|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Convolutional neural networks for time series classification显示文摘Time series classification is an important task in time series data mining, and has attracted great interests and tremendous efforts during last decades. However, it remains a challenging problem due to the nature of time series data: high dimensionality,large in data size and updating continuously. The deep learning techniques are explored to improve the performance of traditional feature-based approaches. Specifically, a novel convolutional neural network(CNN) framework is proposed for time series classification. Different from other feature-based classification approaches,CNN can discover and extract the suitable internal structure to generate deep features of the input time series automatically by using convolution and pooling operations. Two groups of experiments are conducted on simulated data sets and eight groups of experiments are conducted on real-world data sets from different application domains. The final experimental results show that the proposed method outperforms state-of-the-art methods for time series classification in terms of the classification accuracy and noise tolerance. | Bendong Zhao Huanzhang Lu Shangfeng Chen Junliang Liu Dongya Wu | 2017 | Journal of Systems Engineering and Electronics2017，28，1： | 33 |
| 2 | Long-term outcomes and prognostic factors for patients with esophageal cancer following radiotherapy显示文摘AIM:To evaluate long-term outcomes and prognostic factors for esophageal squamous cell carcinoma(SCC) treated with three dimensional conformal radiotherapy(3D-CRT).METHODS:Between January 2005 and December 2006,153 patients(120 males,33 females) with pathologically confirmed esophageal SCC and treated with 3D-CRT in Cancer Hospital of Shantou University were included in this retrospective analysis.Median age was 60 years(range:37-84 years).The proportion of tumor location was as follows:upper thorax(including the cervical region),73(48%);middle thorax,73(48%);lower thorax,7(5%),respectively.The median radiation dose was 64 Gy(range:50-74 Gy).Fifty four cases(35%) received cisplatin-based concurrent chemotherapy.Univariate and multivariate analysis were performed to determine the association between the correlative factors and prognosis.RESULTS:The five-year overall survival rate was 26.3%,with a median follow-up of 49 mo(range:3-66 mo) for patients who were still alive.On univariate analysis,lesion location,lesion length by barium esophagogram,computed tomography imaging characteristics including Y diameter(anterior-posterior,AP,extent of tumor),gross tumor volume of primary lesion(GTV-E),volume of positive lymph nodes(GTV-LN),and the total target volume(GTV-T = GTV-E + GTVLN) were prognostic for overall survival.By multivariate analysis,only the Y diameter [hazard ratio(HR) 2.219,95%CI 1.141-4.316,P = 0.019] and the GTV-T(HR 1.372,95%CI 1.044-1.803,P = 0.023) were independent prognostic factors for survival.CONCLUSION:The overall survival of esophageal carcinoma patients undergoing 3D-CRT was promising.The best predictors for survival were GTV-T and Y diameter. | Chuang-Zhen Chen Jian-Zhou Chen De-Rui Li Zhi-Xiong Lin Ming-Zhen Zhou Dong-Sheng Li Zhi-Jian Chen | 2013 | World Journal of Gastroenterology2013，19，10： | 22 |
| 3 | Multivariate analysis in dam monitoring data with PCA显示文摘Given the limitation of traditional univariate analysis method in processing the multicollinearity of dam monitoring data,this paper reconstructs the multivariate response variables by introducing principal component analysis(PCA) method,explores the ways of determining principal components(PCs),and extracts a few PCs that have major influence on data variance.For steady observation series,a control field for the whole observation values has been established based upon PCA;for unsteady observation series that have significant tendency,a control field for the future observation values has been constructed according to PC statistical predication model.These methods have already been applied to an actual project and the results showed that data interpretation method with PCA can not only realize data reduction,lower data redundancy,and reduce noise and false alarm rate,but also be effective to data analysis,having a broad application prospect. | YU Hong1,2,WU ZhongRu1,2,BAO TengFei1,2 & ZHANG Lan1,2 1 State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering,Hohai University,Nanjing 210098,China 2 National Engineering Research Center of Water Resources Efficient Utilization and Engineering Safety,Hohai University,Nanjing 210098,China | 2010 | Science China(Technological Sciences)2010，53，4： | 16 |
