Article Per Year (5 Year)
p-Index From 2020 - 2025
3.329
P-Index
This Author published in this journals
All Journal Jurnal TIMES Sinkron : Jurnal dan Penelitian Teknik Informatika Journal Information System Development METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi METHODIKA: Jurnal Teknik Informatika dan Sistem Informasi Jurnal Informatika Kaputama (JIK) Jurnal Pengabdian Pada Masyarakat METHABDI Majalah Ilmiah METHODA TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akuntansi Jurnal Pengabdian Masyarakat Nauli
Indra Kelana Jaya
Universitas Methodist Indonesia
Religion Agriculture, Biological Sciences & Forestry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Engineering Immunology & microbiology Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Medicine & Pharmacology Physics Public Health Social Sciences

Published : 27 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 27 Documents
Search

 1   2   3 
ENSEMBLE LEARNING DENGAN METODE SMOTEBAGGING PADA KLASIFIKASI DATA TIDAK SEIMBANG Siringoringo, Rimbun; Jaya, Indra Kelana
Journal Information System Development (ISD) Vol 3, No 2 (2018): Journal Information System Development (ISD)
Publisher : UNIVERSITAS PELITA HARAPAN

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

Abstract

Unbalanced data classification is a crucial problem in the field of machine learning and data mining. Data imbalances have a poor impact on classification results where minority classes are often misclassified as a majority class. Conventional machine learning algorithms are not equipped with the ability to work on unbalanced data, so the performance of conventional algorithms is always not optimal. In this study, ensemble learning using SMOTEBagging method was applied to classify 11 unbalanced datasets. SMOTEBagging performance is also compared with three types of conventional classification algorithms namely SVM, k-NN, and C4.5. By applying the 5 cross-validation scheme, the AUC value generated by SMOTEBagging is higher at 10 datasets. The mean values of the lowest to highest AUC were obtained by SVM, k-NN, C4.5 and SMOTEBagging algorithms with values 0.638, 0.742, 0.770 and 0.895. By applying Friedman test it was found that the performance of AUC SMOTEBagging differed significantly with the other three conventional methods SVM, k-NN and C4.5ENSEMBLE LEARNING DENGAN  METODE  SMOTEBagging PADA KLASIFIKASI DATA TIDAK SEIMBANG
Analisa Alokasi Memori dan Kecepatan Kriptograpi Simetris Dalam Enkripsi dan Dekripsi Perangin-angin, Resianta; Jaya, Indra Kelana; Rumahorbo, Benget; Marpaung, Berlian Juni R
Journal Information System Development (ISD) Vol 4, No 1 (2019): Journal Information System Development (ISD)
Publisher : UNIVERSITAS PELITA HARAPAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (601.236 KB)

Abstract

Currently the focus of cryptography is on the security and speed of data transmission. Cryptography is the study of how to secure information. This security is done by encrypting the information with a special key. This information before being encrypted is called plaintext. After being encrypted with a key called ciphertext. At present, AES (Advanced Encryption Standard) is a cryptographic algorithm that is safe enough to protect confidential data or information. In 2001, AES was used as the latest cryptographic algorithm standard published by NIST (National Institute of Standard and Technology) in lieu of the DES (Data Encryption Standard) algorithm that has expired. The AES algorithm is a cryptographic algorithm that can encrypt and decrypt data with varying key lengths, namely 128 bits, 192 bits, and 256 bits. From the results of tests carried out for speed and classification memory, it can be concluded that the AES cryptographic algorithm is superior or faster if the size or size of the plaint text is not so large, because for the smaller AES algorithm the speed ratio in terms of encryption will become more fast, it becomes very different for the Blowfish algorithm itself where for large sizes plaint text can be encrypted faster than AES but for smaller sizes Blowfish is certainly slower in that case, for memory allocation in this case from the tests performed it can be concluded that AES requires more storage space or larger memory allocation compared to the blowfish algorithm
Machine Learning for Handoffs Classification Based on Effective Communication History Simbolon, Anita Ira Agustina; Pujiastuti, Maria; Jaya, Indra Kelana; Tarigan, Kerista; Sinambela, Marzuki
Sinkron : jurnal dan penelitian teknik informatika Vol. 3 No. 2 (2019): SinkrOn Volume 3 Number 2, April 2019
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (248.188 KB)

