Intelligent and assisted medicine dispensing machine for elderly visual impaired people with deep neural network fingerprint authentication system

Abstract

Offering a medication to Elderly and Visually Impaired People (EVIP) in rural areas without staff assistance is a difficult task in the field of health care. The current pill dispenser has limitations when it comes to administering medication before and after food, doesn't take into account over- and under-dosing situations, and doesn't send notifications to the relevant medical entities when the weight of the pills falls below the threshold. Despite the availability of numerous techniques and methods for automating the delivery of pills, there is no assistive method for the timely and secure delivery of medication. The suggested architecture provides EVIP with five crucial capabilities that aren't present in any of the current pill dispensers in an integrated way. In this paper, we present a biometric sensor-based secure access method for medication kits. The right person is only allowed access to the kit based on the finger print scanner. Second, the suggested architecture provides a self-managed and patient-centric service through assisted and automatic medication delivery. The third feature of this paper is the design method for the efficient delivery of pills before and after meals. A method of alerting the medical entities whenever a medication is over or under dosed is a fourth feature of the system. As a fifth feature, the implementation also automatically notifies the pharmacist and doctor when the weight of the pill strips in the chamber falls below the threshold value. Through the use of an integrated Timely Assistance Messaging (TAM) algorithm, all five features are implemented in the suggested architecture. A finger print recognition system is included with VGG-16 deep neural network with image enhancement. The EVIP can use this proposed system in residences, medical facilities, and retirement communities.