Neural perceptron & strict lossless secret sharing oriented cryptographic science: fostering patients' security in the "new normal" COVID-19 E-Health

TinyML-Based Lightweight AI Healthcare Mobile Chatbot Deployment

Introduction

In healthcare applications, AI-driven innovations are set to revolutionise patient interactions and care, with the aim of improving patient satisfaction. Recent advancements in Artificial Intelligence have significantly affected nursing, assistive management, medical diagnoses, and other critical medical procedures.

Purpose

Many artificial intelligence (AI) solutions operate online, posing potential risks to patient data security. To address these security concerns and ensure swift operation, this study has developed a chatbot tailored for hospital environments, running on a local server, and utilising TinyML for processing patient data.

Patients and Methods

Edge computing technology enables secure on-site data processing. The implementation includes patient identification using a Histogram of Gradient (HOG)-based classification, followed by basic patient care tasks, such as temperature measurement and demographic recording.

Results

The classification accuracy of patient detection was 95.8%. An autonomous temperature-sensing unit equipped with a medical-grade infrared temperature scanner detected and recorded patient temperature. Following the temperature assessment, the tinyML-powered chatbot engaged patients in a series of questions customised by doctors to train the model for diagnostic scenarios. Patients' responses, recorded as "yes" or "no", are stored and printed in their case sheet. The accuracy of the TinyML model is 95.3% and the on-device processing time is 217 ms. The implemented TinyML model uses only 8.8Kb RAM and 50.3Kb Flash memory, with a latency of only 4 ms.

Conclusion

Each patient was assigned a unique ID, and their data were securely stored for further consultation and diagnosis via hospital management. This research demonstrates faster patient data recording and increased security compared to existing AI-based healthcare solutions, as all processes occur within the local host.

Concurring of Neural Machines for Robust Session Key Generation and Validation in Telecare Health System During COVID-19 Pandemic

In this technique, it has been proposed to agree the session keys that have been generated through dual artificial neural networks based on the Telecare Health COVID-19 domain. Electronic health enables secure and protected communication between the patients and physicians, especially during this COVID-19 pandemic. Telecare was the main component which served the remote and non-invasive patients in the crisis period of COVID-19. Neural cryptographic engineering support in terms of data security and privacy is the main theme for Tree Parity Machine (TPM) synchronization in this paper. The session key has been generated on different key lengths and key validation done on the proposed set of robust session keys. A neural TPM network receives a vector designed through same random seed and producing a single output bit. Duo neural TPM networks' intermediate keys would be partially shared between the patient and doctor for the purpose neural synchronization. Higher magnitude of co-existence has been observed at the duo neural networks at the Telecare Health Systems in COVID-19. This proposed technique has been highly protective against several data attacks in the public networks. Partial transmission of the session key disables the intruders to guess the exact pattern, and highly randomized through different tests. The average p-values of different session key lengths of 40 bits, 60 bits, 160 bits, and 256 bits were observed to be 221.9, 259.3, 242, and 262.8 (taken under multiplicative of 1000) respectively.