Ph.D. Degree Awarded
Student’s Name:
Dr. Abhaya Kumar Sahoo
Supervisor’s Name:
Dr. Chittaranjan Pradhan, School of Computer Engineering, Dr. Bhabani Shankar Prasad Mishra, School of Computer Engineering
Thesis Title:
Performance Evaluation of Recommender System using Collaborative Filtering Technique
Abstract:
Smart healthcare can be exemplified as utilizing propitious electronic technology safeguarded with blockchain for superior diagnosis of the disorders, improvised and cost-effective treatment of the patients, and enhanced quality of life. Since blockchain in smart healthcare architecture hosts a substantial amount of patient data, queueing models play a pivotal role to efficiently process the data. This paper highlights the concepts of blockchain, then delves into the smart healthcare architecture and then deals with the several queueing models that already exist. It proposes the model i.e. hQChain which is inculcating M1,b/Mb/1 queueing model into blockchain-based smart healthcare architecture.
Conference Papers
1. Parida, P., and Pradhan, C., (2021) Improved ECC-Based Image Encryption with 3D Arnold Cat Map, In: Springer International Conference on Innovative Computing and Communications (ICICC), New Delhi, India, pp. 771-783.
Abstract:
In this paper, a novel encryption scheme for digital images based on ECC and 3D Arnold cat map is proposed. The 3D Arnold cat map scrambles the position of pixels in the image and then transforms the values of pixels. The transformed pixel values are encrypted and decrypted using the Elliptic Curve Analogue ElGamal Encryption Scheme (ECAEES). The proposed model is implemented using Python. We get an average entropy value of 7.9992, NPCR of 99.6%, UACI of 33.3% and PSNR of 27.89. The correlation coefficient values between adjacent pixels of cipher images are minimized.
Book Chapters
1. Sinha N., Karjee P., Agrawal R., Banerjee A., Pradhan C. (2021), COVID-19 Recommendation System of Chest X-Ray Images using CNN Deep Learning Technique with Optimizers and Activation Functions in Understanding COVID-19: The Role of Computational Intelligence, Janmenjoy Nayak, Bighnaraj Naik, Ajith Abraham (Eds.), Springer, Cham, pp. 141-163.
Abstract:
The proposed CNN model takes input as chest X-ray images and predicts whether a person needs to go for COVID-19 testing or not. At present, the COVID-19 tests are being done clinically through blood tests or nose/throat swab tests which requires around 24 h to give results. The proposed recommendation system takes around 35 min to give the result of a sample and curbs down the chances of virus spread through contact while testing, unlike the presently used methods. The experimental results yielded an accuracy of 97.62% using the chest X-ray scans and requires less computational time.
2. Sahoo A.K., Pradhan C., Mishra B.K., Mishra B.S.P. (2021), An Extensive Study of Privacy Preserving Recommendations System using Collaborative Filtering in Deep Learning in Data Analytics, Debi Prasanna Acharjya, Anirban Mitra, Noor Zaman (Eds.), Springer, Cham, pp. 171-190.
Abstract:
The recommender system’s accuracy usually depends on the quality of the collected data, which cannot be collected from users without concerning their privacy requirements. Today’s recommender systems are obliged to collapse unless they provide a measure of privacy to users. However, privacy and accuracy are conflicting goals because preserving privacy requires a level of distortion in original data. Nowadays, providing privacy to sensitive information in a side recommender system is the main requirement with the best accuracy. This chapter summarizes all privacy-preserving methods for providing security and privacy to the user’s rating of a particular item.