The rapid growth of biomedical data,particularly multi-omics data including genomes,transcriptomics,proteomics,metabolomics,and epigenomics,medical research and clinical decision-making confront both new opportunities...The rapid growth of biomedical data,particularly multi-omics data including genomes,transcriptomics,proteomics,metabolomics,and epigenomics,medical research and clinical decision-making confront both new opportunities and obstacles.The huge and diversified nature of these datasets cannot always be managed using traditional data analysis methods.As a consequence,deep learning has emerged as a strong tool for analysing numerous omics data due to its ability to handle complex and non-linear relationships.This paper explores the fundamental concepts of deep learning and how they are used in multi-omics medical data mining.We demonstrate how autoencoders,variational autoencoders,multimodal models,attention mechanisms,transformers,and graph neural networks enable pattern analysis and recognition across all omics data.Deep learning has been found to be effective in illness classification,biomarker identification,gene network learning,and therapeutic efficacy prediction.We also consider critical problems like as data quality,model explainability,whether findings can be repeated,and computational power requirements.We now consider future elements of combining omics with clinical and imaging data,explainable AI,federated learning,and real-time diagnostics.Overall,this study emphasises the need of collaborating across disciplines to advance deep learning-based multi-omics research for precision medicine and comprehending complicated disorders.展开更多
High-throughput transcriptomics has evolved from bulk RNA-seq to single-cell and spatial profiling,yet its clinical translation still depends on effective integration across diverse omics and data modalities.Emerging ...High-throughput transcriptomics has evolved from bulk RNA-seq to single-cell and spatial profiling,yet its clinical translation still depends on effective integration across diverse omics and data modalities.Emerging foundation models and multimodal learning frameworks are enabling scalable and transferable representations of cellular states,while advances in interpretability and real-world data integration are bridging the gap between discovery and clinical application.This paper outlines a concise roadmap for AI-driven,transcriptome-centered multi-omics integration in precision medicine(Figure 1).展开更多
Gastrointestinal tumors require personalized treatment strategies due to their heterogeneity and complexity.Multimodal artificial intelligence(AI)addresses this challenge by integrating diverse data sources-including ...Gastrointestinal tumors require personalized treatment strategies due to their heterogeneity and complexity.Multimodal artificial intelligence(AI)addresses this challenge by integrating diverse data sources-including computed tomography(CT),magnetic resonance imaging(MRI),endoscopic imaging,and genomic profiles-to enable intelligent decision-making for individualized therapy.This approach leverages AI algorithms to fuse imaging,endoscopic,and omics data,facilitating comprehensive characterization of tumor biology,prediction of treatment response,and optimization of therapeutic strategies.By combining CT and MRI for structural assessment,endoscopic data for real-time visual inspection,and genomic information for molecular profiling,multimodal AI enhances the accuracy of patient stratification and treatment personalization.The clinical implementation of this technology demonstrates potential for improving patient outcomes,advancing precision oncology,and supporting individualized care in gastrointestinal cancers.Ultimately,multimodal AI serves as a transformative tool in oncology,bridging data integration with clinical application to effectively tailor therapies.展开更多
Growing attention has been directed to the use of satellite imagery and open geospatial data to understand large-scale sustainable development outcomes.Health and education are critical domains of the Unites Nations’...Growing attention has been directed to the use of satellite imagery and open geospatial data to understand large-scale sustainable development outcomes.Health and education are critical domains of the Unites Nations’Sus-tainable Development Goals(SDGs),yet existing research on the accessibility of corresponding services focused mainly on detailed but small-scale studies.This means that such studies lack accessibility metrics for large-scale quantitative evaluations.To address this deficiency,we evaluated the accessibility of health and education ser-vices in China's Mainland in 2021 using point-of-interest data,OpenStreetMap road data,land cover data,and WorldPop spatial demographic data.The accessibility metrics used were the least time costs of reaching hospital and school services and population coverage with a time cost of less than 1 h.On the basis of the road network and land cover information,the overall average time costs of reaching hospital and school were 20 and 22 min,respectively.In terms of population coverage,94.7%and 92.5%of the population in China has a time cost of less than 1 h in obtaining hospital and school services,respectively.Counties with low accessibility to hospitals and schools were highly coupled with poor areas and ecological function regions,with the time cost incurred in these areas being more than twice that experienced in non-poor and non-ecological areas.Furthermore,the cumulative time cost incurred by the bottom 20%of counties(by GDP)from access to hospital and school services reached approximately 80%of the national total.Low-GDP counties were compelled to suffer disproportionately increased time costs to acquire health and education services compared with high-GDP counties.The accessibil-ity metrics proposed in this study are highly related to SDGs 3 and 4,and they can serve as auxiliary data that can be used to enhance the evaluation of SDG outcomes.The analysis of the uneven distribution of health and education services in China can help identify areas with backward public services and may contribute to targeted and efficient policy interventions.展开更多
With the increase of different sensors,applications and customers,the demand from data providers and users is for a new geospatial data service model,which supports low cost,high dexterity,and which would provide a co...With the increase of different sensors,applications and customers,the demand from data providers and users is for a new geospatial data service model,which supports low cost,high dexterity,and which would provide a comprehensive service.Based on such requirements and demands,the 21AT TripleSat constellation terminal and data delivery and management system has been developed by a Beijing based high-tech enterprise,Twenty First Century Aerospace Technology Co.,Ltd.(21AT).The company is the first commercial Earth observation satellite operator and service provider in China.This new geospatial data service model allows the user to directly access multi-source satellite data,manage the data order,and carry out automatic massive data production and delivery.The solution also implements safe and hierarchical user management,statistical data analysis,and automatic information reports.In addition,a mobile application is also available for users to easily access system functions.This new geospatial solution has already been successfully applied and installed in many customer sites in China,and is now available globally for international clients interested in fast geospatial solutions.It enables the success of customers’operational services.Besides providing TripleSat Constellation images,the multi-source data access system also allows the users to access other satellite data sources,based on customized agreement.This paper describes and discusses this new geospatial data service model.展开更多
