Browse > Article
http://dx.doi.org/10.9717/kmms.2019.22.6.665

A Study on Classification Performance Analysis of Convolutional Neural Network using Ensemble Learning Algorithm  

Park, Sung-Wook (Dept. of Computer Engineering, Sunchon National University)
Kim, Jong-Chan (Dept. of Computer Engineering, Sunchon National University)
Kim, Do-Yeon (Dept. of Computer Engineering, Sunchon National University)
Publication Information
Journal of Korea Multimedia Society / v.22, no.6, 2019 , pp. 665-675 More about this Journal
Abstract
In this paper, we compare and analyze the classification performance of deep learning algorithm Convolutional Neural Network(CNN) ac cording to ensemble generation and combining techniques. We used several CNN models(VGG16, VGG19, DenseNet121, DenseNet169, DenseNet201, ResNet18, ResNet34, ResNet50, ResNet101, ResNet152, GoogLeNet) to create 10 ensemble generation combinations and applied 6 combine techniques(average, weighted average, maximum, minimum, median, product) to the optimal combination. Experimental results, DenseNet169-VGG16-GoogLeNet combination in ensemble generation, and the product rule in ensemble combination showed the best performance. Based on this, it was concluded that ensemble in different models of high benchmarking scores is another way to get good results.
Keywords
Deep Learning; Computer Vision; CNN; Ensemble Learning Algorithm;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 G. Fumera and F. Roli, "A Theoretical and Experimental Analysis of Linear Combiners for Multiple Classifier Systems," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 27, No. 6, pp. 942-956, 2005.   DOI
2 J. Kittler, M. Hatef, R.P.W. Duin, and J. Matas, "On Combining Classifiers," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, No. 3, pp. 226-239, 1998.   DOI
3 Y. Jeong, L. Ansari, J. Shim, and J. Lee, "A Car Plate Area Detection System Using Deep Convolution Neural Network," J ournal of Korea Multimedia Society, Vol. 20, No. 8, pp. 1166-1174, 2017.   DOI
4 M. Lin, Q. Chen, and S. Yan, "Network in Network," arXiv, arXiv:1312.4400v3, 2014.
5 K. Janocha and W.M. Czarnecki, "On Loss Functions for Deep Neural Networks in Classification," arXiv, arXiv:1702.05659, 2017.
6 V. Nair and G. Hinton, "Rectified Linear Units Improve Restricted Boltzmann Machines," Proceedings of the 27th International Conference on Machine Learning, pp. 807-814, 2010.
7 L. Bottou, "Stochastic Gradient Descent Tricks," Neural Network, Tricks of the Trade, Reloaded, Vol. 7700, pp. 430-445, 2012.
8 I. Sutskever, J. Martens, G. Dahl, and G. Hinton, "On the Importance of Initialization and Momentum in Deep Learning," Proceeding of the 30th International Conference on Machine Learning, Vol. 28, pp. 1139-1147, 2013.
9 T. Tieleman and G. Hinton, RMSProp: Divide the Gradient by a Running Average of I ts Recent Magnitude, COURSERA: Neural Networks for Machine Learning Technical Report, 2012.
10 X. Glorot and Y. Bengio, "Understanding the Difficulty of Training Deep Feedforward Neural Networks," Proceedings of the International Conference on Artificial Intelligence and Statistics, pp. 249-256, 2010.
11 Kaggle: Your Home for Data Science, https://www.kaggle.com/ (accessed Feb., 14, 2019).
12 State Farm Distracted Driver Detection, https://www.kaggle.com/c/state-farm-distracteddriver-detection (accessed Aug., 14, 2019).
13 Santander Product Recommendation, https://www.kaggle.com/c/santander-product-recommendation (accessed Aug., 14, 2019).
14 Tensorflow Speech Recognition Challenge, https://www.kaggle.com/c/tensorflowspeech-recognition-challenge (accessed Aug., 14, 2019).
15 Porto Seguro's Safe Driver Prediction, https://www.kaggle.com/c/porto-seguro-safe-driver-prediction (accessed Aug., 14, 2019).
16 J. Bergstra and Y. Bengio, "Random search for hyper-parameter optimization," The Journal of Machine Learning Research, Vol. 13, No. 1, pp. 281-305, 2012.
17 J. Snoek, H. Larochelle, and R.P. Adams, "Practical Bayesian Optimization of Machine Learning Algorithms," Proceedings of the 25th International Conference on Neural Information Processing Systems, Vol. 2, pp. 2951-2959, 2012.
18 K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," arXiv, arXiv:1512.03385, 2015.
19 L. Yann, B. Yoshua, and H. Geoffrey, “Deep Leaning,” Nature, Vol. 521, No. 7553, pp. 436-444, 2015.   DOI
20 Y. Lecun, L. Bottou, and Y. Bengio, “Gradient-based Learning Applied to Document Recognition,” Proceeding of The IEEE, Vol. 86, No. 11, pp. 2278-2324, 1998.   DOI
21 S.W. Park, J.C. Kim, and D.Y. Kim, "A Study on Classification of Convolutional Neural Network using Ensemble Combining Technique," Proceeding of the Fall Conference of the Korea Multimedia Society, pp. 757, 2018.
22 D. Ciresan, U. Meier, and J. Schmidhuber, "Multi-column Deep Neural Networks for Image Classification," Proceedings of the 25th IEEE Conference on Computer Vision and Pattern Recognition, pp. 3642-3649, 2012.
23 The BellKor Solution to the Netflix Grand Prize, https://www.netflixprize.com/assets/GrandPrize2009_BPC_BellKor.pdf (accessed Feb., 14, 2019).
24 M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, et al., "TensorFlow: Largescale Machine Learning on Heterogeneous Systems," arXiv, arXiv:1603.04467, 2015.
25 K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large-Scale Image Recognition," arXiv, arXiv:1409.1556, 2015.
26 C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, et al., "Going Deeper with Convolutions," arXiv, arXiv:1409.4842, 2014.
27 G. Huang, Z. Liu, L.V.d. Maaten, and K.Q. Weinberger, "Densely Connected Convolutional Networks," Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2261-2269, 2017.
28 Keras, https://github.com/fchollet/keras (accessed Jan., 15, 2019).
29 K. Alex, S. Ilya, and H. Geoffrey, "ImageNet Classification with Deep Convolutional Neural Networks," Proceeding of Advances in Neural Information Processing System, pp. 1097-1105, 2012.