Subham Kumar Gupta

Subham Kumar Gupta

Auto-generated profile, based on publicly available information

Subham Kumar Gupta

The University of Alabama System

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 March 2022 in Computers and Electrical Engineering
Verified
Journal Article
Closed access
SGSubham Kumar Gupta
Subham Kumar Gupta
MTMeenakshi Tripathi
Meenakshi Tripathi
JGJyoti Grover
Jyoti Grover

1 October 2014
Verified
Conference Paper
Closed access
SGSubham Kumar Gupta
Subham Kumar Gupta
SRSeema Rawat
Seema Rawat
PKPraveen Kumar
Praveen Kumar
Cloud computing is considered as the future of IT organizations. In weigh against to conventional solutions where all type of computing services are controlled through any type of personnel controls, it transfers all computing resources to the centralized large data centers, so users can enjoy services in a large scale on demand. Chiefly small and medium-size organizations can manage their projects by using cloud-based services and also able to achieve productivity enhancement with limited budgets. But, apart from all of these benefits, it may not be fully trustworthy. Cloud Computing do not keep data on the user's system, so there is a need of data security. The user pays progressively attention about data security due to this off-side storage of data on cloud computing. In order to retain confidentiality of data against un-trusted cloud service providers, There are so many approaches. All modern cloud service providers solve this problem by encryption and decryption techniques. They all have their merits and demerits. In present thesis, the basic dilemma of cloud computing security is inspected. We have also proposed a survey of various models for cloud security. To ensure the data security in the cloud, we suggest an efficient, accessible and adaptable cryptography based scheme. In-depth security and enactment inspection proved the proposed scheme as greatly efficient and robust against spiteful data alteration outbreak. The proposed scheme achieves scalability as well as flexibility due to its hierarchical structure.

3 September 2021
Verified
Conference Paper
Closed access
SGSubham Kumar Gupta
Subham Kumar Gupta
MTMeenakshi Tripathi
Meenakshi Tripathi
JGJyoti Grover
Jyoti Grover
With the fast growth of network technologies, Experts in many disciplines have shown great interest in network security. Many new assaults occur and it's a challenge for network security mechanisms to detect these sophisticated incursions. Intruders get intelligent each day, consistent with the progress of safety devices. The IDS is a weapon which can prevent the network from several types of interference. IDS evaluate the status of hardware and software operations on a network for threatening players in defense of data confidentiality, integrity and availability. The usage of machine learning algorithms simplified this job for IDS. In this work, the merits and demerits of the current publications from ML-based IDS offered solutions are discussed. This study also points to several research gaps that may be utilized in order to improve and create efficientIDSs.

13 March 2021
Verified
Book Chapter
Closed access
PDF file
SGSubham Gupta
Subham Gupta
KRKoduganti Venkata Rao
Koduganti Venkata Rao
NDNaga Malleswari Dubba
Naga Malleswari Dubba
KSKodukula Subrahmanyam
Kodukula Subrahmanyam

3 January 2022
Verified
Conference Paper
Closed access
SGSubham Gupta
Subham Gupta
APAchyut Paudel
Achyut Paudel
MTMishal Thapa
Mishal Thapa
SMSameer B. Mulani
Sameer B. Mulani
RWRobert Walters
Robert Walters
View Video Presentation: https://doi.org/10.2514/6.2022-0805.vid Complex engineering systems are difficult to model using artificial neural networks (ANN) when the number of samples is limited due to the associated high computational cost. In addition, the distribution of samples impacts the ability of the ANN to capture the true response behavior. Therefore, an adaptive sampling-based ANN is presented to approximate the time-consuming responses. The adaptive D-optimal design, which minimizes the determinant of the inverse of information matrix, is used here as a sampling strategy. The information matrix is formulated by considering the samples and activation values of the neurons in the hidden layers. In addition, a sampling approach based on the max-min technique is used in conjunction with the optimality sampling criterion to avoid repetition of the sampling points and enhance the space-filling property. The proposed approach has been implemented to two non-linear analytical functions and an engineering problem: i) Modified Ishigami function(three-dimensional), ii)Modified Sobol function(eight-dimensional), and iii) Fiber-Metal Laminate(FML) problem(five-dimensional). The results thus obtained were also compared with the regular one-shot sampling and sequential sampling strategy. The proposed approach required fewer training samples and has better convergence than the sequential sampling approach. Finally, to show the efficiency and accuracy of the presented approach in surrogate-based optimization, the optimum results were compared to the true optimum of the function. Hence, the proposed method will aid in obtaining high-precision surrogate models with less computational effort.