scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Hierarchical classification using a Competitive Neural Network

TL;DR: This paper presents an algorithm for hierarchical classification using the global approach, called Hierarchical Classification using a Competitive Neural Network (HC-CNN), which was tested on some datasets from the bioinformatics field and the results are promising.
Abstract: Hierarchical classification is a problem with application in many areas. Therefore, it makes the development of algorithms able to induce hierarchical classification models. This paper presents an algorithm for hierarchical classification using the global approach, called Hierarchical Classification using a Competitive Neural Network (HC-CNN). It was tested on some datasets from the bioinformatics field and the results are promising.
Citations
More filters
01 Jan 1990
TL;DR: An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article, where the authors present an overview of their work.
Abstract: An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

2,933 citations

Journal ArticleDOI
TL;DR: This paper provides a comprehensive review of hierarchical methods for protein function prediction based on ensembles of learning machines, and discusses the main hierarchical ensemble methods proposed in the literature in the context of existing computational methods.
Abstract: Protein function prediction is a complex multiclass multilabel classification problem, characterized by multiple issues such as the incompleteness of the available annotations, the integration of multiple sources of high dimensional biomolecular data, the unbalance of several functional classes, and the difficulty of univocally determining negative examples. Moreover, the hierarchical relationships between functional classes that characterize both the Gene Ontology and FunCat taxonomies motivate the development of hierarchy-aware prediction methods that showed significantly better performances than hierarchical-unaware “flat” prediction methods. In this paper, we provide a comprehensive review of hierarchical methods for protein function prediction based on ensembles of learning machines. According to this general approach, a separate learning machine is trained to learn a specific functional term and then the resulting predictions are assembled in a “consensus” ensemble decision, taking into account the hierarchical relationships between classes. The main hierarchical ensemble methods proposed in the literature are discussed in the context of existing computational methods for protein function prediction, highlighting their characteristics, advantages, and limitations. Open problems of this exciting research area of computational biology are finally considered, outlining novel perspectives for future research.

44 citations


Cites methods from "Hierarchical classification using a..."

  • ...Interestingly enough, in [122], the authors adopted this approach to predict the hierarchy of gene annotations in the yeast model organism, by using a tree-topology according to the FunCat taxonomy: each neuron is connected with its parent or with its children....

    [...]

Journal ArticleDOI
TL;DR: This paper studies the performance of a novel algorithm called Hierarchical Classification using a Competitive Neural Network and compares its performance against the Global-Model Naive Bayes (GMNB) on eight protein function prediction datasets.
Abstract: Several classification tasks in different application domains can be seen as hierarchical classification problems In order to deal with hierarchical classification problems, the use of existing flat classification approaches is not appropriate For these reason, there has been a growing number of studies focusing on the development of novel algorithms able to induce classification models for hierarchical classification problems In this paper we study the performance of a novel algorithm called Hierarchical Classification using a Competitive Neural Network (HC-CNN) and compare its performance against the Global-Model Naive Bayes (GMNB) on eight protein function prediction datasets Interestingly enough, the comparison of two global-model hierarchical classification algorithms for single path of labels hierarchical classification problems has never been done before

16 citations


Cites background or methods from "Hierarchical classification using a..."

  • ...The main novelty of this paper is that we compare the HC-CNN algorithm (proposed in [7] and presented in Section 3) with two versions of the Global Model Naïve Bayes (proposed in [8] and presented in Section 4) on eight hierarchical protein function prediction datasetswith single path of labels....

    [...]

  • ...This paper is an extended version of [7]....

    [...]

Journal ArticleDOI
TL;DR: In this paper , the influence of occurrence of ferroresonance in the utility system is investigated on technical quantities of DFIG and operation of directional overcurrent relay installed in wind farm is assessed by means of PSCAD/EMTDC simulation software.

6 citations

Proceedings ArticleDOI
06 Jul 2014
TL;DR: A hybrid clustering algorithm called KGT2FCM is proposed that combines GT2 FCM with a fast k-means algorithm for input data preprocessing of classification algorithms and shows improved computation time.
Abstract: Recently, clustering has been used for preprocessing datasets before applying classification algorithms in order to enhance classification efficiency. A strong clustered dataset as input to classification algorithms can significantly improve computation time. This can be particularly useful in Big Data where computation time is equally or more important than accuracy. However, there is a trade-off between speed and accuracy among clustering algorithms. Specifically, general type-2 fuzzy c-means (GT2 FCM) is considered to be a highly accurate clustering approach, but it is computationally intensive. To improve its computation time we propose here a hybrid clustering algorithm called KGT2FCM that combines GT2 FCM with a fast k-means algorithm for input data preprocessing of classification algorithms. The proposed algorithm shows improved computation time when compared with GT2 FCM as well as KFGT2FCM on five benchmarks from UCI library.