Although big data are widely used in various fields,its application is still rare in the study of mining subsidence prediction(MSP)caused by underground mining.Traditional research in MSP has the problem of oversimpli...Although big data are widely used in various fields,its application is still rare in the study of mining subsidence prediction(MSP)caused by underground mining.Traditional research in MSP has the problem of oversimplifying geological mining conditions,ignoring the fluctuation of rock layers with space.In the context of geospatial big data,a data-intensive FLAC3D(Fast Lagrangian Analysis of a Continua in 3 Dimensions)model is proposed in this paper based on borehole logs.In the modeling process,we developed a method to handle geospatial big data and were able to make full use of borehole logs.The effectiveness of the proposed method was verified by comparing the results of the traditional method,proposed method,and field observation.The findings show that the proposed method has obvious advantages over the traditional prediction results.The relative error of the maximum surface subsidence predicted by the proposed method decreased by 93.7%and the standard deviation of the prediction results(which was 70 points)decreased by 39.4%,on average.The data-intensive modeling method is of great significance for improving the accuracy of mining subsidence predictions.展开更多
Area Sampling Frames （ASFs） are the basis of many statistical programs around the world. To improve the accuracy, objectivity and efficiency of crop survey estimates, an automated stratification method based on geos...Area Sampling Frames （ASFs） are the basis of many statistical programs around the world. To improve the accuracy, objectivity and efficiency of crop survey estimates, an automated stratification method based on geospatial crop planting frequency and cultivation data is proposed. This paper investigates using 2008-2013 geospatial corn, soybean and wheat planting frequency data layers to create three corresponding single crop specific and one multi-crop specific South Dakota （SD） U.S. ASF stratifications. Corn, soybeans and wheat are three major crops in South Dakota. The crop specific ASF stratifications are developed based on crop frequency statistics derived at the primary sampling unit （PSU） level based on the Crop Frequency Data Layers. The SD corn, soybean and wheat mean planting frequency strata of the single crop stratifications are substratified by percent cultivation based on the 2013 Cultivation Layer. The three newly derived ASF stratifications provide more crop specific information when compared to the current National Agricultural Statistics Service （NASS） ASF based on percent cultivation alone. Further, a multi-crop stratification is developed based on the individual corn, soybean and wheat planting frequency data layers. It is observed that all four crop frequency based ASF stratifications consistently predict corn, soybean and wheat planting patterns well as verified by the 2014 Farm Service Agency （FSA） Common Land Unit （CLU） and 578 administrative data. This demonstrates that the new stratifications based on crop planting frequency and cultivation are crop type independent and applicable to all major crops. Further, these results indicate that the new crop specific ASF stratifications have great potential to improve ASF accuracy, efficiency and crop estimates.展开更多
Extreme weather conditions can adversely impact transport networks and driver behaviour,leading to variations in traffic volumes and travel times and increased accident rates.Emergency services that need to navigate t...Extreme weather conditions can adversely impact transport networks and driver behaviour,leading to variations in traffic volumes and travel times and increased accident rates.Emergency services that need to navigate to an accident site in the shortest possible time require real-time location-based weather and traffic information to coordinate their response.We therefore require historical and high-resolution temporal real-time data to identify districts and roads that are prone to different types of incidents during inclement weather and to better support emergency services in their decision-making.However,real-time assessment of the current transport network requires a dense sensor network that can provide high-resolution data using internet-enabled technology.In this research,we demonstrate how we obtain historical time-series and real-time data from sensors oper-ated by the Tyne and Wear Urban Traffic and Management Control Centre and the Urban Observatory based at Newcastle upon Tyne,UK.In the study,we assess the impact of rainfall on traffic volume and travel time,and the cascading impacts during a storm event in Newcastle during early October 2021.We also estimate the economic cost of the storm,with regards to transport disruption,as the cost of travel,using the“value of time”based on Department for Transport guidelines(2021).Using spatial-temporal analysis,we chose three locations to demonstrate how traffic parameters varied at different times throughout the storm.We identified increases in travel times of up to 600%and decreases in traffic volume of up to 100%when compared to historical data.Further,we assessed cascading impacts at important traffic locations and their broader implications for city areas.We estimated that the storm’s economic impact on one sensor location increased by up to 370%of the reference value.By analysing historical and real-time data,we detected and explained patterns in the data that would have remained uncovered if they had been examined individually.The combination of different data sources,such as traffic and weather,helps explain temporal fluctuations at locations where incidents were recorded near traffic detectors.We anticipate our study to be a starting point for stakeholders involved in incident response to identify bottleneck locations in the network to help prepare for similar future events.展开更多
This article assesses the feasibility of generating the geospatial data from a national classification standard.In this case,the National Standardization Agency(Badan Standardisasi Nasional)of Indonesia created and pu...This article assesses the feasibility of generating the geospatial data from a national classification standard.In this case,the National Standardization Agency(Badan Standardisasi Nasional)of Indonesia created and published a national seabed cover classification standard called SNI 7987–2014 but has not developed corresponding geospatial data.Geospatial data on seabed cover can be generated by integrating related thematic data,such as those on seafloor surficial sediments,coastal ecosystems,and coastal infrastructure.With consideration for these issues,this research evaluated the feasibility of using SNI 7987–2014 as a means of generating seabed cover geospatial data at scales of 1:250,000 and 1:50,000.To this end,the documentation accompanying the standard was evaluated via descriptive quantitative analysis through weighted scoring,and logical testing,after which overlay,feature selection based on the scored method and remote sensing analysis were carried out to develop the geospatial data prototypes.Results showed that the feasibility levels of using the prototypes for generating data at scales of 1:250,000 and 1:50,000 were 87.5%and 86.5%,respectively,indicating that SNI 7987–2014 can be fully used as the basis for generating geospatial data on seabed cover.展开更多
