When dealing with imbalanced datasets,the traditional support vectormachine(SVM)tends to produce a classification hyperplane that is biased towards the majority class,which exhibits poor robustness.This paper proposes...When dealing with imbalanced datasets,the traditional support vectormachine(SVM)tends to produce a classification hyperplane that is biased towards the majority class,which exhibits poor robustness.This paper proposes a high-performance classification algorithm specifically designed for imbalanced datasets.The proposed method first uses a biased second-order cone programming support vectormachine(B-SOCP-SVM)to identify the support vectors(SVs)and non-support vectors(NSVs)in the imbalanced data.Then,it applies the synthetic minority over-sampling technique(SV-SMOTE)to oversample the support vectors of the minority class and uses the random under-sampling technique(NSV-RUS)multiple times to undersample the non-support vectors of the majority class.Combining the above-obtained minority class data set withmultiple majority class datasets can obtainmultiple new balanced data sets.Finally,SOCP-SVM is used to classify each data set,and the final result is obtained through the integrated algorithm.Experimental results demonstrate that the proposed method performs excellently on imbalanced datasets.展开更多
Climate change significantly affects environment,ecosystems,communities,and economies.These impacts often result in quick and gradual changes in water resources,environmental conditions,and weather patterns.A geograph...Climate change significantly affects environment,ecosystems,communities,and economies.These impacts often result in quick and gradual changes in water resources,environmental conditions,and weather patterns.A geographical study was conducted in Arizona State,USA,to examine monthly precipi-tation concentration rates over time.This analysis used a high-resolution 0.50×0.50 grid for monthly precip-itation data from 1961 to 2022,Provided by the Climatic Research Unit.The study aimed to analyze climatic changes affected the first and last five years of each decade,as well as the entire decade,during the specified period.GIS was used to meet the objectives of this study.Arizona experienced 51–568 mm,67–560 mm,63–622 mm,and 52–590 mm of rainfall in the sixth,seventh,eighth,and ninth decades of the second millennium,respectively.Both the first and second five year periods of each decade showed accept-able rainfall amounts despite fluctuations.However,rainfall decreased in the first and second decades of the third millennium.and in the first two years of the third decade.Rainfall amounts dropped to 42–472 mm,55–469 mm,and 74–498 mm,respectively,indicating a downward trend in precipitation.The central part of the state received the highest rainfall,while the eastern and western regions(spanning north to south)had significantly less.Over the decades of the third millennium,the average annual rainfall every five years was relatively low,showing a declining trend due to severe climate changes,generally ranging between 35 mm and 498 mm.The central regions consistently received more rainfall than the eastern and western outskirts.Arizona is currently experiencing a decrease in rainfall due to climate change,a situation that could deterio-rate further.This highlights the need to optimize the use of existing rainfall and explore alternative water sources.展开更多
This paper proposed a method to generate semi-experimental biomedical datasets based on full-wave simulation software.The system noise such as antenna port couplings is fully considered in the proposed datasets,which ...This paper proposed a method to generate semi-experimental biomedical datasets based on full-wave simulation software.The system noise such as antenna port couplings is fully considered in the proposed datasets,which is more realistic than synthetical datasets.In this paper,datasets containing different shapes are constructed based on the relative permittivities of human tissues.Then,a back-propagation scheme is used to obtain the rough reconstructions,which will be fed into a U-net convolutional neural network(CNN)to recover the high-resolution images.Numerical results show that the network trained on the datasets generated by the proposed method can obtain satisfying reconstruction results and is promising to be applied in real-time biomedical imaging.展开更多
Purpose:Many science,technology and innovation(STI)resources are attached with several different labels.To assign automatically the resulting labels to an interested instance,many approaches with good performance on t...Purpose:Many science,technology and innovation(STI)resources are attached with several different labels.To assign automatically the resulting labels to an interested instance,many approaches with good performance on the benchmark datasets have been proposed for multi-label classification task in the literature.Furthermore,several open-source tools implementing these approaches have also been developed.However,the characteristics of real-world multi-label patent and publication datasets are not completely in line with those of benchmark ones.Therefore,the main purpose of this paper is to evaluate comprehensively seven multi-label classification methods on real-world datasets.Research limitations:Three real-world datasets differ in the following aspects:statement,data quality,and purposes.Additionally,open-source tools designed for multi-label classification also have intrinsic differences in their approaches for data processing and feature selection,which in turn impacts the performance of a multi-label classification approach.In the near future,we will enhance experimental precision and reinforce the validity of conclusions by employing more rigorous control over variables through introducing expanded parameter settings.Practical implications:The observed Macro F1 and Micro F1 scores on real-world datasets typically fall short of those achieved on benchmark datasets,underscoring the complexity of real-world multi-label classification tasks.Approaches leveraging deep learning techniques offer promising solutions by accommodating the hierarchical relationships and interdependencies among labels.With ongoing enhancements in deep learning algorithms and large-scale models,it is expected that the efficacy of multi-label classification tasks will be significantly improved,reaching a level of practical utility in the foreseeable future.Originality/value:(1)Seven multi-label classification methods are comprehensively compared on three real-world datasets.(2)The TextCNN and TextRCNN models perform better on small-scale datasets with more complex hierarchical structure of labels and more balanced document-label distribution.(3)The MLkNN method works better on the larger-scale dataset with more unbalanced document-label distribution.展开更多