3 citations

References
More filters
Journal ArticleDOI
01 Sep 1990
TL;DR: The self-organizing map, an architecture suggested for artificial neural networks, is explained by presenting simulation experiments and practical applications, and an algorithm which order responses spatially is reviewed, focusing on best matching cell selection and adaptation of the weight vectors.
Abstract: The self-organized map, an architecture suggested for artificial neural networks, is explained by presenting simulation experiments and practical applications. The self-organizing map has the property of effectively creating spatially organized internal representations of various features of input signals and their abstractions. One result of this is that the self-organization process can discover semantic relationships in sentences. Brain maps, semantic maps, and early work on competitive learning are reviewed. The self-organizing map algorithm (an algorithm which order responses spatially) is reviewed, focusing on best matching cell selection and adaptation of the weight vectors. Suggestions for applying the self-organizing map algorithm, demonstrations of the ordering process, and an example of hierarchical clustering of data are presented. Fine tuning the map by learning vector quantization is addressed. The use of self-organized maps in practical speech recognition and a simulation experiment on semantic mapping are discussed. >

7,883 citations

01 Jan 1990
TL;DR: An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article, where the authors present an overview of their work.
Abstract: An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

2,933 citations

Journal ArticleDOI
TL;DR: This survey defines what is the task of hierarchical classification and discusses why some related tasks should not be considered hierarchical classification, and presents a new perspective about some existing hierarchical classification approaches and proposes a new unifying framework to classify the existing approaches.
Abstract: In this survey we discuss the task of hierarchical classification. The literature about this field is scattered across very different application domains and for that reason research in one domain is often done unaware of methods developed in other domains. We define what is the task of hierarchical classification and discuss why some related tasks should not be considered hierarchical classification. We also present a new perspective about some existing hierarchical classification approaches, and based on that perspective we propose a new unifying framework to classify the existing approaches. We also present a review of empirical comparisons of the existing methods reported in the literature as well as a conceptual comparison of those methods at a high level of abstraction, discussing their advantages and disadvantages.

933 citations


"Hierarchical classification using a..." refers background in this paper

  • ...2) Local Classifier per Parent Node Approach This approach consists in training each parent node of the class hierarchy as a multi-class classifier [4]....

    [...]

  • ...Hierarchical classification is a task of data mining that has been applied in diverse areas such as music prediction [10], [13], [30], images identification [4], text mining, among others....

    [...]

  • ...3) Local Classifier per Level Approach This approach consists in creating a multi-class classifier for each level of the hierarchy [4]....

    [...]

  • ...As Silla and Freitas (2010) explain, this approach can be divided into three kinds of classification: Local Classifier per Node Approach, Local Classifier per Parent Node Approach and Local Classifier per Level Approach....

    [...]

Journal ArticleDOI
TL;DR: HMC trees outperform HSC and SC trees along three dimensions: predictive accuracy, model size, and induction time, and it is concluded that HMC trees should definitely be considered in HMC tasks where interpretable models are desired.
Abstract: Hierarchical multi-label classification (HMC) is a variant of classification where instances may belong to multiple classes at the same time and these classes are organized in a hierarchy. This article presents several approaches to the induction of decision trees for HMC, as well as an empirical study of their use in functional genomics. We compare learning a single HMC tree (which makes predictions for all classes together) to two approaches that learn a set of regular classification trees (one for each class). The first approach defines an independent single-label classification task for each class (SC). Obviously, the hierarchy introduces dependencies between the classes. While they are ignored by the first approach, they are exploited by the second approach, named hierarchical single-label classification (HSC). Depending on the application at hand, the hierarchy of classes can be such that each class has at most one parent (tree structure) or such that classes may have multiple parents (DAG structure). The latter case has not been considered before and we show how the HMC and HSC approaches can be modified to support this setting. We compare the three approaches on 24 yeast data sets using as classification schemes MIPS's FunCat (tree structure) and the Gene Ontology (DAG structure). We show that HMC trees outperform HSC and SC trees along three dimensions: predictive accuracy, model size, and induction time. We conclude that HMC trees should definitely be considered in HMC tasks where interpretable models are desired.

616 citations

Journal ArticleDOI
TL;DR: A Bayesian framework for combining multiple classifiers based on the functional taxonomy constraints is developed using a hierarchy of support vector machine (SVM) classifiers trained on multiple data types to obtain the most probable consistent set of predictions.
Abstract: Motivation: Assigning functions for unknown genes based on diverse large-scale data is a key task in functional genomics. Previous work on gene function prediction has addressed this problem using independent classifiers for each function. However, such an approach ignores the structure of functional class taxonomies, such as the Gene Ontology (GO). Over a hierarchy of functional classes, a group of independent classifiers where each one predicts gene membership to a particular class can produce a hierarchically inconsistent set of predictions, where for a given gene a specific class may be predicted positive while its inclusive parent class is predicted negative. Taking the hierarchical structure into account resolves such inconsistencies and provides an opportunity for leveraging all classifiers in the hierarchy to achieve higher specificity of predictions. Results: We developed a Bayesian framework for combining multiple classifiers based on the functional taxonomy constraints. Using a hierarchy of support vector machine (SVM) classifiers trained on multiple data types, we combined predictions in our Bayesian framework to obtain the most probable consistent set of predictions. Experiments show that over a 105-node subhierarchy of the GO, our Bayesian framework improves predictions for 93 nodes. As an additional benefit, our method also provides implicit calibration of SVM margin outputs to probabilities. Using this method, we make function predictions for multiple proteins, and experimentally confirm predictions for proteins involved in mitosis. Supplementary information: Results for the 105 selected GO classes and predictions for 1059 unknown genes are available at: http://function.princeton.edu/genesite/ Contact: ogt@cs.princeton.edu

526 citations


"Hierarchical classification using a..." refers methods in this paper

  • ...1) Local Classifier per Node Approach This approach is the most used in the literature [5], [6], [15], [14]....

    [...]