Gopalakrishnan Prakash

Gopalakrishnan Prakash

Auto-generated profile, based on publicly available information

Gopalakrishnan Prakash

Vellore Institute of Technology

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
24 July 2023 in IEEE Access
Verified
Journal Article
Open access
BVB. Valarmathi
B. Valarmathi
NGN. Srinivasa Gupta
N. Srinivasa Gupta
GPG. Prakash
G. Prakash
RRR. Hemadri Reddy
R. Hemadri Reddy
SSS. Saravanan
S. Saravanan
SPShanmugasundaram P
Shanmugasundaram P
Deep learning and computer vision algorithms will be applied to find the breed of the dog from an image. The goal is to have the user submit an image of a dog, and the model will choose one of the 120 breeds stated in the dataset to determine the dog’s breed. The proposed work uses various deep learning algorithms like Xception, VGG19, NASNetMobile, EfficientNetV2M, ResNet152V2, Hybrid of Inception &Xception, and Hybrid of EfficientNetV2M, NASNetMobile, Inception & Exception to predict dog breeds. ResNet101, ResNet50, InceptionResNetV2, and Inception-v3 on the Stanford Dogs Standard Datasetswere used in the existing system. They used a transfer learning algorithm with data augmentation to increase their accuracy. They achieved a validation accuracy score of 71.63% for ResNet101, 63.78% for ResNet50, 40.72% for InceptionResNetV2, and 34.84% for InceptionV3. This paper compares the proposed algorithms with existing ones like ResNet101, ResNet50, InceptionResNetV2, and InceptionV3. In the existing system, ResNet101 gave the highest accuracy of 71.63%. The proposed algorithms give a validation accuracy score of 91.9% for Xception, 55% for VGG19, 83.47% for NASNetMobile, 89.05% for EfficientNetV2M, 87.38% for ResNet152V2, 92.4% for Hybrid of Inception-v3 &Xception, and 89.00% for Hybrid of EfficientNetV2M, NASNetMobile, Inception & Exception. Among these algorithms, the Hybrid of Inception-v3 &Xception gives the highest accuracy of 92.4%.

1 August 2019
Verified
Conference Paper
Closed access
AIA. Anasuya Threse Innocent
A. Anasuya Threse Innocent
GPG. Prakash
G. Prakash
Blockchain technology provides a distributed solution, but not privacy of data used. Data privacy is included with the help of secure multiparty computation protocols and which in turn increases the complexity of application. This paper provides an efficient solution for blockchain technology with privacy by including a novel optimization for secure computation protocols.

1 September 2019
Verified
Conference Paper
Closed access
VRVidhisha Reddy
Vidhisha Reddy
GPG. Prakash
G. Prakash
Today the IT environment concentrates on Cloud computing where the usage of cloud based applications poses various security threats. Many possible cloud applications fall victim to a tragedy of the generic approach such that a shared cloud service is becoming unstable and insecure based on the commercial demands by IT and other business organization. Companies should develop proper security guidelines for public and private cloud use and utilize an adequate cloud access model. Based on set of features in the three common cloud services, a set of security capabilities is identified which are needed to exercise those characteristic and the cryptographic dealing they entail. Random Number Generators can be used in cloud hosts especially for virtualized machines. Several purpose of Pseudo Random Number Generator (PRNG) exists in cloud which mainly can be used to authenticate users to the information stored on cloud, salts for the passwords or for statistical sampling. ANSI X9.31 is one standard pseudo random number generator used in many standard cryptographic algorithms like AES, RSA that are managed in securing data access in cloud applications. As ANSI X9.31 seed values are not secure they are directly used for generation. With brute force attack the seed values are exposed. On retrieval of seed values the key can be predicted which leads to insecurity of the information stored on the cloud. The proposed obfuscation technique protects from intruders. The proposed technique takes considerable minimum amount of time when compared with the existing method.


1 May 2018 in Journal of Computational and Theoretical Nanoscience
Verified
Journal Article
Closed access
PGPrakash Gopalakrishnan
Prakash Gopalakrishnan
BMB. Uma Maheswari
B. Uma Maheswari
Smartphone is a leading mobility platform of the present computing era. Nowadays, transmitting precious information securely between mobile phones is considerably a big challenging task. The mobile devices must get paired in such a manner that effective data exchange should take less time and energy consuming, thus overcoming the fraudulent attacks in the communication channel. The most well known technique of building communication protocols for setting up a secure transfer between such mobile devices is the Cryptographic protocols. To confront security by overcoming the dominance of the invader effectively, Cryptographic techniques are now embedded in wireless environment. Keyless Cryptosystem is one such method which is elaborated as Keyless Key Agreement Cryptography method. This review paper throws a lime light on the overview of Keyless Cryptosystem. Various protocols using this technique are compared and highlighted here. This paper further explains the cryptosystem used in primitive pairing of mobile devices in a secure manner.

11 April 2019 in Concurrency and Computation: Practice and Experience
Verified
Journal Article
Closed access
PDF file
AIA. Anasuya Threse Innocent
A. Anasuya Threse Innocent
SKSangeeta K
Sangeeta K
GPG. Prakash
G. Prakash