The aim of my work is to provide secure data sharing in a healthcare environment. I have tried a combination of Cipher-text Policy Attribute Based Encryption and the Blockchain technology to enhance security. I developed a private set of medical files like a pdf, jpg files of health records which I borrowed from a hospital. I tried uploading those pdf, jpg files; then encrypted them. My Panel Members recommended me to employ a benchmark dataset like MIMIC to test my results. Such online repositories contain only CSV files, but I am dealing with PDF and JPG files. Which benchmark dataset should I employ to test my algorithm?
Thank you
You can find a GitHub repo with ~1,000 pdfs at this link https://github.com/tpn/pdfs
Dear A Divya Preetha,
You may want to look at the following links:
https://www.quora.com/How-do-you-find-the-best-datasets-to-use-for-machine-learning-algorithms
https://www.researchgate.net/post/How_can_i_get_a_dataset_of_patient_health_records
https://security.stackexchange.com/questions/1606 11/which-algorithm-works-well-for-encryption-of-large-datasets
- Badges
- Science topic
- Similar topics
- Filing