This article delves into the analysis of performance and utilization of Support Vector Machines (SVMs) for the critical task of forest fire detection using image datasets. With the increasing threat of forest fires to...This article delves into the analysis of performance and utilization of Support Vector Machines (SVMs) for the critical task of forest fire detection using image datasets. With the increasing threat of forest fires to ecosystems and human settlements, the need for rapid and accurate detection systems is of utmost importance. SVMs, renowned for their strong classification capabilities, exhibit proficiency in recognizing patterns associated with fire within images. By training on labeled data, SVMs acquire the ability to identify distinctive attributes associated with fire, such as flames, smoke, or alterations in the visual characteristics of the forest area. The document thoroughly examines the use of SVMs, covering crucial elements like data preprocessing, feature extraction, and model training. It rigorously evaluates parameters such as accuracy, efficiency, and practical applicability. The knowledge gained from this study aids in the development of efficient forest fire detection systems, enabling prompt responses and improving disaster management. Moreover, the correlation between SVM accuracy and the difficulties presented by high-dimensional datasets is carefully investigated, demonstrated through a revealing case study. The relationship between accuracy scores and the different resolutions used for resizing the training datasets has also been discussed in this article. These comprehensive studies result in a definitive overview of the difficulties faced and the potential sectors requiring further improvement and focus.展开更多
Onemust interact with a specific webpage or website in order to use the Internet for communication,teamwork,and other productive activities.However,because phishing websites look benign and not all website visitors ha...Onemust interact with a specific webpage or website in order to use the Internet for communication,teamwork,and other productive activities.However,because phishing websites look benign and not all website visitors have the same knowledge and skills to inspect the trustworthiness of visited websites,they are tricked into disclosing sensitive information and making them vulnerable to malicious software attacks like ransomware.It is impossible to stop attackers fromcreating phishingwebsites,which is one of the core challenges in combating them.However,this threat can be alleviated by detecting a specific website as phishing and alerting online users to take the necessary precautions before handing over sensitive information.In this study,five machine learning(ML)and DL algorithms—cat-boost(CATB),gradient boost(GB),random forest(RF),multilayer perceptron(MLP),and deep neural network(DNN)—were tested with three different reputable datasets and two useful feature selection techniques,to assess the scalability and consistency of each classifier’s performance on varied dataset sizes.The experimental findings reveal that the CATB classifier achieved the best accuracy across all datasets(DS-1,DS-2,and DS-3)with respective values of 97.9%,95.73%,and 98.83%.The GB classifier achieved the second-best accuracy across all datasets(DS-1,DS-2,and DS-3)with respective values of 97.16%,95.18%,and 98.58%.MLP achieved the best computational time across all datasets(DS-1,DS-2,and DS-3)with respective values of 2,7,and 3 seconds despite scoring the lowest accuracy across all datasets.展开更多
The increasing adoption of Industrial Internet of Things(IIoT)systems in smart manufacturing is leading to raise cyberattack numbers and pressing the requirement for intrusion detection systems(IDS)to be effective.How...The increasing adoption of Industrial Internet of Things(IIoT)systems in smart manufacturing is leading to raise cyberattack numbers and pressing the requirement for intrusion detection systems(IDS)to be effective.However,existing datasets for IDS training often lack relevance to modern IIoT environments,limiting their applicability for research and development.To address the latter gap,this paper introduces the HiTar-2024 dataset specifically designed for IIoT systems.As a consequence,that can be used by an IDS to detect imminent threats.Likewise,HiTar-2024 was generated using the AREZZO simulator,which replicates realistic smart manufacturing scenarios.The generated dataset includes five distinct classes:Normal,Probing,Remote to Local(R2L),User to Root(U2R),and Denial of Service(DoS).Furthermore,comprehensive experiments with popular Machine Learning(ML)models using various classifiers,including BayesNet,Logistic,IBK,Multiclass,PART,and J48 demonstrate high accuracy,precision,recall,and F1-scores,exceeding 0.99 across all ML metrics.The latter result is reached thanks to the rigorous applied process to achieve this quite good result,including data pre-processing,features extraction,fixing the class imbalance problem,and using a test option for model robustness.This comprehensive approach emphasizes meticulous dataset construction through a complete dataset generation process,a careful labelling algorithm,and a sophisticated evaluation method,providing valuable insights to reinforce IIoT system security.Finally,the HiTar-2024 dataset is compared with other similar datasets in the literature,considering several factors such as data format,feature extraction tools,number of features,attack categories,number of instances,and ML metrics.展开更多
Scientific knowledge on the chemical compositions of fine particulate matter(PM_(2.5)) is essential for properly assessing its health and climate effects,and for decisionmakers to develop efficient mitigation strategi...Scientific knowledge on the chemical compositions of fine particulate matter(PM_(2.5)) is essential for properly assessing its health and climate effects,and for decisionmakers to develop efficient mitigation strategies.A high-resolution PM_(2.5) chemical composition dataset(CAQRA-aerosol)is developed in this study,which provides hourly maps of organic carbon,black carbon,ammonium,nitrate,and sulfate in China from 2013 to 2020 with a horizontal resolution of 15 km.This paper describes the method,access,and validation results of this dataset.It shows that CAQRA-aerosol has good consistency with observations and achieves higher or comparable accuracy with previous PM_(2.5) composition datasets.Based on CAQRA-aerosol,spatiotemporal changes of different PM_(2.5) compositions were investigated from a national viewpoint,which emphasizes different changes of nitrate from other compositions.The estimated annual rate of population-weighted concentrations of nitrate is 0.23μg m^(−3)yr^(−1) from 2015 to 2020,compared with−0.19 to−1.1μg m^(−3)yr^(−1) for other compositions.The whole dataset is freely available from the China Air Pollution Data Center(https://doi.org/10.12423/capdb_PKU.2023.DA).展开更多
