International Journal of Advanced Networking and Applications

4816-4820

Authors: ZHANG Han-wen, HU Ying*, ZOU Yong-jia, WU Cheng-yu

Sign language as the main communication channel for deaf and hearing people, plays a very important role in daily life. With the rapid development of the field of deep learning, the field of sign language recognition has ushered in new opportunities. Aiming at the small number of sign language samples and low detection accuracy, an American sign language detection method based on Resnet-18 and data augmentation is proposed. First, the sign language picture is adjusted to 64×64 size using the filling method, and then the data is augmented by methods such as chromaticity change, rotation, and noise addition to increase the diversity of data samples and improve the robustness of the detection method. The experimental results show that the accuracy of the sign language recognition method based on Resnet-18 can reach 99%, which provides a new method for sign language recognition.

4827-4832

Authors: Naglaa Saeed Shehata*, Mona Nasr, Laila El Fangary, Laila Abd EL hamid

The world's third most serious and lethal cancer rankings are colon cancer. Like cancer, the most important stage of early diagnosis is. Deep learning has become a leading learning tool for object detection and its successes in advancing the analysis of medical images have attracted attention. Convolutionary neural networks (CNNs), which play an indispensable role in the detection and potential early diagnose of colon cancer, are the most popular method of deep learning algorithms for this purpose. In this article we hope to take a look at the progress of colonic cancer analysis by studying profound learning practices. This study provides an overview of popular profound study algorithms used in analysis of colon cancer. All studies in the fields of colon cancer, including detection, classification as well as segmentation and survival prediction, will then be collected. Finally, we will conclude the work by summarizing the latest deep learning practices in analysis of colon cancer, a critical examination of the challenges and proposals for future research.

4839-4844

Authors: Dr. S. R. SURESH

In earlier days, the customer retrieved library materialized structured information are difficult due to enormous database acted in particular location. This paper deals the privacy and security concern includes threats, attacks, data integrity, data leakage, data availability, loss of control, vulnerability and flaws during distribution of services, resources and information. This technique verifies customer verification and validation between cloud clients and cloud providers. Storing the library information system in digital manner is essential through cloud technologies. As an outcome, library consumers can access resources from outside of physical library using cloud methods. This proposed method enforces the use control and access log technique to reduce the data leakage, improve the efficiency and user privacy of the confidential information. It evaluates the several challenges and issues of cloud such as user authentication, data availability, data confidentiality in a cloud environment. This paper depicted the various investigation reports and reviews of various researchers on electronic digital information based library and its resources by cloud methods and storages. This system provides a scheme of a cloud storages functional construction for building knowledge based digital library. Client’s confidential data are stored in global data center storage and numerous local data centers through redundant array of independent disk method in this cloud environment that leads to recovery from the user control and data leakage. This new innovative flexible system delivers the combination of methods like multi-level security with data availability on dissimilar storages, encryption and decryption technique with customer verification and validation method. The electronic digital library resources and services create novel development in scheme of multiple storages with respect to information access and distribution of confidential data in cloud. The multiple cloud storage architecture for digital electronic library offers data handling, speedy transmission of information and linking of communication among library patrons and cloud providers. It will endorse the maturity level from official level members to higher administrate that meet user request and identify the defensible development of knowledge based digital library system. This capable digital library system maintains the cloud computing environment with better performance evaluation. This functional structure progressively established electronic digital library knowledge management by means of user participation. This digital library using multiple cloud storage implementations creates well organized data integration, reduced cost, accessible any-where at any time of services and resources, scalability, elasticity and portability. Furthermore, cloud security and privacy enquiries know the ability of the adaptable digital library system using cloud computing techniques and extent abundant effectiveness with protected cloud environment.

4855-4860

Authors: Ms. Manpreet Kaur, Dr. Sarpreet Singh

Cloud Computing is proving as an emerging research area in the arena of information technology (IT). The three main services offered by the cloud are IaaS, SaaS, and PaaS. Internet-based technology that emphasizes its use and follows a lead model. The most serious problem in computer computing balances the load across the network. This is how, the heavy load is evenly distributed over the network areas so that no single node is overcrowded. The main purpose of neutralizing the load is to make better use of resources that improve system efficiency and reduce resource utilization that reduces carbon emissions. The content of the paper emphasizes mainly the idea of several load balancing methods used in cloud computing. This paper contributes to the analysis of the problems of the existing loading algorithm and provides comparisons between these algorithms on the basis of various quality metrics such as reliability, performance, energy-saving feature, rating, and more.