Since China’s reform and opening up in 1978,the acceleration of industrialization and urbanization in China had led to dramatic changes in the pattern of urban-rural land use.In this paper,we focused on the rural ind...Since China’s reform and opening up in 1978,the acceleration of industrialization and urbanization in China had led to dramatic changes in the pattern of urban-rural land use.In this paper,we focused on the rural industrialized areas in central China(Xinxiang County and Changyuan City of Henan Province).We used the average nearest neighbor index,spatial statistical analysis,and a structural equation model to analyze the spatiotemporal evolution and influencing factors of urban-rural construction land based on multisource spatial data and survey data.The results showed that:1)from 1975 to 2019,the spatial distribution of urban-rural construction land in rural industrialized areas had evolved from homogeneous distribution to local agglomeration.In terms of comparative analysis of cases,the spatial distribution of urban-rural construction land in Changyuan City had shown a trend from diffusion to agglomeration,and Xinxiang County had overall shown a spatial change from homogenization to agglomeration and then to regional integration development.2)The hot spots with increased urban-rural construction land significantly expanded,and they had a high degree of spatial overlap with industrial development.Among them,Xinxiang County was concentrated in central and marginal areas,and Changyuan was mainly concentrated in central urban areas.3)From the evolution of spatial proximity of urban-rural construction land,rural industrialized areas generally decline,showing the characteristics of internal differentiation in the rate of change.4)Industrial development,social economy,the policy environment,and urban development played a positive role in promoting the expansion of urban-rural construction land in rural industrialized areas.To promote the optimal use of regional land and the integrated development of urban-rural areas,we should combine the advantages of regional endowment,formulate development strategies according to local conditions,and adjust the way that land is used in a timely manner.展开更多
目的:分析复发与初发睑板腺囊肿患者的睑板腺组织形态学改变在活体共聚焦显微镜(in v ivo confocal microscope,IVCM)下的表现及特点。方法:采用横断面研究方法,选取2018年10月至2019年4月在汕头大学·香港中文大学联合汕头国际眼...目的:分析复发与初发睑板腺囊肿患者的睑板腺组织形态学改变在活体共聚焦显微镜(in v ivo confocal microscope,IVCM)下的表现及特点。方法:采用横断面研究方法,选取2018年10月至2019年4月在汕头大学·香港中文大学联合汕头国际眼科中心门诊就诊的10例复发性睑板腺囊肿患者、10例初发性睑板腺囊肿以及10例对照组作为观察对象。所有对象行眼科常规检查及IVCM检查。IVCM检测指标包括睑板腺开口面积、开口最短径、开口最长径、睑板腺开口附近腺管形态、睑板腺腺泡样结构形态,分析比较三组的计量指标。结果:复发性睑板腺囊肿组睑板腺开口短径(109.08±49.96)μm,开口长径(144.95±68.10)μm,开口面积为11621.62(3976.49~24828.82)μm^(2);初发性睑板腺囊肿组睑板腺开口短径(101.53±29.55)μm,开口长径(130.08±45.21)μm,开口面积10615.07(5813.29~18275.44)μm^(2);对照组睑板腺开口短径(44.14±14.37)μm,开口长径(55.98±13.46)μm,开口面积2233.29(1437.72~2945.65)μm^(2)。与对照组相比,复发性、初发性睑板腺囊肿组睑板腺开口短径、开口长径及开口面积均明显扩大,差异有统计学意义(P<0.05);复发与初发睑板腺囊肿组之间差异不具有统计学意义(P>0.05)。复发性睑板腺囊肿组睑板腺腺管扩张,周边腺泡样结构纤维组织增生,伴有炎症细胞浸润。初发性睑板腺囊肿组睑板腺腺管扩张,周边腺泡样结构未见明显纤维组织增生。结论:IVCM可在活体下观察睑板腺囊肿患者睑板腺形态学上的微观改变,复发性睑板腺囊肿睑板腺腺泡样结构形态与初发性睑板腺囊肿表现有差异。展开更多
随着互联网的快速发展,网络安全越来越受到人们的重视。传统的异常流量检测模型虽然具有较好的识别率,但需要大量有标记的数据进行训练。因此,基于无监督学习的网络异常流量检测方法被广泛采用。近年来,随着深度学习算法在异常检测中的...随着互联网的快速发展,网络安全越来越受到人们的重视。传统的异常流量检测模型虽然具有较好的识别率,但需要大量有标记的数据进行训练。因此,基于无监督学习的网络异常流量检测方法被广泛采用。近年来,随着深度学习算法在异常检测中的运用,无监督深度学习模型也不同程度地提升了检测算法的性能。然而,无监督深度学习方法往往无法避免异常检测阈值选择的问题。因此,针对现有数据标记困难和阈值选择的问题,文中提出了一种基于代价敏感度改进的K近邻算法结合阈值选择方法的异常流量检测系统。该系统不但可以准确识别恶意流量,也无需有标记数据集,极大减少了人工标注数据的工作量。实验使用UNSW-NB15、NSL-KDD和CICIDS2017数据集来验证模型的适用性,并分别与经典的机器学习算法One Class SVM以及深度学习方法AutoEncoder进行了对比。实验结果表明,在3类数据集上,与深度学习算法和传统的无监督机器学习算法相比,该算法有效提升了网络异常流量检测的性能。展开更多