With the rapid growth of the Internet,the copyright protection problem occurs frequently,and unauthorized copying and distributing of geospatial data threaten the investments of data producers.Digital watermarking is ...With the rapid growth of the Internet,the copyright protection problem occurs frequently,and unauthorized copying and distributing of geospatial data threaten the investments of data producers.Digital watermarking is a possible solution to solve this issue.However,watermarking causes modifications in the original data resulting in distortion and affects accuracy,which is very important to geospatial vector data.This article provides distortion assessment of watermarked geospatial data using wavelet-based invisible watermarking.Eight wavelets at different wavelet decomposition levels are used for accuracy evaluation with the help of error measures such as maximum error and mean square error.Normalized correlation is used as a similarity index between original and extracted watermark.It is observed that the increase in the strength of embedding increases visual degradation.Haar wavelet outperforms the other wavelets,and the third wavelet decomposition level is proved to be optimal level for watermarking.展开更多
Accurate geospatial data are essential for geographic information systems(GIS),environmental monitoring,and urban planning.The deep integration of the open Internet and geographic information technology has led to inc...Accurate geospatial data are essential for geographic information systems(GIS),environmental monitoring,and urban planning.The deep integration of the open Internet and geographic information technology has led to increasing challenges in the integrity and security of spatial data.In this paper,we consider abnormal spatial data as missing data and focus on abnormal spatial data recovery.Existing geospatial data recovery methods require complete datasets for training,resulting in time-consuming data recovery and lack of generalization.To address these issues,we propose a GAIN-LSTM-based geospatial data recovery method(TGAIN),which consists of two main works:(1)it uses a long-short-term recurrent neural network(LSTM)as a generator to analyze geospatial temporal data and capture its temporal correlation;(2)it constructs a complete TGAIN network using a cue-masked fusion matrix mechanism to obtain data that matches the original distribution of the input data.The experimental results on two publicly accessible datasets demonstrate that our proposed TGAIN approach surpasses four contemporary and traditional models in terms of mean absolute error(MAE),root mean square error(RMSE),mean square error(MSE),mean absolute percentage error(MAPE),coefficient of determination(R2)and average computational time across various data missing rates.Concurrently,TGAIN exhibits superior accuracy and robustness in data recovery compared to existing models,especially when dealing with a high rate of missing data.Our model is of great significance in improving the integrity of geospatial data and provides data support for practical applications such as urban traffic optimization prediction and personal mobility analysis.展开更多
The development of technology and the demands of groups of interest for standardized digital geospatial information are increasing daily.The necessity for referred geospatial information,according to a Referencing Coo...The development of technology and the demands of groups of interest for standardized digital geospatial information are increasing daily.The necessity for referred geospatial information,according to a Referencing Coordinating System and European Standards,through a national GIS(Geographic Information System)system,requires a decision making of national and institutional importance.ASIG(State Authority for Geospatial Information)is the institution that administrates,implements,and maintains the NSDI(National Spatial Data Infrastructure).It is calculated that 80%of decision-making by public or private institutions uses geospatial data with a well-organized structure that enables efficiency.Thus,standardization of geospatial data by topic is one of the main objectives of implementing the NSDI in Albania.This is a complex task for the standard and the harmonization of geospatial data,which can be a good opportunity for professional awareness.This study shows in detail the methodology for the creation and implementation of data specification for geospatial information in Albania on the theme:Geology,adoption of the technical specification of the INSPIRE directive as well as the importance of ASIG as an institution that builds and maintains NSDI in Albania.展开更多
This paper endeavours to put the discussion on errors and uncertainties in geographical information systems (GISs) in a more systematic way by examining the strength and weakness of discrete objects and continuous fie...This paper endeavours to put the discussion on errors and uncertainties in geographical information systems (GISs) in a more systematic way by examining the strength and weakness of discrete objects and continuous fields, the two distinct schools of spatial data modelling. In doing so, it argues that neither discrete objects nor continuous fields alone provide objective and complete representations of highly complex geographical phenomena, though there are good reasons for asserting that continuous fields are better suited to modelling spatial dependence, heterogeneity and fuzziness significant in geographical reality than discrete objects. Thus, there seems to be merit in adopting an integrated model incorporating analytical capabilities of fields and generalization functions of objects, for which extended TIN(triangulated irregular network) models along with their duals (Voronoi diagrams) provide a pragmatical solution.展开更多
On the basis of the authors’ experiences of setting up an NGDC Web site,this paper attempts to present some significant aspects about the security of NGDC based on ASP.They include data storing,database maintenance,n...On the basis of the authors’ experiences of setting up an NGDC Web site,this paper attempts to present some significant aspects about the security of NGDC based on ASP.They include data storing,database maintenance,new technical support and so on.Firstly,this paper discusses how to provide the security of data which is saved in the hosts of NGDC.The security model of "Networks_DB Server_DB_DB Object" is also presented.In Windows NT Server,Internet Information Server (i.e.,IIS) is in charge of transferring message and the management of Web sites.ASP is also based on IIS.The advantages of virtual directory technique provided by IIS are emphasized. An NGDC Web site,at the Research Center of GIS in Wuhan Technical University of Surveying and Mapping is also mentioned in this paper.Because it is only an analoge used for case study,the transmission of digital spatial products is not included in the functions in this NGDC Web site.However,the management of spatial metadata is more important and some functions of metadata query are implemented in it.It is illustrated clearly in the functional diagram of the NGDC Web site.展开更多
