Understanding the spatial interaction among residents,cooling service,and heat risk area in complex urban areas is conducive to developing targeted management.However,traditional urban thermal environment assessments ...Understanding the spatial interaction among residents,cooling service,and heat risk area in complex urban areas is conducive to developing targeted management.However,traditional urban thermal environment assessments typically relied on simple linear integration of associated indicators,often neglecting the spatial interaction effect.To explore the spatial interaction among the three elements,this study proposes an accessibility-based urban thermal environment assessment framework.Using Zhengzhou,a rapidly urbanizing city,as an example,remotely sensed images from three periods(2010,2015 and 2020)were applied to extract urban green space(UGS)and hot island area(HIA).An improved two-step floating catchment area(2SFCA)method and bivariate local Moran’s I were employed to explore whether residents’clustering locations are more likely to access cooling service or to be exposed to heat risk.The results demonstrate that the UGS in the city has been expanding,whereas the HIA shrank within the inner city in 2015 and then increased in 2020.Even though the urban thermal environment may have improved in the last decade,the spatial interaction among the residents,cooling service and heat risk area could be exacerbated.Spatial autocorrelation shows an increase in locations that are disadvantageous for resident congregation.Even when sufficient cooling services were provided,residents in these areas could still be exposed to high heat risk.The developed urban thermal environment framework provides a novel insight into the residents’heat risk exposure and cooling service accessibility,and the findings could assist urban planners in targeting the improvement of extra heat exposure risk locations.展开更多
Objective The study aimed to explore the association between the site of interictal epileptic discharges(IEDs)on postoperative electroencephalogram(EEG)and seizure recurrence after antiepileptic drug(AED)withdrawal.Th...Objective The study aimed to explore the association between the site of interictal epileptic discharges(IEDs)on postoperative electroencephalogram(EEG)and seizure recurrence after antiepileptic drug(AED)withdrawal.The study hypothesizes that the concordance of IED sites with surgical sites indicates incomplete resection of epileptic focus,while non-concordance of IED sites with surgical sites indicates postoperative changes or cortical stimulation.The former has a higher risk of seizure recurrence.Methods We retrospectively analyzed the postoperative EEG pattern of 182 consecutive children who underwent resection surgery.To identify the risk factors for seizure recurrence,we compared the attributes of seizure recurred and seizure-free groups by univariate and multivariate analyses.AED tapering was standardized,involving a 25% reduction in the dose of a single type of AED every 2 weeks,independent of the presurgical AED load.Results We attempted AED withdrawal in 116(63.7%)children.Twenty-eight(24.1%)children experienced seizure recurrence during or after AED withdrawal.A greater number of AEDs used at the time of surgery(p=0.005),incomplete resection(p=0.001),and presence of IED on postoperative EEG(p=0.011)are predictors of seizurerecurrence.Thecompletenessof resectionand seizure recurrence after AED withdrawal were related to the presence of IED on the EEG,but not to the concordance of IED with surgical sites.Conclusion For children with abnormal EEG,the decision to discontinue AED should be made more cautiously,regardless of the relative location of the discharge site and the surgical site.展开更多
Plant diseases threaten global food security by reducing crop yield;thus,diagnosing plant diseases is critical to agricultural production.Artificial intelligence technologies gradually replace traditional plant diseas...Plant diseases threaten global food security by reducing crop yield;thus,diagnosing plant diseases is critical to agricultural production.Artificial intelligence technologies gradually replace traditional plant disease diagnosis methods due to their time-consuming,costly,inefficient,and subjective disadvantages.As a mainstream AI method,deep learning has substantially improved plant disease detection and diagnosis for precision agriculture.In the meantime,most of the existing plant disease diagnosis methods usually adopt a pre-trained deep learning model to support diagnosing diseased leaves.However,the commonly used pre-trained models are from the computer vision dataset,not the botany dataset,which barely provides the pre-trained models sufficient domain knowledge about plant disease.Furthermore,this pre-trained way makes the final diagnosis model more difficult to distinguish between different plant diseases and lowers the diagnostic precision.To address this issue,we propose a series of commonly used pre-trained models based on plant disease images to promote the performance of disease diagnosis.In addition,we have experimented with the plant disease pre-trained model on plant disease diagnosis tasks such as plant disease identification,plant disease detection,plant disease segmentation,and other subtasks.The extended experiments prove that the plant disease pre-trained model can achieve higher accuracy than the existing pre-trained model with less training time,thereby supporting the better diagnosis of plant diseases.In addition,our pre-trained models will be open-sourced at https://pd.samlab.cn/and Zenodo platform https://doi.org/10.5281/zenodo.7856293.展开更多
Plant disease diagnosis in time can inhibit the spread of the disease and prevent a large-scale drop in production,which benefits food production.Object detection-based plant disease diagnosis methods have attracted w...Plant disease diagnosis in time can inhibit the spread of the disease and prevent a large-scale drop in production,which benefits food production.Object detection-based plant disease diagnosis methods have attracted widespread attention due to their accuracy in classifying and locating diseases.However,existing methods are still limited to single crop disease diagnosis.More importantly,the existing model has a large number of parameters,which is not conducive to deploying it to agricultural mobile devices.Nonetheless,reducing the number of model parameters tends to cause a decrease in model accuracy.To solve these problems,we propose a plant disease detection method based on knowledge distillation to achieve a lightweight and efficient diagnosis of multiple diseases across multiple crops.In detail,we design 2 strategies to build 4 different lightweight models as student models:the YOLOR-Light-v1,YOLOR-Light-v2,Mobile-YOLOR-v1,and Mobile-YOLOR-v2 models,and adopt the YOLOR model as the teacher model.We develop a multistage knowledge distillation method to improve lightweight model performance,achieving 60.4%mAP@.5 in the PlantDoc dataset with small model parameters,outperforming existing methods.Overall,the multistage knowledge distillation technique can make the model lighter while maintaining high accuracy.Not only that,the technique can be extended to other tasks,such as image classification and image segmentation,to obtain automated plant disease diagnostic models with a wider range of lightweight applicability in smart agriculture.Our code is available at https://github.com/QDH/MSKD.展开更多
To improve the accuracy of typhoon prediction,it is necessary to detect the internal structure of a typhoon.The motion model of a floating weather sensing node becomes the key to affect the channel frequency expansion...To improve the accuracy of typhoon prediction,it is necessary to detect the internal structure of a typhoon.The motion model of a floating weather sensing node becomes the key to affect the channel frequency expansion performance and communication quality.This study proposes a floating weather sensing node motion modeling method based on the chaotic mapping.After the chaotic attractor is obtained by simulation,the position trajectory of the floating weather sensing node is obtained by space and coordinate conversion,and the three-dimensional velocity of each point on the position trajectory is obtained by multidimensional linear interpolation.On this basis,the established motion model is used to study the Doppler frequency shift,which is based on the software and physical platform.The software simulates the relative motion of the transceiver and calculates the Doppler frequency shift.The physical platform can add the Doppler frequency shift to the actual transmitted signal.The results show that this method can effectively reflect the influence of the floating weather sensing node motion on signal transmission.It is helpful to research the characteristics of the communication link and the design of a signal transceiver for typhoon detection to further improve the communication quality and to obtain more accurate interior structure characteristic data of a typhoon.展开更多
通过全基因组关联分析(genome-wide association study,GWAS)探索中国汉族人群疼痛诱发脑岛神经响应个体差异背后的遗传影响因素.研究共纳入333名经质控合格且同时采集了基因和脑影像数据的中国汉族健康被试,基因型数据经质控插补后包含...通过全基因组关联分析(genome-wide association study,GWAS)探索中国汉族人群疼痛诱发脑岛神经响应个体差异背后的遗传影响因素.研究共纳入333名经质控合格且同时采集了基因和脑影像数据的中国汉族健康被试,基因型数据经质控插补后包含5270947个单核苷酸多态性(single nucleotide polymorphism,SNP)位点,脑影像数据为痛觉刺激任务态功能磁共振成像(functional magnetic resonance imaging,fMRI)数据.首先基于f MRI数据利用一般线性模型(general linear model,GLM)获得痛觉刺激条件下每位被试左侧和右侧脑岛区域各自的平均激活值以及双侧脑岛的平均激活值,并将其作为GWAS表型数据分别对5270947个SNP逐一计算脑岛激活与SNP之间的关联.结果显示,在P<5×10^(-6)阈值下,10个独立SNP位点与左侧脑岛的激活水平存在显著关联,7个独立SNP位点与右侧脑岛的激活水平存在显著关联,12个独立SNP位点与双侧脑岛的平均激活水平存在显著关联.所有显著位点可注释到9个基因上,其中BACE1基因已被报道与疼痛相关,其他基因与脑影像表型或常见神经精神疾病相关.这些发现为深入理解疼痛诱发脑岛神经响应个体差异背后的遗传机制提供了有力证据.展开更多
基金funded by the Major Project of the National Social Science Foundation of China(Grant No.19ZDA088)the National Natural Science Foundation of China Projects(Grant No.72204101).
