S Dinesh Krishnan
@bvrit.ac.in
Assistant Professor and Computer Science and Engineering
B V Raju Institute of Technology, Narsapur
RESEARCH, TEACHING, or OTHER INTERESTS
Engineering
Scopus Publications
Scholar Citations
Scholar h-index
Scopus Publications
R. Pitchai, Pasham Tejaswini yadav, Pasupula Harshavardhan, Parlapati Sudheer kumar, S. Dinesh Krishnan, and G. Arun Prasath
IEEE
S Dinesh Krishnan, Arun Prasath G, Rahul Gatla, Bindhusri Kommula, Vishnu Vardhan Kalali, and Bharath Kaparthi
IEEE
S. Dinesh Krishnan, G. Prathyusha, and V. Sathya Priya
IEEE
Blockchain technology is revolutionizing industries all over the world. Due to recent developments in machine learning, new technologies like cloud computing and safe data exchange have evolved. The collecting and processing of training data on centralized systems is required for conventional machine learning methods. New decentralized machine learning algorithms and cloud computing have made ML on-device information learning possible. IoT devices may use cloud computing services to outsource training duties, enabling AI at the network edge. Nevertheless, these scattered edges intelligence systems introduce new problems, such as concerns over user privacy and information security. Blockchain has been suggested as a workable solution to these problems. Due to its decentralized, accessible, and secure structure, blockchain has developed into a breakthrough invention for the future of numerous sectors' purposes. Additionally, this system has reliable automated scripting execution and immutable information recorders. Recently, as quantum technologies have become more practical, blockchain has begun to face potential threats from quantum computing. In this work, we summaries the literature in the research domains of blockchain-based cloud computing, machine learning, and safe data sharing in order to offer a synopsis of the present state-of-the-art in these cutting-edge developments. We also provide a basic introduction to post-quantum blockchain.
S. Dinesh Krishnan, Danilo Pelusi, A. Daniel, V. Suresh, and Balamurugan Balusamy
American Institute of Mathematical Sciences (AIMS)
<abstract> <p>Normal lung cells incur genetic damage over time, which causes unchecked cell growth and ultimately leads to lung cancer. Nearly 85% of lung cancer cases are caused by smoking, but there exists factual evidence that beta-carotene supplements and arsenic in water may raise the risk of developing the illness. Asbestos, polycyclic aromatic hydrocarbons, arsenic, radon gas, nickel, chromium and hereditary factors represent various lung cancer-causing agents. Therefore, deep learning approaches are employed to quicken the crucial procedure of diagnosing lung cancer. The effectiveness of these methods has increased when used to examine cancer histopathology slides. Initially, the data is gathered from the standard benchmark dataset. Further, the pre-processing of the collected images is accomplished using the Gabor filter method. The segmentation of these pre-processed images is done through the modified expectation maximization (MEM) algorithm method. Next, using the histogram of oriented gradient (HOG) scheme, the features are extracted from these segmented images. Finally, the classification of lung cancer is performed by the improved graph neural network (IGNN), where the parameter optimization of graph neural network (GNN) is done by the green anaconda optimization (GAO) algorithm in order to derive the accuracy maximization as the major objective function. This IGNN classifies lung cancer into normal, adeno carcinoma and squamous cell carcinoma as the final output. On comparison with existing methods with respect to distinct performance measures, the simulation findings reveal the betterment of the introduced method.</p> </abstract>
C. N. Ravi, S Dinesh Krishnan, Manikannan Kaliyaperumal, Sumita Kumar, A. V. S. Ram Prasad, and S. Suma Christal Mary
IEEE
The shortcomings of conventional healthcare systems are becoming more apparent as the Internet of Things (IoT) becomes ever more pervasive in people's daily lives. The standard procedure for dealing with confidential data frequently results in unwanted public disclosure. Blockchain's agreements make it possible to automate the safe transfer of patient data based on their individual authorization settings. To create a completely untraceable trading platform, blockchain technology is frequently implemented. To protect user data in the Internet of Things (IoT), a privacy-protecting protocol is developed using the blockchain. It is important to consider that the rogue cloud server might potentially develop a database of user behaviour profiles, which could be a serious breach of privacy. Confidentiality makes it more difficult to resolve disagreements about private data exchange transactions. When users of metadata are falsely accused, their rights are difficult to defend. Also, smart contracts are used to enforce security protocols and data privacy for multisharing adaptable access control. There is no reason to doubt the safety of the proposed work. The proposed work is efficient and applicable, as demonstrated by the efficiency evaluation and experimental findings.
Ankit Kumar Navalakha, S Dinesh Krishnan, Sunita Pachar, Pratap Patil, Ajay Singh Yadav, and Sarvesh Kumar
IEEE
In the current research scenarios cloud computing is a vital role in which services are provided based on proper security on both sides. The CSPs and the end users get attacked by the most of the attackers. So, there is need to make the services more secure. In any case, these reasonable strategies perhaps manage the situation when the district-based realities have been misused. In that capacity, experts are propelling undertakings to tune down a reaction for impervious area information. The cloud services which are provided by the different cloud service providers are providing the authenticated services to the end users. The on-the-spot sales systems are working for the security on the cloud service providers. The analysts in which the quality speed of the purchaser can be utilized in uncovering the area of the client.