The rapid urbanization and increasing challenges are faced by cities globally,including climate change,population growth,and resource constraints.Sustainable smart city(also referred to as“smart sustainable city”)ca...The rapid urbanization and increasing challenges are faced by cities globally,including climate change,population growth,and resource constraints.Sustainable smart city(also referred to as“smart sustainable city”)can offer innovative solutions by integrating advanced technologies to build smarter,greener,and more livable urban environments with significant benefits.Using the Web of Science(WoS)database,this study examined:(i)the mainstream approaches and current research trends in the literature of sustainable smart city;(ii)the extent to which the research of sustainable smart city aligns with Sustainable Development Goals(SDGs);(iii)the current topics and collaboration patterns in sustainable smart city research;and(iv)the potential opportunities for future research on the sustainable smart city field.The findings indicated that research on sustainable smart city began in 2010 and gained significant momentum in 2013,with China leading,followed by Italy and Spain.Moreover,59.00%of the selected publications on the research of sustainable smart city focus on SDG 11(Sustainable Cities and Communities).Bibliometric analysis outcome revealed that artificial intelligence(AI),big data,machine learning,and deep learning are emerging research fields.The terms smart city,smart cities,and sustainability emerged as the top three co-occurring keywords with the highest link strength,followed by frequently co-occurring keywords such as AI,innovation,big data,urban governance,resilience,machine learning,and Internet of Things(IoT).The clustering results indicated that current studies explored the theoretical foundation,challenges,and future prospects of sustainable smart city,with an emphasis on sustainability.To further support urban sustainability and the attainment of SDGs,the future research of sustainable smart city should explore the application and implications of AI and big data on urban development including cybersecurity and governance challenges.展开更多
Background:People working outdoors in the Map Ta Phut pollution control area of Thailand require comprehen-sive health monitoring.In the past,studies have been done on the health effects of pollutants.However,there ar...Background:People working outdoors in the Map Ta Phut pollution control area of Thailand require comprehen-sive health monitoring.In the past,studies have been done on the health effects of pollutants.However,there are few studies on musculoskeletal disorders(MSDs),and Thailand is struggling to meet the Sustainable Development Goals.Methods:This cross-sectional study examines access to health services and factors affecting MSDs among outdoor pollution workers(OPWs).The sample group includes OPWs,including local fisherman,street vendors,public car drivers,and traffic police.We studied 50 people from each of these groups,for a total of 200 people.Data were analyzed with inferential statistics using Chi-square test,McNemar test,and Univariate logistic regression.Results:The OPWs reported experiencing significantly more total MSDs pain than they did in the past(P<0.05).Factors affecting current MSDs pain,including occupation and working days per week,were significant(P<0.05).The street vendor group and public car driver group had(odds ratio[OR]=2.253,95%confidence interval[CI]:1.101 to 5.019)and(OR=2.681,95%CI:1.191 to 6.032)times higher risks of MSDs pain,respectively.OPWs who work>5 days per week had a(OR=1.464,95%CI:1.093 to 2.704)times higher risk of MSDs pain.52.7%of OPWs with MSDs,pain(n=110)had received an annual health check-up.In the past year,50.9%had minor illnesses and 21.8%had severe illnesses.OPWs receiving free treatment and visiting health service stations for no cost comprised 77.3%and 51.8%,respectively.60.9%used their right to receive treatment with universal health insurance cards.Conclusions:The study indicates that occupational groups with MSDs pain problems should exercise this right,according to the worker protection law.Local health agencies should organize activities or create accessible media to promote preventive medicine services,as many OPWs believe that health services can only be accessed when illness occurs.展开更多
In the Government Work Report released on March 5,the main goals for China’s economic development in 2025 were clarified.Some may seem consistent with last year,but they still contain profound considerations and trad...In the Government Work Report released on March 5,the main goals for China’s economic development in 2025 were clarified.Some may seem consistent with last year,but they still contain profound considerations and trade-offs,while others have changed unexpectedly to better match the reality on the ground.展开更多
Urban areas’performance in water,energy,infrastructure,and socio-economic sectors is intertwined and measurable through Sustainable Development Goals(SDGs)6–13.Effective synergy among these is critical for sustainab...Urban areas’performance in water,energy,infrastructure,and socio-economic sectors is intertwined and measurable through Sustainable Development Goals(SDGs)6–13.Effective synergy among these is critical for sustainability.This study constructs an indicator framework that reflects progress towards these urban SDGs in China.Findings indicate underperformance in SDGs 8–11,suggesting the need for transformative actions.Through network analysis,the research reveals complementarities among these SDGs.Notably,the SDG space divides into socio-economic and ecological clusters,with SDG 6(Clean Water and Sanitation)central to both.Additionally,SDG 8(Decent Work and Economic Growth)and SDG 9(Industry,Innovation,and Infrastructure)act as bridges,while greater synergies exist between SDG 12(Responsible Consumption and Production)and SDG 13(Climate Action).An in-depth view at the indicator-level shows a core-periphery structure,emphasizing indicators like SDG 6.2(Wastewater Treatment Rate)and SDG 6.6(Recycled Water Production Capacity per capita)as pivotal.This study confirms the urban SDG space’s stability and predictiveness,underscoring its value in steering well-aligned policy decisions for sustainable growth.展开更多
Geography is a discipline that touches multiple sciences and has been key to bridging numerous fields of knowl edge.This gives geography the advantage of connecting natural(e.g.,biology,ecology,climatology,geomorphol ...Geography is a discipline that touches multiple sciences and has been key to bridging numerous fields of knowl edge.This gives geography the advantage of connecting natural(e.g.,biology,ecology,climatology,geomorphol ogy)with social and human(e.g.,education,demography,sociology)sciences.The spatialisation of information from different sciences allows us to understand distribution patterns and connections between different realities.Thus,geographical knowledge is essential for an integrated and consistent understanding of our world.The Sus tainable Development Goals(SDGs)established by the United Nations(UN)in 2015 were essential to unifying the world towards a common goal.To achieve these,17 goals and 169 targets were created,and knowledge from multiple sciences is needed to support them.It is a huge challenge,and different knowledge branches are needed to connect.Geography and geographical knowledge have this capacity and support all 17 goals and 169 targets.Although this is a reality,as it will be explained in this editorial,SDG’s achievement for some is becoming utopic and unrealistic due to our world’s differences.It is time to think about the post-2030 SDGs,in which geography and geographic knowledge will be essential unequivocally.展开更多
