On the Use of Local Search in the Evolution of Neural Networks for the Diagnosis of Breast Cancer

被引:3
作者
Gupta, Agam [1 ]
Bhalla, Shiva [1 ]
Dwivedi, Shishir [1 ]
Verma, Nitin [1 ]
Kala, Rahul [1 ]
机构
[1] Indian Inst Informat Technol, Dept Informat Technol, Allahabad 211012, Uttar Pradesh, India
关键词
medical expert systems; neural network; back-propagation algorithm; genetic algorithms; local search; breast cancer diagnosis; evolutionary algorithm;
D O I
10.3390/technologies3030162
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
With the advancement in the field of Artificial Intelligence, there have been considerable efforts to develop technologies for pattern recognition related to medical diagnosis. Artificial Neural Networks (ANNs), a significant piece of Artificial Intelligence forms the base for most of the marvels in the former field. However, ANNs face the problem of premature convergence at a local minimum and inability to set hyper-parameters (like the number of neurons, learning rate, etc.) while using Back Propagation Algorithm (BPA). In this paper, we have used the Genetic Algorithm (GA) for the evolution of the ANN, which overcomes the limitations of the BPA. Since GA alone cannot fit for a high-dimensional, complex and multi-modal optimization landscape of the ANN, BPA is used as a local search algorithm to aid the evolution. The contributions of GA and BPA in the resultant approach are adjudged to determine the magnitude of local search necessary for optimization, striking a clear balance between exploration and exploitation in the evolution. The algorithm was applied to deal with the problem of Breast Cancer diagnosis. Results showed that under optimal settings, hybrid algorithm performs better than BPA or GA alone.
引用
收藏
页码:162 / 181
页数:20
相关论文
共 22 条
[1]  
[Anonymous], 2014, P 2014 REC ADV ENG C, DOI DOI 10.1109/RAECS.2014.6799655
[2]  
Arram A, 2013, INT CONF INTELL SYST, P336, DOI 10.1109/ISDA.2013.6920760
[3]  
Banik Shipra, 2008, 2008 11th International Conference on Computer and Information Technology (ICCIT), P735, DOI 10.1109/ICCITECHN.2008.4802997
[4]  
Begg R., 2006, NEURAL NETWORKS HEAL
[5]  
Bennett K. P., 1992, OPTIMIZATION METHODS, V1, P23, DOI [DOI 10.1080/10556789208805504, DOI 10.1080/10556789208805504.25]
[6]  
BURKE HB, 1994, 1994 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOL 1-7, P2213, DOI 10.1109/ICNN.1994.374560
[7]  
Haykin S., 2009, NEURAL NETWORKS LEAR, V3rd, DOI DOI 10.1063/1.3141672
[8]  
Holland John H., 1992, ADAPTATION NATURAL A
[9]  
Kala Rahul, 2009, Proceedings of the 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC 2009), P947, DOI 10.1109/NABIC.2009.5393877
[10]   Breast Cancer Diagnosis Using Optimized Attribute Division in Modular Neural Networks [J].
Kala, Rahul ;
Shukla, Anupam ;
Tiwari, Ritu .
JOURNAL OF INFORMATION TECHNOLOGY RESEARCH, 2011, 4 (01) :34-47