An improved error-correcting output coding framework with kernel-based decoding

Multi-class classification is one of the fundamental tasks in bioinformatics and typically arises in cancer diagnosis studies by gene expression profiling. This article reviews two recent approaches to multi-class classification by combining multiple binary classifiers, which are formulated based on a unified framework of error-correcting output coding (ECOC). The first approach is to construct a multi-class classifier in which each binary classifier to be aggregated has a weight value to be optimally tuned based on the observed data. In the second approach, misclassification of each binary classifier is formulated as a bit inversion error with a probabilistic model by making an analogy to the context of information transmission theory. Experimental studies using various real-world datasets including cancer classification problems reveal that both of the new methods are superior or comparable to other multi-class classification methods.

Error Correcting Output Codes reveal an efficient strategy in dealing with multi-class classification problems. According to this technique, a multi-class problem is decomposed into several binary ones. On these created sub-problems we apply binary classifiers and then, by combining the acquired solutions, we are able to solve the initial multi-class problem. In this paper we consider the optimization of the Linear Discriminant Error Correcting Output Codes framework using Particle Swarm Optimization. In particular, we apply the Particle Swarm Optimization algorithm in order to optimally select the free parameters that control the split of the initial problem’s classes into sub-classes. Moreover, by using the Support Vector Machine as classifier we can additionally apply the Particle Swarm Optimization algorithm to tune its free parameters. Our experimental results show that by applying Particle Swarm Optimization on the Sub-class Linear Discriminant Error Correcting Output Codes framework we get a significant improvement in the classification performance.

Traffic sign classification is a challenging problem in Computer Vision due to the high variability of sign appearance in uncontrolled environments. Lack of visibility, illumination changes, and partial occlusions are just a few problems. In this paper, we introduce a classification technique for traffic signs recognition by means of Error Correcting Output Codes. Recently, new proposals of coding and decoding strategies for the Error Correcting Output Codes framework have been shown to be very effective in front of multiclass problems. We review the state-of-the-art ECOC strategies and combinations of problem-dependent coding designs and decoding techniques. We apply these approaches to the Mobile Mapping problem. We detect the sign regions by means of Adaboost. The Adaboost in an attentional cascade with the extended set of Haar-like features estimated on the integral shows great performance at the detection step. Then, a spatial normalization using the Hough transform and the fast radial symmetry is done. The model fitting improves the final classification performance by normalizing the sign content. Finally, we classify a wide set of traffic signs types, obtaining high success in adverse conditions.

Error-Correcting Output Codes (ECOC) provides an effective solution for the multiclass classification problem by decomposing a multiclass problem into a set of binary class problems. In an ECOC algorithm, the design of coding matrix is the key to its performance. In this paper, we propose a Genetic Programming (GP) based ECOC algorithm, aiming to produce optimal coding matrices through the evolutionary process. In our GP, each terminal node denotes a column in the coding matrix, and each nonterminal node represents an operator, which combines the columns represented by its terminal nodes. In this way, an individual is interpreted as a coding matrix, and a set of operators are proposed to exchange information between column pairs, so as to produce new columns. Feature selection methods are also integrated into the terminal nodes, so that individuals are dynamically assigned to optimal feature subspaces for diverse classification problems. With evolutionary operators, offspring with high discriminant capability would be produced in the evolution. Our experiments compare our algorithm with other 7 classic ECOC algorithms with the deployment of diverse basic classifiers based on a set of UCI data sets, and results prove the superiority and robustness of our algorithm.

Error-correcting output codes based ensemble feature extraction

Convolutional Neural Networks (CNNs) demonstrate state-of-the-art performance in large-scale multi-class image classification tasks. CNNs consist of convolution layers that progressively construct features and a classification layer. Typically, a softmax function is used in the classification layer to learn joint probabilities for the classes, which are subsequently used for class prediction. We refer to such an approach as the joint approach to multi-class classification. There exists another approach in the literature which determines the multi-class prediction outcome through a sequence of binary decisions, and is christened the class binarization approach. A popular type of class binarization is error-correcting output codes. In this paper, we propose to incorporate error-correcting output codes into convolutional neural networks by inserting a latent binarization layer in a CNN classification layer. This approach encapsulates both encoding and decoding steps of error-correcting output codes into a single CNN architecture that is capable of discovering an optimal coding matrix during training. The latent binarization layer is motivated by the family of latent-trait and latent-class models used in behavioral research. We call the proposed convolutional neural networks with Latent Binarization as LB-CNNs, and develop algorithms combining expectation maximization algorithms and back-propagation to train LB-CNNs. The proposed models and algorithms are applied to several image recognition tasks, producing excellent results. Furthermore, our model enhances the interpretability of the decision process of standard convolutional neural networks.

