Computer Science and Information Systems 2022 Volume 19, Issue 1, Pages: 25-45
https://doi.org/10.2298/CSIS201218041L
Full text (
431 KB)
Cited by
Link quality estimation based on over-sampling and weighted random forest
Liu Linlan (School of Information Engineering, Nanchang Hangkong University, Nanchang, China), 765693987@qq.com
Feng Yi (School of Engineering, Zhejiang Normal University Xingzhi College, Jinhua, China + School of Information Engineering, Nanchang Hangkong University, Nanchang, China), 458018002@qq.com
Gao Shengrong (School of Information Engineering, Nanchang Hangkong University, Nanchang, China), 1322415547@qq.com
Shu Jian (School of Software, Nanchang Hangkong University, Nanchang, China), shujian@nchu.edu.cn
Aiming at the imbalance problem of wireless link samples, we propose the link quality estimation method which combines the K-means synthetic minority over-sampling technique (K-means SMOTE) and weighted random forest. The method adopts the mean, variance and asymmetry metrics of the physical layer parameters as the link quality parameters. The link quality is measured by link quality level which is determined by the packet receiving rate. K-means is used to cluster link quality samples. SMOTE is employed to synthesize samples for minority link quality samples, so as to make link quality samples of different link quality levels reach balance. Based on the weighted random forest, the link quality estimation model is constructed. In the link quality estimation model, the decision trees with worse classification performance are assigned smaller weight, and the decision trees with better classification performance are assigned bigger weight. The experimental results show that the proposed link quality estimation method has better performance with samples processed by K-means SMOTE. Furthermore, it has better estimation performance than the ones of Naive Bayesian, Logistic Regression and K-nearest Neighbour estimation methods.
Keywords: Wireless Sensor Network, Link Quality Estimation, Weighted Random Forest, Over sampling
Show references
Buşoniu, L., Babuška, R., Schutter, B. D.: Multi-agent Reinforcement Learning: An Overview. Innovations in Multi-Agent Systems and Applications, Vol. 38, No. 2, 156-172. (2010)
Babuška, R., buşoniu, L., and De Schutter, B.: Reinforcement learning for multi-agent systems. IEEE International Conference on Emerging Technologies and Factory Automation. IEEE, 1-7. (2006)
Liu, Z., Wang, F.: Scale-free topology for wireless sensor networks with energy efficient characteristics, Journal of Beijing University of Posts and Telecommunications, Vol. 38, No. 1, 87-91. (2015)
Cao, N., Liu, P., Li, G., Zhang, C.: Evaluation models for the nearest closer routing protocol in wireless sensor networks, IEEE Access, Vol. 6, No. 1, 77043-77054. (2018)
Gao, D., Zhang, S., Zhang, F.: RowBee: A routing protocol based on cross-technology communication for energy-harvesting wireless sensor networks, IEEE Access, Vol. 7, No. 1, 40663-40673. (2019)
Lowrance, C. J., Lauf, A. P.: Link quality estimation in ad hoc and mesh networks: A survey and future directions, Wireless Personal Communications, Vol. 96, No. 1, 475-508. (2017)
Bote-Lorenzo, M. L., Gómez-Sánchez, E., Mediavilla-Pastor, C.: Online machine learning algorithms to predict link quality in community wireless mesh networks, Computer Networks, Vol. 132, No. 1, 68-80. (2018)
Lu, J., Zhu, Y., Xu, Z.: A reliable wireless sensor network routing method for power transmission line monitoring, Power System Technology, Vol. 41, No. 2, 644-650. (2017).