Sustainable Development Goal 2(SDG 2,zero hunger)highlights that global hunger and food insecurity have worsened since 2015,driven in part by growing imbalance.Addressing the challenge of achieving SDG 2 in the face o...Sustainable Development Goal 2(SDG 2,zero hunger)highlights that global hunger and food insecurity have worsened since 2015,driven in part by growing imbalance.Addressing the challenge of achieving SDG 2 in the face of rapid global population growth requires sustained attention to global and national cropland changes.Accurately quantifying the correlation between population and cropland area(i.e.,SDG 2.4.1 per capita cropland)and analyzing the trends of global cropland imbalance are essential for a comprehensive understanding of SDG 2.In this study,we utilized a new global 30 m land-cover dynamic dataset(GLC_FCS30D)to analyze cropland dynamics,quantify per capita cropland and its changes across various countries and levels of development.Our results indicate that the global cropland area expanded by 0.944 million km^(2)from 1985 to 2022,with an average expansion rate of 2.42×10^(4)km^(2)/yr.However,the global per capita cropland area decreased from 0.347 ha in 1985 to 0.217 ha in 2022,mainly due to a higher population increase of nearly 65%in the same period.In the context of globalization,cropland expansion and per capita cropland exhibited spatial imbalances globally,particularly in developing countries.Developing countries saw an increase in total cropland area by 7.09%but a significant decrease in per capita cropland area by 37.38%.From a temporal perspective,the global imbalance has been steadily increasing with the Gini index rising from 0.895 in 1985 to 0.909 in 2022.Consequently,this study reveals an increasing imbalance of global per capita cropland across various countries,which threatens the attainment of the targets of SDG 2.展开更多
This year marks the 50th anniversary of diplomatic relations between China and Mozambique.To commemorate this milestone,ChinAfrica spoke with Maria Gustava,Mozambique’s ambassador to China,about the state of bilatera...This year marks the 50th anniversary of diplomatic relations between China and Mozambique.To commemorate this milestone,ChinAfrica spoke with Maria Gustava,Mozambique’s ambassador to China,about the state of bilateral relations,China-Africa cooperation,and key developments shaping the global landscape.展开更多
Ecosystems play a pivotal role in advancing Sustainable Development Goals(SDGs)by providing indispensable and resilient ecosystem services(ESs).However,the limited analysis of spatiotemporal heterogeneity often re str...Ecosystems play a pivotal role in advancing Sustainable Development Goals(SDGs)by providing indispensable and resilient ecosystem services(ESs).However,the limited analysis of spatiotemporal heterogeneity often re stricts the recognition of ESs’roles in attaining SDGs and landscape planning.We selected 183 counties in the Sichuan Province as the study area and mapped 10 SDGs and 7 ESs from 2000 to 2020.We used correlation analysis,principal component analysis,Geographically and Temporally Weighted Regression model,and self organizing maps to reveal the spatiotemporal heterogeneity of the impacts of the bundle of ESs on the SDGs and to develop spatial planning and management strategies.The results showed that(1)SDGs were improved in all counties,with SDG 1(No Poverty)and SDG 3(Good Health and Well-being)exhibiting poor performance.West ern Sichuan demonstrated stronger performance in environment-related SDGs in the Sichuan Province,while the Sichuan Basin showed better progress in socio-economic-related SDGs;(2)habitat quality,carbon sequestration,air pollution removal,and soil retention significantly influenced the development of 9 SDGs;(3)supporting,regulating,and provisioning service bundles have persistent and stable spatiotemporal heterogeneity effects on SDG1,SDG8,SDG11,SDG13,and SDG15.These findings substantiate the need for integrated management of multiple ESs and facilitate the regional achievement of SDGs in geographically intricate areas.展开更多
Blindness affected 45 million people globally in 2021,and moderate to severe vision loss a further 295 million.[1]The most common causes,cataract and uncorrected refractive error,are generally the easiest to treat,and...Blindness affected 45 million people globally in 2021,and moderate to severe vision loss a further 295 million.[1]The most common causes,cataract and uncorrected refractive error,are generally the easiest to treat,and are among the most cost-effective procedures in all of medicine and international development.[1-2]Thus,vision impairment is both extremely common and,in principle,readily manageable.展开更多
Ecosystem services in urban agglomerations are the environmental conditions under which human survival and development are sustained.Quantitative assessment of ecosystem services and complex interactions can contribut...Ecosystem services in urban agglomerations are the environmental conditions under which human survival and development are sustained.Quantitative assessment of ecosystem services and complex interactions can contribute positively to the achievement of the Sustainable Development Goals(SDGs)for urban agglomerations.However,studies on the future contribution of multi-scenario ecosystem services to the SDGS are lacking.We pronovel integrated modeling framework that integrates the CLUES,InVEST,SOM,and GWR approaches to address the complex relationship between ecosystem services over a long“past-present-future”time series.We construct a novel ecosystem service bundle-based approach for measuring urban agglomerations progress towards achieving ecologically relevant sustainable development goals at multiple scales.In the future scenario,the water yield(WY),habitat quality(HQ),and soil conservation(SC)show similar spatial patterns,with comparable spatial grids,while carbon stock(CS)remains predominantly unchanged and the ecological protection scenario(EPS)improves more significantly.The high-synergy regions are mainly distributed in bundle 4,and most of the trade-off regions appear in bundles 1 and 2.Over the last 30 years,all but the water-related SDGs are declining in bundle 1 of the two urban agglomerations,which are 15%higher in the Guangxi Beibu Gulf(GBG)than in the Guangdong-Hong Kong-Macao Greater Bay Area(GBA).From 2020 to 2035,the three scenarios demonstrate that the optimization of the SDGs progresses most effectively under the future ecological protection scenario(EPS).In particular,bundles 3 and 4 are significantly improved.This critical new knowledge can be used in sustainable ecosystem management and decision-making in urban agglomerations.展开更多
This paper reviews the history and lessons of global oil crises while exploring the establishment of a quantitative evaluation model for oil security with Chinese characteristics.Using principal component analysis,it ...This paper reviews the history and lessons of global oil crises while exploring the establishment of a quantitative evaluation model for oil security with Chinese characteristics.Using principal component analysis,it constructs an oil security evaluation indicator system for China with two main-level indicators:foreign oil dependency and its impacts,and market intervention and security assurance.展开更多