Abstract

An important step in data effective communication in handoffs process analysis is data exploration and representation. Communication in handoff treatment is crucial to protect the patients and it can lead to patient’s safety, discontinue care of a patient or the cause loss of important information related to the continuum of care. In this case, we use the machine learning technique by using Support Vector Machine for classification the handoffs for twenty weeks to analysis and represented based on the effective communication history. We used handoffs dataset which employed from Arifin Achmad Hospital in Pekanbaru, Indonesia. The result indicated the performance of the designed system was successful and could be used in handoffs analysis based on the effective communication histories in Arifin Achmad Hospital in Pekanbaru, Indonesia.
Analisa Perbandingan Rasio Kecepatan Kompresi Algoritma Dynamic Markov Compression Dan Huffman Jaya, Indra Kelana; Perangin-angin, Resianta
Sinkron : jurnal dan penelitian teknik informatika Vol. 2 No. 2 (2018): SinkrOn Volume 2 Nomor 2 April 2018
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (827.074 KB)

Abstract

Kompresi menjadi penting dikarenakan penyimpanan ruang yang terbatas, oleh karena itu kompresi merupakan satu-satu nya cara untuk meminimalisir percepatan overload size data, dalam penelitian ini dilakukan sebuah ujicoba menggunakan algoritm DMC dan Huffman dalam hal kompresi file, dimana dari 15 iterasi yang dilakukan didapat bahwasanya algoritma DMC untuk setiap iterasi yang dilakukan rata-rata mengkompres diatas 50% dari kapasistas aslinya sedangkan algoritma Huffman diatas 76% untuk hasil kompresi dari setiap file yang di ujikan, sedangkan untuk kecepatan sendiri ini berbanding lurus dengan besarnya file yang telah di kompresi untuk algoritma DMC sendiri apa bila file yang dikompresi masih dalam kapasistas kecil maka algoritma ini akan lebih cepat dibandingkan dengan algoritma Huffman, namun menjadi menarik dikarenakan apabila kompresi file menggunkan size yang cukup besar maka kecepatan kompresi menjadi lebih baik metode Huffman. Rasio ukuran file yang diperoleh dengan algoritma Huffman cukup tinggi berkisar minimal 76% Jadi dapat dikatakan dengan rasio kompresi ini algoritma Huffman sudah dikatakan baik dalam hal mengkompresi file khususnya file .Tingkat kompresi dipengaruhi oleh banyaknya nada yang sama dalam file .Kecepatan proses tidak bergantung pada data yang diproses tetapi berbanding lurus dengan ukuran file , artinya semakin besar ukuran file yang diproses maka semakin lama waktu prosesnya.Proses dekompresi lebih cepat dilakukan dibandingkan dengan proses kompresi karena pada proses dekompresi tidak dilakukan lagi proses pembentukan pohon Huffman dari data melainkan hanya langsung membaca dari tabel code pohon Huffman yang disimpan pada file sewaktu proses kompresi. Kata kunci : huffman, dmc, kompresi, perbandingan, analisa
APLIKASI E-ULOS DENGAN KONSEP CUSTOMER RELATIONSHIP MANAGEMENT UNTUK MEMBANGUN LOYALITAS PELANGGAN Indra Kelana Jaya; Harlen Gilbert Simanullang; Asaziduhu Gea
Jurnal Informatika Kaputama (JIK) Vol 4, No 1 (2020): VOLUME 4 NOMOR 1, EDISI JANUARI 2020
Publisher : STMIK KAPUTAMA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.1234/jik.v4i1.224

Abstract

Bataknese (such as Batak Toba, Karo, Simalungun, Pakpak) in their ceremonial events (birth, marriage, death) are use of Ulos. Gallery Ulos Sianipar is a business unit selling various Batak weaving such as Ulos, Songket, Kebaya and Batak Traditional Clothing. Gallery Ulos Sianipar use minimum Information Technology in business activities. Analysis SWOT (Strength, Weakness, Opportunities, Threat) aims to capture the organization's needs for system development. IDIC Model (Identify, Differentiate, Interact, Customize) aim to implement the concept of customer relationship management to increase the loyalty of customers
Analisa Alokasi Memori dan Kecepatan Kriptograpi Simetris Dalam Enkripsi dan Dekripsi Resianta Perangin-angin; Indra Kelana Jaya; Benget Rumahorbo; Berlian Juni R Marpaung
Journal Information System Development Vol 4, No 1 (2019): Journal Information System Development (ISD)
Publisher : UNIVERSITAS PELITA HARAPAN