文摘Understanding the spatial interaction among residents,cooling service,and heat risk area in complex urban areas is conducive to developing targeted management.However,traditional urban thermal environment assessments typically relied on simple linear integration of associated indicators,often neglecting the spatial interaction effect.To explore the spatial interaction among the three elements,this study proposes an accessibility-based urban thermal environment assessment framework.Using Zhengzhou,a rapidly urbanizing city,as an example,remotely sensed images from three periods(2010,2015 and 2020)were applied to extract urban green space(UGS)and hot island area(HIA).An improved two-step floating catchment area(2SFCA)method and bivariate local Moran’s I were employed to explore whether residents’clustering locations are more likely to access cooling service or to be exposed to heat risk.The results demonstrate that the UGS in the city has been expanding,whereas the HIA shrank within the inner city in 2015 and then increased in 2020.Even though the urban thermal environment may have improved in the last decade,the spatial interaction among the residents,cooling service and heat risk area could be exacerbated.Spatial autocorrelation shows an increase in locations that are disadvantageous for resident congregation.Even when sufficient cooling services were provided,residents in these areas could still be exposed to high heat risk.The developed urban thermal environment framework provides a novel insight into the residents’heat risk exposure and cooling service accessibility,and the findings could assist urban planners in targeting the improvement of extra heat exposure risk locations.
基金Supported by the National Natural Science Foundation of China(grant no:81971217).
文摘Objective The study aimed to explore the association between the site of interictal epileptic discharges(IEDs)on postoperative electroencephalogram(EEG)and seizure recurrence after antiepileptic drug(AED)withdrawal.The study hypothesizes that the concordance of IED sites with surgical sites indicates incomplete resection of epileptic focus,while non-concordance of IED sites with surgical sites indicates postoperative changes or cortical stimulation.The former has a higher risk of seizure recurrence.Methods We retrospectively analyzed the postoperative EEG pattern of 182 consecutive children who underwent resection surgery.To identify the risk factors for seizure recurrence,we compared the attributes of seizure recurred and seizure-free groups by univariate and multivariate analyses.AED tapering was standardized,involving a 25% reduction in the dose of a single type of AED every 2 weeks,independent of the presurgical AED load.Results We attempted AED withdrawal in 116(63.7%)children.Twenty-eight(24.1%)children experienced seizure recurrence during or after AED withdrawal.A greater number of AEDs used at the time of surgery(p=0.005),incomplete resection(p=0.001),and presence of IED on postoperative EEG(p=0.011)are predictors of seizurerecurrence.Thecompletenessof resectionand seizure recurrence after AED withdrawal were related to the presence of IED on the EEG,but not to the concordance of IED with surgical sites.Conclusion For children with abnormal EEG,the decision to discontinue AED should be made more cautiously,regardless of the relative location of the discharge site and the surgical site.
基金supported by the National Natural Science Foundation of China(Nos.62162008,62006046,32125033,and 31960548)the National Key R&D Program of China(2020YFB1713300 and 2021YFD1700102)+5 种基金the Innovation and Entrepreneurship Project for Overseas Educated Talents in Guizhou Province(2022)-04the Guizhou Province Graduate Research Fund(YJSKYJJ(2021)060)the Guizhou Provincial Science and Technology Projects(ZK[2022]-108)the Guizhou University Cultivation Project(No.2021-55)the Natural Science Special Research Fund of Guizhou University(No.2021-24)the Program of Introducing Talents of Discipline to Universities of China(111 Program,D20023).
文摘Plant diseases threaten global food security by reducing crop yield;thus,diagnosing plant diseases is critical to agricultural production.Artificial intelligence technologies gradually replace traditional plant disease diagnosis methods due to their time-consuming,costly,inefficient,and subjective disadvantages.As a mainstream AI method,deep learning has substantially improved plant disease detection and diagnosis for precision agriculture.In the meantime,most of the existing plant disease diagnosis methods usually adopt a pre-trained deep learning model to support diagnosing diseased leaves.However,the commonly used pre-trained models are from the computer vision dataset,not the botany dataset,which barely provides the pre-trained models sufficient domain knowledge about plant disease.Furthermore,this pre-trained way makes the final diagnosis model more difficult to distinguish between different plant diseases and lowers the diagnostic precision.To address this issue,we propose a series of commonly used pre-trained models based on plant disease images to promote the performance of disease diagnosis.In addition,we have experimented with the plant disease pre-trained model on plant disease diagnosis tasks such as plant disease identification,plant disease detection,plant disease segmentation,and other subtasks.The extended experiments prove that the plant disease pre-trained model can achieve higher accuracy than the existing pre-trained model with less training time,thereby supporting the better diagnosis of plant diseases.In addition,our pre-trained models will be open-sourced at https://pd.samlab.cn/and Zenodo platform https://doi.org/10.5281/zenodo.7856293.
