The use of genetic algorithm for feature selection in video concept detection

The analytic hierarchy process (AHP) is a method to help people make a complex decision by analyzing and synthesizing multiple criteria for the decision objective in a hierarchy. We adopt the AHP as a new strategy for the semantic concept detection (SCD) in video so that multiple factors involved in SCD, including multiple modalities and relating concepts, can be hierarchically analyzed and synthesized. In this paper, we first explain, by an example, why and how the SCD problem can be analyzed by the AHP. Then, following the idea of the AHP, we develop a new rank aggregation (RA) method, called AHP-RA. Experimental results of RA for SCD in video show the effectiveness of this method.

One of the important practical applications of computer vision techniques is computer-aided diagnosis (CAD) in medical imaging. It has been shown that CAD can improve the accuracy of breast cancer detection and characterization by radiologists on mammograms. In this chapter, we discuss an important step — feature selection — in classifier design for CAD algorithms. Feature selection reduces the dimensionality of an available feature space and is therefore often used to prevent over-parameterization of a classifier. Many feature selection techniques have been proposed in the literature. We will illustrate the usefulness of genetic algorithms (GAs) for feature selection by comparing GA with a commonly used sequential selection method. A brief introduction to the GA is given and several examples using GA feature selection for the characterization of mammographic lesions are discussed. The examples illustrate the design of a fitness function for optimizing classification accuracy in terms of the receiver operating characteristics of the classifier, the dependence of GA performance on its evolution parameters, and the design of a fitness function tailored to a specific classification task.

The goal of the feature selection process is, given a dataset described by n attributes (features), to find the minimum number m of relevant attributes which describe the data as well as the original set of attributes do. Genetic algorithms have been used to implement feature selection algorithms. Previous algorithms presented in the literature used the predictive accuracy of a specific learning algorithm as the fitness function to maximize over the space of possible feature subsets. Such an approach to feature selection requires a large amount of CPU time to reach a good solution on large datasets. This paper presents a genetic algorithm for feature selection which improves previous results presented in the literature for genetic-based feature selection. It is independent of a specific learning algorithm and requires less CPU time to reach a relevant subset of features. Reported experiments show that the proposed algorithm is at least ten times faster than a standard genetic algorithm for feature selection without a loss of predictive accuracy when a learning algorithm is applied to reduced data.

With the rapid growth of multimedia application technologies and network technologies, especially the proliferation of Web 2.0 and digital cameras, there has been an explosion of images and videos in the Internet. For example, the volume of videos uploaded to the YouTube every minute is amounting to 48 hours by May 2011, having doubled in the last two years. Such huge video collections hold useful yet implicit and nontrivial knowledge about various domains. To manage and utilize these resources effectively, video concept detection becomes a very important subject of intensive research by a large research community (Over et al., 2008). It is an integral part of visual data mining that is automatically extracting such knowledge from the huge unstructured visual data. It aims to automatically annotate video shots or keyframes with respect to a semantic concept (Tang et al., 2012). Ranging from objects like airplane and car to scenes like urban street and sky, semantic concepts serve as good intermediate semantic features for video content indexing and understanding, and thus, spurring much research attention (Jiang et al., 2010; Naphade & Smith, 2004; Snoek et al., 2006; Zheng et al., 2008). Essentially, concept detection is a classification task, in which a binary classifier is usually learned to predict the presence of a certain concept in a video shot or keyframe (image). Traditional concept detection methods are mainly global classification: use supervised machine learning techniques, such as single Support Vector Machine (SVM), etc., over whole training dataset.

Multi-level feature representations for video semantic concept detection

This paper presents a new hybrid genetic algorithm (HGA) for feature selection (FS) called as HGAFS. HGAFS incorporates a new local search operation that is devised and embedded in HGA to fine-tune the search in FS. The proposed local search operation works on basis of the distinct and informative nature of input features that is computed by their correlation information. The aim of using correlation information is to encourage the local search strategy for selecting less correlated (distinct) features. Such an encouragement reduces the redundancy of information in the generated subset of salient features. We have tested our methods on several real-world datasets and have compared the performances with the results of other existing algorithms. It is found that HGAFS produces consistently better performances.

A feature selection approach combining genetic algorithm (GA) with mutual information (FSGM) is proposed. In fact, FSGM is a genetic algorithm applied to feature selection. For feature selection task, an individual of GA represents a feature subset, and the fitness function is the evaluation of the feature subset. With elaborating design, the global searching and completely evaluation can be realized in FSGM. The experimental results confirm the effectiveness of the proposed algorithm in improving the generalization and reducing the over fitting of selected feature subset.

A belt conveyor roller defect detection method based on genetic algorithm feature selection and stacking learning was proposed. Roller defect data from 1620 samples of three types of roller defects was first collected. To improve the detection efficiency of roller defects, a feature selection method based on a genetic algorithm for selecting roller defect features was proposed. The model classification efficiency of roller features after feature selection by the genetic algorithm was found to be higher. The feature subset with the highest fitness had a feature number of 35. A stacking learning model for detecting roller defects was also constructed. The stacking method enhanced the comprehensive performance of the base learner model for detecting roller defects. The stacking learning model finally achieved a classification accuracy of 94.86% on the roller defect dataset. The classification performance of the stacking learning model was better than that of its base learning model. The results showed that the stacking learning model was preferred for detecting roller defects. The proposed conveyor belt roller defect detection method, while achieving high accuracy, may be limited by potential overfitting and sensitivity to environmental conditions. The next steps in refining the conveyor belt roller defect detection method will focus on dataset expansion, algorithm parameter tuning, and environmental robustness testing.

