[UCS, Gamma-ray, sonic wave, pore pressure] that are not always available in real-time during the drilling operation, limiting the applicability of the approach for real-time optimization; (4) hybrid machine-le
Occupant behaviour has significant impacts on the performance of machine learning algorithms when predicting building energy consumption. Due to a variety of reasons (e.g., underperforming building energy management systems or restrictions due to privacy policies), the availability of occupational data has...
Sharma, A., Sajjad, H., Rahaman, M.H.et al.Effectiveness of hybrid ensemble machine learning models for landslide susceptibility analysis: Evidence from Shimla district of North-west Indian Himalayan region.J. Mt. Sci.21, 2368–2393 (2024). https://doi.org/10.1007/s11629-024-8651-7 DOI...
DL networks usually require a large amount of data to train a strong classifier, compared to traditional ML algorithms. This is because the number of parameters that need to be learned is much higher than most other learning algorithms. Second, DL requires significant hyper...
cause errors during modeling. The “StandardScaler” normalizes the numerical columns by subtracting the mean and scaling to unit variance. This standardization of features is important since it ensures that each feature contributes equally to the distance computations in machine learning algorithms. ...
The online sequential ELM or OS-ELM [27] can learn data one-by-one or chunk-by-chunk (a block of data) with fixed or varying chunk size, which makes it faster than other sequential algorithms. In voting based extreme learning machine [28], multiple independent ELM trainings are performed...
A resource utilization prediction model for cloud data centers using evolutionary algorithms and machine learning techniques. Appl. Sci. 12(4), 2160 (2022). Article CAS Google Scholar Mohammadzadeh, A., Masdari, M. & Gharehchopogh, F. S. Energy and cost-aware workflow scheduling in cloud ...
Does this method outperform the physics-informed machine learning algorithms? We have not carried out any comparative studies between these two groups of algorithms, as it is outside the scope of this research. But in general, physics-informed surrogates have typically more complex training implementa...
The use of strongly biased data generally leads to large distortions in a trained machine learning model. We face this problem when constructing a predictor for earthquake-generated ground-motion intensity with machine learning. The machine learning predictor constructed in this study has an underestimat...
The machine learning models have also started to be coupled with pre-treatment or heuristic algorithms for daily Rd prediction, such as wavelet transform (WT) and generic algorithm (GA), to optimize the training processes and further enhance the accuracy of standalone machine learning models. For...