大型语言模型(LLM)已成为推进Text-to-SQL任务的强大工具。研究发现,基于LLM的模型在不同评估指标下,其性能表现与经过微调的模型存在显著差异。因此,文章分析了测试套件执行准确度(EXE)和精确集匹配准确度(ESM)在评估基于LLM的Text-to-...大型语言模型(LLM)已成为推进Text-to-SQL任务的强大工具。研究发现,基于LLM的模型在不同评估指标下,其性能表现与经过微调的模型存在显著差异。因此,文章分析了测试套件执行准确度(EXE)和精确集匹配准确度(ESM)在评估基于LLM的Text-to-SQL模型时的不足,并提出了改进指标EESM(Enhanced Exact Set Matching)。实验结果表明,EXE和ESM分别存在高达13.2%和10.8%的假阳性和假阴性率,而EESM的假阳性率和假阴性率分别仅为0.2%和1.8%,表明EESM能够提供更准确的评估。展开更多
In this study, the upper ocean heat content （OHC） variations in the South China Sea （SCS） during 1993- 2006 were investigated by examining ocean temperatures in seven datasets, including World Ocean Atlas 2009 （W...In this study, the upper ocean heat content （OHC） variations in the South China Sea （SCS） during 1993- 2006 were investigated by examining ocean temperatures in seven datasets, including World Ocean Atlas 2009 （WOA09） （climatology）, Ishii datasets, Ocean General Circulation ModeI for the Earth Simulator （OFES）, Simple Ocean Data Assimilation system （SODA）, Global Ocean Data Assimilation System （GODAS）, China Oceanic ReAnalysis system （CORA） , and an ocean reanalysis dataset for the joining area of Asia and Indian-Pacific Ocean （AIPO1.0）. Among these datasets, two were independent of any numerical model, four relied on data assimilation, and one was generated without any data assimilation. The annual cycles revealed by the seven datasets were similar, but the interannual variations were different. Vertical structures of temperatures along the 18~N, 12.75~N, and 120~E sections were compared with data collected during open cruises in 1998 and 2005-08. The results indicated that Ishii, OFES, CORA, and AIPO1.0 were more consistent with the observations. Through systematic shortcomings and advantages in presenting the upper comparisons, we found that each dataset had its own OHC in the SCS.展开更多
Based on C-LSAT2.0,using high-and low-frequency components reconstruction methods,combined with observation constraint masking,a reconstructed C-LSAT2.0 with 756 ensemble members from the 1850s to 2018 has been develo...Based on C-LSAT2.0,using high-and low-frequency components reconstruction methods,combined with observation constraint masking,a reconstructed C-LSAT2.0 with 756 ensemble members from the 1850s to 2018 has been developed.These ensemble versions have been merged with the ERSSTv5 ensemble dataset,and an upgraded version of the CMSTInterim dataset with 5°×5°resolution has been developed.The CMST-Interim dataset has significantly improved the coverage rate of global surface temperature data.After reconstruction,the data coverage before 1950 increased from 78%−81%of the original CMST to 81%−89%.The total coverage after 1955 reached about 93%,including more than 98%in the Northern Hemisphere and 81%−89%in the Southern Hemisphere.Through the reconstruction ensemble experiments with different parameters,a good basis is provided for more systematic uncertainty assessment of C-LSAT2.0 and CMSTInterim.In comparison with the original CMST,the global mean surface temperatures are estimated to be cooler in the second half of 19th century and warmer during the 21st century,which shows that the global warming trend is further amplified.The global warming trends are updated from 0.085±0.004℃(10 yr)^(–1)and 0.128±0.006℃(10 yr)^(–1)to 0.089±0.004℃(10 yr)^(–1)and 0.137±0.007℃(10 yr)^(–1),respectively,since the start and the second half of 20th century.展开更多
Version 4(v4) of the Extended Reconstructed Sea Surface Temperature(ERSST) dataset is compared with its precedent, the widely used version 3b(v3b). The essential upgrades applied to v4 lead to remarkable differences i...Version 4(v4) of the Extended Reconstructed Sea Surface Temperature(ERSST) dataset is compared with its precedent, the widely used version 3b(v3b). The essential upgrades applied to v4 lead to remarkable differences in the characteristics of the sea surface temperature(SST) anomaly(SSTa) in both the temporal and spatial domains. First, the largest discrepancy of the global mean SSTa values around the 1940 s is due to ship-observation corrections made to reconcile observations from buckets and engine intake thermometers. Second, differences in global and regional mean SSTa values between v4 and v3b exhibit a downward trend(around-0.032℃ per decade) before the 1940s, an upward trend(around 0.014℃ per decade) during the period of 1950–2015, interdecadal oscillation with one peak around the 1980s, and two troughs during the 1960s and 2000s, respectively. This does not derive from treatments of the polar or the other data-void regions, since the difference of the SSTa does not share the common features. Third, the spatial pattern of the ENSO-related variability of v4 exhibits a wider but weaker cold tongue in the tropical region of the Pacific Ocean compared with that of v3b, which could be attributed to differences in gap-filling assumptions since the latter features satellite observations whereas the former features in situ ones. This intercomparison confirms that the structural uncertainty arising from underlying assumptions on the treatment of diverse SST observations even in the same SST product family is the main source of significant SST differences in the temporal domain. Why this uncertainty introduces artificial decadal oscillations remains unknown.展开更多
Prediction of tunneling-induced ground settlements is an essential task,particularly for tunneling in urban settings.Ground settlements should be limited within a tolerable threshold to avoid damages to aboveground st...Prediction of tunneling-induced ground settlements is an essential task,particularly for tunneling in urban settings.Ground settlements should be limited within a tolerable threshold to avoid damages to aboveground structures.Machine learning(ML)methods are becoming popular in many fields,including tunneling and underground excavations,as a powerful learning and predicting technique.However,the available datasets collected from a tunneling project are usually small from the perspective of applying ML methods.Can ML algorithms effectively predict tunneling-induced ground settlements when the available datasets are small?In this study,seven ML methods are utilized to predict tunneling-induced ground settlement using 14 contributing factors measured before or during tunnel excavation.These methods include multiple linear regression(MLR),decision tree(DT),random forest(RF),gradient boosting(GB),support vector regression(SVR),back-propagation neural network(BPNN),and permutation importancebased BPNN(PI-BPNN)models.All methods except BPNN and PI-BPNN are shallow-structure ML methods.The effectiveness of these seven ML approaches on small datasets is evaluated using model accuracy and stability.The model accuracy is measured by the coefficient of determination(R2)of training and testing datasets,and the stability of a learning algorithm indicates robust predictive performance.Also,the quantile error(QE)criterion is introduced to assess model predictive performance considering underpredictions and overpredictions.Our study reveals that the RF algorithm outperforms all the other models with the highest model prediction accuracy(0.9)and stability(3.0210^(-27)).Deep-structure ML models do not perform well for small datasets with relatively low model accuracy(0.59)and stability(5.76).The PI-BPNN architecture is proposed and designed for small datasets,showing better performance than typical BPNN.Six important contributing factors of ground settlements are identified,including tunnel depth,the distance between tunnel face and surface monitoring points(DTM),weighted average soil compressibility modulus(ACM),grouting pressure,penetrating rate and thrust force.展开更多