Morphological(e.g.shape,size,and height)and function(e.g.working,living,and shopping)information of buildings is highly needed for urban planning and management as well as other applications such as city-scale buildin...Morphological(e.g.shape,size,and height)and function(e.g.working,living,and shopping)information of buildings is highly needed for urban planning and management as well as other applications such as city-scale building energy use modeling.Due to the limited availability of socio-economic geospatial data,it is more challenging to map building functions than building morphological information,especially over large areas.In this study,we proposed an integrated framework to map building functions in 50 U.S.cities by integrating multi-source web-based geospatial data.First,a web crawler was developed to extract Points of Interest(POIs)from Tripadvisor.com,and a map crawler was developed to extract POIs and land use parcels from Google Maps.Second,an unsupervised machine learning algorithm named OneClassSVM was used to identify residential buildings based on landscape features derived from Microsoft building footprints.Third,the type ratio of POIs and the area ratio of land use parcels were used to identify six non-residential functions(i.e.hospital,hotel,school,shop,restaurant,and office).The accuracy assessment indicates that the proposed framework performed well,with an average overall accuracy of 94%and a kappa coefficient of 0.63.With the worldwide coverage of Google Maps and Tripadvisor.com,the proposed framework is transferable to other cities over the world.The data products generated from this study are of great use for quantitative city-scale urban studies,such as building energy use modeling at the single building level over large areas.展开更多
Climate change effects have had negative effects on most farmers, both small and large-scale, with weather patterns increasingly becoming unpredictable, such that farmers are unable to plan well for their farming, res...Climate change effects have had negative effects on most farmers, both small and large-scale, with weather patterns increasingly becoming unpredictable, such that farmers are unable to plan well for their farming, resulting in reduced harvests and sometimes losses for farmers. Better availability of information such as weather patterns, suitable crops, nutrient requirements based on soil types and conditions would greatly alleviate these challenges. While geospatial information is being developed and improved continuously by researchers, its accessibility and use by the counties has not been established and cannot be identified as contributing to better crop production outcomes. The aim of this study, therefore, was to assess the awareness and status of geospatial data availability and use for crop production, and the level of the relevant capacities, both human and infrastructural, in selected Counties of Kenya. A survey was conducted in the four counties of Vihiga, Kilifi, Wajir and Nyeri and key informant interviews were conducted with both management and technical County Agricultural Officers, as well as sub-county agricultural extension officers. From the results of the survey, out of the four counties, only one has adequate infrastructure in terms of hard-ware, software and connectivity to conduct useful geospatial data acquisition and processing. While most indicated awareness of the existence of geospatial data, limited resources, low skills and knowledge have restricted any meaningful sourcing of and access to data, with only 38% moderately or highly skilled in acquisition, 48% in processing and 57% in interpretation and use of geospatial data. The study concludes that moderate skills and capacities available within the counties have considerable potential to make use the available geospatial data to inform farmers accordingly and improve their farming outcomes.展开更多
In general, geospatial data can be divided into two formats, raster and vector formats. A raster consists of a matrix of cells where each cell contains a value representing quantitative information, such as temperatur...In general, geospatial data can be divided into two formats, raster and vector formats. A raster consists of a matrix of cells where each cell contains a value representing quantitative information, such as temperature, vegetation intensity, land use/cover, elevation, etc. A vector data consists of points, lines and polygons representing location or distance or area of landscape features in graphical forms. Many raster data are derived from remote sensing techniques using sophisticated sensors by quantitative approach and many vector data are generated from GIS processes by qualitative approach. Among them, land use/cover data is frequently used in many GIS analyses and spatial modeling processes. However, proper use of quantitative and qualitative geospatial data is important in spatial modeling and decision making. In this article, we discuss common geospatial data formats, their origins and proper use in spatial modelling and decision making processes.展开更多
The Kinta Valley is an area of karst in the north-western part of Peninsular Malaysia. Over 30 years of uncontrolled land use and development has led to significant changes in topography and geomorphology, such as the...The Kinta Valley is an area of karst in the north-western part of Peninsular Malaysia. Over 30 years of uncontrolled land use and development has led to significant changes in topography and geomorphology, such as the appearance of sinkholes. In this paper, geospatial techniques were utilized to the task of evaluating sinkholes susceptibility map using a spatial multi criteria evaluation approach (SMCE). Sinkhole location and a spatial database were applied to calculate eight inherent causative factors for limestone instability namely: lithology, structure (lineament), soil cover, slope, land use mining, urban area features, ponds and rivers. The preparation of the sinkhole geohazard map involved summing the weighted values for each hazard element, which permits the construction of geohazard model;the results of the analysis were validated using the previous actual sinkholes locations in the study area. The spatial distribution of sinkholes occurrence, urban development, faults distribution and ex-mining ponds are factors that are directly responsible for all sinkholes subsidence hazards. Further, the resulting geo-hazard map shows that 93% of recent sinkholes occur in areas where the model flags as “high” and “very high” potential hazard, located in the urbanized part of the valley, while less-developed areas to the west and southwest suffered less sinkhole development. The results can be used for hazard prevention and land-use planning.展开更多
The basic procedure of the Italian Civil Protection Department aims at reducing disaster losses by giving prominence to a proactive strategy, focusing on prevision and prevention of hazard events rather than postdisat...The basic procedure of the Italian Civil Protection Department aims at reducing disaster losses by giving prominence to a proactive strategy, focusing on prevision and prevention of hazard events rather than postdisater activities. Italian law commits municipalities to produce Emergency Plans that include risk scenarios as well as all data required for emergency management, such as structures, infrastructures and human resources. However the law in the matter of Civil Protection does not supply information about how to produce and archive necessary data for emergency planning and management. For this reason, we propose a standard methodology to create a geodatabase using GIS software, to collect all data that could be used by municipalities to create Emergency Plans. The resulting geodatabase provides a tool for hazard mitigation planning, allowing not only the identification of areas at risk, but also the structures, infrastructures and resources needed to overcome a crisis, thus improving all strategies of risk reduction and the resilience of the system [1].展开更多
