Key points are not available for this paper at this time.
The most efficient use of storage space is anticipated to be made possible by the adoption of one or more data compression techniques, which are expected to increase transmission bandwidth. The majority of IoT-based devices may store data on the cloud, which emphasizes the importance of making the best use of already-available storage. Due to these and other factors, data reduction is a crucial topic for IoT vision research. The main idea of our proposed work is to develop an IoT-based Smart healthcare management framework to achieve lossless data compression with the help of ontology. In this proposed work, a framework is divided into three modules namely pre-processing, ontology, and compression module. The sampling is done with the help of a healthcare analytics dataset taken from the Kaggle repository. The results are evaluated using metrics affecting data compression. The results obtained showed that the average compression ratio and average compression factor of the proposed work are 0.69 and 1.40 which is much better than existing recent works and compression algorithms. Furthermore, the proposed framework achieves highest compression percentage (31%), lesser time to compress original data (5.12 sec), highest peak signal to noise ratio value (91.18) and the lowest root mean squared error value (0.7853) thereby validating the performance of the given IoT-based framework. It shows that the proposed approach is better than existing compression techniques and recent review studies.
A Fri, study studied this question.