The quantization algorithm compresses the original network by reducing the numerical bit width of the model,which improves the computation speed. Because different layers have different redundancy and sensitivity to d...The quantization algorithm compresses the original network by reducing the numerical bit width of the model,which improves the computation speed. Because different layers have different redundancy and sensitivity to databit width. Reducing the data bit width will result in a loss of accuracy. Therefore, it is difficult to determinethe optimal bit width for different parts of the network with guaranteed accuracy. Mixed precision quantizationcan effectively reduce the amount of computation while keeping the model accuracy basically unchanged. In thispaper, a hardware-aware mixed precision quantization strategy optimal assignment algorithm adapted to low bitwidth is proposed, and reinforcement learning is used to automatically predict the mixed precision that meets theconstraints of hardware resources. In the state-space design, the standard deviation of weights is used to measurethe distribution difference of data, the execution speed feedback of simulated neural network accelerator inferenceis used as the environment to limit the action space of the agent, and the accuracy of the quantization model afterretraining is used as the reward function to guide the agent to carry out deep reinforcement learning training. Theexperimental results show that the proposed method obtains a suitable model layer-by-layer quantization strategyunder the condition that the computational resources are satisfied, and themodel accuracy is effectively improved.The proposed method has strong intelligence and certain universality and has strong application potential in thefield of mixed precision quantization and embedded neural network model deployment.展开更多
To realize a hyperconnected smart society with high productivity,advances in flexible sensing technology are highly needed.Nowadays,flexible sensing technology has witnessed improvements in both the hardware performan...To realize a hyperconnected smart society with high productivity,advances in flexible sensing technology are highly needed.Nowadays,flexible sensing technology has witnessed improvements in both the hardware performances of sensor devices and the data processing capabilities of the device’s software.Significant research efforts have been devoted to improving materials,sensing mechanism,and configurations of flexible sensing systems in a quest to fulfill the requirements of future technology.Meanwhile,advanced data analysis methods are being developed to extract useful information from increasingly complicated data collected by a single sensor or network of sensors.Machine learning(ML)as an important branch of artificial intelligence can efficiently handle such complex data,which can be multi-dimensional and multi-faceted,thus providing a powerful tool for easy interpretation of sensing data.In this review,the fundamental working mechanisms and common types of flexible mechanical sensors are firstly presented.Then how ML-assisted data interpretation improves the applications of flexible mechanical sensors and other closely-related sensors in various areas is elaborated,which includes health monitoring,human-machine interfaces,object/surface recognition,pressure prediction,and human posture/motion identification.Finally,the advantages,challenges,and future perspectives associated with the fusion of flexible mechanical sensing technology and ML algorithms are discussed.These will give significant insights to enable the advancement of next-generation artificial flexible mechanical sensing.展开更多
Flexible pressure sensors are unprecedentedly studied on monitoring human physical activities and robotics.Simultaneously,improving the response sensitivity and sensing range of flexible pressure sensors is a great ch...Flexible pressure sensors are unprecedentedly studied on monitoring human physical activities and robotics.Simultaneously,improving the response sensitivity and sensing range of flexible pressure sensors is a great challenge,which hinders the devices’practical application.Targeting this obstacle,we developed a Ti_(3)C_(2)T_(x)-derived iontronic pressure sensor(TIPS)by taking the advantages of the high intercalation pseudocapacitance under high pressure and rationally designed structural configuration.TIPS achieved an ultrahigh sen-sitivity(S_(min)>200 kPa^(−1),S_(max)>45,000 kPa^(−1))in a broad sensing range of over 1.4 MPa and low limit of detection of 20 Pa as well as stable long-term working durability for 10,000 cycles.The practical application of TIPS in physical activity monitoring and flexible robot manifested its versatile potential.This study provides a demonstration for exploring pseudocapacitive materials for building flexible iontronic sensors with ultrahigh sensitivity and sensing range to advance the development of high-performance wearable electronics.展开更多
Developing flexible sensors with high working performance holds intense interest for diverse applications in leveraging the Internet-of-things(IoT)infrastructures.For flexible piezoresistive sensors,traditionally most...Developing flexible sensors with high working performance holds intense interest for diverse applications in leveraging the Internet-of-things(IoT)infrastructures.For flexible piezoresistive sensors,traditionally most efforts are focused on tailoring the sensing materials to enhance the contact resistance variation for improving the sensitivity and working range,and it,however,remains challenging to simultaneously achieve flexible sensor with a linear working range over a high-pressure region(>100 kPa)and keep a reliable sensitivity.Herein,we devised a laserengraved silver-coated fabric as"soft"sensor electrode material to markedly advance the flexible sensor's linear working range to a level of 800 kPa with a high sensitivity of 6.4 kPa^-1 yet a fast response time of only 4 ms as well as long-time durability,which was rarely reported before.The integrated sensor successfully routed the wireless signal of pulse rate to the portable smartphone,further demonstrating its potential as a reliable electronic.Along with the rationally building the electrode instead of merely focusing on sensing materials capable of significantly improving the sensor's performance,we expect that this design concept and sensor system could potentially pave the way for developing more advanced wearable electronics in the future.展开更多
We consider a branching random walk in an independent and identically distributed random environment ξ=(ξn) indexed by the time. Let W be the limit of the martingale Wn=∫e^-txZn(dx)/Eξ∫e^-txZn(dx), with Zn denoti...We consider a branching random walk in an independent and identically distributed random environment ξ=(ξn) indexed by the time. Let W be the limit of the martingale Wn=∫e^-txZn(dx)/Eξ∫e^-txZn(dx), with Zn denoting the counting measure of particles of generation n, and Eξ the conditional expectation given the environment ξ. We find necessary and sufficient conditions for the existence of quenched moments and weighted moments of W, when W is non-degenerate.展开更多
Nursing Human Resource Management is part of the human resources is nursing human resources by organizing nurses study, planning, training, and ultimately serve the medical career management stated objectives. Nursing...Nursing Human Resource Management is part of the human resources is nursing human resources by organizing nurses study, planning, training, and ultimately serve the medical career management stated objectives. Nursing human resource development of our human resources there are insufficient care, nurses configuration structure is irrational, the management system is not perfect, nurses are not high quality is the current status of nursing human resource mauagemenL and problems. This paper proposes a "human resource is the first resource" human resources management concept, has taken to develop a reasonable management mechanism, improve relevant laws and regulations of nursing human resources development, increase investment in education, strengthen education and training for nurses, the rational allocation of nursing human resources and other measures. In this paper, the connotation of Human Resources Management in the current situation as the starting point of care, from the current situation of nursing human resource development and the problems of the current situation of nursing human resource management and problems of nursing human resources management to discuss and propose appropriate for the development of human resource management solutions.展开更多
Significant efforts have been devoted to enhancing the sensitivity and working range of flexible pressure sensors to improve the precise measurement of subtle variations in pressure over a wide detection spectrum. How...Significant efforts have been devoted to enhancing the sensitivity and working range of flexible pressure sensors to improve the precise measurement of subtle variations in pressure over a wide detection spectrum. However,achieving sensitivities exceeding 1000 kPa^(-1) while maintaining a pressure working range over 100 kPa is still challenging because of the limited intrinsic properties of soft matrix materials. Here, we report a magnetic field-induced porous elastomer with micropillar arrays(MPAs) as sensing materials and a well-patterned nickel fabric as an electrode. The developed sensor exhibits an ultrahigh sensitivity of 10,268 kPa^(-1)(0.6–170 kPa) with a minimum detection pressure of 0.25 Pa and a fast response time of 3 ms because of the unique structure of the MPAs and the textured morphology of the electrode. The porous elastomer provides an extended working range of up to 500 kPa with long-time durability. The sophisticated sensor system coupled with an integrated wireless recharging system comprising a flexible supercapacitor and inductive coils for transmission achieves excellent performance. Thus, a diverse range of practical applications requiring a low-to-high pressure range sensing can be developed. Our strategy, which combines a microstructured high-performance sensor device with a wireless recharging system, provides a basis for creating next-generation flexible electronics.展开更多
Monitoring biophysical signals such as body or organ movements and other physical phenomena is necessary for patient rehabilitation.However,stretchable flexible pressure sensors with high sensitivity and a broad range...Monitoring biophysical signals such as body or organ movements and other physical phenomena is necessary for patient rehabilitation.However,stretchable flexible pressure sensors with high sensitivity and a broad range that can meet these requirements are still lacking.Herein,we successfully monitored various vital biophysical features and implemented in-sensor dynamic deep learning for knee rehabilitation using an ultrabroad linear range and highsensitivity stretchable iontronic pressure sensor(SIPS).We optimized the topological structure and material composition of the electrode to build a fully stretching on-skin sensor.The high sensitivity(12.43 kPa^(−1)),ultrabroad linear sensing range(1 MPa),high pressure resolution(6.4 Pa),long-term durability(no decay after 12000 cycles),and excellent stretchability(up to 20%)allow the sensor to maintain operating stability,even in emergency cases with a high sudden impact force(near 1 MPa)applied to the sensor.As a practical demonstration,the SIPS can positively track biophysical signals such as pulse waves,muscle movements,and plantar pressure.Importantly,with the help of a neuro-inspired fully convolutional network algorithm,the SIPS can accurately predict knee joint postures for better rehabilitation after orthopedic surgery.Our SIPS has potential as a promising candidate for wearable electronics and artificial intelligent medical engineering owing to its unique high signal-to-noise ratio and ultrabroad linear range.展开更多
Regiodivergent asymmetric cycloadditions from the same set of starting materials offer interesting opportunities for rapid construction of optically active cyclic molecules with structural diversity.However,this remai...Regiodivergent asymmetric cycloadditions from the same set of starting materials offer interesting opportunities for rapid construction of optically active cyclic molecules with structural diversity.However,this remains a challenging task due to the difficulty of simultaneously controlling the regio-,diastereo-,and enantioselectivity in the ring formation processes.To address this long-standing problem.展开更多
Introduction:Multivariate time series prediction of infectious diseases is significant to public health,and the deep learning method has attracted increasing attention in this research field.Material and methods:An ad...Introduction:Multivariate time series prediction of infectious diseases is significant to public health,and the deep learning method has attracted increasing attention in this research field.Material and methods:An adaptively temporal graph convolution(ATGCN)model,which leams the contact patterns of multiple age groups in a graph-based approach,was proposed for COVID-19 and influenza prediction.We compared ATGCN with autoregressive models,deep sequence learning models,and experience-based ATGCN models in short-term and long-term prediction tasks.Results:Results showed that the ATGCN model performed better than the autoregressive models and the deep sequence learning models on two datasets in both short-term(12.5%and 10%improvements on RMSE)and longterm(12.4%and 5%improvements on RMSE)prediction tasks.And the RMSE of ATGCN predictions fluctuated least in different age groups of COVID-19(0.029±0.003)and influenza(0.059±0.008).Compared with the Ones-ATGCN model or the Pre-ATGCN model,the ATGCN model was more robust in performance,with RMSE of 0.0293 and 0.06 on two datasets when horizon is one.Discussion:Our research indicates a broad application prospect of deep learning in the field of infectious disease prediction.Transmission characteristics and domain knowledge of infectious diseases should be further applied to the design of deep learning models and feature selection.Conclusion:The ATGCN model addressed the multivariate time series forecasting in a graph-based deep learning approach and achieved robust prediction on the confirmed cases of multiple age groups,indicating its great potentials for exploring the implicit interactions of multivariate variables.展开更多
文摘The quantization algorithm compresses the original network by reducing the numerical bit width of the model,which improves the computation speed. Because different layers have different redundancy and sensitivity to databit width. Reducing the data bit width will result in a loss of accuracy. Therefore, it is difficult to determinethe optimal bit width for different parts of the network with guaranteed accuracy. Mixed precision quantizationcan effectively reduce the amount of computation while keeping the model accuracy basically unchanged. In thispaper, a hardware-aware mixed precision quantization strategy optimal assignment algorithm adapted to low bitwidth is proposed, and reinforcement learning is used to automatically predict the mixed precision that meets theconstraints of hardware resources. In the state-space design, the standard deviation of weights is used to measurethe distribution difference of data, the execution speed feedback of simulated neural network accelerator inferenceis used as the environment to limit the action space of the agent, and the accuracy of the quantization model afterretraining is used as the reward function to guide the agent to carry out deep reinforcement learning training. Theexperimental results show that the proposed method obtains a suitable model layer-by-layer quantization strategyunder the condition that the computational resources are satisfied, and themodel accuracy is effectively improved.The proposed method has strong intelligence and certain universality and has strong application potential in thefield of mixed precision quantization and embedded neural network model deployment.