In the past two to three years, the world has been heavily affected by the infectious coronavirus disease and Malawi has not been spared due to its interconnection with neighboring countries. There is no management to...In the past two to three years, the world has been heavily affected by the infectious coronavirus disease and Malawi has not been spared due to its interconnection with neighboring countries. There is no management tool to identify and model the vulnerabilities of Malawi’s districts in prioritizing health services as far as coronavirus prevalence and other infectious diseases are concerned. The aim of this study was to model coronavirus vulnerability in all districts in Malawi using Geographic Information System (GIS) to monitor the disease’s cumulative prevalence over the severely affected period between 2020 and 2021. To achieve this, four parameters associated with coronavirus prevalence, including population density, percentage of older people, temperature, and humidity, were prepared in a GIS environment and used in the modelling process. A multiscale geographically weighted regression (MGWR) model was used to model and determine the vulnerability of coronavirus in Malawi. In the MGWR modelling, the Fixed Spatial Kernel was used following a Gaussian distribution model type. The Results indicated that population density and older people (age greater than 60 years) have a more significant impact on coronavirus prevalence in Malawi. The modelling further shows that Malawi, between April 2020 and May 2021, Lilongwe, Blantyre and Thyolo were more vulnerable to coronavirus than other districts. This research has shown that spatial variability of Covid-19 cases using MGWR has the potential of providing useful insights to policymakers for targeted interventions that could otherwise not be possible to detect using non-geovisualization techniques.展开更多
文摘The rapid growth of biomedical data,particularly multi-omics data including genomes,transcriptomics,proteomics,metabolomics,and epigenomics,medical research and clinical decision-making confront both new opportunities and obstacles.The huge and diversified nature of these datasets cannot always be managed using traditional data analysis methods.As a consequence,deep learning has emerged as a strong tool for analysing numerous omics data due to its ability to handle complex and non-linear relationships.This paper explores the fundamental concepts of deep learning and how they are used in multi-omics medical data mining.We demonstrate how autoencoders,variational autoencoders,multimodal models,attention mechanisms,transformers,and graph neural networks enable pattern analysis and recognition across all omics data.Deep learning has been found to be effective in illness classification,biomarker identification,gene network learning,and therapeutic efficacy prediction.We also consider critical problems like as data quality,model explainability,whether findings can be repeated,and computational power requirements.We now consider future elements of combining omics with clinical and imaging data,explainable AI,federated learning,and real-time diagnostics.Overall,this study emphasises the need of collaborating across disciplines to advance deep learning-based multi-omics research for precision medicine and comprehending complicated disorders.
文摘High-throughput transcriptomics has evolved from bulk RNA-seq to single-cell and spatial profiling,yet its clinical translation still depends on effective integration across diverse omics and data modalities.Emerging foundation models and multimodal learning frameworks are enabling scalable and transferable representations of cellular states,while advances in interpretability and real-world data integration are bridging the gap between discovery and clinical application.This paper outlines a concise roadmap for AI-driven,transcriptome-centered multi-omics integration in precision medicine(Figure 1).
基金Supported by Xuhui District Health Commission,No.SHXH202214.
文摘Gastrointestinal tumors require personalized treatment strategies due to their heterogeneity and complexity.Multimodal artificial intelligence(AI)addresses this challenge by integrating diverse data sources-including computed tomography(CT),magnetic resonance imaging(MRI),endoscopic imaging,and genomic profiles-to enable intelligent decision-making for individualized therapy.This approach leverages AI algorithms to fuse imaging,endoscopic,and omics data,facilitating comprehensive characterization of tumor biology,prediction of treatment response,and optimization of therapeutic strategies.By combining CT and MRI for structural assessment,endoscopic data for real-time visual inspection,and genomic information for molecular profiling,multimodal AI enhances the accuracy of patient stratification and treatment personalization.The clinical implementation of this technology demonstrates potential for improving patient outcomes,advancing precision oncology,and supporting individualized care in gastrointestinal cancers.Ultimately,multimodal AI serves as a transformative tool in oncology,bridging data integration with clinical application to effectively tailor therapies.
基金This work was supported by the National Natural Science Foundation for Distinguished Young Scholars of China(Grant No.41725006).
文摘Growing attention has been directed to the use of satellite imagery and open geospatial data to understand large-scale sustainable development outcomes.Health and education are critical domains of the Unites Nations’Sus-tainable Development Goals(SDGs),yet existing research on the accessibility of corresponding services focused mainly on detailed but small-scale studies.This means that such studies lack accessibility metrics for large-scale quantitative evaluations.To address this deficiency,we evaluated the accessibility of health and education ser-vices in China's Mainland in 2021 using point-of-interest data,OpenStreetMap road data,land cover data,and WorldPop spatial demographic data.The accessibility metrics used were the least time costs of reaching hospital and school services and population coverage with a time cost of less than 1 h.On the basis of the road network and land cover information,the overall average time costs of reaching hospital and school were 20 and 22 min,respectively.In terms of population coverage,94.7%and 92.5%of the population in China has a time cost of less than 1 h in obtaining hospital and school services,respectively.Counties with low accessibility to hospitals and schools were highly coupled with poor areas and ecological function regions,with the time cost incurred in these areas being more than twice that experienced in non-poor and non-ecological areas.Furthermore,the cumulative time cost incurred by the bottom 20%of counties(by GDP)from access to hospital and school services reached approximately 80%of the national total.Low-GDP counties were compelled to suffer disproportionately increased time costs to acquire health and education services compared with high-GDP counties.The accessibil-ity metrics proposed in this study are highly related to SDGs 3 and 4,and they can serve as auxiliary data that can be used to enhance the evaluation of SDG outcomes.The analysis of the uneven distribution of health and education services in China can help identify areas with backward public services and may contribute to targeted and efficient policy interventions.
基金supported by the project of Beijing Municipal Science and Technology Commission and Science and Technology Innovation Base of Cultivating and Developing Engineering[grant number Z161100005016069]the National High Technology Research and Development Program[grant number 2013AA12A303].
