Research on Routing Algorithm of mobile wireless packet switching computer network based on deep learning

Author(s):  
Zhicong Guan
2017 ◽  
Vol 66 (11) ◽  
pp. 1946-1960 ◽  
Author(s):  
Bomin Mao ◽  
Zubair Md. Fadlullah ◽  
Fengxiao Tang ◽  
Nei Kato ◽  
Osamu Akashi ◽  
...  

The fashion industry has developed in many fields and its growth is making an enormous promote in article of clothing company and e-commerce entity. The difficult task for IT industry in this field is designing the predictive system of data mining to model this. E-commerce uses electronic communication as well as information technology in many transactions for creating, transforming or for redefining the relationships between individuals and organizations. It simply means buying of products, services and information and selling them through computer network. It is totally changing the traditional approach of business. The main change in business is noticeable growth and it has many significant effects on environment as well. This is the reason why it is so preferred in business nowadays. The important part of the proposed system is to rate the fashionable outfit individual and it is considers appearances as well as meta-data. Our approach has first implemented a system of encoding visual characteristics with the help of deep convolution network for complicated contents because it is not possible to list or to label every attribute of a image. Secondly, we proposed a multi-model deep learning framework for rich contexts of fashion outfit. We propose a system which will recommend with review comments and which product should purchase and the system will display a rating of the product.


In biometric acknowledgment, which is generally utilized in different fields. As of late, numerous profound learning strategies have been utilized in biometric acknowledgment, attributable to their points of interest. In this deep learning process we adjust the existing network structure and providing the modified routing algorithm technique which is depends on dynamic routing between two capsule layers. This layers helps to maintain and adopt a iris recognition. Various iris data sets are used for recognition. These datasets are trained and tested with the help of different pupil size of an iris. In order to show the recognition ability when the environment varies. The test of dataset achieves 96.2%. CASIA-V4 Lamp dataset gives the highest accuracy of 98.34%. It shows the apply of capsule network in iris recognition.


Sign in / Sign up

Export Citation Format

Share Document