Article Per Year (5 Year)
p-Index From 2019 - 2024
4.039
P-Index
This Author published in this journals
All Journal Jurnal Edukasi dan Penelitian Informatika (JEPIN) JURNAL MEDIA INFORMATIKA BUDIDARMA J-SAKTI (Jurnal Sains Komputer dan Informatika) Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) KOMIK (Konferensi Nasional Teknologi Informasi dan Komputer) Jurnal Sistem Komputer dan Informatika (JSON) JUKI : Jurnal Komputer dan Informatika TIN: TERAPAN INFORMATIKA NUSANTARA Brahmana : Jurnal Penerapan Kecerdasan Buatan Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Jurnal Tunas Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) RESOLUSI : REKAYASA TEKNIK INFORMATIKA DAN INFORMASI KLIK: Kajian Ilmiah Informatika dan Komputer J-SAKTI (Jurnal Sains Komputer dan Informatika) BEES: Bulletin of Electrical and Electronics Engineering Bulletin of Data Science Journal of Artificial Intelligence and Engineering Applications (JAIEA) JOMLAI: Journal of Machine Learning and Artificial Intelligence Journal of Informatics, Electrical and Electronics Engineering
Okprana, Harly
STIKOM Tunas Bangsa, Pematangsiantar, Indonesia
Aerospace Engineering Arts Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Law, Crime, Criminology & Criminal Justice Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Neuroscience Nursing Physics Social Sciences Veterinary Other

Published : 29 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 29 Documents
Search

 1   2   3 
Prediksi Kelulusan TOEFL Menggunakan Metode Resilient Backpropagation Okprana, Harly; Lubis, Muhammad Ridwan; Hadinata, Jaya Tata
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol 6, No 2 (2020): Volume 6 No 2
Publisher : Program Studi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jp.v6i2.41224

Abstract

Prediksi kelulusan TOEFL peserta didik Michigan Computer English Course diperlukan untuk meninjau sejauh mana tingkat pemahaman peserta didik. Backpropagation merupakan salah satu teknik yang baik digunakan untuk prediksi, akan tetapi jika backpropagation dalam training data dengan jumlah besar serta parameter-parameter yang digunakan kurang tepat, akan terjadi proses traning data lebih lambat. Maka diperlukan metode optimasi untuk mempercepat training Bacpropagation dalam memprediksi kelulusan dengan menggunakan metode Resilient Backpropagation. Data yang diolah sebanyak 182 data peserta didik tahun 2016-2018. Tingkat akurasi pengujian semakin baik yakni 100% dengan nilai MSE semakin kecil 0.00342 serta nilai Epoch juga semakin kecil menjadi 5. Sehingga penelitian ini menjadi indikator dalam pengembangan prediksi TOEFL dimasa yang akan datang.
Sistem Pendukung Keputusan Penentuan Pemberian Insentif Pegawai THL Menggunakan Metode Promethee Pada Kantor Walikota Pematangsiantar Sepridho, Jaka; Damanik, Irfan Sudahri; Okprana, Harly
Jurnal Sistem Komputer dan Informatika (JSON) Vol 2, No 3 (2021): Mei 2021
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v2i3.2853

Abstract

Pematangsiantar Mayor Office is an institution that is used and functions to serve and protect the community. This paper proposes a decision support system research using the Promethee method. Promethee is one of several methods of determining the order or priority in multi-criteria analysis. This writing uses the Promethee method as a step in determining the provision of incentives for freelance daily staff at the Pematangsiantar Mayor's Office. In this study the authors took 10 alternatives with 5 assessment criteria including absenteeism, achievement, behavior, long history of work and teamwork. With the highest result obtained by alternative 9 on behalf of Triono with a value of 0.422 and the lowest result obtained by alternative 6 on behalf of Soraya with a value of -0.211.
Penerapan Algoritma K-Means Pada Penjualan Frozen Food Pada UD Soise Sosis Pematangsiantar Nasution, Siti Andry Yani; Poningsih, Poningsih; Okprana, Harly
Jurnal Sistem Komputer dan Informatika (JSON) Vol 2, No 2 (2021): Januari 2021
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v2i2.2768

