Claim Missing Document
Check
Articles

Found 13 Documents
Search

Performance evaluation of pre-trained deep learning model on garbage classification with data augmentation approach Wiguna, I Komang Arya Ganda; Desnanjaya, I Gusti Made Ngurah; Sandika, I Kadek Budi
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 6: December 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i6.pp4971-4981

Abstract

Waste classification is one of the interesting topics for classifications in which data can be very varied and complex. This data diversity is a challenge to develop a model that is able to classify well. The purpose of this study is to analyze the performance of the pre-trained deep learning model using a data augmentation approach. There are three pre-training models used in this study, namely residual networks 50 (ResNet50), visual geometric group with 16 layers (VGG-16), and MobileNetV2. The results showed that the MobileNetV2 model received the highest accuracy value, reaching 84.45% for data without augmentation. With data augmentation there is a decrease of 2.73%. Conversely, VGG-16 shows performance stability with an increase in accuracy with augmentation data, reaching 75.84%. While ResNet50 gets the lowest results compared to both models. The application of data augmentation techniques with the aim of increasing data variations does not always have an impact on increasing the generalization of the model.
Audit Tata Kelola Teknologi Informasi Menggunakan Framework Cobit 5 Pada Pt. Bisma Tunas Jaya Sentral Devanti, Khairunnisa; Parwita, Wayan Gede Suka; Sandika, I Kadek Budi
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 2 No 2 (2019): December
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (350.368 KB) | DOI: 10.33173/jsikti.59

Abstract

Abstract PT. Bisma Tunas Jaya Sentral is a company engaged in the sale of finished goods (especially motorcycles), spare parts, and motorcycle service specifically for the Yamaha brand. To support business services, IT services in the form of software and hardware are used in business processes.To ensure optimal IT management, measurements of the level of IT governance that have been carried out and compare it with the level expected by management. This measurement refers to the COBIT domain 5. The steps of this study start from research planning, design of data collection instruments, data collection and data processing to conduct a final evaluation that results in recommendations for improved management in accordance with the maturity of the COBIT model.The results of data processing that have been carried out indicate that the IT infrastructure management method that is already running at PT Bisma Tunas Jaya is not good enough. It is proven by the high gap between the current management level and the level desired by management.
Rancang Bangun Sistem Informasi Geografis Pelanggan Unit Jasa Pengelolaan Sampah pada BUMDesa Catu Krewo Sedana Widiartha, Komang; Sandika, I Kadek Budi; Kumala Dewi, Desak Putu Diah
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 2 No 4 (2020): June
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1032.298 KB) | DOI: 10.33173/jsikti.84

Abstract

Badan Usaha Milik Desa (BUMDesa) Catu Kwero Sedana is BUMDesa located in Pecatu village, South Kuta District, Badung-Bali Regency. The waste handling mechanism carried out by the waste management service unit at the BUMDesa Catu Kwero Sedana is the collection of garbage to residents' houses or businesses in the village of Pecatu. BUMDesa focuses on the quality of services provided to its customers. Until now there are still complaints from customers, especially new customers and prospective customers, related to the start of service and / or registration as new customers. The problem that often occurs is the difficulty of finding the location of garbage collection at the customer's site. If the customer registers himself through a contribution collector who is collecting customer bills, the employee in charge of transporting waste is sometimes constrained to find the customer's location. In addition, related to the amount of tariffs that will be charged to customers. Employees of garbage transport who do not know the size of the contribution rates of customers will find it difficult to provide the range of tariffs that will be charged to customers according to the rules stated in the regulations of Pecatu village. To overcome these problems, it is necessary to have a system that can provide information to employees of garbage transport regarding the position / location of garbage collection of each customer, the amount of tariff in accordance with applicable regulations, and recapitulation of payment of customer contributions. This information system can be developed based on websites with a geographic information system (GIS) model by utilizing the Application Programming Interface (API) maps owned by Google. The application of GIS to waste management has been extensively investigated and shows positive results