Machine learning algorithms are an important measure with which to perform landslide susceptibility assessments, but most studies use GIS-based classification methods to conduct susceptibility zonation.This study pres...Machine learning algorithms are an important measure with which to perform landslide susceptibility assessments, but most studies use GIS-based classification methods to conduct susceptibility zonation.This study presents a machine learning approach based on the C5.0 decision tree(DT) model and the K-means cluster algorithm to produce a regional landslide susceptibility map. Yanchang County, a typical landslide-prone area located in northwestern China, was taken as the area of interest to introduce the proposed application procedure. A landslide inventory containing 82 landslides was prepared and subsequently randomly partitioned into two subsets: training data(70% landslide pixels) and validation data(30% landslide pixels). Fourteen landslide influencing factors were considered in the input dataset and were used to calculate the landslide occurrence probability based on the C5.0 decision tree model.Susceptibility zonation was implemented according to the cut-off values calculated by the K-means cluster algorithm. The validation results of the model performance analysis showed that the AUC(area under the receiver operating characteristic(ROC) curve) of the proposed model was the highest, reaching 0.88,compared with traditional models(support vector machine(SVM) = 0.85, Bayesian network(BN) = 0.81,frequency ratio(FR) = 0.75, weight of evidence(WOE) = 0.76). The landslide frequency ratio and frequency density of the high susceptibility zones were 6.76/km^(2) and 0.88/km^(2), respectively, which were much higher than those of the low susceptibility zones. The top 20% interval of landslide occurrence probability contained 89% of the historical landslides but only accounted for 10.3% of the total area.Our results indicate that the distribution of high susceptibility zones was more focused without containing more " stable" pixels. Therefore, the obtained susceptibility map is suitable for application to landslide risk management practices.展开更多
Based on the data of daily precipitation in Lianyungang area from 1951 to 2012 and various climate signal data from the National Climate Center website and the NOAA website,a model for predicting whether the number of...Based on the data of daily precipitation in Lianyungang area from 1951 to 2012 and various climate signal data from the National Climate Center website and the NOAA website,a model for predicting whether the number of rainstorm days in summer in Lianyungang area is large was established by the classical C5. 0 decision tree algorithm. The data samples in 48 years( accounting for about 80% of total number of samples)was as the training set of a model,and the training accuracy rate of the model was 95. 83%. The data samples in the remaining 14 years( accounting for about 20% of total number of samples) were used as the test set of the model to test the model,and the test accuracy of the model was 85. 71%. The results showed that the prediction model of number of rainstorm days in summer constructed by C5. 0 algorithm had high accuracy and was easy to explain. Moreover,it is convenient for meteorological staff to use directly. At the same time,this study provides a new idea for short-term climate prediction of number of rainstorm days in summer.展开更多
This paper proposes a novel cargo loading algorithm applicable to automated conveyor-type loading systems.The algorithm offers improvements in computational efficiency and robustness by utilizing the concept of discre...This paper proposes a novel cargo loading algorithm applicable to automated conveyor-type loading systems.The algorithm offers improvements in computational efficiency and robustness by utilizing the concept of discrete derivatives and introducing logistics-related constraints.Optional consideration of the rotation of the cargoes was made to further enhance the optimality of the solutions,if possible to be physically implemented.Evaluation metrics were developed for accurate evaluation and enhancement of the algorithm’s ability to efficiently utilize the loading space and provide a high level of dynamic stability.Experimental results demonstrate the extensive robustness of the proposed algorithm to the diversity of cargoes present in Business-to-Consumer environments.This study contributes practical advancements in both cargo loading optimization and automation of the logistics industry,with potential applications in last-mile delivery services,warehousing,and supply chain management.展开更多
使用医疗信息系统的数据进行睡眠呼吸暂停低通气综合征(OSAHS)预测和分析过程中,存在不平衡数据问题。为此,在现有临床研究的基础上,提出了一种基于ROSE(Random Over Sampling Examples)和C5.0算法的初筛模型。利用收集到的人体测量学...使用医疗信息系统的数据进行睡眠呼吸暂停低通气综合征(OSAHS)预测和分析过程中,存在不平衡数据问题。为此,在现有临床研究的基础上,提出了一种基于ROSE(Random Over Sampling Examples)和C5.0算法的初筛模型。利用收集到的人体测量学指标数据,通过数据预处理,删除异常值并填补缺失值。然后采用ROSE算法对数据进行平衡,利用C5.0分类器对平衡后的数据构建筛查模型,通过十则交叉验证的方法检验模型的筛查效果。实验结果表明,使用该模型进行打鼾患者的OSAHS筛查,可以有效地提高筛查效率。展开更多
基金This research is funded by the National Natural Science Foundation of China(Grant Nos.41807285 and 51679117)Key Project of the State Key Laboratory of Geohazard Prevention and Geoenvironment Protection(SKLGP2019Z002)+3 种基金the National Science Foundation of Jiangxi Province,China(20192BAB216034)the China Postdoctoral Science Foundation(2019M652287 and 2020T130274)the Jiangxi Provincial Postdoctoral Science Foundation(2019KY08)Fundamental Research Funds for National Universities,China University of Geosciences(Wuhan)。
