Sleep posture monitoring is an essential assessment for obstructive sleep apnea(OSA)patients.The objective of this study is to develop a machine learning-based sleep posture recognition system using a dual ultra-wideb...Sleep posture monitoring is an essential assessment for obstructive sleep apnea(OSA)patients.The objective of this study is to develop a machine learning-based sleep posture recognition system using a dual ultra-wideband radar system.We collected radiofrequency data from two radars positioned over and at the side of the bed for 16 patients performing four sleep postures(supine,left and right lateral,and prone).We proposed and evaluated deep learning approaches that streamlined feature extraction and classification,and the traditional machine learning approaches that involved different combinations of feature extractors and classifiers.Our results showed that the dual radar system performed better than either single radar.Predetermined statistical features with random forest classifier yielded the best accuracy(0.887),which could be further improved via an ablation study(0.938).Deep learning approach using transformer yielded accuracy of 0.713.展开更多
Phantom limb is a disabling neuropsychiatric condition among amputees resulting in pain and disturbance that impact their functions,quality of life,and autonomy.While pharmacological approaches appeared to be ineffec-...Phantom limb is a disabling neuropsychiatric condition among amputees resulting in pain and disturbance that impact their functions,quality of life,and autonomy.While pharmacological approaches appeared to be ineffec-tive,the emergence and integration of X-reality,including virtual reality,augmented reality,and mixed reality,might elevate the effectiveness of mirror therapy in managing phantom limb.The objective of this study is to review X-reality for managing phantom pain.A systematic search was conducted on PubMed,Scopus,Web of Science,PsycINFO,Embase,and CINAHL.Sixteen(n=16)studies containing 66 lower-limb and 53 upper-limb amputees were included for the review over the thematic framework of amputee characteristics and intervention designs,while thirteen(n=13)studies were further proceeded for the meta-analysis.We found eleven studies on virtual reality(n=11),four studies on marker-based augmented reality(n=4)and one study on mixed reality(n=1)with a total of 40 game/task themes involving,motor skills,motor control,and stimulus-sensing.Regardless,all these interventions adopted the movement representation strategies with different techniques.Overall,the X-reality interventions reduced the pain level of the amputees(mean difference:-2.30,95%CI,-3.38 to-1.22),especially the virtual reality subgroup(mean difference:-2.83,95%CI,-4.43 to-1.22).However,there were substantial heterogeneity and partially explained by the subgroup analysis on publication year.The strength of evidence was limited by case reports and case series in this review.展开更多
The authors regret that the name of the ethic committee that approved the study and the reference number was omitted from the published paper.In this research,all participants signed an informed consent after receivin...The authors regret that the name of the ethic committee that approved the study and the reference number was omitted from the published paper.In this research,all participants signed an informed consent after receiving an oral and written description of the experiment before the start of the experiment.The study was approved by the Human Subjects Ethics HSEARS20210127007.展开更多
基金supported by General Research Fund from the Research Grants Council of Hong Kong,China (Project No.PolyU15223822)Internal fund from the Research Institute for Smart Ageing (Project No.P0039001)Department of Biomedical Engineering (Project No.P0033913 and P0035896)from the Hong Kong Polytechnic University.
文摘Sleep posture monitoring is an essential assessment for obstructive sleep apnea(OSA)patients.The objective of this study is to develop a machine learning-based sleep posture recognition system using a dual ultra-wideband radar system.We collected radiofrequency data from two radars positioned over and at the side of the bed for 16 patients performing four sleep postures(supine,left and right lateral,and prone).We proposed and evaluated deep learning approaches that streamlined feature extraction and classification,and the traditional machine learning approaches that involved different combinations of feature extractors and classifiers.Our results showed that the dual radar system performed better than either single radar.Predetermined statistical features with random forest classifier yielded the best accuracy(0.887),which could be further improved via an ablation study(0.938).Deep learning approach using transformer yielded accuracy of 0.713.
基金The work was supported by the Research Institute for Sports Science and Technology(Reference number:P0043798)Internal Fund(Ref-erence number:P0035805)of the Hong Kong Polytechnic University.
文摘Phantom limb is a disabling neuropsychiatric condition among amputees resulting in pain and disturbance that impact their functions,quality of life,and autonomy.While pharmacological approaches appeared to be ineffec-tive,the emergence and integration of X-reality,including virtual reality,augmented reality,and mixed reality,might elevate the effectiveness of mirror therapy in managing phantom limb.The objective of this study is to review X-reality for managing phantom pain.A systematic search was conducted on PubMed,Scopus,Web of Science,PsycINFO,Embase,and CINAHL.Sixteen(n=16)studies containing 66 lower-limb and 53 upper-limb amputees were included for the review over the thematic framework of amputee characteristics and intervention designs,while thirteen(n=13)studies were further proceeded for the meta-analysis.We found eleven studies on virtual reality(n=11),four studies on marker-based augmented reality(n=4)and one study on mixed reality(n=1)with a total of 40 game/task themes involving,motor skills,motor control,and stimulus-sensing.Regardless,all these interventions adopted the movement representation strategies with different techniques.Overall,the X-reality interventions reduced the pain level of the amputees(mean difference:-2.30,95%CI,-3.38 to-1.22),especially the virtual reality subgroup(mean difference:-2.83,95%CI,-4.43 to-1.22).However,there were substantial heterogeneity and partially explained by the subgroup analysis on publication year.The strength of evidence was limited by case reports and case series in this review.
文摘The authors regret that the name of the ethic committee that approved the study and the reference number was omitted from the published paper.In this research,all participants signed an informed consent after receiving an oral and written description of the experiment before the start of the experiment.The study was approved by the Human Subjects Ethics HSEARS20210127007.