The county(city)located on the northern slope of the Kunlun Mountains is the primary area to solidify and extend the success of Xinjiang Uygur Autonomous Region,China in poverty alleviation.Its Sustainable Development...The county(city)located on the northern slope of the Kunlun Mountains is the primary area to solidify and extend the success of Xinjiang Uygur Autonomous Region,China in poverty alleviation.Its Sustainable Development Goals(SDGs)are intertwined with the concerted economic and social development of Xinjiang and the objective of achieving shared prosperity within the region.This study established a sustainable development evaluation framework by selecting 15 SDGs and 20 secondary indicators from the United Nations’SDGs.The aim of this study is to quantitatively assess the progress of SDGs at the county(city)level on the northern slope of the Kunlun Mountains.The results indicate that there are substantial variations in the scores of SDGs among the nine counties and one city located on the northern slope of the Kunlun Mountains.Notable high scores of SDGs are observed in the central and eastern regions,whereas lower scores are prevalent in the western areas.The scores of SDGs,in descending order,are as follows:62.22 for Minfeng County,54.22 for Hotan City,50.21 for Qiemo County,42.54 for Moyu County,41.56 for Ruoqiang County,41.39 for Qira County,39.86 for Lop County,38.25 for Yutian County,38.10 for Pishan County,and 36.87 for Hotan County.The performances of SDGs reveal that Hotan City,Lop County,Minfeng County,and Ruoqiang County have significant sustainable development capacity because they have three or more SDGs ranked as green color.However,Hotan County,Moyu County,Qira County,and Yutian County show the poorest performance,as they lack SDGs with green color.It is important to establish and enhance mechanisms that can ensure sustained income growth among poverty alleviation beneficiaries,sustained improvement in the capacity of rural governance,and the gradual improvement of social security system.These measures will facilitate the effective implementation of SDGs.Finally,this study offers a valuable support for governmental authorities and relevant departments in their decision-making processes.In addition,these results hold significant reference value for assessing SDGs at the county(city)level,particularly in areas characterized by low levels of economic development.展开更多
Background: Guidelines are issued by most major organizations that focus on a specific disease entity. Guidelines should be a significant help to the practicing physician who may not be up-to-date with the recent medi...Background: Guidelines are issued by most major organizations that focus on a specific disease entity. Guidelines should be a significant help to the practicing physician who may not be up-to-date with the recent medical literature. Unfortunately, when conflicting guidelines for a specific disease are published, confusion results. Purpose: This article provides a suggested guideline outcome measure that would benefit the physician and patient. Methods: A review of 19 different guidelines for cardiovascular disease treatment is one example of the lack of specific outcomes that currently exist. The basic problem with most guidelines is that they do not state the expected end result (i.e., the benefit to the patient) if that guideline is followed. When guidelines use cardiovascular disease risk factors to dictate therapy, the end benefit is never stated so that the patient can make an appropriate choice of which (if any) guideline to follow. Results: A good example is guidelines published by the American Heart Association for reducing cardiovascular disease. These guidelines are risk factor based and only indicate that cardiovascular disease would be reduced if followed. No specific percentage in the reduction of the incidence of disease is given. In contrast, when elimination of the disease is the stated goal of the guideline, the end result is clear. To date, this goal has been stated by only one organization devoted to eliminating cardiovascular disease. Conclusion: Guidelines need to be written to provide the physician and the patient with a specific end point that is expected when the guideline is followed. Patient acceptance and compliance will be much improved if the patient knows the risk/benefit of following the guideline’s recommendations.展开更多
This study examines the transformative role of self-help groups(SHGs)in the socioeconomic development of rural women in Cooch Behar District,India,and their contribution toward achieving Sustainable Development Goals(...This study examines the transformative role of self-help groups(SHGs)in the socioeconomic development of rural women in Cooch Behar District,India,and their contribution toward achieving Sustainable Development Goals(SDGs)of the United Nations.In this study,we explored the effect of SHGs on rural women by specifically addressing SDGs,such as no poverty(SDG 1),zero hunger(SDG 2),good health and well-being(SDG 3),quality education(SDG 4),and gender equality(SDG 5).Given this issue,a cross-sectional survey and comparison analyses are needed to assess the socioeconomic development of rural women and their awareness level before and after the participation of rural women in SHGs.The survey conducted as part of this study was divided into three sections,namely,demographic characteristics,socioeconomic development,and awareness level,with each focusing on different aspects.A group of 400 individuals who were part of SHGs completed the questionnaire survey form.The results showed that the participation of rural women in SHGs significantly improved their socioeconomic development and awareness level,as supported by both mean values and t test results.Memberships in SHGs and microcredit programs were the major elements that boosted the socioeconomic development of rural women,which also achieves SDGs 1,2,3,4,and 5.This study revealed that participation in SHGs and related financial services significantly aided rural women in economically disadvantaged communities in accumulating savings and initiating entrepreneurial ventures.Moreover,participation in SHGs was instrumental in enhancing the self-confidence,self-efficacy,and overall self-esteem of rural women.Finally,doing so enabled them to move more freely for work and other activities and to make family and common decisions.展开更多
The umbilical,a key component in offshore energy extraction,plays a vital role in ensuring the stable operation of the entire production system.The extensive variety of cross-sectional components creates highly comple...The umbilical,a key component in offshore energy extraction,plays a vital role in ensuring the stable operation of the entire production system.The extensive variety of cross-sectional components creates highly complex layout combinations.Furthermore,due to constraints in component quantity and geometry within the cross-sectional layout,filler bodies must be incorporated to maintain cross-section performance.Conventional design approaches based on manual experience suffer from inefficiency,high variability,and difficulties in quantification.This paper presents a multi-level automatic filling optimization design method for umbilical cross-sectional layouts to address these limitations.Initially,the research establishes a multi-objective optimization model that considers compactness,balance,and wear resistance of the cross-section,employing an enhanced genetic algorithm to achieve a near-optimal layout.Subsequently,the study implements an image processing-based vacancy detection technique to accurately identify cross-sectional gaps.To manage the variability and diversity of these vacant regions,the research introduces a multi-level filling method that strategically selects and places filler bodies of varying dimensions,overcoming the constraints of uniform-size fillers.Additionally,the method incorporates a hierarchical strategy that subdivides the complex cross-section into multiple layers,enabling layer-by-layer optimization and filling.This approach reduces manufac-turing equipment requirements while ensuring practical production process feasibility.The methodology is validated through a specific umbilical case study.The results demonstrate improvements in compactness,balance,and wear resistance compared with the initial cross-section,offering novel insights and valuable references for filler design in umbilical cross-sections.展开更多