文摘With the increase of different sensors,applications and customers,the demand from data providers and users is for a new geospatial data service model,which supports low cost,high dexterity,and which would provide a comprehensive service.Based on such requirements and demands,the 21AT TripleSat constellation terminal and data delivery and management system has been developed by a Beijing based high-tech enterprise,Twenty First Century Aerospace Technology Co.,Ltd.(21AT).The company is the first commercial Earth observation satellite operator and service provider in China.This new geospatial data service model allows the user to directly access multi-source satellite data,manage the data order,and carry out automatic massive data production and delivery.The solution also implements safe and hierarchical user management,statistical data analysis,and automatic information reports.In addition,a mobile application is also available for users to easily access system functions.This new geospatial solution has already been successfully applied and installed in many customer sites in China,and is now available globally for international clients interested in fast geospatial solutions.It enables the success of customers’operational services.Besides providing TripleSat Constellation images,the multi-source data access system also allows the users to access other satellite data sources,based on customized agreement.This paper describes and discusses this new geospatial data service model.
文摘Although big data are widely used in various fields,its application is still rare in the study of mining subsidence prediction(MSP)caused by underground mining.Traditional research in MSP has the problem of oversimplifying geological mining conditions,ignoring the fluctuation of rock layers with space.In the context of geospatial big data,a data-intensive FLAC3D(Fast Lagrangian Analysis of a Continua in 3 Dimensions)model is proposed in this paper based on borehole logs.In the modeling process,we developed a method to handle geospatial big data and were able to make full use of borehole logs.The effectiveness of the proposed method was verified by comparing the results of the traditional method,proposed method,and field observation.The findings show that the proposed method has obvious advantages over the traditional prediction results.The relative error of the maximum surface subsidence predicted by the proposed method decreased by 93.7%and the standard deviation of the prediction results(which was 70 points)decreased by 39.4%,on average.The data-intensive modeling method is of great significance for improving the accuracy of mining subsidence predictions.
文摘Area Sampling Frames （ASFs） are the basis of many statistical programs around the world. To improve the accuracy, objectivity and efficiency of crop survey estimates, an automated stratification method based on geospatial crop planting frequency and cultivation data is proposed. This paper investigates using 2008-2013 geospatial corn, soybean and wheat planting frequency data layers to create three corresponding single crop specific and one multi-crop specific South Dakota （SD） U.S. ASF stratifications. Corn, soybeans and wheat are three major crops in South Dakota. The crop specific ASF stratifications are developed based on crop frequency statistics derived at the primary sampling unit （PSU） level based on the Crop Frequency Data Layers. The SD corn, soybean and wheat mean planting frequency strata of the single crop stratifications are substratified by percent cultivation based on the 2013 Cultivation Layer. The three newly derived ASF stratifications provide more crop specific information when compared to the current National Agricultural Statistics Service （NASS） ASF based on percent cultivation alone. Further, a multi-crop stratification is developed based on the individual corn, soybean and wheat planting frequency data layers. It is observed that all four crop frequency based ASF stratifications consistently predict corn, soybean and wheat planting patterns well as verified by the 2014 Farm Service Agency （FSA） Common Land Unit （CLU） and 578 administrative data. This demonstrates that the new stratifications based on crop planting frequency and cultivation are crop type independent and applicable to all major crops. Further, these results indicate that the new crop specific ASF stratifications have great potential to improve ASF accuracy, efficiency and crop estimates.
基金supported by the United Kingdom’s Engineering and Physical Sciences Research Council(EPSRC)under grant number EP/S023577/1,and Ordnance Survey of Great Britain.
文摘Extreme weather conditions can adversely impact transport networks and driver behaviour,leading to variations in traffic volumes and travel times and increased accident rates.Emergency services that need to navigate to an accident site in the shortest possible time require real-time location-based weather and traffic information to coordinate their response.We therefore require historical and high-resolution temporal real-time data to identify districts and roads that are prone to different types of incidents during inclement weather and to better support emergency services in their decision-making.However,real-time assessment of the current transport network requires a dense sensor network that can provide high-resolution data using internet-enabled technology.In this research,we demonstrate how we obtain historical time-series and real-time data from sensors oper-ated by the Tyne and Wear Urban Traffic and Management Control Centre and the Urban Observatory based at Newcastle upon Tyne,UK.In the study,we assess the impact of rainfall on traffic volume and travel time,and the cascading impacts during a storm event in Newcastle during early October 2021.We also estimate the economic cost of the storm,with regards to transport disruption,as the cost of travel,using the“value of time”based on Department for Transport guidelines(2021).Using spatial-temporal analysis,we chose three locations to demonstrate how traffic parameters varied at different times throughout the storm.We identified increases in travel times of up to 600%and decreases in traffic volume of up to 100%when compared to historical data.Further,we assessed cascading impacts at important traffic locations and their broader implications for city areas.We estimated that the storm’s economic impact on one sensor location increased by up to 370%of the reference value.By analysing historical and real-time data,we detected and explained patterns in the data that would have remained uncovered if they had been examined individually.The combination of different data sources,such as traffic and weather,helps explain temporal fluctuations at locations where incidents were recorded near traffic detectors.We anticipate our study to be a starting point for stakeholders involved in incident response to identify bottleneck locations in the network to help prepare for similar future events.
文摘This article assesses the feasibility of generating the geospatial data from a national classification standard.In this case,the National Standardization Agency(Badan Standardisasi Nasional)of Indonesia created and published a national seabed cover classification standard called SNI 7987–2014 but has not developed corresponding geospatial data.Geospatial data on seabed cover can be generated by integrating related thematic data,such as those on seafloor surficial sediments,coastal ecosystems,and coastal infrastructure.With consideration for these issues,this research evaluated the feasibility of using SNI 7987–2014 as a means of generating seabed cover geospatial data at scales of 1:250,000 and 1:50,000.To this end,the documentation accompanying the standard was evaluated via descriptive quantitative analysis through weighted scoring,and logical testing,after which overlay,feature selection based on the scored method and remote sensing analysis were carried out to develop the geospatial data prototypes.Results showed that the feasibility levels of using the prototypes for generating data at scales of 1:250,000 and 1:50,000 were 87.5%and 86.5%,respectively,indicating that SNI 7987–2014 can be fully used as the basis for generating geospatial data on seabed cover.
