Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal JOIN (Jurnal Online Informatika) Jurnal Pilar Nusa Mandiri
Wardhana, Sukma
Unknown Affiliation
Computer Science & IT

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
The CLUSTER ANALYSIS OF SALES TRANSACTION DATA USING K-MEANS CLUSTERING AT TOKO USAHA MANDIRI Fithri, Fauzia Allamatul; Wardhana, Sukma
Jurnal Pilar Nusa Mandiri Vol 17 No 2 (2021): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Peri
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v17i2.2273

Abstract

Data mining is a process to obtain useful information from a database warehouse in the form of knowledge. Data transaction history of sales can be information for a business decision. Toko Usaha Mandiri has a problem with the stock of goods, and there are passive goods that settle in the warehouse for a relatively long period. Previous research conducted data analysis to form data clustering into useful information. This study aims to analyze sales data by applying the K-Means Clustering algorithm to form sales clusters. The results of data clustering form cluster1, cluster2 and cluster3 with percentage values of 62% (11 data), 8% (56 data) and 30% (25 data), respectively. Cluster validation of K-Means Clustering algorithm with Davies Bouldin Index produces a value of 0.2. The information of sales clustering can be an alternative solution, input for stock management and marketing strategies.
CLASSIFICATION OF CORONAVIRUS DISEASE (COVID-19) THROUGH CHEST X-RAY IMAGES BASED ON DEEP LEARNING Farhandy, Erzha Anges; Wardhana, Sukma
Jurnal Pilar Nusa Mandiri Vol 18 No 2 (2022): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Peri
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v18i2.3293

Abstract

CoV-2 virus this disease is spreading rapidly throughout the world. Various studies were carried out to control the spread of Covid-19. One way to detect Covid-19 is to study chest X-ray images of patients with Covid-19 symptoms. However, to detect Covid-19 through x-ray images, there are currently few radiology specialists needed. This study researched to detection of Covid-19 disease through chest x-ray images with a deep learning approach based on a convolutional neural network (CNN). Before training the model, data preprocessing is carried out, such as labeling and resizing. This study uses a CNN model with three layers of convolution and max-pooling layers and a fully-connected layer for the output. The results of the training using the CNN method produced a pretty good performance, with the best training accuracy (acc) value obtained in the 31st epoch with a value of 0.9593, training loss (loss) 0.1306, validation accuracy (val_acc) 0.9604, and loss validation (val_loss). 0.1399.
Computer Networks Optimization using Load Balancing Algorithms on the Citrix ADC Virtual Server Ramadhan, Hardiyan Kesuma; Wardhana, Sukma
JOIN (Jurnal Online Informatika) Vol 6 No 1 (2021)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v6i1.672

Abstract

In the digital era and the outbreak of the COVID-19 pandemic, all activities are online. If the number of users accessing the server exceeds IT infrastructure, server down occurs. A load balancer device is required to share the traffic request load. This study compares four algorithms on Citrix ADC VPX load balancer: round-robin, least connection, least response time and least packet using GNS3. The results of testing response time and throughput parameters show that the least connection algorithm is superior. There were a 33% reduction in response time and a 53% increase in throughput. In the service hits parameter, the round-robin algorithm has the evenest traffic distribution. While least packet superior in CPU utilization with 76% reduction. So algorithm with the best response time and throughput is the least connection. The algorithm with the best service hits is round-robin. Large scale implementation is recommended using the least connection algorithm regarding response time and throughput. When emphasizing evenest distribution, use a round-robin algorithm.
Co-Authors Farhandy, Erzha Anges Fithri, Fauzia Allamatul Ramadhan, Hardiyan Kesuma