Skip to main content

Research Repository

Advanced Search

Outputs (15)

A method to resolve the overfitting problem in recurrent neural networks for prediction of complex system's behavior (2008)
Presentation / Conference
Mahdaviani, K., Mazyar, H., Majidi, S., & Saraee, M. (2008, June). A method to resolve the overfitting problem in recurrent neural networks for prediction of complex system's behavior. Presented at IEEE World Congress on Computational Intelligence / IEEE International Joint Conference on Neural Networks, Hong Kong, China

In this paper a new method to resolve the overfitting problem for predicting complex systems' behavior has been proposed. This problem occurs when a neural network loses its generalization. The method is based on the training of recurrent neural... Read More about A method to resolve the overfitting problem in recurrent neural networks for prediction of complex system's behavior.

A new color based method for skin detection using RGB vector space (2008)
Presentation / Conference
Aznaveh, M., Mirzaei, H., Roshan, E., & Saraee, M. (2008, May). A new color based method for skin detection using RGB vector space. Presented at 2008 IEEE Conference on Human System Interactions, Krakow, Poland

This paper describes a new method for skin detection based on RGB vector space. Skin color has proven to be a useful cue for pre-process of face detection, localization and tracking. Image content filtering, content aware video compression and image... Read More about A new color based method for skin detection using RGB vector space.

A new linear appearance-based method in face recognition (2008)
Book Chapter
Hajiarbabi, M., Askari, J., Sadri, S., & Saraee, M. (2008). A new linear appearance-based method in face recognition. In Advances in Communication Systems and Electrical Engineering (579-587). Springer. https://doi.org/10.1007/978-0-387-74938-9_39

Human identification recognition has attracted scientists for many years. During these years, and due to increases in terrorism, the need for such systems has increased much more. The most important biometric systems that have been used during these... Read More about A new linear appearance-based method in face recognition.

Genome-wide efficient attribute selection for purely epistatic models via Shannon entropy (2008)
Journal Article
Manzourolajdad, A., Saraee, M., Mirlohi, A., & Javan, A. (2008). Genome-wide efficient attribute selection for purely epistatic models via Shannon entropy. International Journal of Business Intelligence and Data Mining, 3(4), 390. https://doi.org/10.1504/IJBIDM.2008.022736

Epistasis plays an important role in the genetic architecture of common human diseases. Most complex diseases are believed to have multiple contributing loci that often have subtle patterns which make them fairly difficult to find in large data sets.... Read More about Genome-wide efficient attribute selection for purely epistatic models via Shannon entropy.