A feed-forward network for input that is both categorical and quantitative

Brouwer, Roelof K.

doi:10.1016/s0893-6080(02)00090-4

Cited by 30 publications

(11 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compressor 3 has a control type of on/off dual control, therefore, the measurement is similar to a binary categorical value. Brouwer (2002) investigated the forecasting ability of FFNN with categorical inputs and found that the result is not sound. This could be one of the reasons that the FFNN model did not yield an acceptable result in this case.…”

Section: Load Forecasting For Compressor 3 (On/off)mentioning

confidence: 99%

Air compressor load forecasting using artificial neural network

Asl

Razban

et al. 2021

Expert Systems with Applications

View full text Add to dashboard Cite

Section: Load Forecasting For Compressor 3 (On/off)mentioning

confidence: 99%

Air compressor load forecasting using artificial neural network

Asl

Razban

et al. 2021

Expert Systems with Applications

View full text Add to dashboard Cite

“…In actual slashing process, the range of operating parameters are not continuous because raw materials or product specifications is different. Therefore, we should establish add-on prediction sub-model according to different kinds of raw materials, and combine these sub-models to a complete add-on prediction model by network output selector [11].…”

Section: Size Add-on Intelligent Modelmentioning

confidence: 99%

A hybrid model for size add-on in slashing processes

Zhang

Liu

Wang

2011

2011 Chinese Control and Decision Conference (CCDC)

View full text Add to dashboard Cite

A hybrid model for size add-on is built in slashing process. In the hybrid model, mechanism model is master model, intelligent model is auxiliary model, and the output relationship is determined by integrated rule in output model. When either sensors break down or operation conditions are abnormal, auxiliary model will estimate output by the external input variables. This hybrid model uses adequately field data so that predictive performance of hybrid model is multi-sided guaranteed.

show abstract

“…Also, categorical inputs may produce discontinuous relationships between input and output parameters. Therefore, the hybrid networks used in this work were constructed with clearly defined categorical and continuous inputs, with additional inputs generated for every category of the categorical inputs [25]. The calculated molecular descriptors were entered as categorical (functional group count) or continuous input data (remaining molecular descriptors) for the D1 like and D2 like ANN models, with log 10 Ki for each compound used as the target output for the ANN models.…”

Section: Network Training and Designmentioning

confidence: 99%

Artificial Neural Network (ANN) Based Modelling for D1 Like and D2 Like Dopamine Receptor Affinity and Selectivity

Karolidis¹,

Agatonović-Kuštrin²,

Morton

2010

View full text Add to dashboard Cite

Dopamine and its receptors play a critical role in diseases such as Parkinson's disease and schizophrenia. A problem with developing specific drugs for such diseases is that there are five subtypes of dopamine receptors that can be categorized as either D1 like or D2 like. Since the binding sites are quite similar, it is difficult to design the subtype specific agonists and antagonists required for therapy with minimal side effects. Thus, the aim of this study was to identify the molecular characteristics important to the selective binding of dopamine D1 like and D2 like receptors using quantitative structure activity relationships (QSARs). Datasets of 29 and 69 molecules capable of binding to cloned human D1 and D2 receptors were used to build QSAR models. The dissociation constants (Ki) for these molecules were taken from the literature. The optimized 3D structure of each molecule was encoded with 62 theoretical molecular descriptors. The QSAR, using hybrid neural network modeling, was built using categorical and continuous molecular descriptors as inputs, with dissociation constants (Ki) as outputs. Categorically assigned molecular descriptors improved performance in both models. Secondary amines and other nitrogen-containing moieties were shown to be important for the D1 like receptor selectivity, whereas molecular size, volume and tertiary and quaternary carbons were found to be of significant importance for the D2 like receptor selectivity.

show abstract

A feed-forward network for input that is both categorical and quantitative

Cited by 30 publications

References 3 publications

Air compressor load forecasting using artificial neural network

Air compressor load forecasting using artificial neural network

A hybrid model for size add-on in slashing processes

Artificial Neural Network (ANN) Based Modelling for D1 Like and D2 Like Dopamine Receptor Affinity and Selectivity

Contact Info

Product

Resources

About