Article Per Year (5 Year)
p-Index From 2020 - 2025
1.116
P-Index
This Author published in this journals
All Journal Riau Journal of Computer Science MATRIK : Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer JURNAL TEKNOLOGI DAN ILMU KOMPUTER PRIMA (JUTIKOMP) Jurnal Mantik Jurnal Informatika dan Rekayasa Perangkat Lunak REMIK : Riset dan E-Jurnal Manajemen Informatika Komputer Budapest International Research and Critics Institute-Journal (BIRCI-Journal): Humanities and Social Sciences Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI)
Abdi Dharma
Universitas Prima Indonesia
Religion Arts Humanities Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Languange, Linguistic, Communication & Media Social Sciences

Published : 10 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 10 Documents
Search

 1 
Analisa Perbandingan Sistem Pendeteksian Kemiripan Judul Skripsi Menggunakan Algoritma Winnowing Dan Algoritma Rabin Karp Sibarani, Lelawati; Magdalena, Magdalena; Dharma, Abdi
REMIK: Riset dan E-Jurnal Manajemen Informatika Komputer Vol. 4 No. 1 (2019): Remik Volume 4 Nomor 1 Oktober 2019
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (441.008 KB) | DOI: 10.33395/remik.v4i1.10174

Abstract

Dalam Perguruan Tinggi salah satu kewajiban yang harus dilakukan adalah penyelesaian tugas akhir yaitu skripsi. Sebagian besar mahasiswa saat ini banyak yang melakukan kecurangan atau pun cara yang tidak efektif dalam menyelesaikan skripsinya, salah satu yang sering dilakukan adalah copy-paste dari skripsi atau jurnal yang sudah ada sebelumnya atau bisa disebut plagiarisme. Tindakan plagiarisme atau penjiplakan ini dilakukan dengan cara yang sangat mudah yaitu mereka yang dapat mengganti sebagian kata-kata dengan mengambil sinonim dari artikel tersebut. Solusi yang dapat diberikan untuk mengatasi masalah seperti ini yaitu dengan system pendeteksian kemiripan judul atau pun teks skripsi yang dilakukan dengan menggunakan Algoritma Winnowing dan Algoritma Rabin-Karp. Algoritma winnowing ini digunakan untuk mendeteksi adanya keberadaan kesamaan kata dalam dua buah judul, sedangkan Algoritma Rabin-Karp digunakan untuk melakukan pendeteksian atau pun pencarian untuk string yang berjumlah banyak. Oleh sebab itu dengan adanya aplikasi ini akan sangat membantu dan memudahkan dosen atau pun kaprodi dalam melakukan pengecekan judul skripsi. Pengujian algoritma winnowing dan rabin-karp ini memiliki tingkat akurasi yang sudah mendekati 75% dan dirancang dapat membandingkan dua judul skripsi.
Analisa Metode Random Forest Tree dan K-Nearest Neighbor dalam Mendeteksi Kanker Serviks Andrian; Steele; Salim, Edward Suwandy; Hartato Bindan; Endy Pranoto; Abdi Dharma
Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI) Vol. 3 No. 2 (2020): Jurnal Ilmu Komputer dan Sistem Informasi
Publisher : Utility Project Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.9767/jikomsi.v3i2.73