Data-driven algorithms for predicting mechanical properties with small datasets are evaluated in a case study on gear steel hardenability.The limitations of current data-driven algorithms and empirical models are iden...Data-driven algorithms for predicting mechanical properties with small datasets are evaluated in a case study on gear steel hardenability.The limitations of current data-driven algorithms and empirical models are identified.Challenges in analysing small datasets are discussed,and solution is proposed to handle small datasets with multiple variables.Gaussian methods in combination with novel predictive algorithms are utilized to overcome the challenges in analysing gear steel hardenability data and to gain insight into alloying elements interaction and structure homogeneity.The gained fundamental knowledge integrated with machine learning is shown to be superior to the empirical equations in predicting hardenability.Metallurgical-property relationships between chemistry,sample size,and hardness are predicted via two optimized machine learning algorithms:neural networks(NNs)and extreme gradient boosting(XGboost).A comparison is drawn between all algorithms,evaluating their performance based on small data sets.The results reveal that XGboost has the highest potential for predicting hardenability using small datasets with class imbalance and large inhomogeneity issues.展开更多
Comparisons of the west Pacific subtropical high with the South Asia High are made using the NCEP/NCAR and ECMWF 500 hPa and 100 hPa monthly boreal geopotential height fields for the period 1961-2000. Discrepancies ar...Comparisons of the west Pacific subtropical high with the South Asia High are made using the NCEP/NCAR and ECMWF 500 hPa and 100 hPa monthly boreal geopotential height fields for the period 1961-2000. Discrepancies are found for the time prior to 1980. The west Pacific subtropical high in the NCEP/NCAR data is less intense than in ECMWF data before 1980. The range and strength of the west Pacific subtropical high variation described by the NCEP/NCAR data are larger than those depicted by ECMWF data. The same situation appears in the 100-hPa geopotential field. These discoveries suggest that the interdecadal variation of the two systems as shown by the NCEP/NCAR data may not be true. Besides, the South Asia High center in the NCEP/NCAR data is obviously stronger than in the ECMWF data during the periods 1969, 1979-1991 and 1992-1995. Furthermore, the range is larger from 1992 to 1995.展开更多
This is a study to compare three selected tropical cyclone datasets separately compiled by CMA Shanghai Typhoon Institute （CMA SHI）, the Joint Typhoon Warning Center （JTWC）, and the Japan Meteorological Agency （...This is a study to compare three selected tropical cyclone datasets separately compiled by CMA Shanghai Typhoon Institute （CMA SHI）, the Joint Typhoon Warning Center （JTWC）, and the Japan Meteorological Agency （JMA）. The annual fi＇equencies, observation times and destructive power index as the characteristic quantities are investigated of the tropical cyclones over the western North Pacific. The comparative study has resulted in the following findings： 1） Statistical gaps between the datasets compared are narrowing down as the intensity of tropical cyclones increases. 2） In the context of interdecadal distribution, there is for the 1950s a relatively large gap between the datasets, as compared with a narrowed gap for the period from the mid 1970s to the 1980s, and a recurring widened gap for the mid and late 1990s. Additionally, an approach is proposed in the paper to correct the wind speed data in the TC Yearbook.展开更多
Total Cloud Cover （TCC） over China deter- mined from four climate datasets including the Interna- tional Satellite Cloud Climatology Project （ISCCP）, the 40-year Re-Analysis Project of the European Centre for Medi...Total Cloud Cover （TCC） over China deter- mined from four climate datasets including the Interna- tional Satellite Cloud Climatology Project （ISCCP）, the 40-year Re-Analysis Project of the European Centre for Medium-Range Weather Forecasts （ERA-40）, Climate Research Unit Time Series 3.0 （CRU3）, and ground sta- tion datasets are used to show spatial and temporal varia- tion of TCC and their differences. It is demonstrated that the four datasets show similar spatial pattern and seasonal variation. The maximum value is derived from ISCCE TCC value in North China derived from ERA-40 is 50% larger than that from the station dataset; however, the value is 50% less than that in South China. The annual TCC of ISCCP, ERA-40, and ground station datasets shows a decreasing trend during 1984-2002; however, an increasing trend is derived from CRU3. The results of this study imply remarkable differences of TCC derived from surface and satellite observations as well as model simu- lations. The potential effects of these differences on cloud climatology and associated climatic issues should be carefully considered.展开更多
In this study,through experimental research and an investigation on large datasets of the durability parameters in ocean engineering,the values,ranges,and types of distribution of the durability parameters employed fo...In this study,through experimental research and an investigation on large datasets of the durability parameters in ocean engineering,the values,ranges,and types of distribution of the durability parameters employed for the durability design in ocean engineering in northern China were confirmed.Based on a modified theoretical model of chloride diffusion and the reliability theory,the service lives of concrete structures exposed to the splash,tidal,and underwater zones were calculated.Mixed concrete proportions meeting the requirement of a service life of 100 or 120 years were designed,and a cover thickness requirement was proposed.In addition,the effects of the different time-varying relationships of the boundary condition(Cs)and diffusion coefficient(Df)on the service life were compared;the results showed that the time-varying relationships used in this study(i.e.,Cscontinuously increased and then remained stable,and Dfcontinuously decreased and then remained stable)were beneficial for the durability design of concrete structures in marine environment.展开更多
基金supported by the Natural Science Basic Research Program of Shaanxi(Program No.2024JC-YBMS-026).
