Volume 6, Issue 1 (January 2019), Pages: 106-113

----------------------------------------------

 Original Research Paper

 Title: Utilizing hierarchical extreme learning machine based reinforcement learning for object sorting

 Author(s): Nouar AlDahoul *, ZawZaw Htike

 Affiliation(s):

 Mechatronics Department, International Islamic University Malaysia, Kuala Lumpur, Malaysia

  Full Text - PDF          XML

 * Corresponding Author. 

  Corresponding author's ORCID profile: https://orcid.org/0000-0001-5522-0033

 Digital Object Identifier: 

 https://doi.org/10.21833/ijaas.2019.01.015

 Abstract:

Automatic and intelligent object sorting is an important task that can sort different objects without human intervention, using the robot arm to carry each object from one location to another. These objects vary in colours, shapes, sizes and orientations. Many applications, such as fruit and vegetable grading, flower grading, and biopsy image grading depend on sorting for a structural arrangement. Traditional machine learning methods, with extracting handcrafted features, are used for this task. Sometimes, these features are not discriminative because of the environmental factors, such as light change. In this study, Hierarchical Extreme Learning Machine (HELM) is utilized as an unsupervised feature learning to learn the object observation directly, and HELM was found to be robust against external change. Reinforcement learning (RL) is used to find the optimal sorting policy that maps each object image to the object’s location. The reason for utilizing RL is lack of output labels in this automatic task. The learning is done sequentially in many episodes. At each episode, the accuracy of sorting is increased to reach the maximum level at the end of learning. The experimental results demonstrated that the proposed HELM-RL sorting can provide the same accuracy as the labelled supervised HELM method after many episodes. 

 © 2018 The Authors. Published by IASE.

 This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

 Keywords: Object sorting, Reinforcement learning, Hierarchical extreme learning-machine, Deep learning, Feature learning

 Article History: Received 22 August 2018, Received in revised form 6 December 2018, Accepted 7 December 2018

 Acknowledgement:

This work was supported by the International Islamic University Malaysia under the Research initiatives Grant Scheme (RIGS16-350-0514).

 Compliance with ethical standards

 Conflict of interest:  The authors declare that they have no conflict of interest.

 Citation:

 AlDahoul N and Htike Z (2019). Utilizing hierarchical extreme learning machine based reinforcement learning for object sorting. International Journal of Advanced and Applied Sciences, 6(1): 106-113

 Permanent Link to this page

 Figures

 Fig. 1 Fig. 2 Fig. 3 Fig. 4 Fig. 5 Fig. 6 Fig. 7 Fig. 8 Fig. 9 Fig. 10

 Tables

 Table 1 Table 2 Table 3 Table 4

----------------------------------------------

 References (11) 

1. AlDahoul N, Htike ZZ, and Akmeliawati R (2017). Hierarchical extreme learning machine based reinforcement learning for goal localization. In the IOP Conference Series: Materials Science and Engineering, IOP Publishing, 184(1): 012055. https://doi.org/10.1088/1757-899X/184/1/012055   [Google Scholar]
2. AlDahoul N, Sabri M, Qalid A, and Mansoor AM (2018). Real-time human detection for aerial captured video sequences via deep models. Computational Intelligence and Neuroscience, 2018: Article ID 1639561, 14 pages. https://doi.org/10.1155/2018/1639561   [Google Scholar]
3. Huang GB, Zhu QY, and Siew CK (2006). Extreme learning machine: Theory and applications. Neurocomputing, 70(1-3): 489-501. https://doi.org/10.1016/j.neucom.2005.12.126   [Google Scholar]
4. Pandey R, Naik S, and Marfatia R (2013). Image processing and machine learning for automated fruit grading system: A technical review. International Journal of Computer Applications, 81(16): 29-39.   [Google Scholar]
5. Piñol M, Sappa AD, and Toledo R (2015). Adaptive feature descriptor selection based on a multi-table reinforcement learning strategy. Neurocomputing, 150: 106-115. https://doi.org/10.1016/j.neucom.2014.03.080   [Google Scholar]
6. Sun Y, Zhu L, Wang G, and Zhao F (2017). Multi-input convolutional neural network for flower grading. Journal of Electrical and Computer Engineering, 2017: Article ID 9240407, 8 pages. https://doi.org/10.1155/2017/9240407   [Google Scholar]
7. Susnjak T, Barczak A, and Reyes N (2013). A decomposition machine-learning strategy for automated fruit grading. In the World Congress on Engineering and Computer Science, San Francisco, USA, 2: 819-825.   [Google Scholar]
8. Sutton RS and Barto AG (2018). Reinforcement learning: An introduction. MIT Press, Cambridge, USA.   [Google Scholar]
9. Tang J, Deng C, and Huang GB (2016). Extreme learning machine for multilayer perceptron. IEEE Transactions on Neural Networks and Learning Systems, 27(4): 809-821. https://doi.org/10.1109/TNNLS.2015.2424995   [Google Scholar]  PMid:25966483
10. Tho TP and Thinh NT (2015). Design and development of the sorting system based on robot. In the 15^th International Conference on Control, Automation and Systems, IEEE, Busan, South Korea: 1639-1644. https://doi.org/10.1109/ICCAS.2015.7364620   [Google Scholar]
11. Tho TP, Thinh NT, and Bich NH (2016). Design and development of the vision sorting system. In the International Conference on Green Technology and Sustainable Development, IEEE, Kaohsiung, Taiwan: 217-223. https://doi.org/10.1109/GTSD.2016.57   [Google Scholar]