Soeleman
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Other

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
Background Subtraction Berbasis Algorithma K-Means Klastering untuk Deteksi Objek Bergerak Moch Arief Soeleman; Ricardus Anggi P; Pulung Nurtantio Andono
Semantik Vol 4, No 1 (2014): Semantik 2014
Publisher : Semantik

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2994.549 KB)

Abstract

Background subtraction menjadi bagian yang sangat penting dari deteksi objek bergerak di video. Problem utamanya adalahketepatan dalam proses menentukan objek bergerak. Makalah ini mengusulkan metode klastering dengan k-means padabackground subtraction dalam mendeteksi objek bergerak. Untuk mengevaluasi performa dari k-means digunakan MeanSquare Error (MSE) dan Peak Signal Noise Ratio (PSNR). Hasil eksperimen menunjukkan bahwa k-means mampu untukmelakukan klasifikasi piksel latar depan atau latar belakang dalam mendeteksi objek.Keyword : k-means, background subtraction, objek bergerak
PENENTUAN JURUSAN SISWA SEKOLAH MENENGAH ATAS DISESUAIKAN DENGAN MINAT SISWA MENGGUNAKAN ALGORITMA FUZZY C-MEANS Altanova Reza; Abdul Syukur; Moch Arief Soeleman
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 13 No 1 (2017): Jurnal Teknologi Informasi CyberKU Vol. 13, no 1
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (166.147 KB)

Abstract

Majors are held no valid high school in Indonesia is conducted when students are still in grade X. This includes the areas of interest Majors Natural Sciences, Social Sciences, and science of language. Majors will depend on the capability of student achievement in the areas of interest / courses available and in accordance with the conditions at the school. If it is not possible then the only department of particular interest are provided in school. The results of tests that tested students' interest through psychological tests aimed to help the school and the students themselves so that later, the lessons will be given to students become more focused as it has in accordance with the capability in the field of interest. Fuzzy C-Means algorithm is an algorithm that is easy and is often used in the technique of grouping the data as it makes an estimate efficient and does not require a lot of parameters. Several studies have concluded that the Fuzzy C-Means algorithm can be used to classify data based on certain attributes. In this study will be used Fuzzy C-Means algorithm to classify the student data High School (SMA) based on the value of the core subjects for the majors that are appropriated to the interests test results. The study also examined the level of accuracy of Fuzzy C-Means algorithm in determining the majors in high school. Application of Fuzzy C-Means algorithm in determining the majors in the 278 high school students were tested in this study, indicating that the FCM algorithm has a good degree of accuracy (in an average of 82.01%) by including interest test scores compared with the manual method based on the selection of individual students only 63.67%.
PENENTUAN TINGKAT KESEJAHTERAAN ANAK MENGGUNAKAN ALGORITMA C 4.5 Yuli Murdianingsih; Abdul Syukur; Moch Arief Soeleman
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 12 No 1 (2016): Jurnal Teknologi Informasi CyberKU Vol. 12, no 1
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (246.849 KB)

Abstract

Realization of child welfare is a right of every child and is the responsibility of all. Today the program services are sporadic, discontinue and responsiveness is a result of not optimal data management with social welfare problems is very large. Need a model system that can help make decisions quickly, precisely and accurately. In this research the basic needs of children based on four parameters: physical, intellectual, emotional, social and spiritual. C4.5 algorithm implementated in the m system’s model of children's basic needs level is done by calculating the entropy and the gain of the parameters of physical, intellectual, emotional and spiritual social iteratively in order to obtain a decision tree and rules used to model. Data analisys base on 149 datas as the training data and the testing data is 37. The accuracy of the model to look at the performance of the system using confusion matrix. Systems decision trees obtained the degree of basic needs of children, from the decision tree obtained seven rules that are used in view, values of accuracy obtained 94,59 % . C 4.5 algorithm can be used for classification of the level of a child's basic needs are met and not met.
PREDIKSI RENTET WAKTU JUMLAH PENUMPANG BANDARA MENGGUNAKAN ALGORITMA NEURAL NETWORK BERBASIS GENETIC ALGORITHM Mohamad Ilyas Abas; Abdul Syukur; Moch Arief Soeleman
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 13 No 2 (2017): Jurnal Teknologi Informasi CyberKU Vol. 13, no 2
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (826.212 KB)