文摘When dealing with imbalanced datasets,the traditional support vectormachine(SVM)tends to produce a classification hyperplane that is biased towards the majority class,which exhibits poor robustness.This paper proposes a high-performance classification algorithm specifically designed for imbalanced datasets.The proposed method first uses a biased second-order cone programming support vectormachine(B-SOCP-SVM)to identify the support vectors(SVs)and non-support vectors(NSVs)in the imbalanced data.Then,it applies the synthetic minority over-sampling technique(SV-SMOTE)to oversample the support vectors of the minority class and uses the random under-sampling technique(NSV-RUS)multiple times to undersample the non-support vectors of the majority class.Combining the above-obtained minority class data set withmultiple majority class datasets can obtainmultiple new balanced data sets.Finally,SOCP-SVM is used to classify each data set,and the final result is obtained through the integrated algorithm.Experimental results demonstrate that the proposed method performs excellently on imbalanced datasets.
文摘Climate change significantly affects environment,ecosystems,communities,and economies.These impacts often result in quick and gradual changes in water resources,environmental conditions,and weather patterns.A geographical study was conducted in Arizona State,USA,to examine monthly precipi-tation concentration rates over time.This analysis used a high-resolution 0.50×0.50 grid for monthly precip-itation data from 1961 to 2022,Provided by the Climatic Research Unit.The study aimed to analyze climatic changes affected the first and last five years of each decade,as well as the entire decade,during the specified period.GIS was used to meet the objectives of this study.Arizona experienced 51–568 mm,67–560 mm,63–622 mm,and 52–590 mm of rainfall in the sixth,seventh,eighth,and ninth decades of the second millennium,respectively.Both the first and second five year periods of each decade showed accept-able rainfall amounts despite fluctuations.However,rainfall decreased in the first and second decades of the third millennium.and in the first two years of the third decade.Rainfall amounts dropped to 42–472 mm,55–469 mm,and 74–498 mm,respectively,indicating a downward trend in precipitation.The central part of the state received the highest rainfall,while the eastern and western regions(spanning north to south)had significantly less.Over the decades of the third millennium,the average annual rainfall every five years was relatively low,showing a declining trend due to severe climate changes,generally ranging between 35 mm and 498 mm.The central regions consistently received more rainfall than the eastern and western outskirts.Arizona is currently experiencing a decrease in rainfall due to climate change,a situation that could deterio-rate further.This highlights the need to optimize the use of existing rainfall and explore alternative water sources.
基金National Natural Science Foundation of China(No.61971036)Fundamental Research Funds for the Central Universities(No.2023CX01011)Beijing Nova Program(No.20230484361)。
文摘This paper proposed a method to generate semi-experimental biomedical datasets based on full-wave simulation software.The system noise such as antenna port couplings is fully considered in the proposed datasets,which is more realistic than synthetical datasets.In this paper,datasets containing different shapes are constructed based on the relative permittivities of human tissues.Then,a back-propagation scheme is used to obtain the rough reconstructions,which will be fed into a U-net convolutional neural network(CNN)to recover the high-resolution images.Numerical results show that the network trained on the datasets generated by the proposed method can obtain satisfying reconstruction results and is promising to be applied in real-time biomedical imaging.
基金the Natural Science Foundation of China(Grant Numbers 72074014 and 72004012).
文摘Purpose:Many science,technology and innovation(STI)resources are attached with several different labels.To assign automatically the resulting labels to an interested instance,many approaches with good performance on the benchmark datasets have been proposed for multi-label classification task in the literature.Furthermore,several open-source tools implementing these approaches have also been developed.However,the characteristics of real-world multi-label patent and publication datasets are not completely in line with those of benchmark ones.Therefore,the main purpose of this paper is to evaluate comprehensively seven multi-label classification methods on real-world datasets.Research limitations:Three real-world datasets differ in the following aspects:statement,data quality,and purposes.Additionally,open-source tools designed for multi-label classification also have intrinsic differences in their approaches for data processing and feature selection,which in turn impacts the performance of a multi-label classification approach.In the near future,we will enhance experimental precision and reinforce the validity of conclusions by employing more rigorous control over variables through introducing expanded parameter settings.Practical implications:The observed Macro F1 and Micro F1 scores on real-world datasets typically fall short of those achieved on benchmark datasets,underscoring the complexity of real-world multi-label classification tasks.Approaches leveraging deep learning techniques offer promising solutions by accommodating the hierarchical relationships and interdependencies among labels.With ongoing enhancements in deep learning algorithms and large-scale models,it is expected that the efficacy of multi-label classification tasks will be significantly improved,reaching a level of practical utility in the foreseeable future.Originality/value:(1)Seven multi-label classification methods are comprehensively compared on three real-world datasets.(2)The TextCNN and TextRCNN models perform better on small-scale datasets with more complex hierarchical structure of labels and more balanced document-label distribution.(3)The MLkNN method works better on the larger-scale dataset with more unbalanced document-label distribution.
