Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Journal of Tropical Life Science : International Journal of Theoretical, Experimental, and Applied Life Sciences
Mahmudi, Wayan Firdaus
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Computer Science & IT Engineering Environmental Science

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Constructing Phenetic and Phylogenetic Relationship Using Clad'97 Rahardi, Brian; Arumningtyas, Estri Laras; Mahmudi, Wayan Firdaus
Journal of Tropical Life Science Vol 2, No 1 (2012)
Publisher : Journal of Tropical Life Science

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

Abstract

Relationship construction has a very important position in classification process for arranging taxonomy of organism. In the world of taxonomy, there are two the most familiar relationship diagram, cladogram and phenogram. In every construction activity, a researcher is always facing character state data from taxa that becomes components of the diagram. Calculation that is used for construction is often incorporate iterative or repetitive process that needs time and precision. The existence of calculating tools that produces both text and graphical output are hopefully decrease time and error during construction. Basic algorithm that is used in calculation is for phylogenetic construction by Kluge and Farris in 1969,for phenetic construction using cluster analysis with slight modification. Basic common algorithm used in the software is by calculating two dimensional arrays of taxa x characters matrix and creating distance or similarity matrix. In more detail the program creates one dimensional array of taxonomical object and each object has some other one dimensional array containing data commonly exist in a taxonomic unit. The relationship between one object and theother are regulated by an object that created by class representing taxonomic tree. Cladogram is constructed by calculating nearest distance between each taxon (OTU) and creating one HTU in every bifurcation. Phenogram is constructed agglomeratively by searching highest similarity between taxon then grouped into new taxon. Program calculates numerical data after we do character scoring. Final result for each user may be different; this may be due to decision by user during construction process. This paper hopefully attracts people from systematic computation to develop further into open source software and multi-platform feature.
Improving multilayer perceptron on rainfall data using modified genetics algorithm Marji, Marji; Mahmudi, Wayan Firdaus; Handamari, Endang Wahyu; Santoso, Edy; Arifin, Maulana Muhamad
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 5: October 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i5.pp3994-4005

Abstract

Rainfall prediction is essential for managing water resources, agriculture, and disaster response, particularly in regions affected by climate variability. This study introduces a modified genetic algorithm (MGA) to optimize hyperparameters of a multilayer perceptron (MLP) for rainfall forecasting. The MGA incorporates elitism to retain top-performing solutions and adaptive selection based on model accuracy. The proposed MGA–MLP model was tested on rainfall datasets from Australia and Indonesia (BMKG). Experimental results show that configurations with two hidden layers, rectified linear unit (ReLU) activation and limited-memory Broyden Fletcher Goldfarb Shannon (LBFGS) optimizer, a learning rate of 0.001 and 1000 epochs consistently delivered strong performance. The model achieved accuracies of 86.02% and 79.05%, respectively. These findings indicate that MGA significantly improves MLP performance and provides a reliable, generalizable method for rainfall prediction across diverse climatic conditions.
Co-Authors Arifin, Maulana Muhamad Brian Rahardi Edy Santoso Endang Wahyu Handamari Estri Laras Arumingtyas Marji Marji