Article Per Year (5 Year)
p-Index From 2019 - 2024
3.492
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Jurnal Ilmu Komputer Perfecting a Video Game with Game Metrics Jurnal Teknologi Informasi dan Ilmu Komputer Proceedings Konferensi Nasional Sistem dan Informatika (KNS&I) POSITIF KLIK (Kumpulan jurnaL Ilmu Komputer) (e-Journal) Jurnal Komputasi Jurnal Mnemonic Journal of Data Science and Software Engineering Jurnal Informatika Polinema (JIP)
Radityo Adi Nugroho
Universitas Lambung Mangkurat
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Library & Information Science

Published : 36 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 36 Documents
Search

 1   2   3   4 
Peramalan Permintaan Paving Blok dengan Metode ARIMA Nofiyanto, Adin; Nugroho, Radityo Adi; Kartini, Dwi
Proceedings Konferensi Nasional Sistem dan Informatika (KNS&I) 2015
Publisher : Proceedings Konferensi Nasional Sistem dan Informatika (KNS&I)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (438.595 KB)

Abstract

Persaingan usaha di bidang pembuatan paving blok yang harus dihadapi perusahaan Benawa Putra khususnya didaerah banjarbaru semakin berat. Oleh karena untuk menghadapi tuntutan persaingan pasar perlu dilakukan analisa lingkungan usaha yang terus berkembang dan memprediksi segala yang dapat mempengaruhi kelangsungan usahanya. Metode yang digunakan pada peramalan ini adalah metode ARIMA, kelebihan dari metode ini dapat menerima semua jenis model data walaupun dalam prosesnya harus distasionerkan dulu. Serta metode ini lebih akurat jika digunakan untuk peramalan jangka pendek.
Klasifikasi Kelulusan Mahasiswa Menggunakan Algoritma Learning Vector Quantization Kartini, Dwi; Nugroho, Radityo Adi; Faisal, Mohammad Reza
POSITIF : Jurnal Sistem dan Teknologi Informasi Vol 3 No 2 (2017): POSITIF - Jurnal Sistem dan Teknologi Informasi
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/positif.v3i2.420

Abstract

Computer Science Study Program FMIPA ULM graduates dozens of undergraduate students every year. One of the assessment criteria for the accreditation of the study program is the assessment of the duration of the study of students who graduated on time. In this research will be done classification of graduation based on the status of student study year = timely and study length 4.5 years = not on time. Classification of students passing graduation based on IP semester I, Semester II, Semester III and Semester IV that have passed. If a system can classify students' graduation as a predictor of the duration of a student study, it is expected to be a recommendation for the Academic Advisors lecturers giving advice to students who are detected in the timely graduation possibilities so that Drop Out (DO) prevention measures may be taken earlier. Accuracy results are in accordance with the test data of 70% by using α = 0.5, decrement alfa 0.35 and maxepoch = 500.
Improvement on KNN using genetic algorithm and combined feature extraction to identify COVID-19 sufferers based on CT scan image Radityo Adi Nugroho; Arie Sapta Nugraha; Aylwin Al Rasyid; Fenny Winda Rahayu
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 19, No 5: October 2021
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v19i5.18535

Abstract

Coronavirus disease 2019 (COVID-19) has spread throughout the world. The detection of this disease is usually carried out using the reverse transcriptase polymerase chain reaction (RT-PCR) swab test. However, limited resources became an obstacle to carrying out the massive test. To solve this problem, computerized tomography (CT) scan images are used as one of the solutions to detect the sufferer. This technique has been used by researchers but mostly using classifiers that required high resources, such as convolutional neural network (CNN). In this study, we proposed a way to classify the CT scan images by using the more efficient classifier, k-nearest neighbors (KNN), for images that are processed using a combination of these feature extraction methods, Haralick, histogram, and local binary pattern. Genetic algorithm is also used for feature selection. The results showed that the proposed method was able to improve KNN performance, with the best accuracy of 93.30% for the combination of Haralick and local binary pattern feature extraction, and the best area under the curve (AUC) for the combination of Haralick, histogram, and local binary pattern with a value of 0.948. The best accuracy of our models also outperforms CNN by a 4.3% margin.
Implementasi Reduksi Fitur t-SNE Pada Clustering Gambar Head shape Nematoda Muhammad Rizky Adriansyah; Mohammad Reza Faisal; Abdul Gafur; Radityo Adi Nugroho; Irwan Budiman; Muliadi Muliadi
Jurnal Komputasi Vol 10, No 1 (2022)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v10i1.2963

