Improving accuracy of medical data handling and processing using DCAF for IoT-based healthcare scenarios

• Published in: Biomedical signal processing and control Vol. 86; p. 105294
• Main Authors: Pethuraj, Mohamed Shakeel, Burhanuddin, M.A., Brindha Devi, V.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.09.2023
• Subjects: Data classification; Decision-making; IoT; Medical data; Precision processing; Decision-making; Medical data; Data classification; Precision processing; IoT
• ISSN: 1746-8094; 1746-8108
• DOI: 10.1016/j.bspc.2023.105294

•The proposed framework incorporates the IoT paradigm for transmission and classifying redundancies.•Data handling process is classified under transmission by regulating transmission flow regardless of the density and time.•Both processes are assimilated for handling unpredictable sensitive medical data transmission using IoT devices. The Internet of Things (IoT), uses communication technologies and intelligent computing to improve data analysis and computation accuracy, which is essential to the healthcare industry. The sensitivity and requirement for precision in managing and processing medical data make it a difficult task for diagnosing patients. To handle medical data in a healthcare scenario based on the IoT, a Data Classification and Analysis Framework (DCAF) is proposed in this research. The proposed framework seeks to improve the precision and dependability of handling and processing medical data, which are essential components of biomedical signal processing. By reducing errors and accelerating the processing of medical data, the framework can help in improving the accuracy of medical diagnosis and therapy, which is a key objective of biomedical signal processing and control. The goal of this framework is to increase the reliability of message delivery by concentrating on data classification and analysis. The earlier procedure is in charge of decreasing the volume of medical data transfers and ensuring the accuracy and delivery of consent data. The framework's latter process is in charge of allotting suitable processing time slots to increase delivery speed and lower data handling faults. A linear decision-making process based on accessibility, sequence order, and accuracy constraints and conditions supports the framework's joint process. Utilizing measures such as an accuracy ratio 0f 93.09 %, message delivery rate of 0.949 %, error with a range of 0.052 %, classification of 73.81 ms, and analysis time over fluctuating flow instances and analysis slots, the suggested framework's performance is validated.