Sumarsih Condroayu Purbarani

Adaptive genetic algorithm for reliable training population in plant breeding genomic selection

Many algorithms are developed to model Genomic Estimated Breeding Value (GEBV). Modeling GEBV evolves a huge size of genotype in both terms of the dimension (columns) and the instances (rows). Good combinations of features help in predicting which phenotype is being represented. Preparing a good training population sample is assumed to be a convenient solution to deal with such complex genotype data. In this research, an Adaptive Genetic Algorithm (AGA) is proposed. The adaptive characteristic of AGA by adjusting probabilities in crossover and mutation is expected to converge into the global optimum without getting trapped in local optima. The proposed method using AGA to optimize the feature selection and shrinkage mechanism is looked forward to provide a reliable model to be reused in other similar datasets.

A survey of whole genome alignment tools and frameworks based on Hadoop's MapReduce

Next generation DNA sequencing (NGS) project that aims to give understandings in various genes seems to boosts innovative breakthrough in whole genome issues. Dealing with genomic data requires large-scale data storage and processing. Big data technology could be the most appropriate solution to gaining useful knowledge from data comprehensively. This study discusses about genome tools and framework that implement MapReduce of Hadoops components in sequence alignment computation. The aim of this discussion is presenting an overview of whole genome alignment software tools and the implementation in big data.

Implementation of grid mapped robot planning algorithm in a continuous map for fire fighting robot

Fire-fighting robot is still one of the fields in robotic competitions held these days. This paper is aimed to see the implementation of the Markov Decision Planning (MDP) problem in a fire-fighting robots navigation. The MDP algorithm evolves planning of the actions the robot should take according to the policy. This planning is mapped into a grid map. Yet in the implementation, this planning is applied in a continuous map. Using a fire-fighting robot the succession of this planning implementation is undertaken. The result shows that the implementation of grid mapped in a continuous map yields significant impacts that lead the MDP to be able to solve the limitation of wall following algorithm. This algorithm is also applied in the real autonomous mobile robot.

Genetic algorithm optimization for extreme learning machine based microalgal growth forecasting of Chlamydomonas sp

Currently, microalgae cultivation is one of the most promising alternative solutions to alleviate the value of CO2 concentration. Microalgae growth rate is convinced to be the indicator to measure the effectiveness in capturing CO2. In this paper, the microalgal growth behavior by means of various pH concentrations is observed. From the observation data, the growth behavior is modeled by regression graphs using single hidden layer feed-forward network (SLFN). To train and test the data, extreme learning machine (ELM) algorithm is applied. Recently, ELM is approved to be the fastest algorithm to learn an SLFN for regression. ELM is also well-known for its high learning accuracy as various activation functions can be applied in hidden layer. Yet the over-fitting in regression is still an issue in ELM. Thus to alleviate this problem cross-validation method is employed. To optimize the algorithm, ELM is also combined with Genetic Algorithm. The result shows that regression using ELM-GA is more accurate than ELM in various numbers of neurons.