Abstract

Pada penelitan ini dilakukan clustering terhadap gambar head shape nematoda, dalam melakukan pengolahan gambar diperlukan metode ekstraksi fitur untuk menemukan informasi penting dari gambar yang akan diolah, salah satu esktraksi fitur yang bisa digunakan adalah wavelet. Setelah gambar melewati ekstraksi fitur dihasilkan sebanyak 5624 fitur, dengan fitur sebanyak ini dapat mengakibatkan waktu komputasi yang lama. Oleh sebab itu perlu dilakukan reduksi fitur untuk mengurangi jumlah fitur yang awalnya 5624 fitur menjadi 2 atau 3 fitur saja, salah satu metode reduksi fitur terbaru yang bisa digunakan adalah t-SNE. Pada penelitian ini dilakukan perbandingan hasil kualitas cluster antara yang menggunakan reduksi fitur dengan yang tidak. Hasil Silhouette Index   yang didapatkan tanpa reduksi fitur adalah 0.046 dan setelah menggunakan reduksi fitur t-SNE terjadi peningkatan yang cukup signifikan menjadi 0.418.
Metrics Based Feature Selection for Software Defect Prediction Radityo Adi Nugroho; Friska Abadi; M. Reza Faisal; Rudy Herteno; Rahmat Ramadhani
Jurnal Komputasi Vol 8, No 2 (2020)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/komputasi.v8i2.2670

Abstract

Nowadays, software is very influential on various sectors of life, both to solve business needs, as well as personal needs. To have a Software with high quality, testing is needed to avoid software defect. Research on software defects involving Machine Learning is currently being carried out by many researchers. This method contains one important step, which is called feature selection. In this study, researchers conducted a feature selection based on the software metric category to determine the level of accuracy of the prediction of software defects by utilizing 13 (thirteen) datasets from NASA MDP namely CM1, JM1, KC1, KC3, KC4, MC1, MC2, MW1, PC1, PC2, PC3, PC4, and PC5. To classify, the researchers involved 5 (five) classifiers, namely Naive Bayes, Decision Trees, Random Forests, K-Nearest Neighbor, and Support Vector Machines. The research result shows that each attribure on software metric categories has effect on each dataset. Naive Bayes Algorithm and Random Forest Algorithm can give better performance than other algorithm in classifieng software defect with feature selection based on metrics. On the other hand, the best metrics category on each classifier algorithm is metric Misc. From average AUC value, it can be concluded that metrics category which can give best performance is metric LoC, followed by metric Misc. Both categories have achieved highest AUC value in Random Forest classifier.
Intrusion Detection System Berbasis Seleksi Fitur Dengan Kombinasi Filter Information Gain Ratio Dan Correlation Nitami Lestari Putri; Radityo Adi Nugroho; Rudy Herteno
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 8, No 3: Juni 2021
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.0813154

Abstract

Intrusion Detection System merupakan suatu sistem yang dikembangkan untuk memantau dan memfilter aktivitas jaringan dengan mengidentifikasi serangan. Karena jumlah data yang perlu diperiksa oleh IDS sangat besar dan banyaknya fitur-fitur asing yang dapat membuat proses analisis menjadi sulit untuk mendeteksi pola perilaku yang mencurigakan, maka IDS perlu mengurangi jumlah data yang akan diproses dengan cara mengurangi fitur yang dapat dilakukan dengan seleksi fitur. Pada penelitian ini mengkombinasikan dua metode perangkingan fitur yaitu Information Gain Ratio dan Correlation dan mengklasifikasikannya menggunakan algoritma K-Nearest Neighbor. Hasil perankingan dari kedua metode dibagi menjadi dua kelompok. Pada kelompok pertama dicari nilai mediannya dan untuk kelompok kedua dihapus. Lalu dilakukan klasifikasi K-Nearest Neighbor dengan menggunakan 10 kali validasi silang dan dilakukan pengujian dengan nilai k=5. Penerapan pemodelan yang diusulkan menghasilkan akurasi tertinggi sebesar 99.61%. Sedangkan untuk akurasi tanpa seleksi fitur menghasilkan akurasi tertinggi sebesar 99.59%. AbstractIntrusion Detection System is a system that was developed for monitoring and filtering activity in network with identified of attack. Because of the amount of the data that need to be checked by IDS is very large and many foreign feature that can make the analysis process difficult for detection suspicious pattern of behavior, so that IDS need for reduce amount of the data to be processed by reducing features that can be done by feature selection. In this study, combines two methods of feature ranking is Information Gain Ratio and Correlation and classify it using K-Nearest Neighbor algorithm. The result of feature ranking from the both methods divided into two groups. in the first group searched for the median value and in the second group is removed. Then do the classification of  K-Nearest Neighbor using 10 fold cross validation and do the tests with values k=5. The result of the  proposed modelling produce the highest accuracy of 99.61%. While the highest accuracy value of the not using the feature selection is 99.59%.
PERBANDINGAN JUMLAH DATA DAN WAKTU LOADING ANTARA WEB TRADISIONAL DAN WEB BERBASIS AJAX Radityo Adi Nugroho
Jurnal Ilmu Komputer Vol. 4, No. 2 September 2011
Publisher : Informatics Department, Faculty of Mathematics and Natural Sciences, Udayana University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (318.841 KB)

Abstract

Until the beginning of 2005, the characteristic of the web application interaction always depends on the events given by the user. Moreover, must wait for the occurrance of the whole web page to move from one event to another. To repair this problems, appears the Asynchronous Javascript and XML(AJAX) technique which makes the web application similar to desktop application and not depends too much on the event given by the user. Ajax also be claimed has the shorter loading time. However, Ajax also has some weakness because its source code is hard to be written. Some frameworks appear to overcome this weakness, one of them is ASP.NET Ajax.This research tries to make an Ajax web application with ASP.NET Ajax to compare with the traditional web. The compared aspects in this research are the loading time and the data amount. The web application that made is tourism information in Daerah Istimewa Yogyakarta province.The result shows that the traditional web application has the shorter loading time in a whole page refreshing because it passes less data amount rather than Ajax web application using Atlas. However, to change a web page contents, Ajax web application using the ASP.NET Ajax has the shorter loading time because it passes less data amount.
IMPLEMENTASI FUZZY TSUKAMOTO DALAM PENENTUAN KESESUAIAN LAHAN UNTUK TANAMAN KARET DAN KELAPA SAWIT Maya Yusida; Dwi Kartini; Radityo Adi Nugroho; Muliadi Muliadi
KLIK- KUMPULAN JURNAL ILMU KOMPUTER Vol 4, No 2 (2017)
Publisher : Lambung Mangkurat University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/klik.v4i2.115

Abstract

Land suitability is the suitability of a plot of land for a particular use. In the determination of appropriate plant recommendations on land, the Banjarbaru Swampland Food Crops Research Institute sets out 8 criteria in its assessment. These criteria include Soil Depth (cm), CEC Soil (cmol), Saturation Bases (%), pH (H2O), C-Organic (%), N Total (%), P2O5 (mg / 100g), K2O (mg / 100g). Making this expert system using Fuzzy Tsukamoto method. The results obtained from this expert system in the form of data on land suitability for rubber and palm oil plantations that are prioritized to be planted in a field based on the growing requirements of a plant. Keywords: Expert System, Land Suitability, Fuzzy TsukamotoKesesuaian lahan adalah kecocokan sebidang lahan untuk penggunaan tertentu. Dalam penentuan rekomendasi tanaman yang sesuai terhadap lahan, Balai Penelitian Tanaman Pangan Lahan Rawa Banjarbaru menetapkan 8 kriteria dalam penilaiannya. Kriteria tersebut meliputi Kedalaman Tanah (cm), KTK Tanah (cmol), Kejenuhan Basa (%), pH (H2O), C-Organik (%), N Total (%), P2O5 (mg/100g), K2O (mg/100g). Pembuatan sistem pakar ini menggunakan metode Fuzzy Tsukamoto. Hasil yang didapat dari sistem pakar ini berupa data tingkat kesesuaian lahan untuk tanaman karet dan kelapa sawit yang lebih diprioritaskan untuk ditanam disuatu lahan berdasarkan syarat tumbuh suatu tanaman. Kata Kunci : Sistem Pakar, Kesesuaian Lahan, Fuzzy Tsukamoto
UJI EFEKTIVITAS WAKTU IMPLEMENTASI ONE CARD PATIENT SEBAGAI BUSINESS PROCESS REENGINEERING SISTEM INFORMASI KLINIK DOKTER GIGI Septiadi Marwan Annahar; Irwan Budiman; Radityo A Nugroho
KLIK- KUMPULAN JURNAL ILMU KOMPUTER Vol 3, No 2 (2016)
Publisher : Lambung Mangkurat University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/klik.v3i2.61