Abstract

The research objective is the application of the K-Means algorithm in Frozen Food sales, to classify the number of Frozen Food sales in each month, to take what month the highest and lowest sales data. The method used is the K-Means algorithm and is accompanied by a Rapid Miner in processing the data. Data sources obtained from observations, interview and document to shop owners and coworkers. There are several types of Frozen Food and sales data from April to November 2019. Where the results of the study can provide information to business owners, what Frozen Food should be increased in production so that business owners can increase their Frozen Food sales.
Pengelompokan Pembiayaan Nasabah Klaim Asuransi Pengguna Kendaraan Bermotor dengan Metode K-Medoids Aulanda, Lulu; Windarto, Agus Perdana; Okprana, Harly
TIN: Terapan Informatika Nusantara Vol 2 No 4 (2021): September 2021
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

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

Abstract

In general, insurance is providing risk coverage to the insurer, namely the insurance company for a predetermined period and agreements. Insurance or coverage is an agreement between two or more parties, in which the insurer binds himself to the insured, by receiving an insurance premium, to provide compensation to the insured due to loss, damage or loss. The k-medoids method is one of several clustering methods in data mining which is part of partitional clustering. This method uses objects in a collection of objects to represent a cluster. The k-medoids clustering method can be applied to customer financing data for insurance claims on motor vehicle users, so that the financing grouping can be seen based on these data. From the grouping data, the characteristics can be seen so that it is known that the cluster is low, cluster is medium and cluster is high
Analisis Metode Backpropragation DalamMemprediksi Kelulusan Mahasiswa Studi Kasus STIKOM Tunas Bangsa Nasution, Selvi Salsabillah; Okprana, Harly; Saragih, Ilham Syahputra
TIN: Terapan Informatika Nusantara Vol 2 No 5 (2021): Oktober 2021
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

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

Abstract

Abstrak− Prediksi kelulusan Mahasiswa STIKOM Tunas Bangsa diperlukan untuk meninjau sejauh mana tingkat pemaha.man Siswa. Backpropagation merupakan salah satu teknik yang baik digunakan untuk prediksi, Metode yang digunakan adalah metode Backpropagation. Dengan metode ini dapat dilakukan pengolahan data menggunakan nilai input serta target yang ingin dihasilkan. Sehingga dapat memprediksi kelulusan Mahasiswa dalam uji kompetensi keahlian. Selanjutnya data yang akan dikelola adalah rekap nilai rata-rata kejuruan jurusan sistem komputer dari semester 1 sampai semester 5 dengan aspek pengetahuan pada target siswa Tahun Pelajaran 2019 dan Tahun Pelajaran 2020 yang diperoleh dari penjumlahan seluruh mata pelajaran pada setiap semester. Hasil dari perhitungan dengan metode Backpropagation dengan aplikasi Matlab akan menjadi prediksi dalam menghasilkan nilai tingkat kelulusan siswa di masa yang akan datang. Sehingga penelitian ini menjadi indikator dalam pengembangan prediksi Mahasiswa dimasa yang akan datang. Kata Kunci : Jaringan Syaraf Tiruan, Backpropagation, Prediksi Mahasiswa STIKOM Tunas Bangsa Abstract− Predictions of student bud stikom graduation nations are needed to look at the level of insia. Man student. Backpropagation is one of the techniques used for prediction, the method used is the method of backpropagation. This method will allow data processing to use input values and targets to be produced. So it can predict student graduation in competence expertise tests. Furthermore, the data will be managed is the vocational recap of the computer system's department of department from semester 1 to semester 5 with knowledge on student targets of lesson year 2019 and 2020 school years that are generated from a total of entire subjects each semester. The result of calculating the backpropagation method with the matlab application will be the prediction in producing a student's grade level of graduation in the future. So this research should be an indicator of future student development predictions. Keywords: artificial nerve tissue, backpropagation, predictive female to the nation's bud.
Algoritma C4.5 Dalam Data Mining Untuk Menentukan Klasifikasi Penerimaan Calon Mahasiswa Baru Haryoto, Parawystia Prabasini; Okprana, Harly; Saragih, Ilham Syahputra
TIN: Terapan Informatika Nusantara Vol 2 No 5 (2021): Oktober 2021
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

