A Novel Approach of Cloud Based Scheduling Using Deep-Learning Approach in E-Commerce Domain

A Novel Approach of Cloud Based Scheduling Using Deep-Learning Approach in E-Commerce Domain

Abhilasha Rangra (Jaypee University of Information Technology, Waknaghat, India), Vivek Kumar Sehgal (Jaypee University of Information Technology, Waknaghat, India) and Shailendra Shukla (Jaypee University of Information Technology, Waknaghat, India)
Copyright: © 2019 |Pages: 17
DOI: 10.4018/IJISMD.2019070104
OnDemand PDF Download:
No Current Special Offers


Cloud computing represents a new era of using high quality and a lesser quantity of resources in a number of premises. In cloud computing, especially infrastructure base resources (IAAS), cost denotes an important factor from the service provider. So, cost reduction is the major challenge but at the same time, the cost reduction increases the time which affects the quality of the service provider. This challenge in depth is related to the balance between time and cost resulting in a complex decision-based problem. This analysis helps in motivating the use of learning approaches. In this article, the proposed multi-tasking convolution neural network (M-CNN) is used which provides learning of task-based deadline and cost. Further, provides a decision for the process of task scheduling. The experimental analysis uses two types of dataset. One is the tweets and the other is Genome workflow and the comparison of the method proposed has been done with the use of distinct approaches such as PSO and PSO-GA. Simulated results show significant improvement in the use of both the data sets.
Article Preview


The traditional use of business applications always presents a challenging task to deal with its complicated structure and expensive technology. There is a big need of experts to handle such daunting structures or the task scheduled to maintain the system’s installation, configuration, testing, running, securing, and updating procedures. With the help of cloud computing, the problems related to data storage gets easily resolved as the owner of the data just have to pay for what is required on the basis of demand in regard of the software and hardware technology used and it becomes the major responsibility of the experienced vendor to provide the system’s scaling and automatic upgradation facility. In the technological field, the cloud computing is made up of two of its important terms: cloud and computing (Weiwei, Liang & Buyya, 2014). In recent years, Cloud based trading achieves a great success and motivation by using electronic commerce. The cloud provides many services like online shopping, Business-to-Business and electronic data change. The different types of services in cloud provide a lot of opportunities in the field of e-commerce. Nevertheless, cutting-edge e-commerce is facing threats due to counterfeit items. For example, Alibaba Group has a chief counterfeit trouble that fakes still flourish on its virtual shopping center platform (Tsai, Wei, & Rodrigues, 2014). The similar situations also occur at other e-commerce platforms, which includes e-Bay, Amazon, Taobao, Tmall, and AliExpress. It is a venture problem distinguishing the genuine from the fakes, for the reason that maximum digital buying shops, together with Alibaba, do not own personal the products offered on its systems. Current famous answers to the counterfeit hassle is the use of coverage-based tactics, inclusive of signing contract suffering certifications for licensed dealers, and random research mechanisms (Gopinath, Geethu, & Vasudevan, 2015), (Gandhi, Rohan, Harry Liu, Charlie Hu, Lu, Padhye, Yuan, & Zhang, 2015). However, those techniques need a large quantity of exertions workloads and the reaction velocity is a way behind the predicted stage because of the complicated criminal methods and the lengthy execution time (Singh, Aarti, Juneja, & Malhotra, 2015). Limited controls of the products have ended in a severe impediment to the enterprise boom. Neither cutting off nor investigating all suspicious merchandises is a feasible alternative for contemporary e-trade service providers. Addressing this problem, this paper proposes a novel method with building up a deterministic model for suspicious counterfeits predictions.

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 13: 4 Issues (2022): Forthcoming, Available for Pre-Order
Volume 12: 4 Issues (2021): 2 Released, 2 Forthcoming
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing