Shuozhou is a typical coal mining city,and the Pingshuo Antaibao open-pit coal mine in its area is one of the largest open-pit coal mines in China.The mining of coal resources is an important part of ensuring national...Shuozhou is a typical coal mining city,and the Pingshuo Antaibao open-pit coal mine in its area is one of the largest open-pit coal mines in China.The mining of coal resources is an important part of ensuring national energy security,and at the same time,it inevitably has a certain impact on the ecology,such as coal dust generated by open-pit mining will affect air quality,soil,water and vegetation.It is of great significance to explore the temporal and spatial variation of ecological environment quality in coal mining cities for ecological protection and sustainable social and economic development.Based on the Google Earth Engine(GEE)platform,this paper combines the index-based coal dust index(ICDI)and Remote Sensing Ecological Index(RSEI)models to construct an improved RSEI(IRSEI)that can reflect coal mining cities.This paper explores the spatial-temporal evolution characteristics and spatial correlation of ecological environment quality in Shuozhou from 2000 to 2020.The results showed that the average value of IRSEI in Shuozhou was between 0.262 and 0.418,and the overall change showed an upward trend.The growth areas of ecological environment quality are mainly located in the eastern and southwestern areas with good vegetation growth,and these regions have vigorously implemented the Northern Shelter Forest Project,afforestation and greening projects,implemented the forest resource management and protection responsibility system,promoted the construction of ecological civilization,and significantly improved the ecological environment.While the declining areas are mainly located in the central and southern regions where mining activities and human activities are more intensive.The IRSEI in the study area showed a significant spatial positive correlation,and the agglomeration types of the spatial pattern were mainly high-high and low-low agglomeration types,with the high-high agglomeration types mainly distributed in the eastern and southwestern regions,and the low-low agglomeration types distributed in the northern and south-central regions of the study area.The trend of low and low agglomeration has decreased,which further proves that the ecological restoration measures taken by the government,such as returning farmland to forests,integrating protection and restoration of mountains,waters,forests,fields,lakes,grasslands,and sands,controlling soil erosion,and stage wise reclamation of coal mining subsidence areas,have improved the ecological environment quality of Shuozhou.This study provides a reference for understanding the spatiotemporal changes of the ecological environment of coal mining cities,and is conducive to formulating appropriate ecological protection strategies.展开更多
Land surface temperature (LST) is a phenomenon that significantly affects the environment, the cities’ liveability, and the citizens’ well-being. This Study aims to perform a comparative study of the microclimate an...Land surface temperature (LST) is a phenomenon that significantly affects the environment, the cities’ liveability, and the citizens’ well-being. This Study aims to perform a comparative study of the microclimate and Surface Urban Heat Island (SUHI) phenomenon of two metropolitan cities of India, i.e. Jaipur and Ahmedabad, using MODIS Satellite data, whereas Landsat Data was used to analyse the Land Surface Characteristics by an index-based approach. The Study’s findings reveal that Ahmedabad has 35.53 per cent of the total area classified as having a low potential, and 13.55 per cent is designated as a high potential LST zone. Meanwhile, in Jaipur, 30.45 per cent of the city’s total area is identified as a low potential LST zone and 12.69 per cent as a high potential LST zone. This Study highlights the importance of mitigating the UHI phenomenon in urban centres for the overall well-being of city dwellers. It will help policymakers and stakeholders comprehend plans and take initiatives to minimise the effects of the UHI phenomenon on rapidly growing cities. .展开更多
The automatic and accurate classification of Magnetic Resonance Imaging(MRI)radiology report is essential for the analysis and interpretation epilepsy and non-epilepsy.Since the majority of MRI radiology reports are u...The automatic and accurate classification of Magnetic Resonance Imaging(MRI)radiology report is essential for the analysis and interpretation epilepsy and non-epilepsy.Since the majority of MRI radiology reports are unstructured,the manual information extraction is time-consuming and requires specific expertise.In this paper,a comprehensive method is proposed to classify epilepsy and non-epilepsy real brain MRI radiology text reports automatically.This method combines the Natural Language Processing technique and statisticalMachine Learning methods.122 realMRI radiology text reports(97 epilepsy,25 non-epilepsy)are studied by our proposed method which consists of the following steps:(i)for a given text report our systems first cleans HTML/XML tags,tokenize,erase punctuation,normalize text,(ii)then it converts into MRI text reports numeric sequences by using indexbased word encoding,(iii)then we applied the deep learning models that are uni-directional long short-term memory(LSTM)network,bidirectional long short-term memory(BiLSTM)network and convolutional neural network(CNN)for the classifying comparison of the data,(iv)finally,we used 70%of used for training,15%for validation,and 15%for test observations.Unlike previous methods,this study encompasses the following objectives:(a)to extract significant text features from radiologic reports of epilepsy disease;(b)to ensure successful classifying accuracy performance to enhance epilepsy data attributes.Therefore,our study is a comprehensive comparative study with the epilepsy dataset obtained from numeric sequences by using index-based word encoding method applied for the deep learning models.The traditionalmethod is numeric sequences by using index-based word encoding which has been made for the first time in the literature,is successful feature descriptor in the epilepsy data set.The BiLSTM network has shown a promising performance regarding the accuracy rates.We show that the larger sizedmedical text reports can be analyzed by our proposed method.展开更多
基金This research was funded by the National Natural Science Foundation of China(42377472,42174055)Jiangxi Provincial Social Science Foundation Project(23GL34)+4 种基金Humanities and social science research project of universities in Jiangxi Province(GL22228)Open Fund of Key Laboratory of Mine Environmental Monitoring and Improving around Poyang Lake of the Ministry of Natural Resources(MEMI-2021-2022-28)Science and Technology Research Project of Jiangxi Provincial Department of Education(GJJ2200741)the Graduate Innovation Fund of Jiangxi(YC2023-S557)the Doctoral Research Initiation fund of East China University of Technology(DHBK2019184).