With the rapid development of the Internet,network security and data privacy are increasingly valued.Although classical Network Intrusion Detection System(NIDS)based on Deep Learning(DL)models can provide good detecti...With the rapid development of the Internet,network security and data privacy are increasingly valued.Although classical Network Intrusion Detection System(NIDS)based on Deep Learning(DL)models can provide good detection accuracy,but collecting samples for centralized training brings the huge risk of data privacy leakage.Furthermore,the training of supervised deep learning models requires a large number of labeled samples,which is usually cumbersome.The“black-box”problem also makes the DL models of NIDS untrustworthy.In this paper,we propose a trusted Federated Learning(FL)Traffic IDS method called FL-TIDS to address the above-mentioned problems.In FL-TIDS,we design an unsupervised intrusion detection model based on autoencoders that alleviates the reliance on marked samples.At the same time,we use FL for model training to protect data privacy.In addition,we design an improved SHAP interpretable method based on chi-square test to perform interpretable analysis of the trained model.We conducted several experiments to evaluate the proposed FL-TIDS.We first determine experimentally the structure and the number of neurons of the unsupervised AE model.Secondly,we evaluated the proposed method using the UNSW-NB15 and CICIDS2017 datasets.The exper-imental results show that the unsupervised AE model has better performance than the other 7 intrusion detection models in terms of precision,recall and f1-score.Then,federated learning is used to train the intrusion detection model.The experimental results indicate that the model is more accurate than the local learning model.Finally,we use an improved SHAP explainability method based on Chi-square test to analyze the explainability.The analysis results show that the identification characteristics of the model are consistent with the attack characteristics,and the model is reliable.展开更多
基金Under the auspices of National Natural Science Foundation of China(No.42271225)Research Program Fund for Humanities and Social Sciences of the Ministry of Education of China(No.22YJA790050)+2 种基金Henan Provincial Planning Fund for Philosophy and Social Sciences(No.2022BJJ011)Postgraduate Cultivating Innovation Action Plan of Henan University(No.SYLYC2022014)Henan University of Economics and Law Huang Tingfang/Xinhe Young Scholars Program(No.13)。
文摘Since China’s reform and opening up in 1978,the acceleration of industrialization and urbanization in China had led to dramatic changes in the pattern of urban-rural land use.In this paper,we focused on the rural industrialized areas in central China(Xinxiang County and Changyuan City of Henan Province).We used the average nearest neighbor index,spatial statistical analysis,and a structural equation model to analyze the spatiotemporal evolution and influencing factors of urban-rural construction land based on multisource spatial data and survey data.The results showed that:1)from 1975 to 2019,the spatial distribution of urban-rural construction land in rural industrialized areas had evolved from homogeneous distribution to local agglomeration.In terms of comparative analysis of cases,the spatial distribution of urban-rural construction land in Changyuan City had shown a trend from diffusion to agglomeration,and Xinxiang County had overall shown a spatial change from homogenization to agglomeration and then to regional integration development.2)The hot spots with increased urban-rural construction land significantly expanded,and they had a high degree of spatial overlap with industrial development.Among them,Xinxiang County was concentrated in central and marginal areas,and Changyuan was mainly concentrated in central urban areas.3)From the evolution of spatial proximity of urban-rural construction land,rural industrialized areas generally decline,showing the characteristics of internal differentiation in the rate of change.4)Industrial development,social economy,the policy environment,and urban development played a positive role in promoting the expansion of urban-rural construction land in rural industrialized areas.To promote the optimal use of regional land and the integrated development of urban-rural areas,we should combine the advantages of regional endowment,formulate development strategies according to local conditions,and adjust the way that land is used in a timely manner.
