Claim Missing Document
Check
Articles

Found 22 Documents
Search

Community Service Assistance in the Use of the "BUMDES PECATU" Application to Customers in the Waste Management Unit in Pecatu Village Sandika, I Kadek Budi; Widiartha, Komang Kurniawan; Ariantini, Made Suci; Parwita, Wayan Gede Suka; Putra, Desak Made Dwi Utami; Wiguna, I Komang Arya Ganda; Sudipa, I Gede Iwan
Abdimas Paspama Vol. 2 No. 1 (2023): Abdimas Paspama, December 2023
Publisher : Abdimas Paspama

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

Abstract

BUMDes Catu Kwero Sedana Pecatu, Pecatu Village utilizes the " BUMDES PECATU" application as an innovative solution in increasing community involvement and optimizing waste management units. Through community service activities that focus on assisting the use of the application, with a door to door approach to customer addresses, the service team supported by the Pecatu village government provides counseling, education, and direct technical support to the community. The results show an increase in understanding and community participation in waste management through the use of the "BUMDES PECATU" application. Regular mentoring activities are expected to ensure the continuity and optimization of the BUMDES PECATU application in supporting operations in the waste management unit and active participation of the village community.
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.