With the widespread use of social media,the propagation of health-related rumors has become a significant public health threat.Existing methods for detecting health rumors predominantly rely on external knowledge or p...With the widespread use of social media,the propagation of health-related rumors has become a significant public health threat.Existing methods for detecting health rumors predominantly rely on external knowledge or propagation structures,with only a few recent approaches attempting causal inference;however,these have not yet effectively integrated causal discovery with domain-specific knowledge graphs for detecting health rumors.In this study,we found that the combined use of causal discovery and domain-specific knowledge graphs can effectively identify implicit pseudo-causal logic embedded within texts,holding significant potential for health rumor detection.To this end,we propose CKDG—a dual-graph fusion framework based on causal logic and medical knowledge graphs.CKDG constructs a weighted causal graph to capture the implicit causal relationships in the text and introduces a medical knowledge graph to verify semantic consistency,thereby enhancing the ability to identify the misuse of professional terminology and pseudoscientific claims.In experiments conducted on a dataset comprising 8430 health rumors,CKDG achieved an accuracy of 91.28%and an F1 score of 90.38%,representing improvements of 5.11%and 3.29%over the best baseline,respectively.Our results indicate that the integrated use of causal discovery and domainspecific knowledge graphs offers significant advantages for health rumor detection systems.This method not only improves detection performance but also enhances the transparency and credibility of model decisions by tracing causal chains and sources of knowledge conflicts.We anticipate that this work will provide key technological support for the development of trustworthy health-information filtering systems,thereby improving the reliability of public health information on social media.展开更多
This research focuses on solving the fault detection and health monitoring of high-power thyristor converter.In terms of the critical role of thyristor converter in nuclear fusion system,a method based on long short-t...This research focuses on solving the fault detection and health monitoring of high-power thyristor converter.In terms of the critical role of thyristor converter in nuclear fusion system,a method based on long short-term memory(LSTM)neural network model is proposed to monitor the operational state of the converter and accurately detect faults as they occur.By sampling and processing a large number of thyristor converter operation data,the LSTM model is trained to identify and detect abnormal state,and the power supply health status is monitored.Compared with traditional methods,LSTM model shows higher accuracy and abnormal state detection ability.The experimental results show that this method can effectively improve the reliability and safety of the thyristor converter,and provide a strong guarantee for the stable operation of the nuclear fusion reactor.展开更多
Monitoring minuscule mechanical signals,both in magnitude and direction,is imperative in many application scenarios,e.g.,structural health monitoring and robotic sensing systems.However,the piezoelectric sensor strugg...Monitoring minuscule mechanical signals,both in magnitude and direction,is imperative in many application scenarios,e.g.,structural health monitoring and robotic sensing systems.However,the piezoelectric sensor struggles to satisfy the requirements for directional recognition due to the limited piezoelectric coefficient matrix,and achieving sensitivity for detecting micrometer-scale deformations is also challenging.Herein,we develop a vector sensor composed of lead zirconate titanate-electronic grade glass fiber composite filaments with oriented arrangement,capable of detecting minute anisotropic deformations.The as-prepared vector sensor can identify the deformation directions even when subjected to an unprecedented nominal strain of 0.06%,thereby enabling its utility in accurately discerning the 5μm-height wrinkles in thin films and in monitoring human pulse waves.The ultra-high sensitivity is attributed to the formation of porous ferroelectret and the efficient load transfer efficiency of continuous lead zirconate titanate phase.Additionally,when integrated with machine learning techniques,the sensor’s capability to recognize multi-signals enables it to differentiate between 10 types of fine textures with 100%accuracy.The structural design in piezoelectric devices enables a more comprehensive perception of mechanical stimuli,offering a novel perspective for enhancing recognition accuracy.展开更多
Soil Plant Analysis Development(SPAD)Chlorophyll Meter reading was used to effectively characterize chlorophyll content,which is an important indicator of the health status of plant leaves.In this study,the hyperspect...Soil Plant Analysis Development(SPAD)Chlorophyll Meter reading was used to effectively characterize chlorophyll content,which is an important indicator of the health status of plant leaves.In this study,the hyperspectral images of apple leaves infected by apple mosaic virus(ApMV)were captured,and their SPAD values were measured.The spectral reflectance of leaves with varying degree infection of disease is significantly different.In particular,the reflectance in visible wavebands of leaves with a more serious infection was higher than that of leaves with a less severe infection.Several hyperspectral vegetation indices were highly correlated with the SPAD values of apple leaves(correlation coefficient>0.9).Models were established to estimate apple foliar SPAD values based on these vegetation indices.Among the models,the multivariate regression model with partial least square regression(PLSR)method achieved the highest accuracy.The SPAD value of a whole apple leaf was calculated from its SPAD distribution image and used as a quantitative index to represent the health status of an apple leaf.Furthermore,the SPAD value of a whole apple leaf could also be estimated rapidly and accurately by extracting the spectral average value of the whole leaf using a simple model.It can be used as a rapid detection method of SPAD values of apple leaves to monitor and describe the health conditions of apple leaves quantitatively.展开更多
基金funded by the Hunan Provincial Natural Science Foundation of China(Grant No.2025JJ70105)the Hunan Provincial College Students’Innovation and Entrepreneurship Training Program(Project No.S202411342056)The article processing charge(APC)was funded by the Project No.2025JJ70105.
