Claim Missing Document
Check
Articles

Found 3 Documents
Search

IMPLEMENTATION OF SMARTER AND ORESTE METHODS FOR DETERMINING UNDERDEVELOPED VILLAGES Riska Amalia Praptiwi; Suaidah Suaidah; Rakhmat Dedi Gunawan; Ryo Cahyo Prakoso; Deddy Rudhistiar; Patricia Evericho Mountaines; Thesa Adi Saputra
Jurnal Data Mining dan Sistem Informasi Vol 4, No 2 (2023): AGUSTUS 2023
Publisher : Universitas Teknokrat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33365/jdmsi.v4i2.3239

Abstract

Villages have less development than cities because villages have bigger problems such as higher poverty rates, lower health, lower human resources, facilities and infrastructure that are more difficult to reach than cities. Therefore we need the concept of sustainable village development. In sustainable development, the aspect of development is not only aimed at present society but also society in the future. Before making the concept of sustainable village development, so that village development in a city/regency/district area is conceptualized evenly, decision support is needed to identify underdeveloped villages. Some indicators villages or underdeveloped regions mostly related to the survey of Potensi Desa activities by BPS from 1980 to 2014 continually participated. Related to that conditions, criteria obtained underdeveloped villages by DPU and indicator data PODES by BPS, it can be applied on Decision Making System. In this research selected case studies are census data from Potensi Desa by BPS in Magetan. This system uses SMARTER (Simple Multi-Attribute Rating Technique Exploiting Ranks) methods as the calculation of the weights to the criteria and ORESTE methods used for the rankings of underdeveloped villages. In this system SMARTER methods using a weighting formula Rank Order Centroid (ROC) that is proportional weighting which reflects the distance and the priority of each criteria appropriately. Furthermore, the ranking process using Oreste methods by three main stages that is Projection Matrix position, Ranking of projections and Agegration of Global Ranking. Testing of this system, which one is changing the parameters of Oreste (α value) and obtained compatibility reach 91.06% of accuracy to the experts data of underdeveloped villages from the BPS Magetan by the number 100% alternative data with value 0:01 of alpha
Brain Tumor Detection Through Image Enhancement Methods and Transfer Learning Techniques Thohari, Afandi Nur Aziz; Mountaines, Patricia Evericho; Mohd Isa, Mohd Rizal
JURNAL INFOTEL Vol 17 No 1 (2025): February 2025
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v17i1.1262

Abstract

A brain tumor is dangerous and must be treated immediately to prevent worsening. The identification of brain tumors can be performed by a more in-depth examination by specialists or by using artificial intelligence technology through MRI datasets. Several studies have examined how artificial intelligence could be used to find brain cancer in MRI images. The algorithm usually used is CNN with the addition of transfer learning. Previous studies have produced very high accuracy, but the accuracy value can still be improved. In this study, MRI image quality is improved as a new input for modeling. The test results show that the proposed CNN Model produces an accuracy of 98.50% on the test data. This result is higher than the baseline method of 98.45%. Analysis of other metrics, such as precision, recall, and F1-score, indicates consistent performance across classes. These findings suggest that using preprocessing to improve image quality can improve Model performance. Using CLAHE and median blur to improve image quality can improve accuracy by 14.5%. This study contributes to identifying an effective combination of Model optimization techniques for image classification tasks.
Technology-Based Fish Health Service Innovation for Sustainable Aquaculture Practices in Indonesia Ferdiansyah, Fadlil; Yulianto, Irawan Habib; Imada, Muhammad Zamrol; Mountaines, Patricia Evericho; Adriono, Erwin; Windarto, Yudi Eko; Nugroho, Arseto Satriyo
SPEKTA (Jurnal Pengabdian Kepada Masyarakat : Teknologi dan Aplikasi) Vol. 6 No. 2 (2025)
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/spekta.v6i2.13492

Abstract

Background: Indonesia’s aquaculture sector holds vast potential, yet many fish farmers, especially those in remote areas like offshore cages, face limited access to timely fish health services, leading to undetected disease outbreaks, mass fish mortality, and significant economic losses. Contribution: This study introduces Fish Doctor, a scalable platform integrating fish species detection, disease diagnosis, and expert consultation. It bridges the gap between AI-based detection and practical aquaculture needs in developing countries, supporting sustainable practices aligned with SDG 2 (Zero Hunger) and SDG 12 (Responsible Consumption and Production). Method: The application was built using Next.js, Express.js, MySQL, and integrates computer vision and expert systems. Its core features include image-based fish species detection using YOLOv11, rule-based disease diagnosis through forward chaining, and an online expert consultation module.  Designed as a Progressive Web App (PWA), the system offers offline-first capabilities, enabling its use in low-connectivity environments. Results: The system was evaluated using test datasets of five fish species, achieving an average diagnostic accuracy above 80% and response times of less than 2 seconds per case. Conclusion: The developed platform demonstrates potential for improving early disease detection and reducing reliance on chemical treatments in aquaculture. Future research will involve usability testing with more than 100 fish farmers across multiple provinces to assess scalability and generalizability.