Article Per Year (5 Year)
p-Index From 2021 - 2026
0.817
P-Index
This Author published in this journals
All Journal JAST Malcom: Indonesian Journal of Machine Learning and Computer Science SAINTEK
Asfan Muqtadir
Universitas PGRI Ronggolawe Tuban
Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Mechanical Engineering

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

Found 3 Documents
Search

 1 
Decision Support System of Determining E-Commerce With The Topsis and Comparation With Ahp for UMKM In the Tuban Regency Area Asfan Muqtadir; Reza Agit Alfaridzi; Amaludin Arifia
Journal of Applied Science and Technology Vol 2, No 02 (2022): Juli 2022
Publisher : Universitas Islam Sultan Agung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30659/jast.2.02.9-15

Abstract

E-Commerce has had a major impact on social and economic growth in society. However, E-Commerce system is not always profitable for UMKM actors themselves, there are several factors that cause UMKM quality assessments to decline from tight competitiveness. Many consumers consider buying products from the many existing E-Commerce systems. For this reason, this goal is to implement a decision support system in determining E-Commerce using the TOPSIS method with AHP method. Of course, in implementing a decision support system, it is necessary to have assessment criteria and a number of alternatives that will be used as a reference to determine E-Commerce for UMKM by calculating the TOPSIS method which will produce the final result of the value of each E-Commerce in the form of ranking. From research conducted on 38 UMKM in Tuban Regency, the results of E-Commerce Shopee are 60.5%, Tokopedia 15.8%, Blibli 10.5%, Lazada 7.9% and Bukalapak 5.3%. The data will be grouped from each alternative to find the average value based on predetermined criteria and calculated using the TOPSIS method AHP method, it can be concluded that the E-Commerce that is widely used by UMKM in the Tuban Regency area is Shopee > Tokopedia > Bukalapak > Lazada > Blibli. while with AHP resulted in the order of Tokopedia > Shopee > Bukalapak > Blibli > Lazada.
Aplikasi Pencarian Rute Tambal Ban Terdekat Dengan Metode Dijkstra Berbasis Mapbox Yulistyadi Firman Dwi P.; Asfan Muqtadir; Andik Adi Suryanto; Siti Rachmawati
Prosiding Sains dan Teknologi Vol. 2 No. 1 (2023): Seminar Nasional Sains dan Teknologi (SAINTEK) ke 2 - Februari 2023
Publisher : DPPM Universitas Pelita Bangsa

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

Abstract

Sering terjadi kebocoran ban ditengah perjalanan dapat disebabkan banyak hal, seperti terkena benda tajam, usia ban terlalu tua, bocor di bekas tambalan atau bisa juga disebabkan oleh lainya. Untuk memudahkan pengguna kendaraan dalam mencari lokasi tambal ban, dibutuhkan aplikasi pencarian tambal ban terdekat yang mudah diakses. Salah satu untuk meningkatkan informasi pengendara tentang pencarian rute lokasi tambal ban dengan cara menyajikan sesuatu yang baru, dengan menggunakan aplikasi ini pihak-pihak yang berkepentingan dapat melihat dan mendapatkan informasi langsung tanpa harus bertanya kepada orang lain, sehingga pengguna dapat secara langsung mencari lokasi tambal ban terdekat yang diinginkan.
Performance Comparison of Facial Skin Type Classification Using the Segment Anything Model Nisrina Nur Kumala; Asfan Muqtadir; Amaludin Arifia
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 2 (2026): MALCOM April 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i2.2604

Abstract

The facial skin is the first area to often experience various problems. Knowing one’s skin type is an important step in choosing the right skincare routine, but it can be difficult to determine accurately without a specialist's help, which can be costly. To address this, a deep learning approach can be applied to help automatically classify skin types. In this study, several combinations of CNN, MobileNetV3, and SAM models were applied and compared for facial skin type classification. The dataset used, sourced from the figshare platform, consists of 2,250 facial images representing 5 skin types: normal, dry, oily, sensitive, and combination. The dataset was divided into three parts: training (80%), validation (10%), and testing (10%). Each model was evaluated using a confusion matrix, with accuracy, precision, recall, and F1-score metrics used to determine and compare model performance. The results show that the CNN performed worst, while the MobileNetV3-based CNN was the best-performing model, achieving an accuracy of 97%. Meanwhile, adding SAM did not improve performance and actually decreased accuracy. This study demonstrates that using MobileNetV3 without segmentation is more effective than adding SAM segmentation for facial skin type classification.
Co-Authors Amaludin Arifia Amaludin Arifia Andik Adi Suryanto Fitroh Amaluddin Nisrina Nur Kumala Reza Agit Alfaridzi Siti Rachmawati Yulistyadi Firman Dwi P.