Search results

Filters

  • Journals
  • Authors
  • Keywords
  • Date
  • Type

Search results

Number of results: 3
items per page: 25 50 75
Sort by:
Download PDF Download RIS Download Bibtex

Abstract

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.
Go to article

Authors and Affiliations

Robert Szmurło
1
ORCID: ORCID
Stanislaw Osowski
2
ORCID: ORCID

  1. Faculty of Electrical Engineering, Warsaw University of Technology, Koszykowa 75, 00-662 Warszawa, Poland
  2. Faculty of Electronic Engineering, Military University of Technology, gen. S. Kaliskiego 2, 00-908 Warszawa, Poland
Download PDF Download RIS Download Bibtex

Abstract

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.
Go to article

Authors and Affiliations

Fabian Gil
1
Stanisław Osowski
1 2
Bartosz Świderski
3
Monika Słowińska
4

  1. Military University of Technology, Faculty of Electronics, Institute of Electronic Systems, ul. gen. Sylwestra Kaliskiego 2, 00-908 Warsaw, Poland
  2. Warsaw University of Technology, Faculty of Electrical Engineering, pl. Politechniki 1, 00-661 Warsaw, Poland
  3. University of Life Sciences, ul. Nowoursynowska 166, 02-787 Warsaw
  4. Central Clinical Hospital Ministry of Defense, Military Institute of Medicine – National Research Institute, ul. Szaserów 128, 04-141 Warsaw, Poland
Download PDF Download RIS Download Bibtex

Abstract

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.

Go to article

Bibliography

  1.  C. Sammut and G. I. Webb, Encyclopedia of Machine Learning and Data Mining. Springer US, 2016.
  2.  M. Mohri, A. Rostamizadeh, and A. Talwalkar, Foundations of machine learning. MIT press, 2018.
  3.  S. Osowski and K. Siwek, “Local dynamic integration of ensemble in prediction of time series”, Bull. Pol. Ac.: Tech. 67(3), 517–525 (2019).
  4.  O. Sagi and L. Rokach, “Ensemble learning: A survey”, Wiley Interdiscip. Rev.-Data Mining Knowl. Discov. 8(4), e1249 (2018).
  5.  R.M. Cruz, R. Sabourin, and G.D. Cavalcanti, “Dynamic classifier selection: Recent advances and perspectives”, Inf. Fusion 41, 195–216 (2018).
  6.  O.A. Alzubi, J.A. Alzubi, M. Alweshah, I. Qiqieh, S. AlShami, and M. Ramachandran, “An optimal pruning algorithm of classifier ensembles: dynamic programming approach”, Neural Comput. Appl. 32, 16091–16107 (2020).
  7.  Y. Bian, Y. Wang, Y. Yao, and H. Chen, “Ensemble pruning based on objection maximization with a general distributed framework”, IEEE Trans. Neural Netw. Learn. Syst. 31(9), 3766‒3774 (2020).
  8.  R.M. Cruz, D.V. Oliveira, G.D. Cavalcanti, and R. Sabourin, “Fire-des++: Enhanced online pruning of base classifiers for dynamic ensemble selection”, Pattern Recognit. 85, 149–160 (2019).
  9.  T.T. Nguyen, A.V. Luong, M.T. Dang, A.W.-C. Liew, and J. McCall, “Ensemble selection based on classifier prediction confidence”, Pattern Recognit. 100, 107104 (2020).
  10.  Z.-L. Zhang, X.-G. Luo, S. García, J.-F. Tang, and F. Herrera, “Exploring the effectiveness of dynamic ensemble selection in the one- versus-one scheme”, Knowledge-Based Syst. 125, 53–63 (2017).
  11.  M. Galar, A. Fernández, E. Barrenechea, H. Bustince, and F. Herrera, “Dynamic classifier selection for one-vs-one strategy: avoiding non-competent classifiers”, Pattern Recognit. 46(12), 3412–3424 (2013).
  12.  M. Pawlicki, A. Giełczyk, R. Kozik, and M. Choraś, “Faultprone software classes recognition via artificial neural network with granular dataset balancing”, in International Conference on Computer Recognition Systems 2019, Springer, 2019, pp. 130–140.
  13.  D. Rajeev, D. Dinakaran, and S. Singh, “Artificial neural network based tool wear estimation on dry hard turning processes of aisi4140 steel using coated carbide tool”, Bull. Pol. Ac.: Tech. 65(4), 553–559 (2017).
  14.  D. Więcek, A. Burduk, and I. Kuric, “The use of ann in improving efficiency and ensuring the stability of the copper ore mining process”, Acta Montanistica Slovaca 24(1), 1‒14 (2019).
  15.  P. Raja, R. Malayalamurthim, and M. Sakthivel, “Experimental investigation of cryogenically treated hss tool in turning on aisi1045 using fuzzy logic–taguchi approach”, Bull. Pol. Ac.: Tech. 67(4), 687–696 (2019).
  16.  T. Andrysiak and L. Saganowski, “Anomaly detection for smart lighting infrastructure with the use of time series analysis”, J. UCS 26(4), 508–527 (2020).
  17.  A. Burduk, K. Musiał, J. Kochańska, D. Górnicka, and A. Stetsenko, “Tabu search and genetic algorithm for production process scheduling problem”, LogForum 15, 181–189 (2019.
  18.  M. Choraś, M. Pawlicki, D. Puchalski, and R. Kozik, “Machine learning–the results are not the only thing that matters! what about security, explainability and fairness?”, in International Conference on Computational Science, Springer, 2020, pp. 615–628.
  19.  P. Zarychta, P. Badura, and E. Pietka, “Comparative analysis of selected classifiers in posterior cruciate ligaments computer aided diagnosis”, Bull. Pol. Ac.: Tech. 65(1), 63–70 (2017).
  20.  I. Rojek, E. Dostatni, and A. Hamrol, “Ecodesign of technological processes with the use of decision trees method”, in International Joint Conference SOCO’17-CISIS’17-ICEUTE’17, León, Spain, 2017, Springer, 2018, pp. 318–327.
  21.  I. Rojek and E. Dostatni, “Machine learning methods for optimal compatibility of materials in ecodesign”, Bull. Pol. Ac.: Tech. 68(2), 199–206 (2020).
  22.  P. Prokopowicz, D. Mikołajewski, K. Tyburek, and E. Mikołajewska, “Computational gait analysis for post-stroke rehabilitation purposes using fuzzy numbers, fractal dimension and neural networks”, Bull. Pol. Ac.: Tech. 68(2), 191–198 (2020).
  23.  S. Igari, F. Tanaka, and M. Onosato, “Customization of a micro process planning system for an actual machine tool based on updating a machining database and generating a database-oriented planning algorithm”, Trans. Inst. Syst. Control Inform. Eng. 26(3), 87–94 (2013).
  24.  C. Tan and S. Ranjit, “An expert carbide cutting tools selection system for cnc lathe machine”, Int. Rev. Mech. Eng. 6(7), 1402–1405 (2012).
  25.  I. Rojek, “Technological process planning by the use of neural networks”, AI EDAM – AI EDAM-Artif. Intell. Eng. Des. Anal. Manuf. 31(1), 1–15 (2017).
  26.  P. Heda, I. Rojek, and R. Burduk, “Dynamic ensemble selection – application to classification of cutting tools”, in International Conference on Computer Information Systems and Industrial Management LNCS(12133), Springer, 2020, pp. 345–354.
  27.  L.I. Kuncheva, Combining Pattern Classifiers. John Wiley & Sons, Inc., 2014.
  28.  E. Santucci, L. Didaci, G. Fumera, and F. Roli, “A parameter randomization approach for constructing classifier ensembles”, Pattern Recognit. 69, 1–13 (2017).
  29.  M. Mohandes, M. Deriche, and S. O. Aliyu, “Classifiers combination techniques: A comprehensive review”, IEEE Access 6, 19626–19639 (2018).
  30.  J. Yan, Z. Zhang, K. Lin, F. Yang, and X. Luo, “A hybrid scheme-based one-vs-all decision trees for multi-class classification tasks”, Knowledge-Based Syst. 198. 105922 (2020).
  31.  P. Chaitra and R.S. Kumar, “A review of multi-class classification algorithms”, Int. J. Pure Appl. Math. 118(14), 17–26 (2018).
  32.  M. Galar, A. Fernández, E. Barrenechea, H. Bustince, and F. Herrera, “An overview of ensemble methods for binary classifiers in multi- class problems: Experimental study on onevs-one and one-vs-all schemes”, Pattern Recognit. 44(8), 1761–1776 (2011).
  33.  R. Burduk, “Integration base classifiers based on their decision boundary”, in International Conference on Artificial Intelligence and Soft Computing, Springer, 2017, pp. 13–20.
  34.  M.P. Groover, Fundamentals of modern manufacturing: materials, processes and systems, Willey, 2010.
  35.  M. Sokolova and G. Lapalme, “A systematic analysis of performance measures for classification tasks”, Inf. Process. Manage. 45, 427–437 (2009).
  36.  I. Rojek, “Classifier models in intelligent capp systems”, in Man-Machine Interactions, pp. 311–319, Springer, 2009.
Go to article

Authors and Affiliations

Izabela Rojek
1
ORCID: ORCID
Robert Burduk
2
ORCID: ORCID
Paulina Heda
2

  1. Institute of Computer Science, Kazimierz Wielki University, ul. Chodkiewicza 30, 85-064 Bydgoszcz, Poland
  2. Faculty of Electronic, Wroclaw University of Science and Technology, ul. Wybrzeze Wyspianskiego 27, 50-370 Wroclaw, Poland

This page uses 'cookies'. Learn more