In the environment of smart examination rooms, it is important to quickly and accurately detect abnormal behavior(human standing) for the construction of a smart campus. Based on deep learning, we propose an intellige...In the environment of smart examination rooms, it is important to quickly and accurately detect abnormal behavior(human standing) for the construction of a smart campus. Based on deep learning, we propose an intelligentstanding human detection (ISHD) method based on an improved single shot multibox detector to detect thetarget of standing human posture in the scene frame of exam room video surveillance at a specific examinationstage. ISHD combines the MobileNet network in a single shot multibox detector network, improves the posturefeature extractor of a standing person, merges prior knowledge, and introduces transfer learning in the trainingstrategy, which greatly reduces the computation amount, improves the detection accuracy, and reduces the trainingdifficulty. The experiment proves that the model proposed in this paper has a better detection ability for the smalland medium-sized standing human body posture in video test scenes on the EMV-2 dataset.展开更多
AIM To determine the feasibility of introducing video recording(VR) of neonatal resuscitation(NR) in a perinatal centre.METHODS This was a prospective cohort quality improvement study on preterm infants and their care...AIM To determine the feasibility of introducing video recording(VR) of neonatal resuscitation(NR) in a perinatal centre.METHODS This was a prospective cohort quality improvement study on preterm infants and their caregivers.Based on evidence and experience of other centers using VR intervention,a contextually relevant implementation and evaluation strategy was designed in the planning phase.The components of intervention were pre-resuscitation team huddle,VR of NR and video debriefing(VD),all occurringon the same day.Various domains of feasibility and sustainability as well as feasibility criteria were predefined.Data for analysis was collected using quantitative and qualitative methods.RESULTS Seventy-one caregivers participated in VD of 14 NRs facilitated by six trained instructors.Ninety-one percent of caregivers perceived enhanced learning and patient safety and,48 issues were identified related to policy,caregiver roles,and latent safety threats.Ninety percent of caregivers expressed their willingness to participate in VD activity and supported the idea of integrating it into a resuscitation team routine.Eighty-three percent and 50% of instructors expressed satisfaction with video review software and quality of audio VR.No issues about maintenance of infant or caregivers' confidentiality and erasure of videos were reported.Criteria for feasibility were met(refusal rate of < 10%,VR performed on > 50% of occasions,and < 20% caregivers' perceiving a negative impact on team performance).Necessary adaptations to enhance sustainability were identified.CONCLUSION VR of NR as a standard of care quality assurance activity to enhance caregivers' learning and create opportunities that improve patient safety is feasible.Despite its complexity with inherent challenges in implementation,the intervention was acceptable,implementable,and potentially sustainable with adaptations.展开更多
基金supported by the Natural Science Foundation of China 62102147National Science Foundation of Hunan Province 2022JJ30424,2022JJ50253,and 2022JJ30275+2 种基金Scientific Research Project of Hunan Provincial Department of Education 21B0616 and 21B0738Hunan University of Arts and Sciences Ph.D.Start-Up Project BSQD02,20BSQD13the Construct Program of Applied Characteristic Discipline in Hunan University of Science and Engineering.
文摘In the environment of smart examination rooms, it is important to quickly and accurately detect abnormal behavior(human standing) for the construction of a smart campus. Based on deep learning, we propose an intelligentstanding human detection (ISHD) method based on an improved single shot multibox detector to detect thetarget of standing human posture in the scene frame of exam room video surveillance at a specific examinationstage. ISHD combines the MobileNet network in a single shot multibox detector network, improves the posturefeature extractor of a standing person, merges prior knowledge, and introduces transfer learning in the trainingstrategy, which greatly reduces the computation amount, improves the detection accuracy, and reduces the trainingdifficulty. The experiment proves that the model proposed in this paper has a better detection ability for the smalland medium-sized standing human body posture in video test scenes on the EMV-2 dataset.
基金Supported by the Centre for Healthcare Optimization Research and Delivery(CHORD)at Hamilton Health Sciences with an aim of facilitating knowledge transfer initiatives from health care and supportive teams
文摘AIM To determine the feasibility of introducing video recording(VR) of neonatal resuscitation(NR) in a perinatal centre.METHODS This was a prospective cohort quality improvement study on preterm infants and their caregivers.Based on evidence and experience of other centers using VR intervention,a contextually relevant implementation and evaluation strategy was designed in the planning phase.The components of intervention were pre-resuscitation team huddle,VR of NR and video debriefing(VD),all occurringon the same day.Various domains of feasibility and sustainability as well as feasibility criteria were predefined.Data for analysis was collected using quantitative and qualitative methods.RESULTS Seventy-one caregivers participated in VD of 14 NRs facilitated by six trained instructors.Ninety-one percent of caregivers perceived enhanced learning and patient safety and,48 issues were identified related to policy,caregiver roles,and latent safety threats.Ninety percent of caregivers expressed their willingness to participate in VD activity and supported the idea of integrating it into a resuscitation team routine.Eighty-three percent and 50% of instructors expressed satisfaction with video review software and quality of audio VR.No issues about maintenance of infant or caregivers' confidentiality and erasure of videos were reported.Criteria for feasibility were met(refusal rate of < 10%,VR performed on > 50% of occasions,and < 20% caregivers' perceiving a negative impact on team performance).Necessary adaptations to enhance sustainability were identified.CONCLUSION VR of NR as a standard of care quality assurance activity to enhance caregivers' learning and create opportunities that improve patient safety is feasible.Despite its complexity with inherent challenges in implementation,the intervention was acceptable,implementable,and potentially sustainable with adaptations.