As a key node of modern transportation network,the informationization management of road tunnels is crucial to ensure the operation safety and traffic efficiency.However,the existing tunnel vehicle modeling methods ge...As a key node of modern transportation network,the informationization management of road tunnels is crucial to ensure the operation safety and traffic efficiency.However,the existing tunnel vehicle modeling methods generally have problems such as insufficient 3D scene description capability and low dynamic update efficiency,which are difficult to meet the demand of real-time accurate management.For this reason,this paper proposes a vehicle twin modeling method for road tunnels.This approach starts from the actual management needs,and supports multi-level dynamic modeling from vehicle type,size to color by constructing a vehicle model library that can be flexibly invoked;at the same time,semantic constraint rules with geometric layout,behavioral attributes,and spatial relationships are designed to ensure that the virtual model matches with the real model with a high degree of similarity;ultimately,the prototype system is constructed and the case region is selected for the case study,and the dynamic vehicle status in the tunnel is realized by integrating real-time monitoring data with semantic constraints for precise virtual-real mapping.Finally,the prototype system is constructed and case experiments are conducted in selected case areas,which are combined with real-time monitoring data to realize dynamic updating and three-dimensional visualization of vehicle states in tunnels.The experiments show that the proposed method can run smoothly with an average rendering efficiency of 17.70 ms while guaranteeing the modeling accuracy(composite similarity of 0.867),which significantly improves the real-time and intuitive tunnel management.The research results provide reliable technical support for intelligent operation and emergency response of road tunnels,and offer new ideas for digital twin modeling of complex scenes.展开更多
In my opinion,we should have more goals in our lives and have fewer complaints.As is known to all,goals make us go further and prevent us from being lazy.When we have goals,we are encouraged to work hard to achieve th...In my opinion,we should have more goals in our lives and have fewer complaints.As is known to all,goals make us go further and prevent us from being lazy.When we have goals,we are encouraged to work hard to achieve them.But if we lose our goals,we may feel uncertain and insecure.For a student,goals do play an essential role in study.I once set a goal to play better in basketball games,and I tried my best to train myself without any fear and hesitation.It was the goal that helped me accomplish my ambition.展开更多
Accurate prediction of landslide displacement is crucial for effective early warning of landslide disasters.While most existing prediction methods focus on time-series forecasting for individual monitoring points,ther...Accurate prediction of landslide displacement is crucial for effective early warning of landslide disasters.While most existing prediction methods focus on time-series forecasting for individual monitoring points,there is limited research on the spatiotemporal characteristics of landslide deformation.This paper proposes a novel Multi-Relation Spatiotemporal Graph Residual Network with Multi-Level Feature Attention(MFA-MRSTGRN)that effectively improves the prediction performance of landslide displacement through spatiotemporal fusion.This model integrates internal seepage factors as data feature enhancements with external triggering factors,allowing for accurate capture of the complex spatiotemporal characteristics of landslide displacement and the construction of a multi-source heterogeneous dataset.The MFA-MRSTGRN model incorporates dynamic graph theory and four key modules:multilevel feature attention,temporal-residual decomposition,spatial multi-relational graph convolution,and spatiotemporal fusion prediction.This comprehensive approach enables the efficient analyses of multi-source heterogeneous datasets,facilitating adaptive exploration of the evolving multi-relational,multi-dimensional spatiotemporal complexities in landslides.When applying this model to predict the displacement of the Liangshuijing landslide,we demonstrate that the MFA-MRSTGRN model surpasses traditional models,such as random forest(RF),long short-term memory(LSTM),and spatial temporal graph convolutional networks(ST-GCN)models in terms of various evaluation metrics including mean absolute error(MAE=1.27 mm),root mean square error(RMSE=1.49 mm),mean absolute percentage error(MAPE=0.026),and R-squared(R^(2)=0.88).Furthermore,feature ablation experiments indicate that incorporating internal seepage factors improves the predictive performance of landslide displacement models.This research provides an advanced and reliable method for landslide displacement prediction.展开更多
As we look ahead to future lunar exploration missions, such as crewed lunar exploration and establishing lunar scientific research stations, the lunar rovers will need to cover vast distances. These distances could ra...As we look ahead to future lunar exploration missions, such as crewed lunar exploration and establishing lunar scientific research stations, the lunar rovers will need to cover vast distances. These distances could range from kilometers to tens of kilometers, and even hundreds and thousands of kilometers. Therefore, it is crucial to develop effective long-range path planning for lunar rovers to meet the demands of lunar patrol exploration. This paper presents a hierarchical map model path planning method that utilizes the existing high-resolution images, digital elevation models and mineral abundance maps. The objective is to address the issue of the construction of lunar rover travel costs in the absence of large-scale, high-resolution digital elevation models. This method models the reference and semantic layers using the middle- and low-resolution remote sensing data. The multi-scale obstacles on the lunar surface are extracted by combining the deep learning algorithm on the high-resolution image, and the obstacle avoidance layer is modeled. A two-stage exploratory path planning decision is employed for long-distance driving path planning on a global–local scale. The proposed method analyzes the long-distance accessibility of various areas of scientific significance, such as Rima Bode. A high-precision digital elevation model is created using stereo images to validate the method. Based on the findings, it can be observed that the entire route spans a distance of 930.32 km. The route demonstrates an impressive ability to avoid meter-level impact craters and linear structures while maintaining an average slope of less than 8°. This paper explores scientific research by traversing at least seven basalt units, uncovering the secrets of lunar volcanic activities, and establishing ‘golden spike’ reference points for lunar stratigraphy. The final result of path planning can serve as a valuable reference for the design, mission demonstration, and subsequent project implementation of the new manned lunar rover.展开更多
Deep learning networks are increasingly exploited in the field of neuronal soma segmentation.However,annotating dataset is also an expensive and time-consuming task.Unsupervised domain adaptation is an effective metho...Deep learning networks are increasingly exploited in the field of neuronal soma segmentation.However,annotating dataset is also an expensive and time-consuming task.Unsupervised domain adaptation is an effective method to mitigate the problem,which is able to learn an adaptive segmentation model by transferring knowledge from a rich-labeled source domain.In this paper,we propose a multi-level distribution alignment-based unsupervised domain adaptation network(MDA-Net)for segmentation of 3D neuronal soma images.Distribution alignment is performed in both feature space and output space.In the feature space,features from different scales are adaptively fused to enhance the feature extraction capability for small target somata and con-strained to be domain invariant by adversarial adaptation strategy.In the output space,local discrepancy maps that can reveal the spatial structures of somata are constructed on the predicted segmentation results.Then thedistribution alignment is performed on the local discrepancies maps across domains to obtain a superior discrepancy map in the target domain,achieving refined segmentation performance of neuronal somata.Additionally,after a period of distribution align-ment procedure,a portion of target samples with high confident pseudo-labels are selected as training data,which assist in learning a more adaptive segmentation network.We verified the superiority of the proposed algorithm by comparing several domain adaptation networks on two 3D mouse brain neuronal somata datasets and one macaque brain neuronal soma dataset.展开更多
文摘The rapid urbanization and increasing challenges are faced by cities globally,including climate change,population growth,and resource constraints.Sustainable smart city(also referred to as“smart sustainable city”)can offer innovative solutions by integrating advanced technologies to build smarter,greener,and more livable urban environments with significant benefits.Using the Web of Science(WoS)database,this study examined:(i)the mainstream approaches and current research trends in the literature of sustainable smart city;(ii)the extent to which the research of sustainable smart city aligns with Sustainable Development Goals(SDGs);(iii)the current topics and collaboration patterns in sustainable smart city research;and(iv)the potential opportunities for future research on the sustainable smart city field.The findings indicated that research on sustainable smart city began in 2010 and gained significant momentum in 2013,with China leading,followed by Italy and Spain.Moreover,59.00%of the selected publications on the research of sustainable smart city focus on SDG 11(Sustainable Cities and Communities).Bibliometric analysis outcome revealed that artificial intelligence(AI),big data,machine learning,and deep learning are emerging research fields.The terms smart city,smart cities,and sustainability emerged as the top three co-occurring keywords with the highest link strength,followed by frequently co-occurring keywords such as AI,innovation,big data,urban governance,resilience,machine learning,and Internet of Things(IoT).The clustering results indicated that current studies explored the theoretical foundation,challenges,and future prospects of sustainable smart city,with an emphasis on sustainability.To further support urban sustainability and the attainment of SDGs,the future research of sustainable smart city should explore the application and implications of AI and big data on urban development including cybersecurity and governance challenges.
基金grant Fundamental Fund of National Science Research and Innovation Fund(NSRF)via Burapha University of Thailand(Grant number 52/2024).
文摘Background:People working outdoors in the Map Ta Phut pollution control area of Thailand require comprehen-sive health monitoring.In the past,studies have been done on the health effects of pollutants.However,there are few studies on musculoskeletal disorders(MSDs),and Thailand is struggling to meet the Sustainable Development Goals.Methods:This cross-sectional study examines access to health services and factors affecting MSDs among outdoor pollution workers(OPWs).The sample group includes OPWs,including local fisherman,street vendors,public car drivers,and traffic police.We studied 50 people from each of these groups,for a total of 200 people.Data were analyzed with inferential statistics using Chi-square test,McNemar test,and Univariate logistic regression.Results:The OPWs reported experiencing significantly more total MSDs pain than they did in the past(P<0.05).Factors affecting current MSDs pain,including occupation and working days per week,were significant(P<0.05).The street vendor group and public car driver group had(odds ratio[OR]=2.253,95%confidence interval[CI]:1.101 to 5.019)and(OR=2.681,95%CI:1.191 to 6.032)times higher risks of MSDs pain,respectively.OPWs who work>5 days per week had a(OR=1.464,95%CI:1.093 to 2.704)times higher risk of MSDs pain.52.7%of OPWs with MSDs,pain(n=110)had received an annual health check-up.In the past year,50.9%had minor illnesses and 21.8%had severe illnesses.OPWs receiving free treatment and visiting health service stations for no cost comprised 77.3%and 51.8%,respectively.60.9%used their right to receive treatment with universal health insurance cards.Conclusions:The study indicates that occupational groups with MSDs pain problems should exercise this right,according to the worker protection law.Local health agencies should organize activities or create accessible media to promote preventive medicine services,as many OPWs believe that health services can only be accessed when illness occurs.
文摘In the Government Work Report released on March 5,the main goals for China’s economic development in 2025 were clarified.Some may seem consistent with last year,but they still contain profound considerations and trade-offs,while others have changed unexpectedly to better match the reality on the ground.
基金supported by the Excellent Young Scientists Fund from the National Natural Science Foundation of China(No.72022004)the National Key Scientific Research Project(No.2021YFC3200200).
文摘Urban areas’performance in water,energy,infrastructure,and socio-economic sectors is intertwined and measurable through Sustainable Development Goals(SDGs)6–13.Effective synergy among these is critical for sustainability.This study constructs an indicator framework that reflects progress towards these urban SDGs in China.Findings indicate underperformance in SDGs 8–11,suggesting the need for transformative actions.Through network analysis,the research reveals complementarities among these SDGs.Notably,the SDG space divides into socio-economic and ecological clusters,with SDG 6(Clean Water and Sanitation)central to both.Additionally,SDG 8(Decent Work and Economic Growth)and SDG 9(Industry,Innovation,and Infrastructure)act as bridges,while greater synergies exist between SDG 12(Responsible Consumption and Production)and SDG 13(Climate Action).An in-depth view at the indicator-level shows a core-periphery structure,emphasizing indicators like SDG 6.2(Wastewater Treatment Rate)and SDG 6.6(Recycled Water Production Capacity per capita)as pivotal.This study confirms the urban SDG space’s stability and predictiveness,underscoring its value in steering well-aligned policy decisions for sustainable growth.
文摘Geography is a discipline that touches multiple sciences and has been key to bridging numerous fields of knowl edge.This gives geography the advantage of connecting natural(e.g.,biology,ecology,climatology,geomorphol ogy)with social and human(e.g.,education,demography,sociology)sciences.The spatialisation of information from different sciences allows us to understand distribution patterns and connections between different realities.Thus,geographical knowledge is essential for an integrated and consistent understanding of our world.The Sus tainable Development Goals(SDGs)established by the United Nations(UN)in 2015 were essential to unifying the world towards a common goal.To achieve these,17 goals and 169 targets were created,and knowledge from multiple sciences is needed to support them.It is a huge challenge,and different knowledge branches are needed to connect.Geography and geographical knowledge have this capacity and support all 17 goals and 169 targets.Although this is a reality,as it will be explained in this editorial,SDG’s achievement for some is becoming utopic and unrealistic due to our world’s differences.It is time to think about the post-2030 SDGs,in which geography and geographic knowledge will be essential unequivocally.
基金supported by the National Key Research and Development Program of China(Grant No.2023YFB3907403)the National Natural Science Foundation of China(Grant No.42201499)the Open Research Program of the International Research Center of Big Data for Sustainable Development Goals(Grant No.CBAS2022ORP03).
