In the Covid-19 pandemic, information about the medical equipment such as personal protective equipment, ventilators, testing kits, oxygen cylinders, ICU beds, and patient diagnostic status is a black box for the patients. This article proposes a blockchain-assisted Covid-19 big data chain (CovidBChain) framework to handle the Covid-19 data, which is of colossal size (volume), coming from different sources (variety) and generated at every time instance (velocity). CovidBChain is proposed to protect electronic health records and Covid-19 equipment's information from illegal modification. CovidBChain provides transparency, access control, and integrity to Covid-19 data. The status of critical equipment like ventilator, Covid-19 beds, oxygen cylinder, and ICU status each such operation is integrated into the CovidBChain as a transaction. A prototype has been simulated using Ganache, Metamask, InterPlanetary File System, and Reactjs. The comparative assessment using proof-of-work (PoW) and proof-of-authority (PoA) deduces that the upload and retrieval time in PoA is less than PoW, while the transaction cost is more in PoW. The overhead of message exchange communication is reduced by a factor of 4.3× in PoA as compared to the PoW approach. CovidBChain has been tested on the Ethereum official test network Ropsten for PoW and Goerli for PoA.

No abstract

Object recognition is basically invariant to the dramatic changes caused in objects' appearance such as location, size, viewpoint, illumination, occlusion and more by the variability in viewing conditions. In this paper, we employ an efficient approach for object recognition using invariant features and machine learning technique. The invariant features namely color, shape and texture invariant features of the objects are extracted separately with the aid of suitable feature extraction techniques. In the proposed approach, we integrate the color, shape and texture invariant features of the objects at the feature level, so as to improve the recognition performance. The fused feature set serves as the pattern for the forthcoming processes involved in the proposed approach. We employed the pattern recognition algorithms, like Discriminative Canonical Correlation (DCC) and attain distinct or identical results concerned with false positives. Our proposed approach is evaluated on the ALOI collection, a large collection of object images consists of 1000 objects recorded under various imaging circumstances. The experiments clearly demonstrate that our proposed approach significantly outperforms the state-of-the-art methods for combining color, shape and texture features. The proposed method is shown to be effective under a wide variety of imaging conditions.

The blockchain‐enabled healthcare system assists in tackling the inherent issues of centralized healthcare systems, such as data stewardship, single point of failure, and data integrity. However, existing blockchain‐enabled healthcare systems suffer from high‐energy consumption, low transaction throughput, and poor scalability. This work proposes the healthcare framework ParallelChain to tackle the low scalability and high‐energy consumption issue. ParallelChain divides the network into clusters, enabling linear scalability of nodes. The parallel execution of transactions in each cluster improves the throughput. The leader selection process of ParallelChain does not require solving computer‐intensive puzzles, making it more energy efficient than proof‐of‐work. The performance of ParallelChain is validated using metrics such as data transfer, processing time, consensus delay, block congestion, and message exchange. It shows that the amount of data transmitted is 4.6 times more in Bitcoin than ParallelChain with varying nodes. The number of messages exchanged is reduced by 48%, and the processing time is reduced by 2.17 and 1.7 times for varying nodes and block sizes, respectively.

The Object recognition is the task of finding and labeling parts of a two-dimensional (2D) image of a scene that correspond to objects in the scene. In this paper, we have proposed an efficient approach using level set method for extracting object shape contour and convex hull as a shape invariant features to the Feed forward Neural Network classifier for object recognition. We extracted the shape contour by level set method. Then, we have obtained invariant shape feature, convex hull of the objects. This convex hull set serves as a pattern for the Neural Network. Initially Feed forward neural network trained on the odd data set and tested on even data set. Our approach is evaluated on the Amsterdam Library of Object Images collection, a large collection of object images containing 1000 objects recorded under various imaging circumstances. The experimental results clearly demonstrate that our approach significantly outperforms. The proposed method is shown to be effective under a wide variety of imaging conditions.