It can be acknowledged from the literature that the high density of breast tissue is a root cause for the escalation of breast cancer among the women, imparting its prime role in Cancer Death among women. Moreover, in this era where computer-aided diagnosis systems have become the right hand of the radiologists, the researchers still find room for improvement in the feature selection techniques. This research aspires to propose hybrid versions of Biogeography-Based Optimization and Genetic Algorithm for feature selection in Breast Density Classification, to get rid of redundant and irrelevant features from the dataset; along with it to achieve the superior classification accuracy or to uphold the same accuracy with lesser number of features. For experimentation, 322 mammogram images from mini-MIAS database are chosen, and then Region of Interests (ROI) of seven different sizes are extracted to extract a set of 45 texture features corresponding to each ROI. Subsequently, the proposed algorithms are used to extract an optimal subset of features from the hefty set of features corresponding to each ROI. The results indicate the outperformance of the proposed algorithms when results were compared with some of the other nature-inspired metaheuristic algorithms using various parameters.

The presence of microcalcification clusters in digital mammograms is a primary indicator of early stages of malignant types of breast cancer and its detection is important to prevent the disease. This paper uses a procedure for the classification of microcalcification clusters in mammograms using sequential Difference of Gaussian filters (DoG) and feedforward Neural Networks (NN). Three methods using class separability, forward sequential search and genetic algorithms for feature selection are compared. We found that the use of Genetic Algorithms (GAs) for selecting the features from microcalcifications and microcalcification clusters that will be the inputs of a feedforward Neural Network (NN) results mainly in improvements in overall accuracy, sensitivity and specificity of the classification.

In recent years, detecting credit card fraud transactions has been a difficult task due to the high dimensions and imbalanced datasets. Selecting a subset of important features from a high-dimensional dataset has proven to be the most prominent approach for solving high-dimensional dataset issues, and the selection of features is critical for improving classification performance, such as the fraud transaction identification process. To contribute to the field, this paper proposes a novel feature selection (FS) approach based on a metaheuristic algorithm called Rock Hyrax Swarm Optimization Feature Selection (RHSOFS), inspired by the actions of rock hyrax swarms in nature, and implements supervised machine learning techniques to improve credit card fraud transaction identification approaches. This approach is used to select a subset of optimal relevant features from a high-dimensional dataset. In a comparative efficiency analysis, RHSOFS is compared with Differential Evolutionary Feature Selection (DEFS), Genetic Algorithm Feature Selection (GAFS), Particle Swarm Optimization Feature Selection (PSOFS), and Ant Colony Optimization Feature Selection (ACOFS) in a comparative efficiency analysis. The proposed RHSOFS outperforms existing approaches, such as DEFS, GAFS, PSOFS, and ACOFS, according to the experimental results. Various statistical tests have been used to validate the statistical significance of the proposed model.

Discusses the use of genetic algorithms for feature selection for handwriting recognition. Its novelty lies in the use of multi-objective genetic algorithms where sensitivity analysis and neural networks are employed to allow the use of a representative database to evaluate fitness and the use of a validation database to identify the subsets of selected features that provide a good generalization. Comprehensive experiments on the NIST database confirm the effectiveness of the proposed strategy.

Dynamic Adaboost learning with feature selection based on parallel genetic algorithm for image annotation

We investigate the usefulness of evolutionary algorithms in three incarnations of the problem of feature relevance assignment in memory-based language processing (MBLP): feature weighting, feature ordering and feature selection. We use a simple genetic algorithm (GA) for this problem on two typical tasks in natural language processing: morphological synthesis and unknown word tagging. We find that GA feature selection always significantly outperforms the MBLP variant without selection and that feature ordering and weighting with GA significantly outperforms a situation where no weighting is used. However, GA selection does not significantly do better than simple iterative feature selection methods, and GA weighting and ordering reach only similar performance as current information-theoretic feature weighting methods.

Recent research has discovered that leveraging ontology is an effective way to facilitate semantic video concept detection. As an explicit knowledge representation, a formal ontology definition usually consists of a lexicon, properties, and relations. In this paper, we present a comprehensive representation scheme for video semantic ontology in which all the three components are well studied. Specifically, we leverage LSCOM to construct the concept lexicon, describe concept property as the weights of different modalities which are obtained manually or by data-driven approach, and model two types of concept relations (i.e., pairwise concept correlation and hierarchical relation). In contrast with most existing ontologies which are only focused on one or two components for domain-specific videos, the proposed ontology is more comprehensive and general. To validate the effectiveness of this ontology, we further apply it to video concept detection. The experiments on TRECVID 2005 corpus have demonstrated a superior performance compared to existing key approaches to video concept detection.