687 research outputs found
Genetic algorithm-based method for mitigating label noise issue in ECG signal classification
No full textClassification of electrocardiographic (ECG) signals can be deteriorated by the presence in the training set of mislabeled samples. To alleviate this issue we propose a new approach that aims at assisting the human user (cardiologist) in his/her work of labeling by removing in an automatic way the training samples with potential mislabeling problems. The proposed method is based on a genetic optimization process, in which each chromosome represents a candidate solution for validating/invalidating the training samples. Moreover, the optimization process consists of optimizing jointly two different criteria, which are the maximization of the statistical separability among classes and the minimization of the number of invalidated samples. Experimental results obtained on real ECG signals extracted from the MIT-BIH arrhythmia database confirm the effectiveness of the proposed solution
A mutual approach based on Markov random fields for multitemporal contextual classification of remote sensing images
No full textMultiobjective PSO for hyperspectral image clustering
No full textIn this chapter, a multiobjective particle-swarm optimization approach is presented as an answer to the problem of hyperspectral remote sensing image clustering. It aims at simultaneously solving the following three different issues: (1) clustering the hyperspectral cube under analysis; (2) detecting the most discriminative bands of the hypercube; (3) avoiding the user to set a priori the number of data classes. The search process is guided by three different statistical criteria, which are the log-likelihood function, the Bhattacharyya distance, and the minimum description length. Experimental results clearly underline the effectiveness of particle-swarm optimizers for a completely automatic and unsupervised analysis of hyperspectral remote sensing images
A statistical approach to the fusion of spectral and spatio-temporal contextual information for the classification of remote-sensing images
No full text
Autoencoding approach to the cloud removal problem
No full textWe propose in this work new strategies to reconstruct areas obscured by opaque clouds in multispectral images. They are based on an autoencoder (AE) neural network which opportunely models the relationships between a given source (cloud-free) image and a target (cloud-contaminated) image. The first strategy estimates the relationship model at a pixel level while the second one operates at a patch level in order profit from spatial contextual information. Experimental results obtained on FORMOSAT-2 images are reported and discussed together with a comparison with reference techniques
Active learning methods for electrocardiographic signal classification
No full textIn this paper, we present three active learning strategies for the classification of electrocardiographic (ECG) signals. Starting from a small and suboptimal training set, these learning strategies select additional beat samples from a large set of unlabeled data. These samples are labeled manually, and then added to the training set. The entire procedure is iterated until the construction of a final training set representative of the considered classification problem. The proposed methods are based on support vector machine classification and on the: 1) margin sampling; 2) posterior probability; and 3) query by committee principles, respectively. To illustrate their performance, we conducted an experimental study based on both simulated data and real ECG signals from the MIT-BIH arrhythmia database. In general, the obtained results show that the proposed strategies exhibit a promising capability to select samples that are significant for the classification process, i.e., to boost the accuracy of the classification process while minimizing the number of involved labeled samples
Gaussian process approach to buried object size estimation in GPR images
No full textRecently, a promising pattern-recognition system has been presented to deal with the extraction of buried-object characteristics in ground-penetrating-radar images. In particular, it allows the detecting of buried objects by means of a search method based on genetic algorithms and the recognizing of the material type of the identified objects through a classification approach based on support vector machines. In this letter, we propose to extend the processing capabilities of this system by addressing the issue of the detected buried-object size estimation. This problem is viewed as a regression issue where it is aimed at reproducing the relationship between a set of opportunely extracted features and the object size. For such purpose, it is formulated within a Gaussian process (GP) regression approach. A detailed experimental study is reported, showing encouraging object-size-estimation accuracies even when buried objects are close to each other
LBP-based multiclass classification method for UAV imagery
No full textIn order to describe images acquired with unmanned aerial vehicles (UAV), we introduce in this paper a multilabeling classification method. It starts by subdividing the original UAV image into a grid of tiles which are then analyzed separately. From each tile, a signature which encodes texture information is extracted and compared with the signatures of the tiles belonging to a pre-built training dictionary in order to acquire the binary multilabel vector of the most similar tile. In order to represent and match the tiles, we exploit a well-known texture operator and a common distance measure, respectively. Promising experimental results, in particular for some classes of objects, are obtained on real UAV images acquired over urban areas
- …