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

Abstract

Conducting a graduation classification of prospective freshmen at a college should be best not only by the written exam value criteria but also the interview test, and other things that can serve as assessment parameters. In this study an increased parameters for classifying potential students in the scarlet hyperlinate's post-collegiate bud with deep learning methods using a c4 algorithc.5. With this method of classification, it is hoped to help academicians determine the criteria of active and exemplary freshman candidates. From experiment with the rapidminer's software on the data of students who have registered from 2016 to 2020, obtained an active student classification defined by the value of the interview being the first node, coupled with the value of an academic potential test. In the meantime, it is found that what can affect a student's performance is the school's origin and duration of college. Students who continue studying => 4 years tend to have grades and achievements under those who continue to study at three to four years. Based on research, score of accuracy at 81.32%.
SISTEM PENDUKUNG KEPUTUSAN PEMILIHAN LOKASI PREWEDDING MENGGUNAKAN METODE WEIGHT PRODUCT Syahputra, Muhammad Riza; Winanjaya, Riki; Okprana, Harly
KOMIK (Konferensi Nasional Teknologi Informasi dan Komputer) Vol 3, No 1 (2019): Smart Device, Mobile Computing, and Big Data Analysis
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/komik.v3i1.1680

Abstract

Marriage is the most awaited moment for everyone. Prawdding is an important thing to do before a wedding. Because prewedding photos become the latest trend for photos that will be displayed during the wedding. But in a lot of prewedding photos brides who are not satisfied with the results of these prewedding photos. This system can facilitate the bride and groom in choosing the location of prawedding photos without the need to meet in person to consult. This decision making system is made using the Weight Product method and is made with the php programming language and MySQL database. The WP method is used to find optimal alternatives from a number of alternatives. The selection of the location of the prewedding photo uses weighting for each criterion. The bride and groom can choose the desired location based on criteria such as the number of spots, themes, location distance, number of shoots with weights determined by the user based on the level of importance. The results of this system are displaying praweding locations based on the location of prawedding photos that can be ordered by the bride and groom. The selection of prewedding photo locations can be done optimally so that the results of the decision are as expected.Keywords: Decision Support System, Prewedding Location, Product Weight
Penerapan Data Mining Klasifikasi C4.5 Pada Penerima Beasiswa di SMK Swasta Anak Bangsa Millah Sari; Agus Perdana Windarto; Harly Okprana
BEES: Bulletin of Electrical and Electronics Engineering Vol 1 No 3 (2021): Maret 2021
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (729.005 KB)

Abstract

Data Mining is a series of processes to explore added value in the form of knowledge that has not been known manually from a data set. There are 5 (five) attributes used in this study, namely: Value, Attendance, Semester, Parents' Income (PO), and Number of Dependent Parents (JTO). Based on data processing using Rapid Miner 5.3.0.0 software, an accuracy value of 92.70% is obtained, meaning that the resulting rule is close to 100% correct. Where the results of the feasible precision label class are 92.05% and the inappropriate label is 93.24%. In accordance with these provisions, the results of manual calculations by Rapid Miner testing produce 9 models of rules or rules for Scholarship Recipients. This means that the results of the process carried out by researchers on the calculation of the C4.5 Algorithm and Rapidminer obtained the same and appropriate results. So that testing with Rapid Miner can be said to be successful and can find a decision tree in the case of Scholarship recipients.
Analisis Laju Pembelajaran dalam Mengklasifikasi Data Wine Menggunakan Algoritma Backpropagation Jaya Tata Hardinata; Harly Okprana; Agus Perdana Windarto; Widodo Saputra
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 3, No 2 (2019): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v3i2.161

