Garuda - Garba Rujukan Digital

Wahju Tjahjo Saputro

Universitas Muhammadiyah Purworejo

Author-ID : 4140135

Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Mechanical Engineering Other

Published : 33 Documents Claim Missing Document

Claim Missing Document

Articles

1 2 3 4

Improving Performance Convolutional Neural Networks Using Modified Pooling Function Achmad Lukman; Wahju Tjahjo Saputro; Erni Seniwati
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 23 No. 2 (2024)
Publisher : LPPM Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v23i2.3763

The Visual Geometry Group-16 (VGG16) network architecture, as part of the development of convolutional neural networks, has been popular among researchers in solving classification tasks, so in this paper, we investigated the number of layers to find better performance. In addition, we also proposed two pooling function techniques inspired by existing research on mixed pooling functions, namely Qmax and Qavg. The purpose of the research was to see the advantages of our method; we conducted several test scenarios, including comparing several modified network configurations based on VGG16 as a baseline and involving our pooling technique and existing pooling functions. Then, the results of the first scenario, we selected a network that can adapt well to our pooling technique, whichwas then carried out several tests involving the Cifar10, Cifar100, TinyImageNet, and Street View House Numbers (SVHN) datasets as benchmarks. In addition, we were also involved in several existing methods. The experiment results showed that Net-E has the highest performance, with 93.90% accuracy for Cifar10, 71.17% for Cifar100, and 52.84% for TinyImageNet. Still, the accuracy was low when the SVHN dataset was used. In addition, in comparison tests with several optimization algorithms using the Qavg pooling function, it can be seen that the best accuracy results lie in the SGD optimization algorithm, with 89.76% for Cifar10 and 89.06% for Cifar100.

User Acceptance Testing to Assess User Receptiveness Toward a Soft Skills Training Information System Hermansah, Lutfi; Murhadi, Murhadi; Saputro, Wahju Tjahjo
SISTEMASI Vol 14, No 5 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i5.5116

Soft skills organizations face significant challenges due to manual management practices, leading to scattered participant data, lack of proper documentation, and manual archiving. The main issue is the absence of a dedicated soft skills training information system. This study aims to develop and evaluate a soft skills training information system to address these organizational problems. The Rapid Application Development (RAD) method was chosen for its ability to accommodate changing requirements and enable rapid deployment of the system. System acceptance testing was conducted using the User Acceptance Test (UAT) method with 70 respondents, covering 20 questionnaire items related to system functionality, user interface experience, performance, efficiency, and productivity. The UAT results indicated that the system received an average acceptance rate of 80.4% for functionality, 76.8% for user experience and interface design, 77.3% for performance, and 78.7% for efficiency and productivity. These results show that the soft skills training information system meets user requirements with an overall interpretation score of "Good." The developed system is considered acceptable and capable of supporting soft skills training activities at Universitas Muhammadiyah Purworejo.

Improving Performance Convolutional Neural Networks Using Modified Pooling Function Lukman, Achmad; Saputro, Wahju Tjahjo; Seniwati, Erni
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 23 No. 2 (2024)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v23i2.3763

The Visual Geometry Group-16 (VGG16) network architecture, as part of the development of convolutional neural networks, has been popular among researchers in solving classification tasks, so in this paper, we investigated the number of layers to find better performance. In addition, we also proposed two pooling function techniques inspired by existing research on mixed pooling functions, namely Qmax and Qavg. The purpose of the research was to see the advantages of our method; we conducted several test scenarios, including comparing several modified network configurations based on VGG16 as a baseline and involving our pooling technique and existing pooling functions. Then, the results of the first scenario, we selected a network that can adapt well to our pooling technique, whichwas then carried out several tests involving the Cifar10, Cifar100, TinyImageNet, and Street View House Numbers (SVHN) datasets as benchmarks. In addition, we were also involved in several existing methods. The experiment results showed that Net-E has the highest performance, with 93.90% accuracy for Cifar10, 71.17% for Cifar100, and 52.84% for TinyImageNet. Still, the accuracy was low when the SVHN dataset was used. In addition, in comparison tests with several optimization algorithms using the Qavg pooling function, it can be seen that the best accuracy results lie in the SGD optimization algorithm, with 89.76% for Cifar10 and 89.06% for Cifar100.

Title

Found 33 Documents
Search

Abstract

Abstract

Abstract

Title Search

Found 33 Documents Search

Abstract

Abstract

Abstract

Title

Found 33 Documents
Search