No abstract

No abstract

The Electronic Medical Records of patients maintained needs to be ensured that privacy is preserved and must be accessible to authorized users such as doctors. Most of the health care systems use the traditional centralized database platforms for these data management; which is neither secure nor easy to maintain. These platforms can be replaced by distributed, efficient, and much more secure platforms which are backed by blockchain technology. In this work, a Decentralized application (dApp) is developed which allows users to upload and download medical data to and from the distributed file storage system. The application’s logic is written in solidity programming language in the smart contract. The application uses IPFS – Interplanetary File System, which is a distributed file storage system to store the medical records. Each file is broken down into pieces and each piece is given a hash which is stored on the blockchain. The user with right authentication has the privilege to access these hashes on the blockchain helping them in downloading the desired file. The application is tested through different nodes on the network which successfully resulted in securely storing and downloading the files from the distributed network. The results envision that the data stored in the IPFS is immutable, distributed across its network which makes it impossible for anyone to just access it. The dApp developed is tested with two performance metrics i.e. the number of transactions per unit time and the time taken to search records in the blockchain network and also the scalability issue pertaining to blockchain is also discussed.

No abstract

This chapter provides insight on pattern recognition by illustrating various approaches and frameworks which aid in the prognostic reasoning facilitated by feature selection and feature extraction. The chapter focuses on analyzing syntactical and statistical approaches of pattern recognition. Typically, a large set of features have an impact on the performance of the predictive model. Hence, there is a need to eliminate redundant and noisy pieces of data before developing any predictive model. The selection of features is independent of any machine learning algorithms. The content-rich information obtained after the elimination of noisy patterns such as stop words and missing values is then used for further prediction. The refinement and extraction of relevant features yields in performance enhancements of future prediction and analysis.