文摘Sustainable Development Goal 2(SDG 2,zero hunger)highlights that global hunger and food insecurity have worsened since 2015,driven in part by growing imbalance.Addressing the challenge of achieving SDG 2 in the face of rapid global population growth requires sustained attention to global and national cropland changes.Accurately quantifying the correlation between population and cropland area(i.e.,SDG 2.4.1 per capita cropland)and analyzing the trends of global cropland imbalance are essential for a comprehensive understanding of SDG 2.In this study,we utilized a new global 30 m land-cover dynamic dataset(GLC_FCS30D)to analyze cropland dynamics,quantify per capita cropland and its changes across various countries and levels of development.Our results indicate that the global cropland area expanded by 0.944 million km^(2)from 1985 to 2022,with an average expansion rate of 2.42×10^(4)km^(2)/yr.However,the global per capita cropland area decreased from 0.347 ha in 1985 to 0.217 ha in 2022,mainly due to a higher population increase of nearly 65%in the same period.In the context of globalization,cropland expansion and per capita cropland exhibited spatial imbalances globally,particularly in developing countries.Developing countries saw an increase in total cropland area by 7.09%but a significant decrease in per capita cropland area by 37.38%.From a temporal perspective,the global imbalance has been steadily increasing with the Gini index rising from 0.895 in 1985 to 0.909 in 2022.Consequently,this study reveals an increasing imbalance of global per capita cropland across various countries,which threatens the attainment of the targets of SDG 2.
文摘This year marks the 50th anniversary of diplomatic relations between China and Mozambique.To commemorate this milestone,ChinAfrica spoke with Maria Gustava,Mozambique’s ambassador to China,about the state of bilateral relations,China-Africa cooperation,and key developments shaping the global landscape.
基金supported by the Second Tibetan Plateau Scien-tific Expedition and Research Program(STEP)of China(Grant No.2019QZKK0402).
文摘Ecosystems play a pivotal role in advancing Sustainable Development Goals(SDGs)by providing indispensable and resilient ecosystem services(ESs).However,the limited analysis of spatiotemporal heterogeneity often re stricts the recognition of ESs’roles in attaining SDGs and landscape planning.We selected 183 counties in the Sichuan Province as the study area and mapped 10 SDGs and 7 ESs from 2000 to 2020.We used correlation analysis,principal component analysis,Geographically and Temporally Weighted Regression model,and self organizing maps to reveal the spatiotemporal heterogeneity of the impacts of the bundle of ESs on the SDGs and to develop spatial planning and management strategies.The results showed that(1)SDGs were improved in all counties,with SDG 1(No Poverty)and SDG 3(Good Health and Well-being)exhibiting poor performance.West ern Sichuan demonstrated stronger performance in environment-related SDGs in the Sichuan Province,while the Sichuan Basin showed better progress in socio-economic-related SDGs;(2)habitat quality,carbon sequestration,air pollution removal,and soil retention significantly influenced the development of 9 SDGs;(3)supporting,regulating,and provisioning service bundles have persistent and stable spatiotemporal heterogeneity effects on SDG1,SDG8,SDG11,SDG13,and SDG15.These findings substantiate the need for integrated management of multiple ESs and facilitate the regional achievement of SDGs in geographically intricate areas.
文摘Blindness affected 45 million people globally in 2021,and moderate to severe vision loss a further 295 million.[1]The most common causes,cataract and uncorrected refractive error,are generally the easiest to treat,and are among the most cost-effective procedures in all of medicine and international development.[1-2]Thus,vision impairment is both extremely common and,in principle,readily manageable.
基金National Natural Science Foundation of China,No.U21A2022,No.U1901219,No.42071393,No.42101369。
文摘Ecosystem services in urban agglomerations are the environmental conditions under which human survival and development are sustained.Quantitative assessment of ecosystem services and complex interactions can contribute positively to the achievement of the Sustainable Development Goals(SDGs)for urban agglomerations.However,studies on the future contribution of multi-scenario ecosystem services to the SDGS are lacking.We pronovel integrated modeling framework that integrates the CLUES,InVEST,SOM,and GWR approaches to address the complex relationship between ecosystem services over a long“past-present-future”time series.We construct a novel ecosystem service bundle-based approach for measuring urban agglomerations progress towards achieving ecologically relevant sustainable development goals at multiple scales.In the future scenario,the water yield(WY),habitat quality(HQ),and soil conservation(SC)show similar spatial patterns,with comparable spatial grids,while carbon stock(CS)remains predominantly unchanged and the ecological protection scenario(EPS)improves more significantly.The high-synergy regions are mainly distributed in bundle 4,and most of the trade-off regions appear in bundles 1 and 2.Over the last 30 years,all but the water-related SDGs are declining in bundle 1 of the two urban agglomerations,which are 15%higher in the Guangxi Beibu Gulf(GBG)than in the Guangdong-Hong Kong-Macao Greater Bay Area(GBA).From 2020 to 2035,the three scenarios demonstrate that the optimization of the SDGs progresses most effectively under the future ecological protection scenario(EPS).In particular,bundles 3 and 4 are significantly improved.This critical new knowledge can be used in sustainable ecosystem management and decision-making in urban agglomerations.
文摘This paper reviews the history and lessons of global oil crises while exploring the establishment of a quantitative evaluation model for oil security with Chinese characteristics.Using principal component analysis,it constructs an oil security evaluation indicator system for China with two main-level indicators:foreign oil dependency and its impacts,and market intervention and security assurance.
基金financially supported by the Natural Science Foundation of Xinjiang Uygur Autonomous Region,China(2022D01B234).