Abstract

AbstractGenerally a dentist practicing in a hospital or clinic, but for now this started many dentists who open private clinics. Currently the service system is used in every place dental clinic still manual. Less effective this system can also be seen from the process of recording patient data, transactions, computation process of goods or drugs, until the process of recording patient medical report. The resulting report was still in the form of paper are easily lost and damaged, so that the process becomes less effective service even slower. It is necessary to test the effectiveness of the time between the old system to the new system created by implementing Patient As One Card Business Process Re-Engineering dental clinics, in order to obtain a level of efficiency that can be saved in dental patient care process. From the test results based on measurement systems test the effectiveness of a comparison between the old system to the new system, the implementation of one patient cards as business process reengineering make dental clinic services to be faster.Keywords : One Card Patient, Reengineering, Dental Clinic. AbstrakPada umumnya dokter gigi membuka praktik di rumah sakit atau poliklinik, tetapi untuk sekarang ini mulai banyak dokter gigi yang membuka klinik pribadi. Saat ini sistem pelayanan yang digunakan di setiap tempat klinik dokter gigi masih bersifat manual. Kurang efektifnya sistem ini juga dapat dilihat mulai dari proses pencatatan data pasien, transaksi-transaksi, proses perhitungan barang atau obat-obatan, sampai pada proses pencatatan laporan kesehatan pasiennya. Laporan yang dihasilkan pun masih berupa kertas yang mudah hilang dan rusak, sehingga proses pelayanan menjadi kurang efektif bahkan lambat. Maka diperlukan uji efektivitas waktu antara sistem lama dengan sistem yang baru dibuat dengan mengimplementasikan One Card Patient Sebagai Rekayasa Ulang Proses Bisnis klinik gigi, demi untuk mendapatkan tingkat efisiensi waktu yang di bisa dihemat pada proses pelayanan pasien gigi. Dari hasil pengujian berdasarkan sistem pengukuran uji efektivitas waktu membandingkan antara sistem lama dengan sistem yang baru, implementasi one card patient sebagai business process reengineering membuat pelayanan klinik gigi menjadi lebih cepat.Kata kunci : One Card Patient, Rekayasa Ulang, Klinik Gigi
IMPLEMENTASI SSD_RESNET50_V1 UNTUK PENGHITUNG KENDARAAN Muhammad Nur Rizal; Radityo Adi Nugroho; Dodon Turianto nugrahadi; Muhammad Reza Faisal; Friska Abadi
KLIK- KUMPULAN JURNAL ILMU KOMPUTER Vol 8, No 2 (2021)
Publisher : Lambung Mangkurat University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/klik.v8i2.383

Abstract

Google has released the Tensorflow Object Detection API to facilitate deep learning application development using the Tensorflow Object Detection API. The TensorFlow Object Detection API is an open-source framework that can be used to develop, train, and deploy object detection models. In this study, the Tensorflow Object Detection API is implemented in a vehicle counter application with the SSD_Resnet50_v1 detection model. From the research that has been done, applications with the detection of the SSD_Resnet50_v1 model get an accuracy of 56.49% in calculating motor-type vehicles and 54.43% for car-type vehicles.Kata Kunci : SSD_Resnet50_v1, Vehicle Counting, Tensorflow Object Detection APIGoogle telah merilis Tensorflow Object Detection API untuk mempermudah pengembangan aplikasi Deep learning dengan menggunakan Tensorflow Object Detection API. TensorFlow Object Detection API adalah open source framework yang dapat digunakan untuk mengembangkan, melatih, dan menggunakan model deteksi objek. Pada penelitian ini Tensorflow Object Detection API diimplementasikan pada aplikasi penghitung kendaraan dengan model deteksi SSD_Resnet50_v1. Dari penelitian yang telah dilakukan, aplikasi dengan model deteksi SSD_Resnet50_v1 mendapatkan akurasi sebesar 56,49% dalam menghitung kendaraan berjenis motor dan 54,43% untuk kendaraan berjenis mobil.Kata Kunci : SSD_Resnet50_v1, penghitung kendaraan, Tensorflow Object Detection API
Co-Authors Abdul Gafur Adin Nofiyanto, Adin Ahmad Bahroini Ahmad Juhdi Ahmad Rusadi Andi Farmadi Andi Farmadi Andi Farmadi Arie Sapta Nugraha Arie Sapta Nugraha Aylwin Al Rasyid Bayu Hadi Sudrajat Dendy Fadhel Adhipratama Dendy Dodon Turianto Nugrahadi Dwi Kartini Dwi Kartini, Dwi Efendi Mohtar Emma Andini Faisal, Mohammad Reza Fatma Indriani Fenny Winda Rahayu Fhadilla Muhammad Friska Abadi Friska Abadi Hanif Rahardian Irwan Budiman Irwan Budiman Irwan Budiman Irwan Budiman Ivan Sitohang Maya Yusida Muhammad Angga Wiratama Muhammad Azmi Adhani Muhammad Itqan Mazdadi Muhammad Latief Saputra Muhammad Reza Faisal, Muhammad Reza Muhammad Rizky Adriansyah Muhammad Rusli Muhammad Syahriani Noor Basya Basya Muhammad Zaien Muliadi Muliadi Muliadi Aziz Muliadi Muliadi Muliadi Muliadi Nitami Lestari Putri Nur Ridha Apriyanti Oni Soesanto Rahmat Ramadhani Reina Alya Rahma Rinaldi Rizal, Muhammad Nur Rudy Herteno Rudy Herteno Rudy Herteno Salsha Farahdiba Saragih, Triando Hamonangan Sarah Monika Nooralifa Septiadi Marwan Annahar Sutan Takdir Alam Wahyu Ramadansyah Zaini Abdan