Wearable wristband systems leverage deep learning to revolutionize hand gesture recognition in daily activities.Unlike existing approaches that often focus on static gestures and require extensive labeled data,the pro...Wearable wristband systems leverage deep learning to revolutionize hand gesture recognition in daily activities.Unlike existing approaches that often focus on static gestures and require extensive labeled data,the proposed wearable wristband with selfsupervised contrastive learning excels at dynamic motion tracking and adapts rapidly across multiple scenarios.It features a four-channel sensing array composed of an ionic hydrogel with hierarchical microcone structures and ultrathin flexible electrodes,resulting in high-sensitivity capacitance output.Through wireless transmission from a Wi-Fi module,the proposed algorithm learns latent features from the unlabeled signals of random wrist movements.Remarkably,only few-shot labeled data are sufficient for fine-tuning the model,enabling rapid adaptation to various tasks.The system achieves a high accuracy of 94.9%in different scenarios,including the prediction of eight-direction commands,and air-writing of all numbers and letters.The proposed method facilitates smooth transitions between multiple tasks without the need for modifying the structure or undergoing extensive task-specific training.Its utility has been further extended to enhance human–machine interaction over digital platforms,such as game controls,calculators,and three-language login systems,offering users a natural and intuitive way of communication.展开更多
Objective In this study we aimed to examine the reliability and validity of the wristband activity monitor against the accelerometer for children.Methods A total of 99 children(mean age = 13.0 ± 2.5 y) wore the t...Objective In this study we aimed to examine the reliability and validity of the wristband activity monitor against the accelerometer for children.Methods A total of 99 children(mean age = 13.0 ± 2.5 y) wore the two monitors in a free-living context for 7 days. Reliability was measured by intraclass correlation to evaluate consistency over time.Repeated-measures analyses of variance was used to detect differences across days. Spearman’s correlation coefficient(rho), median of absolute percentage error, and Bland-Altman analyses were performed to assess the validity of the wristband against the Acti Graph accelerometer. The optimal number of repeated measures for the wristband was calculated by using the Spearman-Brown prophecy formula.Results The wristband had high reliability for all variables, although physical activity data were different across 7 days. A strong correlation for steps(rho: 0.72, P < 0.001), and moderate correlations for time spent on total physical activity(rho: 0.63, P < 0.001) and physical activity energy expenditure(rho: 0.57, P < 0.001) were observed between the wristband and the accelerometer. For different intensities of physical activity, weak to moderate correlations were found(rho: 0.38 to 0.55, P < 0.001).Conclusion The wristband activity monitor seems to be reliable and valid for measurement of overall children’s physical activity, providing a feasible objective method of physical activity surveillance in children.展开更多
The potential role of personal items in the transmission of pathogens is poorly understood. In this study, we cultured bacteria of public health importance found on wristbands, determined whether there is a correlatio...The potential role of personal items in the transmission of pathogens is poorly understood. In this study, we cultured bacteria of public health importance found on wristbands, determined whether there is a correlation between wristband material and prevalence, and tested three household disinfectants for efficacy in reducing bacteria on wristbands made of plastic, rubber, metal, and cloth, using standard microbiological assays. Total cultivable bacteria, Staphylococci, Enterobacteria (Escherichia coli), and Pseudomonas on 20 smartwatch wristbands were cultured from randomly recruited subjects. Nearly all wristbands (95%) were contaminated, with the highest average numbers of 3.46E+4 cfu/cm<sup>2</sup> and 1.52E+4 cfu/cm<sup>2</sup> on rubber and plastic bands respectively. Metallic gold and silver wristbands had zero to 18 cfu/cm<sup>2</sup>. While the high prevalence of Staphylococcus spp (85% of wristbands)—skin microbiota;was not unexpected, the occurrence of Pseudomonas spp (30%), and enteric bacteria (60%), even at relatively low numbers is of public health significance. Bacterial load on individual subjects varied remarkably with males and females harboring average total bacteria of 4.045 and 3.42 log<sub>10</sub>cfu/cm<sup>2</sup> of wristband, respectively. The most important predictor of wristband bacteria load was the texture of wristband material and activity (hygiene) of the subject at sampling time. Potential pathogens—Staphylococcus aureus (8143 cfu/cm<sup>2</sup>) and Pseudomonas spp. (1126 cfu/cm<sup>2</sup>) were most abundant on cloth and rubber wristbands, respectively, while the presence of the E. coli group was associated with animal handling activity by a veterinarian. Lysol Disinfectant Spray and 70% Ethanol were highly effective regardless of wristband material with >99.99% kill rate and a log cfu/cm<sup>2</sup> reduction of 3 - 4.0 and 3 - 4.5 respectively within 30 seconds. Apple Cider Vinegar (ACV) was not as potent. Only 2 - 3.5 log cfu/cm<sup>2</sup> drop was obtained after 120 seconds of exposure. Further susceptibility assays with standard reference bacteria showed that Lysol and 70% alcohol effectively killed > 99.99% (>8 log CFU drop) of Escherichia coli strain 7001, Staphylococcus aureus strain 6538, and Pseudomonas aeruginosa strain 10662 within 30 seconds of contact. Vinegar had a similar efficacy on the gram negatives but little or no effect on Staph aureus (only a 2-log CFU/ml reduction in 5 minutes!) The high prevalence of potential pathogens, some of which could be reservoirs of antibiotic resistance reveals a weak link in infection control and underscores the need for regular cleaning of personal and hand-held accessories with adequate considerations of their texture.展开更多
Atrial fibrillation(AF)is a common and serious disease.Its diagnosis usually requires 12-lead electrocardiogram,which is heavy and inconvenient.At the same time,the venue for diagnosis is also limited to the hospital....Atrial fibrillation(AF)is a common and serious disease.Its diagnosis usually requires 12-lead electrocardiogram,which is heavy and inconvenient.At the same time,the venue for diagnosis is also limited to the hospital.With the development of the concept of intelligent medical,a wearable,portable,and reliable diagnostic method is needed to improve the patient’s comfort and alleviate the patient’s pain.Here,we reported a wearable atrial fibrillation prediction wristband(AFPW)which can provide longterm monitoring and AF diagnosis.AFPW uses polyvinylidene fluoride piezoelectric film as sensing material and hydrogel as skin bonding material,of which the structure and design have been optimized and improved.The hydrogel skin bonding layer has good stability and skin affinity,which can greatly improve the user experience.AFPW has enhanced signal,strong signal-tonoise ratio,and wireless transmission function.After a sample library of 385 normal people/patients is analyzed and tested by linear discriminant analysis,the diagnostic success rate of atrial fibrillation is 91%.All these excellent performances demonstrate the great application potential of AFPW in wearable device diagnosis and intelligent medical treatment.展开更多
邻苯二甲酸酯(Phthalates,PAEs)和有机磷酸酯(Organophosphate esters,OPEs)的室内污染和人体暴露日益严重,但目前缺少人群室内PAEs、OPEs昼夜暴露差异的研究.本研究利用硅胶(聚二甲基硅氧烷)手环(PDMS wristband,WB)和胸牌(PDMS sheet,...邻苯二甲酸酯(Phthalates,PAEs)和有机磷酸酯(Organophosphate esters,OPEs)的室内污染和人体暴露日益严重,但目前缺少人群室内PAEs、OPEs昼夜暴露差异的研究.本研究利用硅胶(聚二甲基硅氧烷)手环(PDMS wristband,WB)和胸牌(PDMS sheet,PS)研究了大学生白天佩戴8 h WB(DWB)和PS(DPS)、夜晚佩戴8 h WB(NWB),夜晚悬挂8 h PS(NPS)及夜晚置于被褥中8 h WB(NWBQ)等5种情景下10种PAEs和11种OPEs的暴露浓度及单体组成.5类样品均检测出较高浓度的PAEs、OPEs,其中DWB、NWB、NWBQ中PAEs中值浓度分别为3700、3080、822 ng·dm^(-2)·h^(-1),OPEs的中值浓度为30.2、29.2、17.8 ng·dm^(-2)·h^(-1);DPS和NPS中PAEs的中值浓度分别为347、618 ng·dm^(-2)·h^(-1),OPEs的中值浓度为16.1、31.0 ng·dm^(-2)·h^(-1).人体昼夜暴露剂量存在显著差异,基于WB的暴露量:白天活动>夜间睡眠>被褥接触,而基于PS的暴露量:夜间睡眠>白天活动.人体PAEs、OPEs的昼夜暴露来源相似.女性的PAEs、OPEs的暴露剂量普遍高于男性.基于PS估算的空气PAEs、OPEs浓度评估大学生的暴露风险,发现人体对PAEs、OPEs的昼夜暴露存在低风险.研究结果为控制和消减有机污染人群暴露风险提供依据.展开更多
基金supported by the Research Grant Fund from Kwangwoon University in 2023,the National Natural Science Foundation of China under Grant(62311540155)the Taishan Scholars Project Special Funds(tsqn202312035)the open research foundation of State Key Laboratory of Integrated Chips and Systems.
