Artificial Neural Networks for Prediction of Response to Chemoradiation in HT29 Xenografts

Kakar, Manish; Seierstad, Therese; Røe, Kathrine; Olsen, Dag Rune

doi:10.1016/j.ijrobp.2009.05.036

Cited by 5 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the data, the proposed method is also been compared with other methods that had been proposed in relative research: (1) The time domain and frequency domain features directly been used as the input of the prediction model, and the result are been predicted by neural network algorithm. 28 (2) The principal signal features extracted by PCA are utilized by traditional BPNN model to predict the bearing degradation process. (3) The original features extracted by PCA as the input of the SVM prediction model (the regularity parameter c is set to 90.3, the kernel function parameter 2 is set to 20, the " is set to 0.001).…”

Section: Prediction Results and Discussionmentioning

confidence: 99%

Multi-steps degradation process prediction for bearing based on improved back propagation neural network

Lin

Tan

Chen

2012

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

Bearing degradation process prediction is extremely important in industry. This article proposed a new method to achieve multi-steps bearing degradation prediction based on an improved back propagation neural network model. Firstly, time domain and time–frequency domain features extraction methods are employed to extract the original features from the mass vibration signals. However, the extracted original features still with high dimensional and include superfluous information, the multi-features fusion technique principal component analysis is used to merge the original features and reduce the dimension, the typical sensitive features can be extracted. Then, based on the extracted features, the improved three-layer back propagation neural network model is constructed and trained for multi-steps bearing degradation process prediction. The phase space construction method is used to determine the embedding dimension of the back propagation neural network model. An accelerated bearing run-to-failure experiment was carried out, the results proved the effectiveness of the methodology.

show abstract

Section: Prediction Results and Discussionmentioning

confidence: 99%