基金support from National Natural Science Foundation of China(Nos.62274140,61904141,52173234)the State Key Laboratory of Mechanics and Control of Mechanical Structures(Nanjing University of Aeronautics and Astronautics)(Grant No.MCMS-E-0422G03)the Shenzhen-Hong Kong-Macao Technology Research Program(Type C,202011033000145,SGDX2020110309300301).
文摘To realize a hyperconnected smart society with high productivity,advances in flexible sensing technology are highly needed.Nowadays,flexible sensing technology has witnessed improvements in both the hardware performances of sensor devices and the data processing capabilities of the device’s software.Significant research efforts have been devoted to improving materials,sensing mechanism,and configurations of flexible sensing systems in a quest to fulfill the requirements of future technology.Meanwhile,advanced data analysis methods are being developed to extract useful information from increasingly complicated data collected by a single sensor or network of sensors.Machine learning(ML)as an important branch of artificial intelligence can efficiently handle such complex data,which can be multi-dimensional and multi-faceted,thus providing a powerful tool for easy interpretation of sensing data.In this review,the fundamental working mechanisms and common types of flexible mechanical sensors are firstly presented.Then how ML-assisted data interpretation improves the applications of flexible mechanical sensors and other closely-related sensors in various areas is elaborated,which includes health monitoring,human-machine interfaces,object/surface recognition,pressure prediction,and human posture/motion identification.Finally,the advantages,challenges,and future perspectives associated with the fusion of flexible mechanical sensing technology and ML algorithms are discussed.These will give significant insights to enable the advancement of next-generation artificial flexible mechanical sensing.
基金These authors would like to acknowledge the financial support of the project from the National Natural Science Foundation of China(No.61904141)the funding of Natural Science Foundation of Shaanxi Province(No.2020JQ-295)+4 种基金China Postdoctoral Science Foundation(2020M673340)the Fundamental Research Funds for the Central Universities(JB210407)the Key Research and Development Program of Shaanxi(Program No.2020GY-252No.2021GY-277)National Key Laboratory of Science and Technology on Vacuum Technology and Physics(HTKJ2019KL510007).
文摘Flexible pressure sensors are unprecedentedly studied on monitoring human physical activities and robotics.Simultaneously,improving the response sensitivity and sensing range of flexible pressure sensors is a great challenge,which hinders the devices’practical application.Targeting this obstacle,we developed a Ti_(3)C_(2)T_(x)-derived iontronic pressure sensor(TIPS)by taking the advantages of the high intercalation pseudocapacitance under high pressure and rationally designed structural configuration.TIPS achieved an ultrahigh sen-sitivity(S_(min)>200 kPa^(−1),S_(max)>45,000 kPa^(−1))in a broad sensing range of over 1.4 MPa and low limit of detection of 20 Pa as well as stable long-term working durability for 10,000 cycles.The practical application of TIPS in physical activity monitoring and flexible robot manifested its versatile potential.This study provides a demonstration for exploring pseudocapacitive materials for building flexible iontronic sensors with ultrahigh sensitivity and sensing range to advance the development of high-performance wearable electronics.