文摘This article delves into the analysis of performance and utilization of Support Vector Machines (SVMs) for the critical task of forest fire detection using image datasets. With the increasing threat of forest fires to ecosystems and human settlements, the need for rapid and accurate detection systems is of utmost importance. SVMs, renowned for their strong classification capabilities, exhibit proficiency in recognizing patterns associated with fire within images. By training on labeled data, SVMs acquire the ability to identify distinctive attributes associated with fire, such as flames, smoke, or alterations in the visual characteristics of the forest area. The document thoroughly examines the use of SVMs, covering crucial elements like data preprocessing, feature extraction, and model training. It rigorously evaluates parameters such as accuracy, efficiency, and practical applicability. The knowledge gained from this study aids in the development of efficient forest fire detection systems, enabling prompt responses and improving disaster management. Moreover, the correlation between SVM accuracy and the difficulties presented by high-dimensional datasets is carefully investigated, demonstrated through a revealing case study. The relationship between accuracy scores and the different resolutions used for resizing the training datasets has also been discussed in this article. These comprehensive studies result in a definitive overview of the difficulties faced and the potential sectors requiring further improvement and focus.
文摘Onemust interact with a specific webpage or website in order to use the Internet for communication,teamwork,and other productive activities.However,because phishing websites look benign and not all website visitors have the same knowledge and skills to inspect the trustworthiness of visited websites,they are tricked into disclosing sensitive information and making them vulnerable to malicious software attacks like ransomware.It is impossible to stop attackers fromcreating phishingwebsites,which is one of the core challenges in combating them.However,this threat can be alleviated by detecting a specific website as phishing and alerting online users to take the necessary precautions before handing over sensitive information.In this study,five machine learning(ML)and DL algorithms—cat-boost(CATB),gradient boost(GB),random forest(RF),multilayer perceptron(MLP),and deep neural network(DNN)—were tested with three different reputable datasets and two useful feature selection techniques,to assess the scalability and consistency of each classifier’s performance on varied dataset sizes.The experimental findings reveal that the CATB classifier achieved the best accuracy across all datasets(DS-1,DS-2,and DS-3)with respective values of 97.9%,95.73%,and 98.83%.The GB classifier achieved the second-best accuracy across all datasets(DS-1,DS-2,and DS-3)with respective values of 97.16%,95.18%,and 98.58%.MLP achieved the best computational time across all datasets(DS-1,DS-2,and DS-3)with respective values of 2,7,and 3 seconds despite scoring the lowest accuracy across all datasets.
文摘The increasing adoption of Industrial Internet of Things(IIoT)systems in smart manufacturing is leading to raise cyberattack numbers and pressing the requirement for intrusion detection systems(IDS)to be effective.However,existing datasets for IDS training often lack relevance to modern IIoT environments,limiting their applicability for research and development.To address the latter gap,this paper introduces the HiTar-2024 dataset specifically designed for IIoT systems.As a consequence,that can be used by an IDS to detect imminent threats.Likewise,HiTar-2024 was generated using the AREZZO simulator,which replicates realistic smart manufacturing scenarios.The generated dataset includes five distinct classes:Normal,Probing,Remote to Local(R2L),User to Root(U2R),and Denial of Service(DoS).Furthermore,comprehensive experiments with popular Machine Learning(ML)models using various classifiers,including BayesNet,Logistic,IBK,Multiclass,PART,and J48 demonstrate high accuracy,precision,recall,and F1-scores,exceeding 0.99 across all ML metrics.The latter result is reached thanks to the rigorous applied process to achieve this quite good result,including data pre-processing,features extraction,fixing the class imbalance problem,and using a test option for model robustness.This comprehensive approach emphasizes meticulous dataset construction through a complete dataset generation process,a careful labelling algorithm,and a sophisticated evaluation method,providing valuable insights to reinforce IIoT system security.Finally,the HiTar-2024 dataset is compared with other similar datasets in the literature,considering several factors such as data format,feature extraction tools,number of features,attack categories,number of instances,and ML metrics.
基金support from the National Key Scientific and Technological Infrastructure project “Earth System Science Numerical Simulator Facility” (Earth Lab)sponsored by the National Natural Science Foundation of China (Grant Nos. 42175132, 92044303, and 42205119)+2 种基金the National Key R&D Program (Grant Nos. 2020YFA0607802 and 2022YFC3703003)the CAS Information Technology Program (Grant No. CAS-WX2021SF-0107-02)the fellowship of China Postdoctoral Science Foundation (Grant No. 2022M723093)
文摘Scientific knowledge on the chemical compositions of fine particulate matter(PM_(2.5)) is essential for properly assessing its health and climate effects,and for decisionmakers to develop efficient mitigation strategies.A high-resolution PM_(2.5) chemical composition dataset(CAQRA-aerosol)is developed in this study,which provides hourly maps of organic carbon,black carbon,ammonium,nitrate,and sulfate in China from 2013 to 2020 with a horizontal resolution of 15 km.This paper describes the method,access,and validation results of this dataset.It shows that CAQRA-aerosol has good consistency with observations and achieves higher or comparable accuracy with previous PM_(2.5) composition datasets.Based on CAQRA-aerosol,spatiotemporal changes of different PM_(2.5) compositions were investigated from a national viewpoint,which emphasizes different changes of nitrate from other compositions.The estimated annual rate of population-weighted concentrations of nitrate is 0.23μg m^(−3)yr^(−1) from 2015 to 2020,compared with−0.19 to−1.1μg m^(−3)yr^(−1) for other compositions.The whole dataset is freely available from the China Air Pollution Data Center(https://doi.org/10.12423/capdb_PKU.2023.DA).