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

Abstract

Currently the focus of cryptography is on the security and speed of data transmission. Cryptography is the study of how to secure information. This security is done by encrypting the information with a special key. This information before being encrypted is called plaintext. After being encrypted with a key called ciphertext. At present, AES (Advanced Encryption Standard) is a cryptographic algorithm that is safe enough to protect confidential data or information. In 2001, AES was used as the latest cryptographic algorithm standard published by NIST (National Institute of Standard and Technology) in lieu of the DES (Data Encryption Standard) algorithm that has expired. The AES algorithm is a cryptographic algorithm that can encrypt and decrypt data with varying key lengths, namely 128 bits, 192 bits, and 256 bits. From the results of tests carried out for speed and classification memory, it can be concluded that the AES cryptographic algorithm is superior or faster if the size or size of the plaint text is not so large, because for the smaller AES algorithm the speed ratio in terms of encryption will become more fast, it becomes very different for the Blowfish algorithm itself where for large sizes plaint text can be encrypted faster than AES but for smaller sizes Blowfish is certainly slower in that case, for memory allocation in this case from the tests performed it can be concluded that AES requires more storage space or larger memory allocation compared to the blowfish algorithm
ENSEMBLE LEARNING DENGAN METODE SMOTEBAGGING PADA KLASIFIKASI DATA TIDAK SEIMBANG Rimbun Siringoringo; Indra Kelana Jaya
Journal Information System Development Vol 3, No 2 (2018): Journal Information System Development (ISD)
Publisher : UNIVERSITAS PELITA HARAPAN

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

Abstract

Unbalanced data classification is a crucial problem in the field of machine learning and data mining. Data imbalances have a poor impact on classification results where minority classes are often misclassified as a majority class. Conventional machine learning algorithms are not equipped with the ability to work on unbalanced data, so the performance of conventional algorithms is always not optimal. In this study, ensemble learning using SMOTEBagging method was applied to classify 11 unbalanced datasets. SMOTEBagging performance is also compared with three types of conventional classification algorithms namely SVM, k-NN, and C4.5. By applying the 5 cross-validation scheme, the AUC value generated by SMOTEBagging is higher at 10 datasets. The mean values of the lowest to highest AUC were obtained by SVM, k-NN, C4.5 and SMOTEBagging algorithms with values 0.638, 0.742, 0.770 and 0.895. By applying Friedman test it was found that the performance of AUC SMOTEBagging differed significantly with the other three conventional methods SVM, k-NN and C4.5ENSEMBLE LEARNING DENGAN  METODE  SMOTEBagging PADA KLASIFIKASI DATA TIDAK SEIMBANG
PENERAPAN ALGORITMA SAFE-LEVEL-SMOTE UNTUK PENINGKATAN NILAI G-MEAN DALAM KLASIFIKASI DATA TIDAK SEIMBANG Resianta Perangin-angin; Eva Julia Gunawati Harianja; Indra Kelana Jaya; Benget Rumahorbo
METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 4 No. 1 (2020): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (358.784 KB) | DOI: 10.46880/jmika.Vol4No1.pp67-72

Abstract

Klasifikasi data yang tidak seimbang merupakan masalah yang krusial pada bidang machine learning dan data mining. Ketidakseimbangan data memberikan dampak yang buruk pada hasil klasifikasi dimana kelas minoritas sering disalah klasifikasikan sebagai kelas mayoritas. Dimana kelompok kelas minoritas (minority) adalah kelompok kelas yang memiliki data lebih sedikit, dan kelompok kelas mayoritas (mayority) adalah kelompok kelas yang memiliki jumlah data lebih banyak. Data tidak seimbang adalah suatu kondisi dimana jumlah contoh dari salah satu kelas jauh lebih banyak dari kelas yang lain. Alasan buruknya kinerja metode klasifikasi biasa yang digunakan pada data tidak seimbang adalah bahwa tujuan metode klasifikasi dalam meminimumkan galat secara keseluruhan tidak dapat tercapai karena kelas minoritas hanya sedikit memberikan kontribusi, selain itu keputusan akhir yang dihasilkan tidak tepat karena terjadinya bias. Hal ini disebabkan oleh salah satu kelas mendominasi dalam hal jumlah. Dalam penelitian ini akan berfokus pada peningkatan nilai G-Mean dari dataset yang digunakan, dengan menerapkan algoritma Safe-Level-Smote. Dari hasil ujicoba yang dilakukan terhadap dua dataset yakni Abalon dan Vowel, untuk skema Smote + k-NN nilai G-Mean yang didapat yakni 0,47 untuk dataset Abalon dan 0.94 untuk dataset Vowel. Seletah dilakukan ujicoba terhadap dataset yang sama menggunakan skema Safe-Level-Smote menggunakan algoritma klasifikasi k-NN didapat hasil G-Mean 0,59 untuk dataset Abalon dan 1.00 Untuk dataset Vowel, rerata dari kenaikan nilai G-Mean terhadap algoritma Smote sebesar 12,68%. Hal ini membuktikan bahwasanya algoritma Safe-Level-Smote dapat meningkatkan nilai G-Mean pada klasifikasi data tidak seimbang menggunakan algoritma klasifikasi k-Nearst Neighbors.
PENERAPAN METODE DECISION TREE C4.5 DALAM MEMPREDIKSI KELANCARAN PEMBAYARAN KREDIT DI BPR WAHANA BERSAMA KPUM Nine Situmeang; Indra Kelana Jaya; Margaretha Yohanna
METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 6 No. 2 (2022): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (850.215 KB) | DOI: 10.46880/jmika.Vol6No2.pp215-220