Abstract

Backpropagation is an artificial neural network that has the architecture in conducting training and determining the right parameters to produce the correct output of similar but not the same input. One of the parameters that influences the determination of bacpropagation architecture is the rate of learning, where if the value of the learning rate is too high then the network architecture becomes unstable otherwise if the value of the learning rate is too low the network architecture converges and takes a long time in training network architecture. This research data is secondary data sourced from UCI Data Mechine Learning. The best network architecture in this study is 13-10-3, with different learning rates ranging from 0.01, 0.03, 0.06, 0.01, 0.13, 0.16, 0.2, 0.23, 0.026, 0.3, 0.35, 0.4, 0.45, 0.5, 0.55, 0.6, 0.65, 0.7, 0.75, 0.8, 0.9. From the 21 different learning rate values in the 13-10-3 network architecture, it is found that the level of learning rate is very important to get the right and fast network architecture. This can be seen in experiments with a learning rate of 0.65 can produce a better level of accuracy compared to a learning rate smaller than 0.65.
Penerapan Algoritma K-Medoids dalam Pengelompokan Balita Stunting di Indonesia Halimatusakdiah Pohan; Muhammad Zarlis; Eka Irawan; Harly Okprana; Yuegilion Pranayama
JUKI : Jurnal Komputer dan Informatika Vol. 3 No. 2 (2021): JUKI : Jurnal Komputer dan Informatika, Edisi November 2021
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53842/juki.v3i2.69

Abstract

Stunting adalah kondisi gagal tumbuh pada balita akibat kekurangan asupan gizi dan infeksi yang berkepanjangan yang mengakibatkan tinggi badan yang lebih pendek dari standar usianya. Indonesia saat ini menjadi urutan ke 4 dalam tingginya kasus prevelensi stunting menurut standar World Health Organization. Adapun tujuan dari penelitian ini untuk mengelompokkan provinsi mana yang mengalami bayi stunting dengan cluster tertinggi maupun cluster terendah yang berguna sebagai masukan bagi pemerintah untuk menangani dengan cepat penurunan stunting di Indonesia. Data yang digunakan dari penelitian ini di dapat dari Badan Pusat Statistika (BPS) dengan nama indikator Prevelensi Stunting tahun 2015-2018. Dalam penelitian ini data di olah dengan menggunakan Algoritma K-Medoids yang merupakan salah satu bagian dari algoritma clustering yang dapat memecahkan dataset ke kelompok-kelompok diantara semua objek data dengan menggunakan objek sebagai perwakilan (medoid) dalam sebuah cluster.
Co-Authors Agus Perdana Windarto Ambariyanto Ambariyanto Andi Sahputra Annas Prasetio Aulanda, Lulu Bahrudi Efendi Damanik Cici Astria Dea Dwi Rizki Tampubolon Dedy Hartama Eka Irawan Eka Irawan F Fitriyani Hadinata, Jaya Tata Halimatusakdiah Pohan Haryoto, Parawystia Prabasini Hasudungan Siahaan Hendro Sanjaya Heru Satria Tambunan Heru Satria Tambunan Ilham Syahputra Saragih Ina Syafitri Ingkana Devi Cahaya Irfan Sudahri Damani, Irfan Sudahri Jaya Tata Hardinata Jaya Tatahardinata Millah Sari Muhammad Zarlis Nasution, Rizki Alfadillah Nasution, Selvi Salsabillah Nasution, Siti Andry Yani Poningsih Poningsih Poningsih Poningsih, Poningsih Primatua Sitompul Retno Ayu Syahfitri Riki Winanjaya Rizky Khairunnisa Sormin Sepridho, Jaka Sonia Tarigan Syahputra, Muhammad Riza Tri Ayu Lestari Tri Novika Wanto, Anjar Widodo Saputra Winanjaya, Riki Yuegilion Pranayama