Abstract

Kanker serviks menyerang sel pada leher rahim penderita. Kanker serviks menduduki peringkat dua sebagai penyebab kanker wanita di seluruh dunia. Dari data WHO (World Health Organization), setiap tahun 500.000 wanita terdiagnosis kanker serviks dan 300.000 diantaranya meninggal dunia. Angka kematian akibat kanker serviks terus meningkat sepanjang tahun. Angka kematian dari penyakit tersebut dapat mencapai 60% dan kebanyakan dari mereka adalah petitborgeois atau lebih rendah karena mereka tidak mampu untuk didiagnosis lebih awal. Hinselmann, Schiller, Citology, dan Biopsy merupakan empat teknik skrining untuk mendiagnosis ada tidaknya sel kanker pada serviks pasien. Dalam penelitian ini dataset riwayat kesehatan pasien akan dianalisis menggunakan algoritma Random Forest Tree dan KNN. Kedua algoritma tersebut akan dibandingkan untuk mencari model yang paling akurat untuk diimplementasikan guna mengetahui pola pada pasien kanker serviks dan memprediksi hasil skrining pasien apakah positif kanker serviks atau negatif. Hasil penelitian ini diolah dengan menggunakan kode pemrograman Python sebanyak 214 data uji dari total 854 data. Akurasi akhir ditunjukkan 88,7% untuk Random Forest dan 90,6% untuk KNN. Set data yang digunakan memiliki empat klasifikasi target yang merupakan klasifikasi multilabel. KNN terbukti lebih maju dalam memprediksi klasifikasi multilabel dalam mendeteksi pola kasus penderita kanker serviks
Aplikasi Pembelajaran Linked List Berbasis Mobile Learning Abdi Dharma; Hendra Handoko Syahputra P
RJOCS (Riau Journal of Computer Science) Vol. 4 No. 1 (2018): Riau Jurnal of Computer Science
Publisher : RJOCS (Riau Journal of Computer Science)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (535.124 KB) | DOI: 10.30606/rjocs.v4i1.1442

Abstract

Data structure is a subject that must be taken by a student in Informatics Engineering course. In the process of teaching and learning, students always have difficulty and confusion to study the course of data structures, especially the material Linked List. This is due to the complexity of the workings of the linked list itself. Learning media can be found through various media such as books, journals, e-books, computers, mobile learning, and others. With technology-based mobile learning, researchers are trying to design Linked List learning software. With this application is expected to help students to understand both the workings and processes of the Linked List itself using the model explicit instruction (direct learning). This application is designed as interactive as possible so that students do not feel bored in studying and understanding the material of Linked List. This application displays step by step formation of the Linked List itself and this material can be repeated by students either anywhere and anytime by using Android-based Smartphone.
Penggunaan Machine Learning Di Bidang Kesehatan Fangatulo Dodo Telaumbanua; Peringatan Hulu; Togar Zulfiter Nadeak; Rikky Romeo Lumbantong; Abdi Dharma
JURNAL TEKNOLOGI DAN ILMU KOMPUTER PRIMA (JUTIKOMP) Vol. 2 No. 2 (2019): Jutikomp Volume 2 Nomor 2 Oktober 2019
Publisher : Fakultas Teknologi dan Ilmu Komputer Universitas Prima Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34012/jutikomp.v2i2.657

Abstract

Machine learning adalah pembelajaran mesin yang sangat membantu dalam menyelesaikan masalah, membuat mudah dalam mengerjakan sesuatu. Dibidang rumah sakit atau bidang kesehatan, machine learning membuat mudah dalam mengerjakan sesuatu, contohnya dokter bisa mendiagnosa penyakit jantung dalam waktu cepat tanpa memakan waktu yang lama. Dengan semakin pesat informasi tentang machine learning sebagai mesin yang bisa belajar sendiri tanpa harus dikontrol tiap pemakain.mempunyai kekurangan dan kelebihan. Kelebihan dari artikel ini adalah semua bersifat baru, artikelnya diterbitkan tahun ini, serta memberikan rincian hasil yang sesuai dengan yang diharapkan serta dalam penulisannya singkat dan jelas. Kekurangan dari artikel ini adalah bahan atau dataset yang digunakan tergolong sedikit dan tidak menggunakan banyak data serta menggunakan references yang telalu lama. Berdasarkan hasil penelitian yang dilakukan, machine learning sangatlah bermanfaat dibidang kesehatan dan juga bidang lainnya, yang mebuat segala sesuatu menjadi mudah.
Pengenalan Plat Kendaraan Bermotor dengan Menggunakan Metode Template Matching dan Deep Belief Network Michael Michael; Frenky Tanoto; Eric Wibowo; Frenky Lutan; Abdi Dharma
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol 19 No 1 (2019)
Publisher : LPPM Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1190.47 KB) | DOI: 10.30812/matrik.v19i1.475

