This study introduces a long-short-term memory(LSTM)-based neural network model developed for detecting anomaly events in care-independent smart homes,focusing on the critical application of elderly fall detection.It ...This study introduces a long-short-term memory(LSTM)-based neural network model developed for detecting anomaly events in care-independent smart homes,focusing on the critical application of elderly fall detection.It balances the dataset using the Synthetic Minority Over-sampling Technique(SMOTE),effectively neutralizing bias to address the challenge of unbalanced datasets prevalent in time-series classification tasks.The proposed LSTM model is trained on the enriched dataset,capturing the temporal dependencies essential for anomaly recognition.The model demonstrated a significant improvement in anomaly detection,with an accuracy of 84%.The results,detailed in the comprehensive classification and confusion matrices,showed the model’s proficiency in distinguishing between normal activities and falls.This study contributes to the advancement of smart home safety,presenting a robust framework for real-time anomaly monitoring.展开更多
Older adult falls are a significant public health problem,but one that is amenable to preventive interventions.1,2 Despite the progress made in identifying risk factors,developing efficacious health-related interventi...Older adult falls are a significant public health problem,but one that is amenable to preventive interventions.1,2 Despite the progress made in identifying risk factors,developing efficacious health-related interventions,and promoting evidencebased programs in the community,much work remains before these strategies are broadly available and effectively used to reduce fall-related injuries.3 As Newton and ScottFindlay4 have pointed out,the translation of basic scientific knowledge into clinical studies,and the transformation of clinical studies into improvements in health services and public health practices,remain major obstacles to widespread adoption.展开更多
This quasi-experimental study compared the results of a traditional model of physical therapy(PT)care to a PT wellness model known as GroupHab.The traditional model included discharge from PT with a home exercise prog...This quasi-experimental study compared the results of a traditional model of physical therapy(PT)care to a PT wellness model known as GroupHab.The traditional model included discharge from PT with a home exercise program(HEP)to be self-administered with or without the addition of a community-based exercise program.The wellness model included participation in a PT-designed and supervised group exercise program(GroupHab class)in an outpatient clinical setting following discharge from PT.Independent t-tests were used to compare the number of falls,exercise frequency,and exercise duration between the two groups.A repeated measures,analysis of variance(RM-ANOVA)compared changes in balance confidence scores both within and between groups,and a multivariate analysis of variance(MANOVA)analyzed group differences across multiple quality of life ratings using the SF-20.All data were analyzed at the 0.05 alpha level using SPSS 24 statistical software.Our results showed a significantly greater reduction in recurrent falls among the GroupHab wellness group compared to the HEP group(t=2.811,p=0.009).The resulting odds ratio for subsequent falls was 2.2 among HEP participants and 0.2 among GroupHab participants.Exercise adherence was also greater for those who participated in the GroupHab class.They documented greater exercise frequency(t=-3.253,p=0.002)and more exercise minutes(t=-7.188,p<0.001)than those who participated in the HEP.When comparing changes in the participants’balance confidence,we found an average increase of 5%among GroupHab participants compared to a 6%decrease among HEP participants(F=16.877,p<0.001,power=0.981).Although our multivariate analysis of the SF-20 scores revealed no significant difference overall(F=0.768,p=0.73),the univariate analyses showed significantly greater improvements among GroupHab participants in selected areas of physical function.These results suggest that at-risk older adults who are discharged into a functionally-based group exercise class are less likely to experience recurrent falls and are more likely to have more confidence in their balance than those who are discharged with a standard HEP and/or use of community-based exercise classes.展开更多
In this study,a walking method that prevents a fall of the planetary exploration-legged rover is proposed.In the proposed walking method,the leg is sunk by giving vibration to the ground.The posture of the rover is ch...In this study,a walking method that prevents a fall of the planetary exploration-legged rover is proposed.In the proposed walking method,the leg is sunk by giving vibration to the ground.The posture of the rover is changed to prevent a fall of the rover by sinking the leg.First,the relationship between the kind of vibration and the subsidence of the leg is confirmed.In this experimental result,the leg is shown to be easy to sink to the ground by giving vibration.Moreover,the larger the vibratory force is,the easier the leg sinks to the ground.Finally,the legged testbed walks on the loose ground with a slope using the proposed walking method.In this experimental result,the testbed is difficult to fall down when it uses the proposed walking.Moreover,the angle of a slope that the testbed can walk becomes large by using the proposed walking.展开更多
Long term care facilities have a rising rate of falls and fall related injuries with increasing cost and more hospitalization.Hourly rounding®is an evidenced based intervention that is proactive for nursing staff...Long term care facilities have a rising rate of falls and fall related injuries with increasing cost and more hospitalization.Hourly rounding®is an evidenced based intervention that is proactive for nursing staff to be able to identify patient’s needs.This helps with positive fall prevention outcome.This project focused on process improvement efforts for 10 weeks and examining the education and implementation of an evidenced-based hourly rounding program that assisted in reducing the number of falls in the pilot unit.The implementation of the intervention took place in a long-term care facility located in Dallas,Georgia.The hourly rounding tools used in this project were the Studer Group hourly rounding log and competency checklist with permission.Twenty staff members were included in the sample,age 18 years and 60 years.The unit has 41 residents who were included in the pilot case study design.Staff members were first educated regarding hourly rounding and documentation on the hourly rounding log was done two days before implementation and the pre and post fall rate was retrieved from the facilities fall database.Competency checklist was completed prior to implementation and post implementation to evaluate staff understanding of the main tenets of the 4 P’s(potty,pain,possession,and position).For this project,descriptive statistics was used to help determine fall rates.Minitab was used to analyzed data and to determine if it was clinically significant.In the ten weeks following the hourly rounding implementation,participants performed hourly rounding by incorporating it to each resident’s daily routine and documented their rounds on the log sheet.The results indicated that it is statistically significant and with a P-values=-<0.0001 and t-value=-5.81.展开更多
基金Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2024R 343),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.The authors extend their appreciation to the Deanship of Scientific Research at Northern Border University,Arar,KSA for funding this research work through the Project Number“NBU-FFR-2024-1092-04”.