Abstract

BPR Wahana Bersama KPUM is a lending company. Delay in credit payments is a problem that occurs in credit companies. Customers who don't pay on time can have a bad impact on their credit history. To assess customer profitability, a system is needed that can predict the smoothness of future credit payments in order to assess whether customers are profitable or not. The author uses the Decision Tree C4.5 method in which the method looks for similarities between classes or groups in the data. In this study, the data used is customer data, with training data from 2017-2020 and testing data from 2021. The existence of this system can help BPR Wahana Bersama KPUM in predicting the smoothness of credit payments in the future so that there will be no credit payment jams by customers. , this is proven by the acquisition of the accuracy value using the confusion matrix model reaching 84.18%.
PEMBUATAN MEDIA PEMBELAJARAN DARING PADA MASA PANDEMI COVID-19 DI SMA MASEHI GBKP BRASTAGI, KABUPATEN KARO Surianto Sitepu; Jimmy Febrynus Naibaho; Naikson Fandier Saragih; Samuel Van Basten Manurung; Indra Kelana Jaya; Alfonsus Situmorang; Imelda Sri Dumayanti; Asaziduhu Gea; Benget Rumahorbo; Marzuki Sinambela; Yolanda Yulianti Pratiwi Rumapea; Margaretha Yohanna; Harlen Gilbert Simanullang; Dandi Daniel Siregar
Jurnal Pengabdian Pada Masyarakat METHABDI Vol 1 No 1 (2021): Jurnal Pengabdian Pada Masyarakat METHABDI
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (440.638 KB) | DOI: 10.46880/methabdi.Vol1No1.pp52-56

Abstract

Learning that uses electronic services as a tool is known in general as e-learning or LMS (Learning Management System). Training on e-learning is realized in Community Service Activities (PKM) as the implementation of the Tri Dharma of Higher Education as well as sharing and contributing ideas and transferring knowledge and technology for teachers and students at SMA Masehi GBKP, Brastagi. This service activity was carried out for a day, with material on Making Online Learning Media during the COVID-19 Pandemic. The material for the activities carried out included making online learning media using Edmodo and Easy Class. The online learning media is one of the effective solutions to facilitate online teaching and learning activities for teachers and students. His presence, which is increasingly easy to find, certainly helps teachers and students stay safe studying at home, without being limited by place and time.
Co-Authors Albert Harianja Ambarita, Indah Aritonang, Mendarissan Azli, Putri Berlian Juni R Marpaung Dandi Daniel Siregar Darwis Robinson Manalu DEWI SARTIKA Dian Agaventa, Chrissandro Dumayanti, Imelda Sri Ericho Elovando Surbakti Eva Julia Gunawati Harianja Eva Julia Gunawati Harianja, Eva Julia Gunawati Fajar Fati Gratianus Nafiri Larosa Feruche, Melani Gea, Asaziduhu Girsang, Jhon Vebrianto Harlen G. Simanullang Harlen Gilbert Simanullang Helen Fransisca Simanungkalit Humuntal Rumapea Imelda Sri Dumayanti Jeudi A. T. P. Sianturi Jimmy F. Naibaho Larosa, Fati G. N. Larosa, FGN Larosa Lyna M. N. Hutapea Manurung, Samuel Mariana Tri Susanti Marpaung, Berlian Juni R Marzuki Sinambela Marzuki, Sinambela Melani Feruche Mufria J. Purba Naibaho, Jimmy F. Naikson Fandier Saragih Nine Situmeang Nova Soraya Simanjuntak Panjaitan, Efdi Sarjono Pujiastuti, Maria Putra, Reza Ananda Rambe, Lima Hartima Resianta Perangin-Angin Rika Rosnelly, Rika Rimbun Siringoringo, Rimbun Rumahorbo, Benget Sagala, Tamado Simon Samuel Van Basten Manurung Saragih, Naikson F. Silalahi, Arina Prima Silalahi, Veraci Simanullang, Harlen Simanullang, Harlen Gilbert Simbolon, Anita Ira Agustina Sinambela Marzuki Siska Narulita Siboro Surianto Sitepu Surianto Sitepu Susanti, Mariana Tri Tarigan, Kerista Widya Ompusunggu Yohanna, Margaretha Yolanda Y. P. Rumapea yolanda yulianti pratiwi rumapea Zai, Andreas