Abstract

The license plate of the vehicle is unique and is only owned by one vehicle per vehicle plate series, to make it easier for the police, especially the traffic police, to track traffic violators through the vehicle number plate. The Deep Belief Network algorithm works by processing the dataset through 3 stages, where the first layer is trained, the results of the first layer are then re-trained, and the results of the second layer calculation are made into the third layer count, the mean results on the calculation of the third layer become the result of learning Deep Belief Network then with the Template Matching algorithm, Deep Belief Network is assisted with the introduction of vehicle plates. In a study conducted using the DBN algorithm with the Template Matching method succeeded in recognizing a vehicle plate with a success percentage of 80% from 20 trials. The experiments carried out included plates that were not clearly seen. Failures that occur in the trials are generally due to under- or over-lighting on the vehicle plate.
LVQ Algorithm for The Classification of Hypertension Based on ESH Guideline Elvandric Lase; Wonderson Wonderson; Christensen Christensen; Dinda Afrianti; Andika Dian Permana; Abdi Abdi Dharma
Jurnal Mantik Vol. 4 No. 3 (2020): November: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mantik.Vol4.2020.1006.pp1772-1778

Abstract

Hypertension was a global health problem, including Indonesia, that increases mortality, morbidity, and cost. In Indonesia, hypertension kept on increasing due to change in lifestyle, consumptions of food with a high level of fat, cholesterol, less physical activity, and a high level of stress, etc. One of the classifications of hypertension used in some country were European Society of Hypertension (ESH) guideline. Learning Vector Quantization (LVQ) was a method in machine learning for classifying data. LVQ were often used in pattern recognition processes such as images, sounds, etc. The purpose of this study was to see an increase in accuracy of hypertension classification based on ESH guideline as weight data. In this study, hypertension classification based on ESH guideline was used as weight data with LVQ method and the parameters used were 2 features, 100 epochs, 0.05 learning rate, 0.01 reducing factor, train data 70%, validation data 30%, and test data 30% from total data used. The result obtained in this study were 94.6667% in the hypertension classification process based on ESH guideline using LVQ method. The conclusion of this study, there was an increase in the accuracy of hypertension classification based on ESH guideline using the LVQ method.
Comparative Analysis of Convolutional Neural Network Methods in Detecting Mask Wear Handoko Handoko; Fahrul Rozy; Felix Elbert Gani; Abdi Dharma
Budapest International Research and Critics Institute-Journal (BIRCI-Journal) Vol 5, No 2 (2022): Budapest International Research and Critics Institute May
Publisher : Budapest International Research and Critics University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33258/birci.v5i2.5605

Abstract

Covid19 is a disease caused by the Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2). As a result, the respiratory system becomes disrupted. The spread of this disease is very easy through droplets. The use of masks is one way to prevent being attacked by this virus. The system for detecting the use of masks is very necessary for today in detecting whether someone is wearing a mask. Convolutional Neural Network (CNN) is a method that can be used to detect masks. In this study, the VGG16, Resnet50, and MobileNet models will be used. Before conducting data training, data preprocessing and data augmentation were carried out on the dataset. The test accuracy of the VGG16, Resnet50, and MobileNet models are 96% and 96% and 98%, respectively. From the test results, it is found that the MobileNet model is more appropriate in the case of mask detection. The conclusion obtained is the use of the MobileNet architecture, the resources used for classifying can be reduced compared to other architectures. MobileNet uses the Depth-Wise Separable method in the computing process which reduces the computational process.
Classification Of Indonesian Slang Using Naïve Bayes And Decision Tree Methods On Social Media Abdi Dharma; Aditya Calderon Naibaho; Lolo Mulatua Bancin; Alhoi Andrew Jefferson
Jurnal Mantik Vol. 6 No. 2 (2022): August: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mantik.v6i2.2647

