首页|University of Canberra Reports Findings in Machine Learning (Empirical compariso n of deep learning models for fNIRS pain decoding)
University of Canberra Reports Findings in Machine Learning (Empirical compariso n of deep learning models for fNIRS pain decoding)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report.According to news reporting from Canberra,Australia,by NewsRx journalists,research stated,"Pain assessment is extremely important in patients unable to communicate and it is often done by clinical judgement.Howev er,assessing pain using observable indicators can be challenging for clinicians due to the subjective perceptions,individual differences in pain expression,a nd potential confounding factors." The news correspondents obtained a quote from the research from the University o f Canberra,"Therefore,the need for an objective pain assessment method that ca n assist medical practitioners.Functional near-infrared spectroscopy (fNIRS) ha s shown promising results to assess the neural function in response of nocicepti on and pain.Previous studies have explored the use of machine learning with han d-crafted features in the assessment of pain.In this study,we aim to expand pr evious studies by exploring the use of deep learning models Convolutional Neural Network (CNN),Long Short-Term Memory (LSTM),and (CNN-LSTM) to automatically e xtract features from fNIRS data and by comparing these with classical machine le arning models using hand-crafted features.The results showed that the deep lear ning models exhibited favourable results in the identification of different type s of pain in our experiment using only fNIRS input data.The combination of CNN and LSTM in a hybrid model (CNN-LSTM) exhibited the highest performance (accurac y = 91.2%) in our problem setting.Statistical analysis using one-w ay ANOVA with Tukey's () test performed on accuracies showed that the deep learn ing models significantly improved accuracy performance as compared to the baseli ne models.Overall,deep learning models showed their potential to learn feature s automatically without relying on manually-extracted features and the CNN-LSTM model could be used as a possible method of assessment of pain in non-verbal pat ients."
CanberraAustraliaAustralia and New Z ealandCyborgsEmerging TechnologiesMachine LearningPain AssessmentPain Management
NETL
NSTL