文摘Machine learning algorithms are an important measure with which to perform landslide susceptibility assessments, but most studies use GIS-based classification methods to conduct susceptibility zonation.This study presents a machine learning approach based on the C5.0 decision tree(DT) model and the K-means cluster algorithm to produce a regional landslide susceptibility map. Yanchang County, a typical landslide-prone area located in northwestern China, was taken as the area of interest to introduce the proposed application procedure. A landslide inventory containing 82 landslides was prepared and subsequently randomly partitioned into two subsets: training data(70% landslide pixels) and validation data(30% landslide pixels). Fourteen landslide influencing factors were considered in the input dataset and were used to calculate the landslide occurrence probability based on the C5.0 decision tree model.Susceptibility zonation was implemented according to the cut-off values calculated by the K-means cluster algorithm. The validation results of the model performance analysis showed that the AUC(area under the receiver operating characteristic(ROC) curve) of the proposed model was the highest, reaching 0.88,compared with traditional models(support vector machine(SVM) = 0.85, Bayesian network(BN) = 0.81,frequency ratio(FR) = 0.75, weight of evidence(WOE) = 0.76). The landslide frequency ratio and frequency density of the high susceptibility zones were 6.76/km^(2) and 0.88/km^(2), respectively, which were much higher than those of the low susceptibility zones. The top 20% interval of landslide occurrence probability contained 89% of the historical landslides but only accounted for 10.3% of the total area.Our results indicate that the distribution of high susceptibility zones was more focused without containing more " stable" pixels. Therefore, the obtained susceptibility map is suitable for application to landslide risk management practices.
基金Support by Meteorological Open Research Foundation for the Huaihe River Basin(HRM201602)Foundation for Young Scholars of Jiangsu Meteorological Bureau(Q201708,KQ201802)+2 种基金Science and Technology Innovation Team Foundation for Marine Meteorological Forecast Technology of Lianyungang Meteorological BureauKey Technology R&D Program Project of Lianyungang City(SH1634)Special Project for Forecasters of Jiangsu Meteorological Bureau(JSYBY201811,JSYBY201812,JSYBY201810)
文摘Based on the data of daily precipitation in Lianyungang area from 1951 to 2012 and various climate signal data from the National Climate Center website and the NOAA website,a model for predicting whether the number of rainstorm days in summer in Lianyungang area is large was established by the classical C5. 0 decision tree algorithm. The data samples in 48 years( accounting for about 80% of total number of samples)was as the training set of a model,and the training accuracy rate of the model was 95. 83%. The data samples in the remaining 14 years( accounting for about 20% of total number of samples) were used as the test set of the model to test the model,and the test accuracy of the model was 85. 71%. The results showed that the prediction model of number of rainstorm days in summer constructed by C5. 0 algorithm had high accuracy and was easy to explain. Moreover,it is convenient for meteorological staff to use directly. At the same time,this study provides a new idea for short-term climate prediction of number of rainstorm days in summer.
基金supported by the BK21 FOUR funded by the Ministry of Education of Korea and National Research Foundation of Korea,a Korea Agency for Infrastructure Technology Advancement(KAIA)grant funded by the Ministry of Land,Infrastructure,and Transport(Grant 1615013176)IITP(Institute of Information&Coummunications Technology Planning&Evaluation)-ICAN(ICT Challenge and Advanced Network of HRD)grant funded by the Korea government(Ministry of Science and ICT)(RS-2024-00438411).
文摘This paper proposes a novel cargo loading algorithm applicable to automated conveyor-type loading systems.The algorithm offers improvements in computational efficiency and robustness by utilizing the concept of discrete derivatives and introducing logistics-related constraints.Optional consideration of the rotation of the cargoes was made to further enhance the optimality of the solutions,if possible to be physically implemented.Evaluation metrics were developed for accurate evaluation and enhancement of the algorithm’s ability to efficiently utilize the loading space and provide a high level of dynamic stability.Experimental results demonstrate the extensive robustness of the proposed algorithm to the diversity of cargoes present in Business-to-Consumer environments.This study contributes practical advancements in both cargo loading optimization and automation of the logistics industry,with potential applications in last-mile delivery services,warehousing,and supply chain management.
文摘使用医疗信息系统的数据进行睡眠呼吸暂停低通气综合征(OSAHS)预测和分析过程中,存在不平衡数据问题。为此,在现有临床研究的基础上,提出了一种基于ROSE(Random Over Sampling Examples)和C5.0算法的初筛模型。利用收集到的人体测量学指标数据,通过数据预处理,删除异常值并填补缺失值。然后采用ROSE算法对数据进行平衡,利用C5.0分类器对平衡后的数据构建筛查模型,通过十则交叉验证的方法检验模型的筛查效果。实验结果表明,使用该模型进行打鼾患者的OSAHS筛查,可以有效地提高筛查效率。
