Machine learning for biomedical signal processing

Patel, Vandana; Shah, Ankit

doi:10.1016/b978-0-12-821229-5.00002-1

Cited by 5 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning algorithms can process quickly whatever the complexity and the variety of the data. In literature, the latest studies are focused on the efficiency measurements of machine learning applications for prediction diseases such as breast cancer, heart disease, liver disease, diabetes disease and kidney disease [3].…”

Section: Introductionmentioning

confidence: 99%

SPLIGN: Smart-belt Posture Monitoring System Based on AI-algorithms for Sitting Persons

Tlili,

Haddad,

Bouallegue

2024

IJAEMR

View full text Add to dashboard Cite

The back pain is the main common health problems on this decade because of the sitting for a long time tilted on the computer for working, studying or playing. The back problems are widely spread for different ages from young to old people. Last medical research demonstrates that sitting with the posture align can prevent and remedy many spine problems. In this paper, we propose ’SPLIGN’ which a posture monitoring system designed to help maintaining the good posture during sitting. The SPLIGN is a smart belt equipped with inertial sensors. A mobile and web applications are developed for monitoring and remind the user to correct posture. The proposed system is based on a detailed study of the machine learning algorithms in order to choose the best accurate algorithm for posture prediction. The main studied algorithms are Convolutional neural network (CNN), The K-nearest Neighbors (KNN), Support-vector machines (SVM), Decision tree classification, Random forest, Naive Bayes Classifier and Boosting algorithm. The test results demonstrate that The Random Forest algorithm has the best accuracy 99.67% compared to the other algorithms with appropriate processing time 67.7 ms for real time posture monitoring system.

show abstract

Section: Introductionmentioning

confidence: 99%

SPLIGN: Smart-belt Posture Monitoring System Based on AI-algorithms for Sitting Persons

Tlili,

Haddad,

Bouallegue

2024

IJAEMR

View full text Add to dashboard Cite

show abstract

“…Nowadays, a vast amount of information is available in the healthcare field. It includes electronic medical records (EMRs) with data which could be structured or unstructured [3]. Health data that is easily analyzed in a database is known as structured data.…”

Section: Introductionmentioning

confidence: 99%

The Significance of Machine Learning in Healthcare Data Management

Aligbe

2023

Preprint

View full text Add to dashboard Cite

Healthcare data management in machine Learning is the application of different machine learning techniques to analyse and interpret large amounts of healthcare data, including patient records, administrative data, clinical data, and much more. The history of machine learning, as well as some fundamental knowledge of these methods and the various roles they have played in healthcare data management, are briefly explored in this paper. The impact of machine learning on data collection, analysis, predictive modelling, decision-making procedures, and overall healthcare improvement is given special consideration. The healthcare sector has greatly benefited from machine learning since it can process a variety of datasets and provide early disease diagnosis, individualised treatment plans, disease prevention, and anomaly detection. To predict this disease, various supervised machine learning algorithms are used.

show abstract