Doppler ultrasound signals analysis using multiclass support vector machines with error correcting output codes

The Error-Correcting Output Codes (ECOC) method reduces the multi-class learning problem into a series of binary classifiers. In this paper, we propose a modified Hadamard-type ECOC method. This method uses both N’th order and N/2’th-order Hadamard matrix to construct error correcting output codes, which is called Hybrid Hadamard ECOC. Experiments based on dichotomizers of Support Vector Machines (SVM) have been carried out to evaluate the performance of the proposed method. When compared to normal Hadamard ECOC, computation of the method is reduced greatly while the accuracy of classification only drops slightly.

Social Signal Processing is an emergent area of research that focuses on the analysis of social constructs. Dominance and interest are two of these social constructs. Dominance refers to the level of influence a person has in a conversation. Interest, when referred in terms of group interactions, can be defined as the degree of engagement that the members of a group collectively display during their interaction. In this paper, we argue that only using behavioral motion information, we are able to predict the interest of observers when looking at face-to-face interactions as well as the dominant people. First, we propose a simple set of movement-based features from body, face, and mouth activity in order to define a higher set of interaction indicators. The considered indicators are manually annotated by observers. Based on the opinions obtained, we define an automatic binary dominance detection problem and amulticlass interest quantification problem. Error-Correcting Output Codes framework is used to learn to rank the perceived observer's interest in face-to-face interactions meanwhile Adaboost is used to solve the dominant detection problem. The automatic system shows good correlation between the automatic categorization results and the manual ranking made by the observers in both dominance and interest detection problems.

This paper presents the evaluation of the image segmentation capabilities of a mobile robot agent based on a Google Android Smartphone. The mobile agent was designed to operate autonomously in an environment inspired in a soccer game. The pixel-based color image segmentation capabilities was performed by testing different two-dimensional look up tables created from two-dimensional color histograms of the objects appearing in the scenario. The best segmentation alternative was obtained when using of a two-dimensional look up table based on the H (hue) and V (value) color image description. The final conclusion is that a Google Android Smartphone has enough potential to define an autonomous mobile robot agent and play a game that requires color-based image segmentation capabilities.Keywordssegmentationmobile robot agentAndroidSmartphone

Decoding design based on posterior probabilities in Ternary Error-Correcting Output Codes

Abstract. Image processing has been one of the efficient technologies for GIS data requisition. Support Vector Machines (SVMs) have peculiar advantages in handling problems with small sample sizes, nonlinearity, and high dimensionality. However, SVMs can only solve two-class problems while multi-class decision is impossible. Error correcting output coding (ECOC) SVMs enhance the ability of fault tolerance when solving multi-class classification problems, which makes ECOC SVMs suitable for remote sensing image classification. In this paper, the generalization ability of ECOC SVMs is discussed. ECOC SVMs with optimum coding matrices are selected by experiment, and applied to remote sensing image classification. Experimental results show that, compared with Conventional multi-class classification methods, less SVM sub-classifiers are needed for ECOC SVMs in remote sensing image classification, and the classification accuracy is also improved.

We propose the design of output codes for solving the classification problem in Fast Covering Learning Algorithm (FCLA). For a complex multi-class problem normally the classifiers are constructed by combining the outputs of several binary ones. In this paper, we use the basic methods of decomposition; one per class (OPC) and Error Correcting Output Code (ECOC) with FCLA, binary to binary mapping algorithm as a base binary learner. The methods have been tested on Fisher’s well-known Iris data set and experimental results show that the classification ability is improved by using ECOC method.

Scene understanding is strictly linked to image semantic segmentation, which is the process of associating each pixel of an image with a label, such as sky, clouds, road, building. This paper proposes a new semantic segmentation framework, in which Error-Correcting Output Codes (ECOC) are used to decompose the multiway classification problem into multiple binary classification subtasks. The binary output results are then converted into final class labels following a decoding table established at the beginning of the classification procedure. As part of the recognition framework, color descriptors and high-level visual features are extracted to represent the appearance of the patch surrounding each pixel of interest. The proposed method is validated on an image database containing RGB and Near-Infrared (NIR) imaaes.

In several real-world categorization problems, labeled data is generally hard to acquire when there is a huge number of unlabeled data. Hence, it is very important to devise a novel approaches to solve these problems, thereby choosing the most valuable instances for labeling and creating a superior classifier. Several existing techniques are devised for the binary categorization issues, only a limited number of algorithms are designed for handling the multi-label cases. The multi-label classification problem turns out to be more complex when the sample belongs to multiple labels from the group of accessible classes. In World Wide Web, text data is generally present nowadays, and is an obvious example for such type of tasks. This paper develops a novel technique to perform the multi-label text categorization by modifying the Error-Correcting Output Coding (ECOC) approach. Here, a cluster of binary complimentary classifiers are employed to facilitate the ECOC more effective for the multi-class problems. In addition, a weighted posterior probability is computed to enhance the multi-label text classification performance more effectively. Moreover, the performance of the proposed ECOC with weighted probability is analyzed using the performance metrics, like precision, recall, and f-measure with maximal precision of 0.897, higher recall value of 0.896, and maximum f-measure of 0.895.