Application of artificial intelligence and image processing in a mobile system for managing a set of critical resources (using the example of a personal first aid kit)

This study touches upon a mobile application for accounting of medicines in a universal first aid kit was developed to simplify the management of medicine stocks, monitor expiration dates, and remind users to take their medication. The main goal of the research is to create an intelligent system tha...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Datum:2025
Hauptverfasser: Федорченко, Є. М., Олійник, А. О., Паничук, К. С., Зайко, Т. А., Степаненко, О. О., Федорченко, Ю. В., Федорончак, Т. В.
Format: Artikel
Sprache:Ukrainisch
Veröffentlicht: Інститут проблем реєстрації інформації НАН України 2025
Schlagworte:
Online Zugang:http://drsp.ipri.kiev.ua/article/view/345675
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Назва журналу:Data Recording, Storage & Processing

Institution

Data Recording, Storage & Processing
Beschreibung
Zusammenfassung:This study touches upon a mobile application for accounting of medicines in a universal first aid kit was developed to simplify the management of medicine stocks, monitor expiration dates, and remind users to take their medication. The main goal of the research is to create an intelligent system that provides automatic recognition of medicines by the image of the packaging and storage of data about medicines and their intake. To implement the recognition function, a modified convolutional neural network MediPackNet was developed, which achieved 92 % accuracy and successfully classified all five test ima-ges of medicines. The results have demonstrated the effectiveness of the model at the level of six well-known architectures — InceptionV3, Xception, ResNet50V2, MobileNetV2, NASNetMobile, and DenseNet169. The MediPackNet network is integrated into the server part of the program for automatic recognition of medicines packaging by image, which allows to quickly add medicines to the user database. The mobile application and server part were created using .NET MAUI and Python, which ensures cross-platform compatibility and stable performance. The program implements AES and RSA encryption methods and their hybrid combination, which has demonstrated the highest level of security in the transmission of visual medical data. The proposed software enables effective management of medication stocks, promotes the rational use of medical resources, and improves compliance with medical recommendations thanks to the treatment tracking function. In addition, the use of the program has an impact on the environment — it helps to reduce the amount of hazardous waste generated by improper storage or disposal of expired medicines. Tabl.: 4. Fig.: 33. Refs: 25 titles.