文摘With the rapid growth of the Internet,the copyright protection problem occurs frequently,and unauthorized copying and distributing of geospatial data threaten the investments of data producers.Digital watermarking is a possible solution to solve this issue.However,watermarking causes modifications in the original data resulting in distortion and affects accuracy,which is very important to geospatial vector data.This article provides distortion assessment of watermarked geospatial data using wavelet-based invisible watermarking.Eight wavelets at different wavelet decomposition levels are used for accuracy evaluation with the help of error measures such as maximum error and mean square error.Normalized correlation is used as a similarity index between original and extracted watermark.It is observed that the increase in the strength of embedding increases visual degradation.Haar wavelet outperforms the other wavelets,and the third wavelet decomposition level is proved to be optimal level for watermarking.
基金supported by the National Natural Science Foundation of China(No.62002144)Ministry of Education Chunhui Plan Research Project(Nos.202200345,HZKY20220125).
文摘Accurate geospatial data are essential for geographic information systems(GIS),environmental monitoring,and urban planning.The deep integration of the open Internet and geographic information technology has led to increasing challenges in the integrity and security of spatial data.In this paper,we consider abnormal spatial data as missing data and focus on abnormal spatial data recovery.Existing geospatial data recovery methods require complete datasets for training,resulting in time-consuming data recovery and lack of generalization.To address these issues,we propose a GAIN-LSTM-based geospatial data recovery method(TGAIN),which consists of two main works:(1)it uses a long-short-term recurrent neural network(LSTM)as a generator to analyze geospatial temporal data and capture its temporal correlation;(2)it constructs a complete TGAIN network using a cue-masked fusion matrix mechanism to obtain data that matches the original distribution of the input data.The experimental results on two publicly accessible datasets demonstrate that our proposed TGAIN approach surpasses four contemporary and traditional models in terms of mean absolute error(MAE),root mean square error(RMSE),mean square error(MSE),mean absolute percentage error(MAPE),coefficient of determination(R2)and average computational time across various data missing rates.Concurrently,TGAIN exhibits superior accuracy and robustness in data recovery compared to existing models,especially when dealing with a high rate of missing data.Our model is of great significance in improving the integrity of geospatial data and provides data support for practical applications such as urban traffic optimization prediction and personal mobility analysis.
文摘The development of technology and the demands of groups of interest for standardized digital geospatial information are increasing daily.The necessity for referred geospatial information,according to a Referencing Coordinating System and European Standards,through a national GIS(Geographic Information System)system,requires a decision making of national and institutional importance.ASIG(State Authority for Geospatial Information)is the institution that administrates,implements,and maintains the NSDI(National Spatial Data Infrastructure).It is calculated that 80%of decision-making by public or private institutions uses geospatial data with a well-organized structure that enables efficiency.Thus,standardization of geospatial data by topic is one of the main objectives of implementing the NSDI in Albania.This is a complex task for the standard and the harmonization of geospatial data,which can be a good opportunity for professional awareness.This study shows in detail the methodology for the creation and implementation of data specification for geospatial information in Albania on the theme:Geology,adoption of the technical specification of the INSPIRE directive as well as the importance of ASIG as an institution that builds and maintains NSDI in Albania.
基金Project supported by a Young Teacher Research Foundation Award and a National Bureau of Surveying and Mapping Grant(No.97013)
文摘This paper endeavours to put the discussion on errors and uncertainties in geographical information systems (GISs) in a more systematic way by examining the strength and weakness of discrete objects and continuous fields, the two distinct schools of spatial data modelling. In doing so, it argues that neither discrete objects nor continuous fields alone provide objective and complete representations of highly complex geographical phenomena, though there are good reasons for asserting that continuous fields are better suited to modelling spatial dependence, heterogeneity and fuzziness significant in geographical reality than discrete objects. Thus, there seems to be merit in adopting an integrated model incorporating analytical capabilities of fields and generalization functions of objects, for which extended TIN(triangulated irregular network) models along with their duals (Voronoi diagrams) provide a pragmatical solution.
文摘On the basis of the authors’ experiences of setting up an NGDC Web site,this paper attempts to present some significant aspects about the security of NGDC based on ASP.They include data storing,database maintenance,new technical support and so on.Firstly,this paper discusses how to provide the security of data which is saved in the hosts of NGDC.The security model of "Networks_DB Server_DB_DB Object" is also presented.In Windows NT Server,Internet Information Server (i.e.,IIS) is in charge of transferring message and the management of Web sites.ASP is also based on IIS.The advantages of virtual directory technique provided by IIS are emphasized. An NGDC Web site,at the Research Center of GIS in Wuhan Technical University of Surveying and Mapping is also mentioned in this paper.Because it is only an analoge used for case study,the transmission of digital spatial products is not included in the functions in this NGDC Web site.However,the management of spatial metadata is more important and some functions of metadata query are implemented in it.It is illustrated clearly in the functional diagram of the NGDC Web site.
基金supported by the National Science Foundation[grant numbers 1854502 and 1855902]Publication was made possible in part by support from the HKU Libraries Open Access Author Fund sponsored by the HKU Libraries.USDA is an equal opportunity provider and employer.Mention of trade names or commercial products in this publication is solely for the purpose of providing specific information and does not imply recommendation or endorsement by the U.S.Department of Agriculture.