文摘Wearable wristband systems leverage deep learning to revolutionize hand gesture recognition in daily activities.Unlike existing approaches that often focus on static gestures and require extensive labeled data,the proposed wearable wristband with selfsupervised contrastive learning excels at dynamic motion tracking and adapts rapidly across multiple scenarios.It features a four-channel sensing array composed of an ionic hydrogel with hierarchical microcone structures and ultrathin flexible electrodes,resulting in high-sensitivity capacitance output.Through wireless transmission from a Wi-Fi module,the proposed algorithm learns latent features from the unlabeled signals of random wrist movements.Remarkably,only few-shot labeled data are sufficient for fine-tuning the model,enabling rapid adaptation to various tasks.The system achieves a high accuracy of 94.9%in different scenarios,including the prediction of eight-direction commands,and air-writing of all numbers and letters.The proposed method facilitates smooth transitions between multiple tasks without the need for modifying the structure or undergoing extensive task-specific training.Its utility has been further extended to enhance human–machine interaction over digital platforms,such as game controls,calculators,and three-language login systems,offering users a natural and intuitive way of communication.
基金funded by National Scientific and Technological Basic Resources Investigation Program ‘Research and application of nutrition and health system for children aged 0-18 years in China’[2017FY101107]
文摘Objective In this study we aimed to examine the reliability and validity of the wristband activity monitor against the accelerometer for children.Methods A total of 99 children(mean age = 13.0 ± 2.5 y) wore the two monitors in a free-living context for 7 days. Reliability was measured by intraclass correlation to evaluate consistency over time.Repeated-measures analyses of variance was used to detect differences across days. Spearman’s correlation coefficient(rho), median of absolute percentage error, and Bland-Altman analyses were performed to assess the validity of the wristband against the Acti Graph accelerometer. The optimal number of repeated measures for the wristband was calculated by using the Spearman-Brown prophecy formula.Results The wristband had high reliability for all variables, although physical activity data were different across 7 days. A strong correlation for steps(rho: 0.72, P < 0.001), and moderate correlations for time spent on total physical activity(rho: 0.63, P < 0.001) and physical activity energy expenditure(rho: 0.57, P < 0.001) were observed between the wristband and the accelerometer. For different intensities of physical activity, weak to moderate correlations were found(rho: 0.38 to 0.55, P < 0.001).Conclusion The wristband activity monitor seems to be reliable and valid for measurement of overall children’s physical activity, providing a feasible objective method of physical activity surveillance in children.
文摘The potential role of personal items in the transmission of pathogens is poorly understood. In this study, we cultured bacteria of public health importance found on wristbands, determined whether there is a correlation between wristband material and prevalence, and tested three household disinfectants for efficacy in reducing bacteria on wristbands made of plastic, rubber, metal, and cloth, using standard microbiological assays. Total cultivable bacteria, Staphylococci, Enterobacteria (Escherichia coli), and Pseudomonas on 20 smartwatch wristbands were cultured from randomly recruited subjects. Nearly all wristbands (95%) were contaminated, with the highest average numbers of 3.46E+4 cfu/cm<sup>2</sup> and 1.52E+4 cfu/cm<sup>2</sup> on rubber and plastic bands respectively. Metallic gold and silver wristbands had zero to 18 cfu/cm<sup>2</sup>. While the high prevalence of Staphylococcus spp (85% of wristbands)—skin microbiota;was not unexpected, the occurrence of Pseudomonas spp (30%), and enteric bacteria (60%), even at relatively low numbers is of public health significance. Bacterial load on individual subjects varied remarkably with males and females harboring average total bacteria of 4.045 and 3.42 log<sub>10</sub>cfu/cm<sup>2</sup> of wristband, respectively. The most important predictor of wristband bacteria load was the texture of wristband material and activity (hygiene) of the subject at sampling time. Potential pathogens—Staphylococcus aureus (8143 cfu/cm<sup>2</sup>) and Pseudomonas spp. (1126 cfu/cm<sup>2</sup>) were most abundant on cloth and rubber wristbands, respectively, while the presence of the E. coli group was associated with animal handling activity by a veterinarian. Lysol Disinfectant Spray and 70% Ethanol were highly effective regardless of wristband material with >99.99% kill rate and a log cfu/cm<sup>2</sup> reduction of 3 - 4.0 and 3 - 4.5 respectively within 30 seconds. Apple Cider Vinegar (ACV) was not as potent. Only 2 - 3.5 log cfu/cm<sup>2</sup> drop was obtained after 120 seconds of exposure. Further susceptibility assays with standard reference bacteria showed that Lysol and 70% alcohol effectively killed > 99.99% (>8 log CFU drop) of Escherichia coli strain 7001, Staphylococcus aureus strain 6538, and Pseudomonas aeruginosa strain 10662 within 30 seconds of contact. Vinegar had a similar efficacy on the gram negatives but little or no effect on Staph aureus (only a 2-log CFU/ml reduction in 5 minutes!) The high prevalence of potential pathogens, some of which could be reservoirs of antibiotic resistance reveals a weak link in infection control and underscores the need for regular cleaning of personal and hand-held accessories with adequate considerations of their texture.