文摘Shuozhou is a typical coal mining city,and the Pingshuo Antaibao open-pit coal mine in its area is one of the largest open-pit coal mines in China.The mining of coal resources is an important part of ensuring national energy security,and at the same time,it inevitably has a certain impact on the ecology,such as coal dust generated by open-pit mining will affect air quality,soil,water and vegetation.It is of great significance to explore the temporal and spatial variation of ecological environment quality in coal mining cities for ecological protection and sustainable social and economic development.Based on the Google Earth Engine(GEE)platform,this paper combines the index-based coal dust index(ICDI)and Remote Sensing Ecological Index(RSEI)models to construct an improved RSEI(IRSEI)that can reflect coal mining cities.This paper explores the spatial-temporal evolution characteristics and spatial correlation of ecological environment quality in Shuozhou from 2000 to 2020.The results showed that the average value of IRSEI in Shuozhou was between 0.262 and 0.418,and the overall change showed an upward trend.The growth areas of ecological environment quality are mainly located in the eastern and southwestern areas with good vegetation growth,and these regions have vigorously implemented the Northern Shelter Forest Project,afforestation and greening projects,implemented the forest resource management and protection responsibility system,promoted the construction of ecological civilization,and significantly improved the ecological environment.While the declining areas are mainly located in the central and southern regions where mining activities and human activities are more intensive.The IRSEI in the study area showed a significant spatial positive correlation,and the agglomeration types of the spatial pattern were mainly high-high and low-low agglomeration types,with the high-high agglomeration types mainly distributed in the eastern and southwestern regions,and the low-low agglomeration types distributed in the northern and south-central regions of the study area.The trend of low and low agglomeration has decreased,which further proves that the ecological restoration measures taken by the government,such as returning farmland to forests,integrating protection and restoration of mountains,waters,forests,fields,lakes,grasslands,and sands,controlling soil erosion,and stage wise reclamation of coal mining subsidence areas,have improved the ecological environment quality of Shuozhou.This study provides a reference for understanding the spatiotemporal changes of the ecological environment of coal mining cities,and is conducive to formulating appropriate ecological protection strategies.
文摘Land surface temperature (LST) is a phenomenon that significantly affects the environment, the cities’ liveability, and the citizens’ well-being. This Study aims to perform a comparative study of the microclimate and Surface Urban Heat Island (SUHI) phenomenon of two metropolitan cities of India, i.e. Jaipur and Ahmedabad, using MODIS Satellite data, whereas Landsat Data was used to analyse the Land Surface Characteristics by an index-based approach. The Study’s findings reveal that Ahmedabad has 35.53 per cent of the total area classified as having a low potential, and 13.55 per cent is designated as a high potential LST zone. Meanwhile, in Jaipur, 30.45 per cent of the city’s total area is identified as a low potential LST zone and 12.69 per cent as a high potential LST zone. This Study highlights the importance of mitigating the UHI phenomenon in urban centres for the overall well-being of city dwellers. It will help policymakers and stakeholders comprehend plans and take initiatives to minimise the effects of the UHI phenomenon on rapidly growing cities. .
文摘The automatic and accurate classification of Magnetic Resonance Imaging(MRI)radiology report is essential for the analysis and interpretation epilepsy and non-epilepsy.Since the majority of MRI radiology reports are unstructured,the manual information extraction is time-consuming and requires specific expertise.In this paper,a comprehensive method is proposed to classify epilepsy and non-epilepsy real brain MRI radiology text reports automatically.This method combines the Natural Language Processing technique and statisticalMachine Learning methods.122 realMRI radiology text reports(97 epilepsy,25 non-epilepsy)are studied by our proposed method which consists of the following steps:(i)for a given text report our systems first cleans HTML/XML tags,tokenize,erase punctuation,normalize text,(ii)then it converts into MRI text reports numeric sequences by using indexbased word encoding,(iii)then we applied the deep learning models that are uni-directional long short-term memory(LSTM)network,bidirectional long short-term memory(BiLSTM)network and convolutional neural network(CNN)for the classifying comparison of the data,(iv)finally,we used 70%of used for training,15%for validation,and 15%for test observations.Unlike previous methods,this study encompasses the following objectives:(a)to extract significant text features from radiologic reports of epilepsy disease;(b)to ensure successful classifying accuracy performance to enhance epilepsy data attributes.Therefore,our study is a comprehensive comparative study with the epilepsy dataset obtained from numeric sequences by using index-based word encoding method applied for the deep learning models.The traditionalmethod is numeric sequences by using index-based word encoding which has been made for the first time in the literature,is successful feature descriptor in the epilepsy data set.The BiLSTM network has shown a promising performance regarding the accuracy rates.We show that the larger sizedmedical text reports can be analyzed by our proposed method.
