New Deep Kernel Learning based Models for Image Classification
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 7
Abstract
Deep learning system is used for solving many problems in different domains but it gives an over-fitting risk when richer representations are increased. In this paper, three different models with different deep multiple kernel learning architectures are proposed and evaluated for the breast cancer classification problem. Discrete Wavelet transform and edge histogram descriptor are used to extract the image features. For image classification purpose, support vector machine with the proposed deep multiple kernel models are used. Also, the span bound is employed for optimizing these models over the dual objective function. Furthermore, the comparison between the performance of the traditional support vector machine which uses only single kernel and the introduced models is worked out that show the efficiency of the experimental results of the proposed models.
Authors and Affiliations
Rabha O. Abd-elsalam, Yasser F. Hassan, Mohamed W. Saleh
Keywords
Related Articles
- EP ID EP260467
- DOI 10.14569/IJACSA.2017.080755
- Views 103
- Downloads 0
Research on Chinese University Students’ Media Images
At present, university students, as the "after 90" and a new generation of young intellectuals, are being paid generally attentions by mass media. Nevertheless, university students’ public images are on a decline as they...
New Method of Faults Diagnostic based on Neuro-Dynamic Sliding Mode for Flat Nonlinear Systems
This paper addresses the problem of simultaneous actuator, process and sensor Fault Detection and Isolation (FDI) for nonlinear system having flatness properties with the presence of disturbances and which are operating...
Artificial Intelligence in Bio-Medical Domain
In this era and in the future, artificially intelligent machines are replacing and playing a key role to enhance human capabilities in many areas. It is also making life style better by providing convenience to all inclu...
A Robust MAI Constrained Adaptive Algorithm for Decision Feedback Equalizer for MIMO Communication Systems
Decision feedback equalizer uses prior sensor’s decisions to mitigate damaging effects of intersymbol interference on the received symbols. Due to its inherent non linear nature, decision feedback equalizer outperforms t...
Efficient Load Balancing Algorithm for the Arrangement-Star Network
The Arrangement-Star is a well-known network in the literature and it is one of the promising interconnection networks in the area of super computing, it is expected to be one of the attractive alternatives in the future...