基金supported by the National Natural Science Foundation of China(Nos.T2125003,82202075,and 82102231)the Beijing Natural Science Foundation(Nos.JQ20038 and L212010)+1 种基金the National Postdoctoral Program for Innovative Talent(No.BX20220380)the China Postdoctoral Science Foundation(No.2022M710389).
文摘Atrial fibrillation(AF)is a common and serious disease.Its diagnosis usually requires 12-lead electrocardiogram,which is heavy and inconvenient.At the same time,the venue for diagnosis is also limited to the hospital.With the development of the concept of intelligent medical,a wearable,portable,and reliable diagnostic method is needed to improve the patient’s comfort and alleviate the patient’s pain.Here,we reported a wearable atrial fibrillation prediction wristband(AFPW)which can provide longterm monitoring and AF diagnosis.AFPW uses polyvinylidene fluoride piezoelectric film as sensing material and hydrogel as skin bonding material,of which the structure and design have been optimized and improved.The hydrogel skin bonding layer has good stability and skin affinity,which can greatly improve the user experience.AFPW has enhanced signal,strong signal-tonoise ratio,and wireless transmission function.After a sample library of 385 normal people/patients is analyzed and tested by linear discriminant analysis,the diagnostic success rate of atrial fibrillation is 91%.All these excellent performances demonstrate the great application potential of AFPW in wearable device diagnosis and intelligent medical treatment.
文摘邻苯二甲酸酯(Phthalates,PAEs)和有机磷酸酯(Organophosphate esters,OPEs)的室内污染和人体暴露日益严重,但目前缺少人群室内PAEs、OPEs昼夜暴露差异的研究.本研究利用硅胶(聚二甲基硅氧烷)手环(PDMS wristband,WB)和胸牌(PDMS sheet,PS)研究了大学生白天佩戴8 h WB(DWB)和PS(DPS)、夜晚佩戴8 h WB(NWB),夜晚悬挂8 h PS(NPS)及夜晚置于被褥中8 h WB(NWBQ)等5种情景下10种PAEs和11种OPEs的暴露浓度及单体组成.5类样品均检测出较高浓度的PAEs、OPEs,其中DWB、NWB、NWBQ中PAEs中值浓度分别为3700、3080、822 ng·dm^(-2)·h^(-1),OPEs的中值浓度为30.2、29.2、17.8 ng·dm^(-2)·h^(-1);DPS和NPS中PAEs的中值浓度分别为347、618 ng·dm^(-2)·h^(-1),OPEs的中值浓度为16.1、31.0 ng·dm^(-2)·h^(-1).人体昼夜暴露剂量存在显著差异,基于WB的暴露量:白天活动>夜间睡眠>被褥接触,而基于PS的暴露量:夜间睡眠>白天活动.人体PAEs、OPEs的昼夜暴露来源相似.女性的PAEs、OPEs的暴露剂量普遍高于男性.基于PS估算的空气PAEs、OPEs浓度评估大学生的暴露风险,发现人体对PAEs、OPEs的昼夜暴露存在低风险.研究结果为控制和消减有机污染人群暴露风险提供依据.