基金the financial support of the project from the National Natural Science Foundation of China(No.61904141)the funding of Natural Science Foundation of Shaanxi Province(No.2020JQ-295)+3 种基金the Key Research and Development Program of Shaanxi(Program No.2020GY-252)National Key Laboratory of Science and Technology on Vacuum Technology and Physics(HTKJ2019KL510007)City University of Hong Kong(Project Nos.7005070 and 9667153)Shenzhen Science and Technology Innovation Committee under the Grant JCYJ20170818103206501。
文摘Developing flexible sensors with high working performance holds intense interest for diverse applications in leveraging the Internet-of-things(IoT)infrastructures.For flexible piezoresistive sensors,traditionally most efforts are focused on tailoring the sensing materials to enhance the contact resistance variation for improving the sensitivity and working range,and it,however,remains challenging to simultaneously achieve flexible sensor with a linear working range over a high-pressure region(>100 kPa)and keep a reliable sensitivity.Herein,we devised a laserengraved silver-coated fabric as"soft"sensor electrode material to markedly advance the flexible sensor's linear working range to a level of 800 kPa with a high sensitivity of 6.4 kPa^-1 yet a fast response time of only 4 ms as well as long-time durability,which was rarely reported before.The integrated sensor successfully routed the wireless signal of pulse rate to the portable smartphone,further demonstrating its potential as a reliable electronic.Along with the rationally building the electrode instead of merely focusing on sensing materials capable of significantly improving the sensor's performance,we expect that this design concept and sensor system could potentially pave the way for developing more advanced wearable electronics in the future.
基金benefited from the support of the French government Investissements d’Avenir program ANR-11-LABX-0020-01partially supported by the National Natural Science Foundation of China(11571052,11401590,11731012 and 11671404)by Hunan Natural Science Foundation(2017JJ2271)
文摘We consider a branching random walk in an independent and identically distributed random environment ξ=(ξn) indexed by the time. Let W be the limit of the martingale Wn=∫e^-txZn(dx)/Eξ∫e^-txZn(dx), with Zn denoting the counting measure of particles of generation n, and Eξ the conditional expectation given the environment ξ. We find necessary and sufficient conditions for the existence of quenched moments and weighted moments of W, when W is non-degenerate.
文摘Nursing Human Resource Management is part of the human resources is nursing human resources by organizing nurses study, planning, training, and ultimately serve the medical career management stated objectives. Nursing human resource development of our human resources there are insufficient care, nurses configuration structure is irrational, the management system is not perfect, nurses are not high quality is the current status of nursing human resource mauagemenL and problems. This paper proposes a "human resource is the first resource" human resources management concept, has taken to develop a reasonable management mechanism, improve relevant laws and regulations of nursing human resources development, increase investment in education, strengthen education and training for nurses, the rational allocation of nursing human resources and other measures. In this paper, the connotation of Human Resources Management in the current situation as the starting point of care, from the current situation of nursing human resource development and the problems of the current situation of nursing human resource management and problems of nursing human resources management to discuss and propose appropriate for the development of human resource management solutions.
基金supported by the National Natural Science Foundation of China (61904141)the Funding of the Natural Science Foundation of Shaanxi Province (2020JQ-295)+2 种基金China Postdoctoral Science Foundation (2020M673340)the Key Research and Development Program of Shaanxi (2020GY-252)the National Key Laboratory of Science and Technology on Vacuum Technology and Physics (HTKJ2019KL510007)。
文摘Significant efforts have been devoted to enhancing the sensitivity and working range of flexible pressure sensors to improve the precise measurement of subtle variations in pressure over a wide detection spectrum. However,achieving sensitivities exceeding 1000 kPa^(-1) while maintaining a pressure working range over 100 kPa is still challenging because of the limited intrinsic properties of soft matrix materials. Here, we report a magnetic field-induced porous elastomer with micropillar arrays(MPAs) as sensing materials and a well-patterned nickel fabric as an electrode. The developed sensor exhibits an ultrahigh sensitivity of 10,268 kPa^(-1)(0.6–170 kPa) with a minimum detection pressure of 0.25 Pa and a fast response time of 3 ms because of the unique structure of the MPAs and the textured morphology of the electrode. The porous elastomer provides an extended working range of up to 500 kPa with long-time durability. The sophisticated sensor system coupled with an integrated wireless recharging system comprising a flexible supercapacitor and inductive coils for transmission achieves excellent performance. Thus, a diverse range of practical applications requiring a low-to-high pressure range sensing can be developed. Our strategy, which combines a microstructured high-performance sensor device with a wireless recharging system, provides a basis for creating next-generation flexible electronics.