文摘This study introduces a long-short-term memory(LSTM)-based neural network model developed for detecting anomaly events in care-independent smart homes,focusing on the critical application of elderly fall detection.It balances the dataset using the Synthetic Minority Over-sampling Technique(SMOTE),effectively neutralizing bias to address the challenge of unbalanced datasets prevalent in time-series classification tasks.The proposed LSTM model is trained on the enriched dataset,capturing the temporal dependencies essential for anomaly recognition.The model demonstrated a significant improvement in anomaly detection,with an accuracy of 84%.The results,detailed in the comprehensive classification and confusion matrices,showed the model’s proficiency in distinguishing between normal activities and falls.This study contributes to the advancement of smart home safety,presenting a robust framework for real-time anomaly monitoring.
文摘Older adult falls are a significant public health problem,but one that is amenable to preventive interventions.1,2 Despite the progress made in identifying risk factors,developing efficacious health-related interventions,and promoting evidencebased programs in the community,much work remains before these strategies are broadly available and effectively used to reduce fall-related injuries.3 As Newton and ScottFindlay4 have pointed out,the translation of basic scientific knowledge into clinical studies,and the transformation of clinical studies into improvements in health services and public health practices,remain major obstacles to widespread adoption.
基金Charlotte Walter,DPT assisted in creation of the survey used in this study.
文摘This quasi-experimental study compared the results of a traditional model of physical therapy(PT)care to a PT wellness model known as GroupHab.The traditional model included discharge from PT with a home exercise program(HEP)to be self-administered with or without the addition of a community-based exercise program.The wellness model included participation in a PT-designed and supervised group exercise program(GroupHab class)in an outpatient clinical setting following discharge from PT.Independent t-tests were used to compare the number of falls,exercise frequency,and exercise duration between the two groups.A repeated measures,analysis of variance(RM-ANOVA)compared changes in balance confidence scores both within and between groups,and a multivariate analysis of variance(MANOVA)analyzed group differences across multiple quality of life ratings using the SF-20.All data were analyzed at the 0.05 alpha level using SPSS 24 statistical software.Our results showed a significantly greater reduction in recurrent falls among the GroupHab wellness group compared to the HEP group(t=2.811,p=0.009).The resulting odds ratio for subsequent falls was 2.2 among HEP participants and 0.2 among GroupHab participants.Exercise adherence was also greater for those who participated in the GroupHab class.They documented greater exercise frequency(t=-3.253,p=0.002)and more exercise minutes(t=-7.188,p<0.001)than those who participated in the HEP.When comparing changes in the participants’balance confidence,we found an average increase of 5%among GroupHab participants compared to a 6%decrease among HEP participants(F=16.877,p<0.001,power=0.981).Although our multivariate analysis of the SF-20 scores revealed no significant difference overall(F=0.768,p=0.73),the univariate analyses showed significantly greater improvements among GroupHab participants in selected areas of physical function.These results suggest that at-risk older adults who are discharged into a functionally-based group exercise class are less likely to experience recurrent falls and are more likely to have more confidence in their balance than those who are discharged with a standard HEP and/or use of community-based exercise classes.
文摘In this study,a walking method that prevents a fall of the planetary exploration-legged rover is proposed.In the proposed walking method,the leg is sunk by giving vibration to the ground.The posture of the rover is changed to prevent a fall of the rover by sinking the leg.First,the relationship between the kind of vibration and the subsidence of the leg is confirmed.In this experimental result,the leg is shown to be easy to sink to the ground by giving vibration.Moreover,the larger the vibratory force is,the easier the leg sinks to the ground.Finally,the legged testbed walks on the loose ground with a slope using the proposed walking method.In this experimental result,the testbed is difficult to fall down when it uses the proposed walking.Moreover,the angle of a slope that the testbed can walk becomes large by using the proposed walking.
文摘Long term care facilities have a rising rate of falls and fall related injuries with increasing cost and more hospitalization.Hourly rounding®is an evidenced based intervention that is proactive for nursing staff to be able to identify patient’s needs.This helps with positive fall prevention outcome.This project focused on process improvement efforts for 10 weeks and examining the education and implementation of an evidenced-based hourly rounding program that assisted in reducing the number of falls in the pilot unit.The implementation of the intervention took place in a long-term care facility located in Dallas,Georgia.The hourly rounding tools used in this project were the Studer Group hourly rounding log and competency checklist with permission.Twenty staff members were included in the sample,age 18 years and 60 years.The unit has 41 residents who were included in the pilot case study design.Staff members were first educated regarding hourly rounding and documentation on the hourly rounding log was done two days before implementation and the pre and post fall rate was retrieved from the facilities fall database.Competency checklist was completed prior to implementation and post implementation to evaluate staff understanding of the main tenets of the 4 P’s(potty,pain,possession,and position).For this project,descriptive statistics was used to help determine fall rates.Minitab was used to analyzed data and to determine if it was clinically significant.In the ten weeks following the hourly rounding implementation,participants performed hourly rounding by incorporating it to each resident’s daily routine and documented their rounds on the log sheet.The results indicated that it is statistically significant and with a P-values=-<0.0001 and t-value=-5.81.