文摘目的:分析复发与初发睑板腺囊肿患者的睑板腺组织形态学改变在活体共聚焦显微镜(in v ivo confocal microscope,IVCM)下的表现及特点。方法:采用横断面研究方法,选取2018年10月至2019年4月在汕头大学·香港中文大学联合汕头国际眼科中心门诊就诊的10例复发性睑板腺囊肿患者、10例初发性睑板腺囊肿以及10例对照组作为观察对象。所有对象行眼科常规检查及IVCM检查。IVCM检测指标包括睑板腺开口面积、开口最短径、开口最长径、睑板腺开口附近腺管形态、睑板腺腺泡样结构形态,分析比较三组的计量指标。结果:复发性睑板腺囊肿组睑板腺开口短径(109.08±49.96)μm,开口长径(144.95±68.10)μm,开口面积为11621.62(3976.49~24828.82)μm^(2);初发性睑板腺囊肿组睑板腺开口短径(101.53±29.55)μm,开口长径(130.08±45.21)μm,开口面积10615.07(5813.29~18275.44)μm^(2);对照组睑板腺开口短径(44.14±14.37)μm,开口长径(55.98±13.46)μm,开口面积2233.29(1437.72~2945.65)μm^(2)。与对照组相比,复发性、初发性睑板腺囊肿组睑板腺开口短径、开口长径及开口面积均明显扩大,差异有统计学意义(P<0.05);复发与初发睑板腺囊肿组之间差异不具有统计学意义(P>0.05)。复发性睑板腺囊肿组睑板腺腺管扩张,周边腺泡样结构纤维组织增生,伴有炎症细胞浸润。初发性睑板腺囊肿组睑板腺腺管扩张,周边腺泡样结构未见明显纤维组织增生。结论:IVCM可在活体下观察睑板腺囊肿患者睑板腺形态学上的微观改变,复发性睑板腺囊肿睑板腺腺泡样结构形态与初发性睑板腺囊肿表现有差异。
文摘随着互联网的快速发展,网络安全越来越受到人们的重视。传统的异常流量检测模型虽然具有较好的识别率,但需要大量有标记的数据进行训练。因此,基于无监督学习的网络异常流量检测方法被广泛采用。近年来,随着深度学习算法在异常检测中的运用,无监督深度学习模型也不同程度地提升了检测算法的性能。然而,无监督深度学习方法往往无法避免异常检测阈值选择的问题。因此,针对现有数据标记困难和阈值选择的问题,文中提出了一种基于代价敏感度改进的K近邻算法结合阈值选择方法的异常流量检测系统。该系统不但可以准确识别恶意流量,也无需有标记数据集,极大减少了人工标注数据的工作量。实验使用UNSW-NB15、NSL-KDD和CICIDS2017数据集来验证模型的适用性,并分别与经典的机器学习算法One Class SVM以及深度学习方法AutoEncoder进行了对比。实验结果表明,在3类数据集上,与深度学习算法和传统的无监督机器学习算法相比,该算法有效提升了网络异常流量检测的性能。
基金supported by National Natural Science Fundation of China under Grant 61972208National Natural Science Fundation(General Program)of China under Grant 61972211+2 种基金National Key Research and Development Project of China under Grant 2020YFB1804700Future Network Innovation Research and Application Projects under Grant No.2021FNA020062021 Jiangsu Postgraduate Research Innovation Plan under Grant No.KYCX210794.
文摘With the rapid development of the Internet,network security and data privacy are increasingly valued.Although classical Network Intrusion Detection System(NIDS)based on Deep Learning(DL)models can provide good detection accuracy,but collecting samples for centralized training brings the huge risk of data privacy leakage.Furthermore,the training of supervised deep learning models requires a large number of labeled samples,which is usually cumbersome.The“black-box”problem also makes the DL models of NIDS untrustworthy.In this paper,we propose a trusted Federated Learning(FL)Traffic IDS method called FL-TIDS to address the above-mentioned problems.In FL-TIDS,we design an unsupervised intrusion detection model based on autoencoders that alleviates the reliance on marked samples.At the same time,we use FL for model training to protect data privacy.In addition,we design an improved SHAP interpretable method based on chi-square test to perform interpretable analysis of the trained model.We conducted several experiments to evaluate the proposed FL-TIDS.We first determine experimentally the structure and the number of neurons of the unsupervised AE model.Secondly,we evaluated the proposed method using the UNSW-NB15 and CICIDS2017 datasets.The exper-imental results show that the unsupervised AE model has better performance than the other 7 intrusion detection models in terms of precision,recall and f1-score.Then,federated learning is used to train the intrusion detection model.The experimental results indicate that the model is more accurate than the local learning model.Finally,we use an improved SHAP explainability method based on Chi-square test to analyze the explainability.The analysis results show that the identification characteristics of the model are consistent with the attack characteristics,and the model is reliable.