文摘The county(city)located on the northern slope of the Kunlun Mountains is the primary area to solidify and extend the success of Xinjiang Uygur Autonomous Region,China in poverty alleviation.Its Sustainable Development Goals(SDGs)are intertwined with the concerted economic and social development of Xinjiang and the objective of achieving shared prosperity within the region.This study established a sustainable development evaluation framework by selecting 15 SDGs and 20 secondary indicators from the United Nations’SDGs.The aim of this study is to quantitatively assess the progress of SDGs at the county(city)level on the northern slope of the Kunlun Mountains.The results indicate that there are substantial variations in the scores of SDGs among the nine counties and one city located on the northern slope of the Kunlun Mountains.Notable high scores of SDGs are observed in the central and eastern regions,whereas lower scores are prevalent in the western areas.The scores of SDGs,in descending order,are as follows:62.22 for Minfeng County,54.22 for Hotan City,50.21 for Qiemo County,42.54 for Moyu County,41.56 for Ruoqiang County,41.39 for Qira County,39.86 for Lop County,38.25 for Yutian County,38.10 for Pishan County,and 36.87 for Hotan County.The performances of SDGs reveal that Hotan City,Lop County,Minfeng County,and Ruoqiang County have significant sustainable development capacity because they have three or more SDGs ranked as green color.However,Hotan County,Moyu County,Qira County,and Yutian County show the poorest performance,as they lack SDGs with green color.It is important to establish and enhance mechanisms that can ensure sustained income growth among poverty alleviation beneficiaries,sustained improvement in the capacity of rural governance,and the gradual improvement of social security system.These measures will facilitate the effective implementation of SDGs.Finally,this study offers a valuable support for governmental authorities and relevant departments in their decision-making processes.In addition,these results hold significant reference value for assessing SDGs at the county(city)level,particularly in areas characterized by low levels of economic development.
文摘Background: Guidelines are issued by most major organizations that focus on a specific disease entity. Guidelines should be a significant help to the practicing physician who may not be up-to-date with the recent medical literature. Unfortunately, when conflicting guidelines for a specific disease are published, confusion results. Purpose: This article provides a suggested guideline outcome measure that would benefit the physician and patient. Methods: A review of 19 different guidelines for cardiovascular disease treatment is one example of the lack of specific outcomes that currently exist. The basic problem with most guidelines is that they do not state the expected end result (i.e., the benefit to the patient) if that guideline is followed. When guidelines use cardiovascular disease risk factors to dictate therapy, the end benefit is never stated so that the patient can make an appropriate choice of which (if any) guideline to follow. Results: A good example is guidelines published by the American Heart Association for reducing cardiovascular disease. These guidelines are risk factor based and only indicate that cardiovascular disease would be reduced if followed. No specific percentage in the reduction of the incidence of disease is given. In contrast, when elimination of the disease is the stated goal of the guideline, the end result is clear. To date, this goal has been stated by only one organization devoted to eliminating cardiovascular disease. Conclusion: Guidelines need to be written to provide the physician and the patient with a specific end point that is expected when the guideline is followed. Patient acceptance and compliance will be much improved if the patient knows the risk/benefit of following the guideline’s recommendations.
文摘This study examines the transformative role of self-help groups(SHGs)in the socioeconomic development of rural women in Cooch Behar District,India,and their contribution toward achieving Sustainable Development Goals(SDGs)of the United Nations.In this study,we explored the effect of SHGs on rural women by specifically addressing SDGs,such as no poverty(SDG 1),zero hunger(SDG 2),good health and well-being(SDG 3),quality education(SDG 4),and gender equality(SDG 5).Given this issue,a cross-sectional survey and comparison analyses are needed to assess the socioeconomic development of rural women and their awareness level before and after the participation of rural women in SHGs.The survey conducted as part of this study was divided into three sections,namely,demographic characteristics,socioeconomic development,and awareness level,with each focusing on different aspects.A group of 400 individuals who were part of SHGs completed the questionnaire survey form.The results showed that the participation of rural women in SHGs significantly improved their socioeconomic development and awareness level,as supported by both mean values and t test results.Memberships in SHGs and microcredit programs were the major elements that boosted the socioeconomic development of rural women,which also achieves SDGs 1,2,3,4,and 5.This study revealed that participation in SHGs and related financial services significantly aided rural women in economically disadvantaged communities in accumulating savings and initiating entrepreneurial ventures.Moreover,participation in SHGs was instrumental in enhancing the self-confidence,self-efficacy,and overall self-esteem of rural women.Finally,doing so enabled them to move more freely for work and other activities and to make family and common decisions.
基金financially supported by Guangdong Province Basic and Applied Basic Research Fund Project(Grant No.2022B1515250009)Liaoning Provincial Natural Science Foundation-Doctoral Research Start-up Fund Project(Grant No.2024-BSBA-05)+1 种基金Major Science and Technology Innovation Project in Shandong Province(Grant No.2024CXGC010803)the National Natural Science Foundation of China(Grant Nos.52271269 and 12302147).
文摘The umbilical,a key component in offshore energy extraction,plays a vital role in ensuring the stable operation of the entire production system.The extensive variety of cross-sectional components creates highly complex layout combinations.Furthermore,due to constraints in component quantity and geometry within the cross-sectional layout,filler bodies must be incorporated to maintain cross-section performance.Conventional design approaches based on manual experience suffer from inefficiency,high variability,and difficulties in quantification.This paper presents a multi-level automatic filling optimization design method for umbilical cross-sectional layouts to address these limitations.Initially,the research establishes a multi-objective optimization model that considers compactness,balance,and wear resistance of the cross-section,employing an enhanced genetic algorithm to achieve a near-optimal layout.Subsequently,the study implements an image processing-based vacancy detection technique to accurately identify cross-sectional gaps.To manage the variability and diversity of these vacant regions,the research introduces a multi-level filling method that strategically selects and places filler bodies of varying dimensions,overcoming the constraints of uniform-size fillers.Additionally,the method incorporates a hierarchical strategy that subdivides the complex cross-section into multiple layers,enabling layer-by-layer optimization and filling.This approach reduces manufac-turing equipment requirements while ensuring practical production process feasibility.The methodology is validated through a specific umbilical case study.The results demonstrate improvements in compactness,balance,and wear resistance compared with the initial cross-section,offering novel insights and valuable references for filler design in umbilical cross-sections.
基金National Natural Science Foundation of China(Nos.42301473,42271424,42171397)Chinese Postdoctoral Innovation Talents Support Program(No.BX20230299)+2 种基金China Postdoctoral Science Foundation(No.2023M742884)Natural Science Foundation of Sichuan Province(Nos.24NSFSC2264,2025ZNSFSC0322)Key Research and Development Project of Sichuan Province(No.24ZDYF0633).