文摘Morphological(e.g.shape,size,and height)and function(e.g.working,living,and shopping)information of buildings is highly needed for urban planning and management as well as other applications such as city-scale building energy use modeling.Due to the limited availability of socio-economic geospatial data,it is more challenging to map building functions than building morphological information,especially over large areas.In this study,we proposed an integrated framework to map building functions in 50 U.S.cities by integrating multi-source web-based geospatial data.First,a web crawler was developed to extract Points of Interest(POIs)from Tripadvisor.com,and a map crawler was developed to extract POIs and land use parcels from Google Maps.Second,an unsupervised machine learning algorithm named OneClassSVM was used to identify residential buildings based on landscape features derived from Microsoft building footprints.Third,the type ratio of POIs and the area ratio of land use parcels were used to identify six non-residential functions(i.e.hospital,hotel,school,shop,restaurant,and office).The accuracy assessment indicates that the proposed framework performed well,with an average overall accuracy of 94%and a kappa coefficient of 0.63.With the worldwide coverage of Google Maps and Tripadvisor.com,the proposed framework is transferable to other cities over the world.The data products generated from this study are of great use for quantitative city-scale urban studies,such as building energy use modeling at the single building level over large areas.
文摘Climate change effects have had negative effects on most farmers, both small and large-scale, with weather patterns increasingly becoming unpredictable, such that farmers are unable to plan well for their farming, resulting in reduced harvests and sometimes losses for farmers. Better availability of information such as weather patterns, suitable crops, nutrient requirements based on soil types and conditions would greatly alleviate these challenges. While geospatial information is being developed and improved continuously by researchers, its accessibility and use by the counties has not been established and cannot be identified as contributing to better crop production outcomes. The aim of this study, therefore, was to assess the awareness and status of geospatial data availability and use for crop production, and the level of the relevant capacities, both human and infrastructural, in selected Counties of Kenya. A survey was conducted in the four counties of Vihiga, Kilifi, Wajir and Nyeri and key informant interviews were conducted with both management and technical County Agricultural Officers, as well as sub-county agricultural extension officers. From the results of the survey, out of the four counties, only one has adequate infrastructure in terms of hard-ware, software and connectivity to conduct useful geospatial data acquisition and processing. While most indicated awareness of the existence of geospatial data, limited resources, low skills and knowledge have restricted any meaningful sourcing of and access to data, with only 38% moderately or highly skilled in acquisition, 48% in processing and 57% in interpretation and use of geospatial data. The study concludes that moderate skills and capacities available within the counties have considerable potential to make use the available geospatial data to inform farmers accordingly and improve their farming outcomes.
文摘In general, geospatial data can be divided into two formats, raster and vector formats. A raster consists of a matrix of cells where each cell contains a value representing quantitative information, such as temperature, vegetation intensity, land use/cover, elevation, etc. A vector data consists of points, lines and polygons representing location or distance or area of landscape features in graphical forms. Many raster data are derived from remote sensing techniques using sophisticated sensors by quantitative approach and many vector data are generated from GIS processes by qualitative approach. Among them, land use/cover data is frequently used in many GIS analyses and spatial modeling processes. However, proper use of quantitative and qualitative geospatial data is important in spatial modeling and decision making. In this article, we discuss common geospatial data formats, their origins and proper use in spatial modelling and decision making processes.
文摘The Kinta Valley is an area of karst in the north-western part of Peninsular Malaysia. Over 30 years of uncontrolled land use and development has led to significant changes in topography and geomorphology, such as the appearance of sinkholes. In this paper, geospatial techniques were utilized to the task of evaluating sinkholes susceptibility map using a spatial multi criteria evaluation approach (SMCE). Sinkhole location and a spatial database were applied to calculate eight inherent causative factors for limestone instability namely: lithology, structure (lineament), soil cover, slope, land use mining, urban area features, ponds and rivers. The preparation of the sinkhole geohazard map involved summing the weighted values for each hazard element, which permits the construction of geohazard model;the results of the analysis were validated using the previous actual sinkholes locations in the study area. The spatial distribution of sinkholes occurrence, urban development, faults distribution and ex-mining ponds are factors that are directly responsible for all sinkholes subsidence hazards. Further, the resulting geo-hazard map shows that 93% of recent sinkholes occur in areas where the model flags as “high” and “very high” potential hazard, located in the urbanized part of the valley, while less-developed areas to the west and southwest suffered less sinkhole development. The results can be used for hazard prevention and land-use planning.
文摘The basic procedure of the Italian Civil Protection Department aims at reducing disaster losses by giving prominence to a proactive strategy, focusing on prevision and prevention of hazard events rather than postdisater activities. Italian law commits municipalities to produce Emergency Plans that include risk scenarios as well as all data required for emergency management, such as structures, infrastructures and human resources. However the law in the matter of Civil Protection does not supply information about how to produce and archive necessary data for emergency planning and management. For this reason, we propose a standard methodology to create a geodatabase using GIS software, to collect all data that could be used by municipalities to create Emergency Plans. The resulting geodatabase provides a tool for hazard mitigation planning, allowing not only the identification of areas at risk, but also the structures, infrastructures and resources needed to overcome a crisis, thus improving all strategies of risk reduction and the resilience of the system [1].
文摘In the past two to three years, the world has been heavily affected by the infectious coronavirus disease and Malawi has not been spared due to its interconnection with neighboring countries. There is no management tool to identify and model the vulnerabilities of Malawi’s districts in prioritizing health services as far as coronavirus prevalence and other infectious diseases are concerned. The aim of this study was to model coronavirus vulnerability in all districts in Malawi using Geographic Information System (GIS) to monitor the disease’s cumulative prevalence over the severely affected period between 2020 and 2021. To achieve this, four parameters associated with coronavirus prevalence, including population density, percentage of older people, temperature, and humidity, were prepared in a GIS environment and used in the modelling process. A multiscale geographically weighted regression (MGWR) model was used to model and determine the vulnerability of coronavirus in Malawi. In the MGWR modelling, the Fixed Spatial Kernel was used following a Gaussian distribution model type. The Results indicated that population density and older people (age greater than 60 years) have a more significant impact on coronavirus prevalence in Malawi. The modelling further shows that Malawi, between April 2020 and May 2021, Lilongwe, Blantyre and Thyolo were more vulnerable to coronavirus than other districts. This research has shown that spatial variability of Covid-19 cases using MGWR has the potential of providing useful insights to policymakers for targeted interventions that could otherwise not be possible to detect using non-geovisualization techniques.