基金supported by the National Natural Science Foundation of China(Nos.62162008,62006046,32125033,and 31960548)Innovation and Entrepreneurship Project for Overseas Educated Talents in Guizhou Province[(2022)-04]+3 种基金Guizhou Provincial Science and Technology Projects(ZK[2022]-108)Natural Science Special Research Fund of Guizhou University(No.2021-24)Guizhou University Cultivation Project(No.2021-55)Program of Introducing Talents of Discipline to Universities of China(111 Program,D20023).
文摘Plant disease diagnosis in time can inhibit the spread of the disease and prevent a large-scale drop in production,which benefits food production.Object detection-based plant disease diagnosis methods have attracted widespread attention due to their accuracy in classifying and locating diseases.However,existing methods are still limited to single crop disease diagnosis.More importantly,the existing model has a large number of parameters,which is not conducive to deploying it to agricultural mobile devices.Nonetheless,reducing the number of model parameters tends to cause a decrease in model accuracy.To solve these problems,we propose a plant disease detection method based on knowledge distillation to achieve a lightweight and efficient diagnosis of multiple diseases across multiple crops.In detail,we design 2 strategies to build 4 different lightweight models as student models:the YOLOR-Light-v1,YOLOR-Light-v2,Mobile-YOLOR-v1,and Mobile-YOLOR-v2 models,and adopt the YOLOR model as the teacher model.We develop a multistage knowledge distillation method to improve lightweight model performance,achieving 60.4%mAP@.5 in the PlantDoc dataset with small model parameters,outperforming existing methods.Overall,the multistage knowledge distillation technique can make the model lighter while maintaining high accuracy.Not only that,the technique can be extended to other tasks,such as image classification and image segmentation,to obtain automated plant disease diagnostic models with a wider range of lightweight applicability in smart agriculture.Our code is available at https://github.com/QDH/MSKD.
基金This work was supported in part by the National Natural Science Foundation of China(No.61827901).
文摘To improve the accuracy of typhoon prediction,it is necessary to detect the internal structure of a typhoon.The motion model of a floating weather sensing node becomes the key to affect the channel frequency expansion performance and communication quality.This study proposes a floating weather sensing node motion modeling method based on the chaotic mapping.After the chaotic attractor is obtained by simulation,the position trajectory of the floating weather sensing node is obtained by space and coordinate conversion,and the three-dimensional velocity of each point on the position trajectory is obtained by multidimensional linear interpolation.On this basis,the established motion model is used to study the Doppler frequency shift,which is based on the software and physical platform.The software simulates the relative motion of the transceiver and calculates the Doppler frequency shift.The physical platform can add the Doppler frequency shift to the actual transmitted signal.The results show that this method can effectively reflect the influence of the floating weather sensing node motion on signal transmission.It is helpful to research the characteristics of the communication link and the design of a signal transceiver for typhoon detection to further improve the communication quality and to obtain more accurate interior structure characteristic data of a typhoon.
文摘通过全基因组关联分析(genome-wide association study,GWAS)探索中国汉族人群疼痛诱发脑岛神经响应个体差异背后的遗传影响因素.研究共纳入333名经质控合格且同时采集了基因和脑影像数据的中国汉族健康被试,基因型数据经质控插补后包含5270947个单核苷酸多态性(single nucleotide polymorphism,SNP)位点,脑影像数据为痛觉刺激任务态功能磁共振成像(functional magnetic resonance imaging,fMRI)数据.首先基于f MRI数据利用一般线性模型(general linear model,GLM)获得痛觉刺激条件下每位被试左侧和右侧脑岛区域各自的平均激活值以及双侧脑岛的平均激活值,并将其作为GWAS表型数据分别对5270947个SNP逐一计算脑岛激活与SNP之间的关联.结果显示,在P<5×10^(-6)阈值下,10个独立SNP位点与左侧脑岛的激活水平存在显著关联,7个独立SNP位点与右侧脑岛的激活水平存在显著关联,12个独立SNP位点与双侧脑岛的平均激活水平存在显著关联.所有显著位点可注释到9个基因上,其中BACE1基因已被报道与疼痛相关,其他基因与脑影像表型或常见神经精神疾病相关.这些发现为深入理解疼痛诱发脑岛神经响应个体差异背后的遗传机制提供了有力证据.
