Machine Learning and Secure Image Transmission for Disease Forecasting
Year: 2024
Type: article
Abstract: In today’s era of information technology, the rapid expansion of the Internet, especially in the realm of electronic healthcare, has become both feasible and widespread. Internet-enabled electronic healthcare systems allow patients to consult with specialist doctors remotely for diagnoses. Medical images are frequently stored, processed, and transmitted online, and during this process, sensitive data may be involved, requiring strict privacy measures. Given the importance of protecting patient information, encrypting this data is crucial to ensure that only authorized individuals can access it. Encrypting medical images presents unique challenges, particularly because of the need for fast and accurate data extraction. Traditional encryption methods may not always be suitable for securing large medical images effectively. Therefore, it's essential to safeguard the algorithms used for processing these images from potential attacks. One commonly used encryption tool is a random number generator, which produces sequences of numbers that are not predictable. The more unpredictable the number generation, the stronger the encryption, which makes it more effective. Chaos systems are often employed to generate pseudo-random numbers, providing a robust encryption key.
Authors: Gaurav Sharma, Mandeep Chaudhary, Hariom Kumar, Dr.Ajay Sahu
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4405716787