Comparing ANNs to logistic regression for predicting trauma survival

Fuller, Joseph J.; Forsythe, J.; Kessel, James W; Price, Pamela D; Emmett, Mary

doi:10.1109/ssst.1998.660126

Cited by 1 publication

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the response variable is binary, logistic regression to search the relationship between an independent variable and a binary output variable (response variable) which can be categorical or continuous can be suitable. Logistic regression is also useful for analysing case-control studies [5][6][7] .…”

Section: Hybrid System Modelmentioning

confidence: 99%

“…There are many variations of the back propagation algorithm. The simplest implementation of back propagation learning updates the network weights and biases in the direction in which the performance function decreases most rapidly the negative of the gradient 6,13 .…”

Section: Artificial Neural Networkmentioning

confidence: 99%

“…Logistic regression and neural network models are widely used for classification problems. These models have been used in various research and applications [2][3][4][5][6][7][8][9] .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Determination of the Working States of a Hybrid (wind-PV) Energy Generation System using Feed Forward NNs, Probit, and Logit

2017

JECET

View full text Add to dashboard Cite

Abstract:In this paper, a small hybrid Wind-Photo voltaic (PV) energy generation system to meet dynamic loads is studied. According to climatic conditions, the electricity generations from both PV modules and wind turbine at each hour of a day are calculated. Load demands for each hour of a day are used and a dynamic load demand graph is built. By using the generations and the graph the case for each system is established. An Artificial Neural Network (ANN) is constructed to decide whether the system is in working condition or not. The network is trained and tested with the data for two months and one month, respectively. Also the data is modeled with logistic regression methods; Probit and Logit. The results from these methods are compared and it is established that ANN determines the operating states of the system more accurately than both Probit and Logit.

show abstract

Section: Hybrid System Modelmentioning

confidence: 99%

Section: Artificial Neural Networkmentioning

confidence: 99%