Clinical Prediction on ML based Internet of Things for E-Health Care System
DOI:
https://doi.org/10.59461/ijdiic.v2i3.76Keywords:
IoT, Healthcare system , Classification, ANFIS, KNNAbstract
Machine learning (ML) is a powerful method for uncovering hidden patterns in data from the Internet of Things (IoT). These hybrid solutions intelligently improve decision-making in a variety of fields, including education, security, business, and healthcare. IoT uses machine learning to uncover hidden patterns in bulk data, allowing for better forecasting and referral systems. IoT and machine learning have been embraced in healthcare so that automated computers may generate medical records, anticipate diagnoses, and, most critically, monitor patients in real time. On different databases, different ML algorithms work differently. The overall outcomes may be influenced by the variance in anticipated results. In the clinical decision-making process, there is a lot of variation in prognostic results. As a result, it's critical to comprehend the various machine learning methods utilised to handle IoT data in the healthcare industry. Machine learning of adaptive neuro fuzzy inference system (ANFIS) algorithms is being used to monitor human health in this suggested effort. The UCI database is used for initial training and validation of machine learning systems. Using the IoT system, the test phase collects the person's heart rate, blood pressure, and temperature. The test stage assesses if the sensor data obtained by the IoT framework can predict any irregularities in the health state. To evaluate the accuracy of the forecast %, statistical analysis is performed on cloud data acquired from the IoT. Other routines are derived from K-neighbour results.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Shivi Chaturvedi
![Creative Commons License](http://i.creativecommons.org/l/by-sa/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.