文摘With the widespread use of social media,the propagation of health-related rumors has become a significant public health threat.Existing methods for detecting health rumors predominantly rely on external knowledge or propagation structures,with only a few recent approaches attempting causal inference;however,these have not yet effectively integrated causal discovery with domain-specific knowledge graphs for detecting health rumors.In this study,we found that the combined use of causal discovery and domain-specific knowledge graphs can effectively identify implicit pseudo-causal logic embedded within texts,holding significant potential for health rumor detection.To this end,we propose CKDG—a dual-graph fusion framework based on causal logic and medical knowledge graphs.CKDG constructs a weighted causal graph to capture the implicit causal relationships in the text and introduces a medical knowledge graph to verify semantic consistency,thereby enhancing the ability to identify the misuse of professional terminology and pseudoscientific claims.In experiments conducted on a dataset comprising 8430 health rumors,CKDG achieved an accuracy of 91.28%and an F1 score of 90.38%,representing improvements of 5.11%and 3.29%over the best baseline,respectively.Our results indicate that the integrated use of causal discovery and domainspecific knowledge graphs offers significant advantages for health rumor detection systems.This method not only improves detection performance but also enhances the transparency and credibility of model decisions by tracing causal chains and sources of knowledge conflicts.We anticipate that this work will provide key technological support for the development of trustworthy health-information filtering systems,thereby improving the reliability of public health information on social media.
基金supported by the Open Fund of Magnetic Confinement Fusion Laboratory of Anhui Province(No.2024AMF04003)the Natural Science Foundation of Anhui Province(No.228085ME142)Comprehensive Research Facility for Fusion Technology(No.20180000527301001228)。
文摘This research focuses on solving the fault detection and health monitoring of high-power thyristor converter.In terms of the critical role of thyristor converter in nuclear fusion system,a method based on long short-term memory(LSTM)neural network model is proposed to monitor the operational state of the converter and accurately detect faults as they occur.By sampling and processing a large number of thyristor converter operation data,the LSTM model is trained to identify and detect abnormal state,and the power supply health status is monitored.Compared with traditional methods,LSTM model shows higher accuracy and abnormal state detection ability.The experimental results show that this method can effectively improve the reliability and safety of the thyristor converter,and provide a strong guarantee for the stable operation of the nuclear fusion reactor.
基金financially supported by the National Key Research and Development Program of China(No.2022YFA1205300 and No.2022YFA1205304)the Oceanic Interdisciplinary Program of Shanghai Jiao Tong University(SL2022ZD103).
文摘Monitoring minuscule mechanical signals,both in magnitude and direction,is imperative in many application scenarios,e.g.,structural health monitoring and robotic sensing systems.However,the piezoelectric sensor struggles to satisfy the requirements for directional recognition due to the limited piezoelectric coefficient matrix,and achieving sensitivity for detecting micrometer-scale deformations is also challenging.Herein,we develop a vector sensor composed of lead zirconate titanate-electronic grade glass fiber composite filaments with oriented arrangement,capable of detecting minute anisotropic deformations.The as-prepared vector sensor can identify the deformation directions even when subjected to an unprecedented nominal strain of 0.06%,thereby enabling its utility in accurately discerning the 5μm-height wrinkles in thin films and in monitoring human pulse waves.The ultra-high sensitivity is attributed to the formation of porous ferroelectret and the efficient load transfer efficiency of continuous lead zirconate titanate phase.Additionally,when integrated with machine learning techniques,the sensor’s capability to recognize multi-signals enables it to differentiate between 10 types of fine textures with 100%accuracy.The structural design in piezoelectric devices enables a more comprehensive perception of mechanical stimuli,offering a novel perspective for enhancing recognition accuracy.
基金This work was supported by the National High Technology Research and Development Program of China(Grant No.2013AA102401)the Growth plan for young talents in Shanghai municipal agricultural system(Hu Nong Qing Zi(2018)No.1-29).
文摘Soil Plant Analysis Development(SPAD)Chlorophyll Meter reading was used to effectively characterize chlorophyll content,which is an important indicator of the health status of plant leaves.In this study,the hyperspectral images of apple leaves infected by apple mosaic virus(ApMV)were captured,and their SPAD values were measured.The spectral reflectance of leaves with varying degree infection of disease is significantly different.In particular,the reflectance in visible wavebands of leaves with a more serious infection was higher than that of leaves with a less severe infection.Several hyperspectral vegetation indices were highly correlated with the SPAD values of apple leaves(correlation coefficient>0.9).Models were established to estimate apple foliar SPAD values based on these vegetation indices.Among the models,the multivariate regression model with partial least square regression(PLSR)method achieved the highest accuracy.The SPAD value of a whole apple leaf was calculated from its SPAD distribution image and used as a quantitative index to represent the health status of an apple leaf.Furthermore,the SPAD value of a whole apple leaf could also be estimated rapidly and accurately by extracting the spectral average value of the whole leaf using a simple model.It can be used as a rapid detection method of SPAD values of apple leaves to monitor and describe the health conditions of apple leaves quantitatively.