Jayasri, T., Hemalatha, M.: Link quality estimation for adaptive data streaming in WSN, Wireless Personal Communications, Vol. 94, No. 3, 1543-1562. (2017)
Baccour, N., Koubâa, A., Youssef, H.: F-lqe: A fuzzy link quality estimator for wireless sensor networks, in Proc. 2010 European Conference on Wireless Sensor Networks, Coimbra, Portugal, 240-255. (2010)
Lai, X., Ji, X., Zhou, X.: Energy efficient link-delay aware routing in wireless sensor networks, IEEE Sensors Journal, Vol. 18, No. 2, 837-848. (2018)
Boano, C. A., Zúniga, M. A., Voigt, T.: The triangle metric: Fast link quality estimation for mobile wireless sensor networks, in Proc. 19th International Conference on Computer Communications and Networks, Zurich, Switzerland, 1-7.(2010)
Zhang, Y., Fu, S., Jiang, Y.: An LQI-based packet loss rate model for IEEE 802.15.4 links, in Proc. IEEE Annual International Symposium on Personal, Indoor, and Mobile Radio Communications(PIMRC), Bologna, Italy, 1-7.(2018)
Sun, W., Lu, W., Li, Q.: WNN-LQE: Wavelet-neural-network-based link quality estimation for smart grid WSNs, IEEE Access, Vol. 5, No. 1, 12788-12797. (2017)
Mi, X., Zhao, H., Zhu, J.: Research on EWMA based link quality evaluation algorithm for WSN, in Proc. 2011 Cross Strait Quad-Regional Radio Science and Wireless Technology Conference, Harbin, China, 757-759.( 2011)
Qin, F., Zhang, Q., Zhang, W.: Link quality estimation in industrial temporal fading channel with augmented Kalman filter, IEEE Transactions on Industrial Informatics, Vol. 15, No. 4, 1936-1946. (2019)
Rojas, C., Decotignie, J.: Leveraging MAC preambles for an efficient link estimation, in Proc. International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob), Limassol, Cyprus, 1-10.( 2018)
Sharma, A., Bansal, A., Rishiwal, V.: Selection of high quality path through MXAODV in mobile ad-hoc network, International Journal of Systems Control and Communications, Vol. 10, No. 1, 1-17. (2019)
Liu, W., Xia, Y., Luo, R.: Lightweight, fluctuation insensitive multi-parameter fusion link quality estimation for wireless sensor networks, IEEE ACCESS, Vol. 8, No. 1, 28496-28511. (2020)
Liu, T., Cerpa, A. E.: Data-driven link quality prediction using link features, ACM Trans on Sensor Networks, Vol. 10, No. 2, 1-35. (2014)
Shu, J., Liu, S., Liu, L.: Research on link quality estimation mechanism for wireless sensor networks based on support vector machine, Chinese Journal of Electronics, Vol. 26, No. 2, 377-384. (2017)
Pan, L., Li, J.: K-nearest neighbor based missing data estimation algorithm in wireless sensor networks, Wireless Sensor Network, Vol. 2, No. 2, 115-122. (2010)
Luo, X., Liu, L., Shu, J., AL-KALI, M.: Link quality estimation method for wireless sensor networks based on stacked autoencoder, IEEE Access, Vol. 7, No. 1, 21572-21583. (2019)
Baccour, N., Koubâa, A., Youssef, H.: Reliable link quality estimation in low-power wireless networks and its impact on tree-routing, Ad Hoc Networks, Vol. 27, No. 1, 1-25. (2015)
Bildea, A., Alphand, O., Rousseau, F., Duda, A.: Link quality estimation with Gilbert-Elliot model for wireless sensor networks, in Proc. IEEE 26th Annual Int. Symp. Personal, Indoor, and Mobile Radio Communications (PIMRC), Hong Kong, China, 2049-2054.(2015)
Zhu, M., Xia, J., Jin, X., Yan, M., Cai, G., Yan, J., Ning, G.: Class weights random forest algorithm for processing class imbalanced medical data, IEEE Access, Vol. 6, No. 1, 4641-4652. (2018)
Galar, M., Fernandez, A., Barrenechea, E.: A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches, IEEE Trans on Systems, Man, and Cybernetics, Part C (Applications and Reviews), Vol. 42, No. 4, 463-484. (2012)
Batista, G. E., Prati, R. C., Monard, M. C.: A study of the behavior of several methods for balancing machine learning training data , ACM SIGKDD explorations newsletter, Vol. 6, No. 1, 20-29. (2004)
Chawla, N. V., Bowyer, K. W., Hall, L. O.: SMOTE: Synthetic minority over-sampling technique, Journal of Artificial Intelligence Research, Vol. 16, No. 1, 321-357. (2002)
Douzas, G., Bacao, F., Last, F.: Improving imbalanced learning through a heuristic oversampling method based on K-means and SMOTE, Information Sciences, Vol. 465, No. 1, 1-20. (2018)
Liaw, A., Wiener, M.: Classification and regression by random forest, R News, Vol. 2, No. 3, 18-22. (2002)
Winham, S. J., Freimuth, R. R., Biernacka, J. M.: A weighted random forests approach to improve predictive performance, Statistical Analysis and Data Mining: The ASA Data Science Journal, Vol. 6, No. 6, 496-505. (2013)