Table 1 - uploaded by Denise Fukumi Tsunoda
Content may be subject to copyright.
Source publication
Proteins can be grouped into families according to some features such as hydrophobicity, composition or structure, aiming
to establish common biological functions. This paper presents MAHATMA—memetic algorithm-based highly adapted tool for motif
ascertainment—a system that was conceived to discover features (particular sequences of amino acids, or...
Contexts in source publication
Context 1
... instance, the individual shown in Figure 1 can be read as the rule antecedent: IF "(a protein has the aminoacid sub-sequence MD or MM) and (a protein has the aminoacid sub-sequences LQE and IGA)". Table 1 presents the 20 "standard" monomeric units of proteins, the amino acids (Lesk 2001). It is from these substances that proteins are synthesized. ...
Context 2
... edition operation provides a means to edit and simplify expressions as genetic programming is running. Edition is an asexual operator and it recursively applies a set of simplifying operations (editing rules, Table 1) in order to optimize the rule. If any function has no side effects, the edition operator will evaluate that function and replace it with the value obtained by the evaluation. ...
Similar publications
Traditional methods for flow cytometry (FCM) data processing rely on subjective manual gating. Recently, several groups have developed computational methods for identifying cell populations in multidimensional FCM data. The Flow Cytometry: Critical Assessment of Population Identification Methods (FlowCAP) challenges were established to compare the...
Citations
... A tree-based encoding is a common approach that is used for EAs for the encoding of individuals in the DT. A tree-encoding structure is indeed a common approach for the evaluation of DTs [103], but there are other approaches as well, such as the linear-genome method that can be used to code individuals [104]. Most of these approaches, for instance, GAs, use a fixed-length string (linear chromosomes) to evaluate DTs [105]. ...
The diagnosis of Parkinson's disease (PD) is important in neurological pathology for appropriate medical therapy. Algorithms based on decision tree induction (DTI) have been widely used for diagnosing PD through biomedical voice disorders. However, DTI for PD diagnosis is based on a greedy search algorithm which causes overfitting and inferior solutions. This paper improved the performance of DTI using evolutionary-based genetic algorithms. The goal was to combine evolutionary techniques, namely, a genetic algorithm (GA) and genetic programming (GP), with a decision tree algorithm (J48) to improve the classification performance. The developed model was applied to a real biomedical dataset for the diagnosis of PD. The results showed that the accuracy of the J48, was improved from 80.51% to 89.23% and to 90.76% using the GA and GP, respectively.
... Muitos problemas semelhantes em aprendizado de máquina, inteligência artificial e processamento simbólico podem ser vistos como uma busca ou descoberta de um programa de computador que produza determinadas saídas a partir de um conjunto específico de entradas. Este tipo de problema está presente tanto na engenharia quanto na computação e a PG pode prover soluções interessantes [6][7][8][9] A partir da hipótese de que um programa correto possa ser induzido a partir de um conjunto de casos de testes, pode-se considerar esta atividade como uma tarefa de indução, que por sua vez está sujeita a todos os méritos e problemas do raciocínio indutivo. Um dos principais problemasé que uma hipótese indutiva está ligada diretamenteà capacidade que casos de teste tem de representar o problema inteiro. ...