文摘As a key node of modern transportation network,the informationization management of road tunnels is crucial to ensure the operation safety and traffic efficiency.However,the existing tunnel vehicle modeling methods generally have problems such as insufficient 3D scene description capability and low dynamic update efficiency,which are difficult to meet the demand of real-time accurate management.For this reason,this paper proposes a vehicle twin modeling method for road tunnels.This approach starts from the actual management needs,and supports multi-level dynamic modeling from vehicle type,size to color by constructing a vehicle model library that can be flexibly invoked;at the same time,semantic constraint rules with geometric layout,behavioral attributes,and spatial relationships are designed to ensure that the virtual model matches with the real model with a high degree of similarity;ultimately,the prototype system is constructed and the case region is selected for the case study,and the dynamic vehicle status in the tunnel is realized by integrating real-time monitoring data with semantic constraints for precise virtual-real mapping.Finally,the prototype system is constructed and case experiments are conducted in selected case areas,which are combined with real-time monitoring data to realize dynamic updating and three-dimensional visualization of vehicle states in tunnels.The experiments show that the proposed method can run smoothly with an average rendering efficiency of 17.70 ms while guaranteeing the modeling accuracy(composite similarity of 0.867),which significantly improves the real-time and intuitive tunnel management.The research results provide reliable technical support for intelligent operation and emergency response of road tunnels,and offer new ideas for digital twin modeling of complex scenes.
文摘In my opinion,we should have more goals in our lives and have fewer complaints.As is known to all,goals make us go further and prevent us from being lazy.When we have goals,we are encouraged to work hard to achieve them.But if we lose our goals,we may feel uncertain and insecure.For a student,goals do play an essential role in study.I once set a goal to play better in basketball games,and I tried my best to train myself without any fear and hesitation.It was the goal that helped me accomplish my ambition.
基金the funding support from the National Natural Science Foundation of China(Grant No.52308340)Chongqing Talent Innovation and Entrepreneurship Demonstration Team Project(Grant No.cstc2024ycjh-bgzxm0012)the Science and Technology Projects supported by China Coal Technology and Engineering Chongqing Design and Research Institute(Group)Co.,Ltd.(Grant No.H20230317).
文摘Accurate prediction of landslide displacement is crucial for effective early warning of landslide disasters.While most existing prediction methods focus on time-series forecasting for individual monitoring points,there is limited research on the spatiotemporal characteristics of landslide deformation.This paper proposes a novel Multi-Relation Spatiotemporal Graph Residual Network with Multi-Level Feature Attention(MFA-MRSTGRN)that effectively improves the prediction performance of landslide displacement through spatiotemporal fusion.This model integrates internal seepage factors as data feature enhancements with external triggering factors,allowing for accurate capture of the complex spatiotemporal characteristics of landslide displacement and the construction of a multi-source heterogeneous dataset.The MFA-MRSTGRN model incorporates dynamic graph theory and four key modules:multilevel feature attention,temporal-residual decomposition,spatial multi-relational graph convolution,and spatiotemporal fusion prediction.This comprehensive approach enables the efficient analyses of multi-source heterogeneous datasets,facilitating adaptive exploration of the evolving multi-relational,multi-dimensional spatiotemporal complexities in landslides.When applying this model to predict the displacement of the Liangshuijing landslide,we demonstrate that the MFA-MRSTGRN model surpasses traditional models,such as random forest(RF),long short-term memory(LSTM),and spatial temporal graph convolutional networks(ST-GCN)models in terms of various evaluation metrics including mean absolute error(MAE=1.27 mm),root mean square error(RMSE=1.49 mm),mean absolute percentage error(MAPE=0.026),and R-squared(R^(2)=0.88).Furthermore,feature ablation experiments indicate that incorporating internal seepage factors improves the predictive performance of landslide displacement models.This research provides an advanced and reliable method for landslide displacement prediction.
基金co-supported by the National Key Research and Development Program of China(No.2022YFF0503100)the Youth Innovation Project of Pandeng Program of National Space Science Center,Chinese Academy of Sciences(No.E3PD40012S).
文摘As we look ahead to future lunar exploration missions, such as crewed lunar exploration and establishing lunar scientific research stations, the lunar rovers will need to cover vast distances. These distances could range from kilometers to tens of kilometers, and even hundreds and thousands of kilometers. Therefore, it is crucial to develop effective long-range path planning for lunar rovers to meet the demands of lunar patrol exploration. This paper presents a hierarchical map model path planning method that utilizes the existing high-resolution images, digital elevation models and mineral abundance maps. The objective is to address the issue of the construction of lunar rover travel costs in the absence of large-scale, high-resolution digital elevation models. This method models the reference and semantic layers using the middle- and low-resolution remote sensing data. The multi-scale obstacles on the lunar surface are extracted by combining the deep learning algorithm on the high-resolution image, and the obstacle avoidance layer is modeled. A two-stage exploratory path planning decision is employed for long-distance driving path planning on a global–local scale. The proposed method analyzes the long-distance accessibility of various areas of scientific significance, such as Rima Bode. A high-precision digital elevation model is created using stereo images to validate the method. Based on the findings, it can be observed that the entire route spans a distance of 930.32 km. The route demonstrates an impressive ability to avoid meter-level impact craters and linear structures while maintaining an average slope of less than 8°. This paper explores scientific research by traversing at least seven basalt units, uncovering the secrets of lunar volcanic activities, and establishing ‘golden spike’ reference points for lunar stratigraphy. The final result of path planning can serve as a valuable reference for the design, mission demonstration, and subsequent project implementation of the new manned lunar rover.
基金supported by the Fund of Key Laboratory of Biomedical Engineering of Hainan Province(No.BME20240001)the STI2030-Major Projects(No.2021ZD0200104)the National Natural Science Foundations of China under Grant 61771437.
文摘Deep learning networks are increasingly exploited in the field of neuronal soma segmentation.However,annotating dataset is also an expensive and time-consuming task.Unsupervised domain adaptation is an effective method to mitigate the problem,which is able to learn an adaptive segmentation model by transferring knowledge from a rich-labeled source domain.In this paper,we propose a multi-level distribution alignment-based unsupervised domain adaptation network(MDA-Net)for segmentation of 3D neuronal soma images.Distribution alignment is performed in both feature space and output space.In the feature space,features from different scales are adaptively fused to enhance the feature extraction capability for small target somata and con-strained to be domain invariant by adversarial adaptation strategy.In the output space,local discrepancy maps that can reveal the spatial structures of somata are constructed on the predicted segmentation results.Then thedistribution alignment is performed on the local discrepancies maps across domains to obtain a superior discrepancy map in the target domain,achieving refined segmentation performance of neuronal somata.Additionally,after a period of distribution align-ment procedure,a portion of target samples with high confident pseudo-labels are selected as training data,which assist in learning a more adaptive segmentation network.We verified the superiority of the proposed algorithm by comparing several domain adaptation networks on two 3D mouse brain neuronal somata datasets and one macaque brain neuronal soma dataset.