Abstract

Prediksi terhadap jumlah penumpang dilakukan guna memberikan informasi kepada manajamen bandar udara Djalaluddin Gorontalo. Informasi yang diberikan dapat dijadikan sebagai bahan pertimbangan dalam melakukan pengelolaan dari segi infrastrukur sarana dan prasarana dari pihak bandara. Hasil prediksi terhadap jumlah penumpang tahun mendatang akan memberikan informasi kepada pihak bandara agar dapat meningkatkan pelayanan yang lebih maksimal terhadap penumpang. Untuk itu, perlu adanya prediksi terhadap pertumbuhan jumlah penumpang salah satunya yaitu dengan penerapan salah satu algoritma dalam data mining. Penerapan algoritma Neural Network menjadi salah satu algoritma yang dapat digunakan untuk melakukan prediksi. Serta penerapan Neural Network Backpropagation sebagai proses pelatihan untuk data time series. Penambahan Algoritma Genetika untuk melakukan optimasi dapat memperkecil nilai Root Mean Squared Error (RMSE). RMSE terkecil akan menambah keakuratan dalam melakukan prediksi. Nilai RMSE yang didapat pada penelitian ini yaitu 0.092. Dengan parameter Neural Network Hidden Layer: 10, Training Cycles, 22, Learning Rate: 0.10982546098949762 dan Momentum: 0.1 serta parameter optimasi Max Generations: 50, Population Size: 50, Mutation Type: Gaussian_mutation, Selection Type: Roulette Wheel, dan Crossover Probability: 0.9. Kombinasi NN+GA ini terbukti menghasilkan RMSE terkecil untuk sehingga dapat digunakan untuk melakukan prediksi terhadap jumlah penumpang bandara di Gorontalo.
Penentuan Prioritas Penerima Dana Bantuan Operasional Pendidikan Lembaga Pendidikan Anak Usia Dini dengan Metode KNN, TOPSIS dan K-Means Diwahana Mutiara Candrasari; Abdul Syukur; Moch Arief Soeleman
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 15 No 2 (2019): Jurnal Teknologi Informasi - Jurnal CyberKU Vol. 15, no 2
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (310.24 KB)

Abstract

Education Operational Aid of the Early Childhood Education unit is the financial assistance which is provided to educational institutions, especially for those who engaged in non-formal education, which is used for the process of education in the curriculum of educational institutions in order to give the appropriate and adequate education for students. However, the reality has stated that there is a lot of financial irregularity and inaccuracy of data in the disbursement of the fund of education operational aidat the institute units of Early Childhood Education. On the other hand, there are many complaints that come from the institution itself due to the inaccuracy of data. This research was conducted by applying the KNN, K-Meansalgorithmand TOPSISmethods. The results of the experiment will be tested with two methods that is using cluster distance performance and K-Means cluster count performance. Meanwhile, to measure the level of ranking of TOPSIS method,the experiment will use the percentage calculation method between the experimental data with the implementation of the data to determine the accuracy of TOPSISmethods.
Klasifikasi Penerbitan Surat Keputusan Tunjangan Profesi Guru Menggunakan Naive Bayes Berbasis Information Gain Rani Pratikaningtyas; Purwanto Purwanto; Moch Arief Soeleman
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 15 No 2 (2019): Jurnal Teknologi Informasi - Jurnal CyberKU Vol. 15, no 2
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (204.807 KB)

Abstract

Sertifikasi guru merupakan salah satu upaya pemerintah untuk meningkatkan mutu pendidikan disertai dengan peningkatan kesejahteraan guru. Namun banyaknya penerima sertifikasi yang ternyata tidak cair berpengaruh kepada laporan anggaran belanja negara dan daerah. Penelitian ini bertujuan untuk melakukan seleksi fitur dengan cara memberi bobot pada setiap atribut dari data Penerbitan Surat Keputusan Tunjagan Profesi Guru di Kota Surakarta tahun 2015, menggunakan metode information gain untuk meningkatkan akurasi pada algoritma Naïve Bayes, sehingga dapat mengklasifikaasi penerbitan surat keputusan tunjangan profesi guru dengan baik. Information gain digunakan untuk memilih atribut khususnya dalam menangani data dengan dimensi tinggi. Sedangkan untuk proses klasifikasinya menggunakan algoritma Naïve Bayes yang merupakan teknik prediksi berbasis probabilistic sederhana. Adapun atribut yang digunakan dalam eksperiman ini adalah, NUPTK, Format Bayar, Jenis PTK, Jenis Kelamin, NIP, Status Kepegawaian, Kode Sertifikasi, Area Tugas, Jenjang, JJM Mengajar, Tugas Tambahan, Tugas Mengajar, Golongan, Nama Bank, Keputusan. Hasil Eksperimen dari metode Naïve Bayes didapatkan hasil akurasi sebesar 93,31% sedangkan setelah menggunakan seleksi fitur dengan information gain didapatkan hasil akurasi sebesar 96,11%. Sehingga mengalami peningkatan akurasi sebesar 2,80%.
Co-Authors Abdul Syukur Altanova Reza Diwahana Mutiara Candrasari Hermanto Mohamad Ilyas Abas Pulung Nurtantio Andono Purwanto Purwanto Rani Pratikaningtyas Ricardus Anggi P Yuli Murdianingsih