Wyniki wyszukiwania - BazTech

1

Ensemble of classifiers based on deep learning for medical image recognition

Gil Fabian, Osowski Stanisław, Świderski Bartosz, Słowińska Monika

Metrology and Measurement Systems

|

2023

|

Vol. 30, nr 1

139--156

EN

The paper presents special forms of an ensemble of classifiers for analysis of medical images based on application of deep learning. The study analyzes different structures of convolutional neural networks applied in the recognition of two types of medical images: dermoscopic images for melanoma and mammograms for breast cancer. Two approaches to ensemble creation are proposed. In the first approach, the images are processed by a convolutional neural network and the flattened vector of image descriptors is subjected to feature selection by applying different selection methods. As a result, different sets of a limited number of diagnostic features are generated. In the next stage, these sets of features represent input attributes for the classical classifiers: support vector machine, a random forest of decision trees, and softmax. By combining different selection methods with these classifiers an ensemble classification system is created and integrated by majority voting. In the second approach, different structures of convolutional neural networks are directly applied as the members of the ensemble. The efficiency of the proposed classification systems is investigated and compared to medical data representing dermoscopic images of melanoma and breast cancer mammogram images. Thanks to fusion of the results of many classifiers forming an ensemble, accuracy and all other quality measures have been significantly increased for both types of medical images.

2

Deep Classifiers and Wavelet Transformation for Fake Image Detection

Osowski Stanislaw, Golgowski Maciej

Journal of Telecommunications and Information Technology

|

2023

|

nr 4

1--8

EN

The paper presents a computer system for detecting deep fake images in videos. The system is based on continuous wavelet transformation combined with a set of classifiers composed of a few convolutional neural networks of diversified architectures. Three different forms of forged images taken from the FaceForensics++ database are considered in numerical experiments. The results of experiments involving the proposed system have shown good performance in comparison to other current approaches to this particular problem.

3

Ensemble of classifiers based on CNN for increasing generalization ability in face image recognition

Szmurło Robert, Osowski Stanisław

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2022

|

Vol. 70, nr 3

art. no. e141004

EN

The paper considers the problem of increasing the generalization ability of classification systems by creating an ensemble of classifiers based on the CNN architecture. Different structures of the ensemble will be considered and compared. Deep learning fulfills an important role in the developed system. The numerical descriptors created in the last locally connected convolution layer of CNN flattened to the form of a vector, are subjected to a few different selection mechanisms. Each of them chooses the independent set of features, selected according to the applied assessment techniques. Their results are combined with three classifiers: softmax, support vector machine, and random forest of the decision tree. All of them do simultaneously the same classification task. Their results are integrated into the final verdict of the ensemble. Different forms of arrangement of the ensemble are considered and tested on the recognition of facial images. Two different databases are used in experiments. One was composed of 68 classes of greyscale images and the second of 276 classes of color images. The results of experiments have shown high improvement of class recognition resulting from the application of the properly designed ensemble.

4

Ensemble selection in one-versus-one scheme – case study for cutting tools classification

Rojek Izabela, Burduk Robert, Heda Paulina

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2021

|

Vol. 69, nr 1

art. no. e136044

EN

The binary classifiers are appropriate for classification problems with two class labels. For multi-class problems, decomposition techniques, like one-vs-one strategy, are used because they allow the use of binary classifiers. The ensemble selection, on the other hand, is one of the most studied topics in multiple classifier systems because a selected subset of base classifiers may perform better than the whole set of base classifiers. Thus, we propose a novel concept of the dynamic ensemble selection based on values of the score function used in the one-vs-one decomposition scheme. The proposed algorithm has been verified on a real dataset regarding the classification of cutting tools. The proposed approach is compared with the static ensemble selection method based on the integration of base classifiers in geometric space, which also uses the one-vs-one decomposition scheme. In addition, other base classification algorithms are used to compare results in the conducted experiments. The obtained results demonstrate the effectiveness of our approach.