基金The authors would like to acknowledge the financial support provided by the National Natural Science Foundation of China(No.61904141)the Natural Science Foundation of Shaanxi Province(No.2020JQ-295)+5 种基金the China Postdoctoral Science Foundation(2020M673340)the Fundamental Research Funds for the Central Universities(JB210407)the Key Research and Development Program of Shaanxi(Program No.2020GY-252 and No.2021GY277)the Shenzhen-Hong Kong-Macao Technology Research Program(Type C,SGDX2020110309300301)the Fundamental Research Funds for the Central Universitiesthe Innovation Fund of Xidian University.
文摘Monitoring biophysical signals such as body or organ movements and other physical phenomena is necessary for patient rehabilitation.However,stretchable flexible pressure sensors with high sensitivity and a broad range that can meet these requirements are still lacking.Herein,we successfully monitored various vital biophysical features and implemented in-sensor dynamic deep learning for knee rehabilitation using an ultrabroad linear range and highsensitivity stretchable iontronic pressure sensor(SIPS).We optimized the topological structure and material composition of the electrode to build a fully stretching on-skin sensor.The high sensitivity(12.43 kPa^(−1)),ultrabroad linear sensing range(1 MPa),high pressure resolution(6.4 Pa),long-term durability(no decay after 12000 cycles),and excellent stretchability(up to 20%)allow the sensor to maintain operating stability,even in emergency cases with a high sudden impact force(near 1 MPa)applied to the sensor.As a practical demonstration,the SIPS can positively track biophysical signals such as pulse waves,muscle movements,and plantar pressure.Importantly,with the help of a neuro-inspired fully convolutional network algorithm,the SIPS can accurately predict knee joint postures for better rehabilitation after orthopedic surgery.Our SIPS has potential as a promising candidate for wearable electronics and artificial intelligent medical engineering owing to its unique high signal-to-noise ratio and ultrabroad linear range.
基金from the National Natural Science Foundation of China(grant nos.22071209 and 22071206)the National Youth Talent Support Program,the Natural Science Foundation of Fujian Province of China(grant no.2017J06006)+1 种基金the Fundamental Research Funds for the Central Universities(grant no.20720190048)Basic Disciplines Training Program for Top-notch Students of the Ministry of Education.
文摘Regiodivergent asymmetric cycloadditions from the same set of starting materials offer interesting opportunities for rapid construction of optically active cyclic molecules with structural diversity.However,this remains a challenging task due to the difficulty of simultaneously controlling the regio-,diastereo-,and enantioselectivity in the ring formation processes.To address this long-standing problem.
基金This work was supported in part by grants from the National Natural Science Foundation of China(Grants No.72025404 and 71621002)Beijing Natural Science Foundation(Grant No.LI92012)Beijing Nova Program(Grant No.Z201100006820085).
文摘Introduction:Multivariate time series prediction of infectious diseases is significant to public health,and the deep learning method has attracted increasing attention in this research field.Material and methods:An adaptively temporal graph convolution(ATGCN)model,which leams the contact patterns of multiple age groups in a graph-based approach,was proposed for COVID-19 and influenza prediction.We compared ATGCN with autoregressive models,deep sequence learning models,and experience-based ATGCN models in short-term and long-term prediction tasks.Results:Results showed that the ATGCN model performed better than the autoregressive models and the deep sequence learning models on two datasets in both short-term(12.5%and 10%improvements on RMSE)and longterm(12.4%and 5%improvements on RMSE)prediction tasks.And the RMSE of ATGCN predictions fluctuated least in different age groups of COVID-19(0.029±0.003)and influenza(0.059±0.008).Compared with the Ones-ATGCN model or the Pre-ATGCN model,the ATGCN model was more robust in performance,with RMSE of 0.0293 and 0.06 on two datasets when horizon is one.Discussion:Our research indicates a broad application prospect of deep learning in the field of infectious disease prediction.Transmission characteristics and domain knowledge of infectious diseases should be further applied to the design of deep learning models and feature selection.Conclusion:The ATGCN model addressed the multivariate time series forecasting in a graph-based deep learning approach and achieved robust prediction on the confirmed cases of multiple age groups,indicating its great potentials for exploring the implicit interactions of multivariate variables.