Abstract
Since past decades, tremendous amount of data is being generated and transmitted because of Internet of Things revolution. In agriculture as well as many industrial services, close monitoring of surrounding helps in taking effective decisions at near real time. Focus is much upon forecasting weather in such environments. Many algorithms are being utilized for performing predictions. Linear regressions give satisfactory results. Also time-series models tend to give poor results for nonlinear nature of data. To overcome this drawbacks support vector machines as a regression is being used. This paper gives a brief insight into the way support vector machines can be used for prediction which gives much better prediction results for linear as well as nonlinear nature of data. With proper tuning of model and appropriate kernel selection, around 98% of accurate prediction has been achieved.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gusmeroli, S., Piccione, S., Rotondi, D.: IoT@ Work automation middleware system design and architecture. In: 2012 IEEE 17th Conference on Emerging Technologies & Factory Automation (ETFA). IEEE (2012). Zhang, C., et al.: A multimodal data mining framework for revealing common sources of spam images. J. Multimed. 4(5), 313–320 (2009)
Rani, R.U., Rao, T.K.R.K.: An enhanced support vector regression model for weather forecasting. IOSR J. Comput. Eng. (IOSR-JCE) 12, 21–24 (2013). Zhang, M.: Application of data mining technology in digital library. JCP 6(4), 761–768 (2011)
Paras, S.M.: A simple weather forecasting model using mathematical regression. Indian Res. J. Ext. Educ. 12(2), 161–168 (2016)
Xue, H., Yang, Q., Chen, S.: SVM: support vector machines. Chapman & Hall/CRC, London, UK (2009)
Radhika, Y., Shashi, M.: Atmospheric temperature prediction using support vector machines. Int. J. Comput. Theory Eng. 1(1), 55 (2009)
Kapoor, P., Bedi, S.S.: Weather forecasting using sliding window algorithm. ISRN Signal Process. 2013 (2013)
Suykens, J.A.K., et al.: Weighted least squares support vector machines: robustness and sparse approximation. Neurocomputing 48.1, 85–105 (2002)
Smola, A.J., Schölkopf, B.: A tutorial on support vector regression. Stat. Comput. 14(3), 199–222 (2004)
Meyer, D.: Support Vector Machines: The Interface to libsvm in Package e1071 (2004)
Karatzoglou, A., Meyer, D., Hornik, K.: Support Vector Machines in R (2005)
Jain, R.K., et al.: Forecasting energy consumption of multi-family residential buildings using support vector regression: investigating the impact of temporal and spatial monitoring granularity on performance accuracy. Appl. Energy 123,168–178 (2014)
Yang, H.-T., et al.: A weather-based hybrid method for 1-day ahead hourly forecasting of PV power output. IEEE Trans. Sustain. Energy 5(3), 917–926 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chavan, G., Momin, B. (2019). A Novel Approach for Forecasting the Linear and Nonlinear Weather Data Using Support Vector Regression. In: Sa, P., Bakshi, S., Hatzilygeroudis, I., Sahoo, M. (eds) Recent Findings in Intelligent Computing Techniques . Advances in Intelligent Systems and Computing, vol 707. Springer, Singapore. https://doi.org/10.1007/978-981-10-8639-7_43
Download citation
DOI: https://doi.org/10.1007/978-981-10-8639-7_43
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-8638-0
Online ISBN: 978-981-10-8639-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)