We published a paper that used ISMLR package to predict future influent wastewater flowrate:
Jun-Jie Zhu, & Paul R. Anderson. (2019). Performance evaluation of the ISMLR package for predicting the next day's influent wastewater flowrate at Kirie WRP. Water Sci. Technol. wst2019309. doi: https://doi.org/10.2166/wst.2019.309
ISMLR package version includes data preprocessing tools and the ISMLR application.
Data preprocessing tools include:
• Outlier detection
• Periodogram analysis, and
• Time-series dataset generation
The ISMLR application can:
• Select a subset of important regressors
• Minimize the amount of missing data from a regression analysis
• Provide prediction of the response regressor, or
• Produce pretreated datasets for a subsequent prediction using a more advanced algorithm
Visit: https://junjiezhublog.wordpress.com/ismlr/ for more information and updates.
This work is licensed under a Creative Commons Attribution 4.0 International License.
ISMLR was first introduced by Zhu and Anderson (2016):
Zhu, J. J., & Anderson, P. R. (2016). Assessment of a soft sensor approach for determining influent conditions at the MWRDGC Calumet WRP. Journal of Environmental Engineering, 142(6), 04016023. doi: https://doi.org/10.1061/(ASCE)EE.1943-7870.0001097
ISMLR was also used in the following publications:
Zhu, J. J., Kang, L., & Anderson, P. R. (2018). Predicting influent biochemical oxygen demand: Balancing energy demand and risk management. Water research, 128, 304-313. doi: https://doi.org/10.1016/j.watres.2017.10.053