WALL-FOLLOWING ROBOT NAVIGATION CLASSIFICATION USING DEEP LEARNING WITH SPARSE CATEGORICAL CROSSENTROPY LOSS FUNCTION
Keywords:
Wall-Following Robot Navigation, Deep Learning, Keras, KerasSparse Categorical CrossentropyAbstract
Nowadays, technology has developed in advance. One example of things that are experiencing technological advances are robots. Robots are mechanical devices that were created to replace some of the repetitive human jobs. Where can carry out certain tasks either automatically or by human control or programs that are given based on logic. One example is the navigation on the wall following robot, this robot is a robot that can move independently by detecting the "wall" using the sensors on the robot without hitting the “wall”. One of the studies used a wall-following SCITOS-G5 robot which was installed with 24 ultrasound sensors and it generates a dataset. The dataset can be used as an analysis in this research. Not only robots that experience the development of the times, but the world of research is also experiencing developments, one example is deep learning. This research uses a deep learning neural network method with a keras library in python. The process of this research is to calculate how much accuracy is generated from the deep learning method. The accuracy resulting from this study will be compared with the accuracy in the K-Nearest Neighbor study with the same dataset. The results of the calculation of accuracy in previous studies using the machine learning method K-Nearest Neighbor is 88.17%. Meanwhile, in this study, the accuracy obtained using the deep learning method is 95.27%. Therefore, the use of the deep learning method using a keras library in this study is better than the K-Nearest Neighbor method.
Downloads
References
Thanh, N.N., H.D. Hiep, and P.H. Tung, RELATIONSHIP BETWEEN CHARACTERISTICS AND UNIVERSITY INTENTION: A CASE STUDY OF STUDENTS IN VIETNAM. PalArch's Journal of Archaeology of Egypt/Egyptology, 2021. 18(18): p. 44-69.
Singh, S.K., Data -Enhanced Convolution Neural Networks for Wall Following Robot Navigation. International Journal of Engineering and Advanced Technology (IJEAT), 9(1), 4426-4430. 2019 DOI: https://doi.org/10.35940/ijeat.A1361.109119.
Utami, A.T.W. and B.S.S. Ulama, Application of Backpropagation to Improve Time Effectiveness and Accuracy on Wall-Following Robot Navigation Data. ITS Jurnal Journal of Science and Arts, 2016. 4(2).
Azis, A.I.S., V. Suhartono, and H. Himawan, Multi-Class SVM model using 1V1 strategy for Wall- Following Robot Navigation Data Classification. My Cyber Journal, 2017. 13(2): p. 8-8.
Zdrodowska, M., A. Dardzińska, and A. Kasperczuk. Using Data Mining Tools in Wall-Following Robot Navigation Data Set. IEEE DOI: https://doi.org/10.1109/MSM49833.2020.9201730.
Visaltanachoti, C., C. Viriyavejakul, and T. Ratanaolarn, DEVELOPMENT GUIDELINES FOR AN ARTIFICIAL INTELLIGENCE ALGORITHMIC MODEL IN TEACHING FOREIGN. PalArch's Journal of Archaeology of Egypt/Egyptology, 2021. 18(18): p. 371-380.
Nazir, N., et al., AN IN-DEPTH ANALYSIS OF APPLICABILITY AND EFFECTIVENESS OF LEARNER-CENTERED APPROACH AT UNDERGRADUATE LEVEL IN PAKISTANI CLASSROOM CONTEXT. PalArch's Journal of Archaeology of Egypt/Egyptology, 2021. 18(18): p. 353-370.
Madi, S. and R. Baba-Ali. Classification techniques for wall-following robot navigation: a comparative study. Springer DOI: https://doi.org/10.1007/978-3-319-99010-1_9.
Freire, A.L., et al. Short-term memory mechanisms in neural network learning of robot navigation tasks: A case study. IEEE DOI: https://doi.org/10.1109/LARS.2009.5418323.
Deng, L. and D. Yu, Deep learning: methods and applications. Foundations and trends in signal processing, 2014. 7(3–4): p. 197-387 DOI: https://doi.org/10.1561/2000000039.
Peterson, L.E., K-nearest neighbor. Scholarpedia, 2009. 4(2): p. 1883 DOI: https://doi.org/10.4249/scholarpedia.1883.
Younas, F. and Z. Mubeen, BODY IMAGE SATISFACTION AND EATING ATTITUDES: ROLE OF SOCIODEMOGRAPHIC CHARACTERISTICS. PalArch's Journal of Archaeology of Egypt/Egyptology, 2021. 18(18): p. 273-288.
Downloads
Published
Issue
Section
License
Copyright (c) 2022 Author
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