5

Ensemble of classifiers and wavelet transformation for improved recognition of Fuhrman grading in clear-cell renal carcinoma

Kruk M., Kurek J., Osowski S., Koktysz R., Swiderski B., Markiewicz T.

Biocybernetics and Biomedical Engineering

|

2017

|

Vol. 37, no. 3

357--364

EN

The paper presents an improved system to recognition of Fuhrman grading in clear-cell renal carcinoma using an ensemble of classifiers. The novelty of solution includes the segmentation applying wavelet transformation in preprocessing stage, application of few selection methods for feature generation and using the ensemble of classifiers in final recognition step. The wavelet transformation is a very efficient tool for image de-noising and enhancing the edges of cell nuclei. The important distinction to other approaches is that diagnostic features of nuclei, based on the texture, geometry, color and histogram, are selected by using few methods, each relying on different mechanism of selection. These different sets of features have enabled creating the ensemble of classifiers based on the support vector machine and random forest, both cooperating with them. Such approach has led to the significant increase of the quality factors in comparison to the best existing results: sensitivity (the average of this solution 94.3% compared to 91.5%) and specificity (the average 98.6% compared to 97.5%.

6

Person verification based on keystroke dynamics

Doroz R., Porwik P., Safaverdi H.

Journal of Medical Informatics & Technologies

|

2015

|

Vol. 24

39--44

EN

This paper presents a new multilayer ensemble of classifiers for users verification who use computer keyboard. The special keyboard extracts the key pressure and latency between keyboard keys pressed during password entered. When user is typing password the system creates a pattern based on time and key pressure. For users verification group of classifiers have been proposed. It allows to obtain the higher accuracy level compared to alternative techniques. The efficiency of the proposed method has been confirmed in the experiments carried out.

7

Analyzing tree-shape anatomical structures using topological descriptors of branching and ensemble of classifiers

Skoura A., Bakic P.R., Megalooikonomou V.

Journal of Theoretical and Applied Computer Science

|

2013

|

Vol. 7, nr 1

3--19

EN

The analysis of anatomical tree-shape structures visualized in medical images provides insight into the relationship between tree topology and pathology of the corresponding organs. In this paper, we propose three methods to extract descriptive features of the branching topology; the asymmetry index, the encoding of branching patterns using a node labeling scheme and an extension of the Sholl analysis. Based on these descriptors, we present classification schemes for tree topologies with respect to the underlying pathology. Moreover, we present a classifier ensemble approach which combines the predictions of the individual classifiers to optimize the classification accuracy. We applied the proposed methodology to a dataset of x-ray galactograms, medical images which visualize the breast ductal tree, in order to recognize images with radiological findings regarding breast cancer. The experimental results demonstrate the effectiveness of the proposed framework compared to state-of-the-art techniques suggesting that the proposed descriptors provide more valuable information regarding the topological patterns of ductal trees and indicating the potential of facilitating early breast cancer diagnosis.

8

Local Feature Selection with Dynamic Integration of Classifiers

Puuronen S., Tsymbal A.

Fundamenta Informaticae

|

2001

|

Vol. 47, nr 1,2

91-117

EN

Multidimensional data is often feature space heterogeneous so that individual features have unequal importance in different sub areas of the feature space. This motivates to search for a technique that provides a strategic splitting of the instance space being able to identify the best subset of features for each instance to be classified. Our technique applies the wrapper approach where a classification algorithm is used as an evaluation function to differentiate between different feature subsets. In order to make the feature selection local, we apply the recent technique for dynamic integration of classifiers. This allows to determine which classifier and which feature subset should be used for each new instance. Decision trees are used to help to restrict the number of feature combinations analyzed. For each new instance we consider only those feature combinations that include the features present in the path taken by the new instance in the decision tree built on the whole feature set. We evaluate our technique on data sets from the UCI machine learning repository. In our experiments, we use the C4.5 algorithm as the learning algorithm for base classifiers and for the decision trees that guide the local feature selection. The experiments show some advantages of the local feature selection with dynamic integration of classifiers in comparison with the selection of one feature subset for the whole space.