Abstract

At this time the application of language that appears on social media is the application of slang as a character of current language development. This phenomenon deserves to be discussed because it can find out how much slang is used on social media. The source of the dataset for this research is the verbal form found on the author's personal social media such as Instagram and Tiktok obtained by the web scraping method as many as 2,000 samples and the data will be divided into two categories, namely the category of slang and non-slang. This study aims to compare two classification algorithms, namely Naïve Bayes and Decision Tree to see which algorithm is more effective in classifying how many social media users use slang in commenting based on the dataset we have collected, so that results are obtained to see how high the percentage of usage is. Indonesian people's slang in commenting on social media.
Smart Prediction Model For Unplanned Icu Transfer Based On Deep Learning Optimization : An Article Review Sumita Wardani; Muhammad Uwais Akbar; A. Henpra Yogi Sitanggang; Joshua Baen Tupa; Johanes Pardede; Abdi Dharma
Jurnal Mantik Vol. 6 No. 2 (2022): August: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)
Publisher : Institute of Computer Science (IOCS)

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

Abstract

Problem on units ICU already is problem which critical and already happened since long ago, for the ICU is one of the highest costs unit in hospitals, which made a system to predict activity on ICU is very demanding. COVID-19 shows the need for excellent time management in dealing with the abnormal flow of patients. Prediction of ICU transfer can be useful for patients and medical personnel to reduce medical cost and giving the time required by the nurses to prepare themselves for a huge patients flow. Reviews of related articles are carried out through the Google Scholar database. Screening then conducted based on identified article based on criteria eligibility. There are 7 final articles that assessed on a large scale data samples, method algorithm, and performance from the model which used on the article. Results obtained from this study which follow PRISM flow show a number of variable indicators that are commonly applied, namely: age, gender, liver function, blood pressure, pulse rate, temperature, respiratory rate, kgd and ECG data features. The best test results was achieved by research by Jonathan Rubin, et al due to the large number of varied data sets used, much more than other studies. This research also used adaptive boosting and gradient tree boosting approaches and evaluated with 4 main parameter that is accuracy, sensitivity, specificity, and AUC ROC. This study succeed in reaching performance evaluation model of 72.8% sensitivity, 76.3% specificity, 76.2% accuracy and 79.9% AUC ROC
Classification Model Analysis of ICU Mortality Level using Random Forest and Neural Network Lymin Lymin; Alvin Alvin; Bodhi Lhoardi; Darwis Darwis; Joseph Siahaan; Abdi Dharma
Jurnal Informatika dan Rekayasa Perangkat Lunak Vol 5, No 2 (2023): September
Publisher : Universitas Wahid Hasyim

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36499/jinrpl.v5i2.8749

Abstract

Based on the results of previous studies, research on machine learning for predicting ICU patients is crucial as it can aid doctors in identifying high-risk individuals. A high accuracy in machine learning models is necessary for assisting doctors in making informed decisions. In this study, machine learning models were developed using two models, namely Random Forest and Artificial Neural Network (ANN), to predict patient mortality in the ICU. Patient data was obtained from The Global Open Source Severity of Illness Score (GOSSIS) and underwent preprocessing to address issues of missing values and imbalanced data. The data was then divided into training, validation, and testing sets for model training and evaluation. The results of the study indicate that the Random Forest model performs better with an accuracy of 93% on the testing data compared to the ANN which only achieved an accuracy of 86% on the testing data. Consequently, the Random Forest model can be utilized as a solution for predicting patient mortality in the ICU.
Co-Authors A. Henpra Yogi Sitanggang Aditya Calderon Naibaho Alhoi Andrew Jefferson Alvin Alvin Andika Dian Permana Andrian Bodhi Lhoardi Christensen Christensen Darwis Darwis Dinda Afrianti Elvandric Lase Endy Pranoto Eric Wibowo FAHRUL ROZY Fangatulo Dodo Telaumbanua Felix Elbert Gani Frenky Lutan Frenky Tanoto Handoko Handoko Hartato Bindan Hendra Handoko Syahputra Pasaribu, Hendra Handoko Johanes Pardede Joseph Siahaan Joshua Baen Tupa Lolo Mulatua Bancin Lymin Lymin Magdalena Magdalena Michael Michael Muhammad Uwais Akbar Peringatan Hulu Rikky Romeo Lumbantong Salim, Edward Suwandy Sibarani, Lelawati Steele Sumita Wardani Togar Zulfiter Nadeak Wonderson Wonderson