A data-attribute-space-oriented double parallel (DASODP) structure for enhancing extreme learning machine: Applications to regression datasets

Data driven soft sensor development for complex chemical processes using extreme learning machine

“…The parameters consist of the biases of the hidden layer nodes and the weights that connecting between the nodes. The larger the number of parameters is, the more complex the model is (He et al, 2015a). In our study, the number of the parameters of the three models is calculated out to evaluate the complexity of the network models.…”

“…In the traditional ELM model, the relationship between the input attributes and the output attributes is not taken into consideration, and the input attributes with different influences put together in the input layer may weaken the regression accuracy (He et al, 2015a,b). A classification method was used to separate the original input space into several sub-spaces (He et al, 2015a). However, the influences of the input attributes on the output attributes were not taken into account.…”

A Survey of Distributed and Parallel Extreme Learning Machine for Big Data

“…In order to improve the performance of ELM in dealing with regression problems, the existing research proposes to apply the double-parallel structure to ELM. He et al [89] applied a data-attribute-space-oriented double parallel (DASODP) structure with data-oriented attribute space to ELM (DASODP-ELM). The doubleparallel structure enables DASODP-ELM's output layer to receive not only information from neurons in the hidden layer, but also direct information from neurons in the input layer.…”

Predicting mechanical properties of thermoplastic starch films with artificial intelligence techniques

“…Artificial Intelligence techniques are helping industries to improve their efficiency and performance in a great variety of applications: education Rani et al [8], space Tonutti et al [11], He et al [6], space exploration Guzman et al [5], manufacturing Wilson [12], Rao et al [9], etc. The development of a computer program, that employs artificial intelligence techniques to predict the values of the physical properties of the materials mentioned above without having to resort to the elaboration of the physical parts of biodegradable thermoplastic starch, will be a great utility to extend its industrial application: allowing to reduce time, resources and costs.…”