文摘大型语言模型(LLM)已成为推进Text-to-SQL任务的强大工具。研究发现,基于LLM的模型在不同评估指标下,其性能表现与经过微调的模型存在显著差异。因此,文章分析了测试套件执行准确度(EXE)和精确集匹配准确度(ESM)在评估基于LLM的Text-to-SQL模型时的不足,并提出了改进指标EESM(Enhanced Exact Set Matching)。实验结果表明,EXE和ESM分别存在高达13.2%和10.8%的假阳性和假阴性率,而EESM的假阳性率和假阴性率分别仅为0.2%和1.8%,表明EESM能够提供更准确的评估。
基金supported by the National Basic Research Program of China (Grant Nos. 2010CB950400 and 2013CB430301)the National Natural Science Foundation of China (Grant Nos. 41276025 and 41176023)+2 种基金the R&D Special Fund for Public Welfare Industry (Meteorology) (Grant No. GYHY201106036)The OFES simulation was conducted on the Earth Simulator under the support of JAMSTECsupported by the Data Sharing Infrastructure of Earth System Science-Data Sharing Service Center of the South China Sea and adjacent regions
文摘In this study, the upper ocean heat content （OHC） variations in the South China Sea （SCS） during 1993- 2006 were investigated by examining ocean temperatures in seven datasets, including World Ocean Atlas 2009 （WOA09） （climatology）, Ishii datasets, Ocean General Circulation ModeI for the Earth Simulator （OFES）, Simple Ocean Data Assimilation system （SODA）, Global Ocean Data Assimilation System （GODAS）, China Oceanic ReAnalysis system （CORA） , and an ocean reanalysis dataset for the joining area of Asia and Indian-Pacific Ocean （AIPO1.0）. Among these datasets, two were independent of any numerical model, four relied on data assimilation, and one was generated without any data assimilation. The annual cycles revealed by the seven datasets were similar, but the interannual variations were different. Vertical structures of temperatures along the 18~N, 12.75~N, and 120~E sections were compared with data collected during open cruises in 1998 and 2005-08. The results indicated that Ishii, OFES, CORA, and AIPO1.0 were more consistent with the observations. Through systematic shortcomings and advantages in presenting the upper comparisons, we found that each dataset had its own OHC in the SCS.
文摘Based on C-LSAT2.0,using high-and low-frequency components reconstruction methods,combined with observation constraint masking,a reconstructed C-LSAT2.0 with 756 ensemble members from the 1850s to 2018 has been developed.These ensemble versions have been merged with the ERSSTv5 ensemble dataset,and an upgraded version of the CMSTInterim dataset with 5°×5°resolution has been developed.The CMST-Interim dataset has significantly improved the coverage rate of global surface temperature data.After reconstruction,the data coverage before 1950 increased from 78%−81%of the original CMST to 81%−89%.The total coverage after 1955 reached about 93%,including more than 98%in the Northern Hemisphere and 81%−89%in the Southern Hemisphere.Through the reconstruction ensemble experiments with different parameters,a good basis is provided for more systematic uncertainty assessment of C-LSAT2.0 and CMSTInterim.In comparison with the original CMST,the global mean surface temperatures are estimated to be cooler in the second half of 19th century and warmer during the 21st century,which shows that the global warming trend is further amplified.The global warming trends are updated from 0.085±0.004℃(10 yr)^(–1)and 0.128±0.006℃(10 yr)^(–1)to 0.089±0.004℃(10 yr)^(–1)and 0.137±0.007℃(10 yr)^(–1),respectively,since the start and the second half of 20th century.
基金supported by the National Key Basic Research and Development Plan (No.2015CB953900)the Natural Science Foundation of China (Nos.41330960 and 41776032)
文摘Version 4(v4) of the Extended Reconstructed Sea Surface Temperature(ERSST) dataset is compared with its precedent, the widely used version 3b(v3b). The essential upgrades applied to v4 lead to remarkable differences in the characteristics of the sea surface temperature(SST) anomaly(SSTa) in both the temporal and spatial domains. First, the largest discrepancy of the global mean SSTa values around the 1940 s is due to ship-observation corrections made to reconcile observations from buckets and engine intake thermometers. Second, differences in global and regional mean SSTa values between v4 and v3b exhibit a downward trend(around-0.032℃ per decade) before the 1940s, an upward trend(around 0.014℃ per decade) during the period of 1950–2015, interdecadal oscillation with one peak around the 1980s, and two troughs during the 1960s and 2000s, respectively. This does not derive from treatments of the polar or the other data-void regions, since the difference of the SSTa does not share the common features. Third, the spatial pattern of the ENSO-related variability of v4 exhibits a wider but weaker cold tongue in the tropical region of the Pacific Ocean compared with that of v3b, which could be attributed to differences in gap-filling assumptions since the latter features satellite observations whereas the former features in situ ones. This intercomparison confirms that the structural uncertainty arising from underlying assumptions on the treatment of diverse SST observations even in the same SST product family is the main source of significant SST differences in the temporal domain. Why this uncertainty introduces artificial decadal oscillations remains unknown.
基金funded by the University Transportation Center for Underground Transportation Infrastructure(UTC-UTI)at the Colorado School of Mines under Grant No.69A3551747118 from the US Department of Transportation(DOT).
文摘Prediction of tunneling-induced ground settlements is an essential task,particularly for tunneling in urban settings.Ground settlements should be limited within a tolerable threshold to avoid damages to aboveground structures.Machine learning(ML)methods are becoming popular in many fields,including tunneling and underground excavations,as a powerful learning and predicting technique.However,the available datasets collected from a tunneling project are usually small from the perspective of applying ML methods.Can ML algorithms effectively predict tunneling-induced ground settlements when the available datasets are small?In this study,seven ML methods are utilized to predict tunneling-induced ground settlement using 14 contributing factors measured before or during tunnel excavation.These methods include multiple linear regression(MLR),decision tree(DT),random forest(RF),gradient boosting(GB),support vector regression(SVR),back-propagation neural network(BPNN),and permutation importancebased BPNN(PI-BPNN)models.All methods except BPNN and PI-BPNN are shallow-structure ML methods.The effectiveness of these seven ML approaches on small datasets is evaluated using model accuracy and stability.The model accuracy is measured by the coefficient of determination(R2)of training and testing datasets,and the stability of a learning algorithm indicates robust predictive performance.Also,the quantile error(QE)criterion is introduced to assess model predictive performance considering underpredictions and overpredictions.Our study reveals that the RF algorithm outperforms all the other models with the highest model prediction accuracy(0.9)and stability(3.0210^(-27)).Deep-structure ML models do not perform well for small datasets with relatively low model accuracy(0.59)and stability(5.76).The PI-BPNN architecture is proposed and designed for small datasets,showing better performance than typical BPNN.Six important contributing factors of ground settlements are identified,including tunnel depth,the distance between tunnel face and surface monitoring points(DTM),weighted average soil compressibility modulus(ACM),grouting pressure,penetrating rate and thrust force.
文摘Data-driven algorithms for predicting mechanical properties with small datasets are evaluated in a case study on gear steel hardenability.The limitations of current data-driven algorithms and empirical models are identified.Challenges in analysing small datasets are discussed,and solution is proposed to handle small datasets with multiple variables.Gaussian methods in combination with novel predictive algorithms are utilized to overcome the challenges in analysing gear steel hardenability data and to gain insight into alloying elements interaction and structure homogeneity.The gained fundamental knowledge integrated with machine learning is shown to be superior to the empirical equations in predicting hardenability.Metallurgical-property relationships between chemistry,sample size,and hardness are predicted via two optimized machine learning algorithms:neural networks(NNs)and extreme gradient boosting(XGboost).A comparison is drawn between all algorithms,evaluating their performance based on small data sets.The results reveal that XGboost has the highest potential for predicting hardenability using small datasets with class imbalance and large inhomogeneity issues.
基金Key Laboratory on Natural Disasters for Jiangsu Province (KLME050210)
文摘Comparisons of the west Pacific subtropical high with the South Asia High are made using the NCEP/NCAR and ECMWF 500 hPa and 100 hPa monthly boreal geopotential height fields for the period 1961-2000. Discrepancies are found for the time prior to 1980. The west Pacific subtropical high in the NCEP/NCAR data is less intense than in ECMWF data before 1980. The range and strength of the west Pacific subtropical high variation described by the NCEP/NCAR data are larger than those depicted by ECMWF data. The same situation appears in the 100-hPa geopotential field. These discoveries suggest that the interdecadal variation of the two systems as shown by the NCEP/NCAR data may not be true. Besides, the South Asia High center in the NCEP/NCAR data is obviously stronger than in the ECMWF data during the periods 1969, 1979-1991 and 1992-1995. Furthermore, the range is larger from 1992 to 1995.
基金Monitoring and Detection of Upperair Climate Change in China (GYHY200906014)
文摘This is a study to compare three selected tropical cyclone datasets separately compiled by CMA Shanghai Typhoon Institute （CMA SHI）, the Joint Typhoon Warning Center （JTWC）, and the Japan Meteorological Agency （JMA）. The annual fi＇equencies, observation times and destructive power index as the characteristic quantities are investigated of the tropical cyclones over the western North Pacific. The comparative study has resulted in the following findings： 1） Statistical gaps between the datasets compared are narrowing down as the intensity of tropical cyclones increases. 2） In the context of interdecadal distribution, there is for the 1950s a relatively large gap between the datasets, as compared with a narrowed gap for the period from the mid 1970s to the 1980s, and a recurring widened gap for the mid and late 1990s. Additionally, an approach is proposed in the paper to correct the wind speed data in the TC Yearbook.
基金supported by the "Strategic Priority Research Program" of the Chinese Academy of Sciences(XDA05100300)the National Basic Research Program of China(2013CB955801)the National Natural Science Foundation of China(41175030)
文摘Total Cloud Cover （TCC） over China deter- mined from four climate datasets including the Interna- tional Satellite Cloud Climatology Project （ISCCP）, the 40-year Re-Analysis Project of the European Centre for Medium-Range Weather Forecasts （ERA-40）, Climate Research Unit Time Series 3.0 （CRU3）, and ground sta- tion datasets are used to show spatial and temporal varia- tion of TCC and their differences. It is demonstrated that the four datasets show similar spatial pattern and seasonal variation. The maximum value is derived from ISCCE TCC value in North China derived from ERA-40 is 50% larger than that from the station dataset; however, the value is 50% less than that in South China. The annual TCC of ISCCP, ERA-40, and ground station datasets shows a decreasing trend during 1984-2002; however, an increasing trend is derived from CRU3. The results of this study imply remarkable differences of TCC derived from surface and satellite observations as well as model simu- lations. The potential effects of these differences on cloud climatology and associated climatic issues should be carefully considered.
基金financial support provided by the National Natural Science Foundation of China(51508272,11832013,51878350,and 51678304)。
文摘In this study,through experimental research and an investigation on large datasets of the durability parameters in ocean engineering,the values,ranges,and types of distribution of the durability parameters employed for the durability design in ocean engineering in northern China were confirmed.Based on a modified theoretical model of chloride diffusion and the reliability theory,the service lives of concrete structures exposed to the splash,tidal,and underwater zones were calculated.Mixed concrete proportions meeting the requirement of a service life of 100 or 120 years were designed,and a cover thickness requirement was proposed.In addition,the effects of the different time-varying relationships of the boundary condition(Cs)and diffusion coefficient(Df)on the service life were compared;the results showed that the time-varying relationships used in this study(i.e.,Cscontinuously increased and then remained stable,and Dfcontinuously decreased and then remained stable)were beneficial for the durability design of concrete structures in marine environment.