| 4 | Type 2 diabetes is associated with a worse functional outcome of ischemic stroke显示文摘AIM: To assess whether ischemic stroke severity and outcome is more adverse in patients with type 2 diabetes mellitus(T2DM). METHODS: Consecutive patients hospitalized for acute ischemic stroke between September 2010 and June 2013 were studied prospectively(n = 482; 40.2% males, age 78.8 ± 6.7 years). T2 DM was defined as self-reported T2 DM or antidiabetic treatment. Stroke severity was evaluated with the National Institutes of Health Stroke Scale(NIHSS) score at admission. The outcome was assessed with the modified Rankin scale(m RS) score at discharge and with in-hospital mortality. Adverse outcome was defined as m RS score at discharge ≥ 2 or in-hospital death. The length of hospitalization was also recorded.RESULTS: T2 DM was present in 32.2% of the study population. Patients with T2 DM had a larger waist circumference, higher serum triglyceride and glucose levels and lower serum high-density lipoprotein cholesterol levels as well as higher prevalence of hypertension, coronary heart disease and congestive heart failure than patients without T2 DM. On the other hand, diabetic patients had lower low-density lipoprotein cholesterol levels and reported smaller consumption of alcohol than non-diabetic patients. At admission, the NIHSS score did not differ between patients with and without T2DM(8.7 ± 8.8 and 8.6 ± 9.2, respectively; P = NS). At discharge, the m RS score also did not differ between the two groups(2.7 ± 2.1 and 2.7 ± 2.2 in patients with and without T2 DM, respectively; P = NS). Rates of adverse outcome were also similar in patients with and without T2DM(62.3% and 58.5%, respectively; P = NS). However, when we adjusted for the differences between patients with T2 DM and those without T2 DM in cardiovascular risk factors, T2 DM was independently associated with adverse outcome [relative risk(RR) = 2.39; 95%CI: 1.21-4.72, P = 0.012]. Inhospital mortality rates did not differ between patients with T2 DM and those without T2DM(9.0% and 9.8%, respectively; P = NS). In multivariate analysis adjusting for the difference in cardiovascular risk factors between the two groups, T2 DM was again not associated with in-hospital death. CONCLUSION: T2 DM does not appear to affect ischemic stroke severity but is independently associated with a worse functional outcome at discharge. | Konstantinos Tziomalos Marianna Spanou Stella D Bouziana Maria Papadopoulou Vasilios Giampatzis Stavroula Kostaki Vasiliki Dourliou Maria Tsopozidi Christos Savopoulos Apostolos I Hatzitolios | 2014 | World Journal of Diabetes2014，5，6： | 15 |
| 5 | 多元Lagrange插值与Cayley-Bacharach定理显示文摘1 引言多元Lagrange插值一直是计算数学中一个重要的研究课题.为了解决一些实际科学计算问题(如多元函数的计算,曲面的外形设计和有限元格式的建立等),有关多元多项式插值的理论与方法的研究在近二、三十年中迅速发展起来.在研究多元多项式插值时, 一个首先必须解决的问题就是多元插值的适定性问题.目前。 | 梁学章 张洁琳 崔利宏 | 2005 | 高等学校计算数学学报2005，27，S1： | 13 |
| 6 | 肝癌患者化疗栓塞后肝功能严重失代偿的相关因素分析显示文摘目的:探讨肝癌患者动脉灌注化疗栓塞(TACE)后肝功能严重失代偿的相关因素。方法回顾性分析接受 TACE治疗的109例患者,单因素分析性别、年龄、外科切除史、肝硬化史、肿瘤大体分型、TACE 次数、动门静脉瘘、门脉癌栓、Child-Pugh 分级、血清总胆红素、白蛋白、天门冬氨酸氨基转移酶、吲哚菁绿15 min 滞留率和术中碘油用量与术后发生严重肝功能失代偿的相关性,并将有统计学意义(P 〈0.05)的结果引入 Logistic 回归模型分析。结果肝硬化、Child-Pugh 分级、门脉癌栓、白蛋白和吲哚菁绿15 min 滞留率与术后发生严重的肝功能失代偿相关,多项 Logistic 回归分析显示:肝硬化、门脉癌栓和吲哚菁绿15 min 滞留率是导致术后发生严重肝功能失代偿的危险因素。结论导致 TACE 后发生肝功能严重失代偿的危险因素有肝硬化、门脉癌栓和吲哚菁绿15 min 滞留率,需要在术前评估中引起警惕。 | 张正宇 邓燕贤 徐军红 周志鹏 廖国宇 | 2015 | 实用放射学杂志2015，31，2： | 13 |
| 7 | Metabolomics analysis and rapid identification of changes in chemical ingredients in crude and processed Astragali Radix by UPLC-QTOF-MS combined with novel informatics UNIFI platform显示文摘Astragali Radix, the root of Astragalus membranaceus(Fisch.) Bge. var. mongholicus(Bge.) Hsiao or Astragalus membranaceus(Fisch.) Bge., is widely used as a tonic decoction pieces in the clinic of traditional Chinese medicine(TCM). Astragali Radix has various processed products with varying pharmacological actions. There is no modern scientific evidence to explain the differences in pharmacological activities and related mechanisms. In the present study, we explore the changes in chemical components in Astragali Radix after processing, by ultra-high performance liquid chromatography quadrupole time-of-flight mass spectrometry(UPLC-QTOF-MS) combined with novel informatics UNIFI platform and multivariate statistical analysis. Our results showed that the crude and various processed products could be clearly separated in PCA scores plot and 15 significant markers could be used to distinguish crude and various processed products by OPLS-DA in UNIFI platform. In conclusion, the present study provided a basis of chemical components for revealing connotation of different processing techniques on Astragali Radix. | LIU Peng-Peng SHAN Guo-Shun ZHANG Fan CHEN Jiang-Ning JIA Tian-Zhu | 2018 | Chinese Journal of Natural Medicines2018，16，9： | 12 |
| 8 | Increased postoperative complications after protective ileostomy closure delay: An institutional study显示文摘AIM: To study the morbidity and complications as-sociated to ileostomy reversal in colorectal surgery pa-tients, and if these are related to the time of closure. METHODS: A retrospective analysis of 93 patients, who had undergone elective ileostomy closure between 2009 and 2013 was performed. Demographic, clinical and surgical variables were reviewed for analysis. All complications were recorded, and classified according to the Clavien-Dindo Classification. Statistical univariate and multivariate analysis was performed, setting a P value of 0.05 for significance.RESULTS: The patients had a mean age of 60.3 years, 58% male. The main procedure for ileostomy cre-ation was rectal cancer(56%), and 37% had received preoperative chemo-radiotherapy. The average delay from creation to closure of the ileostomy was 10.3 mo. Postoperative complications occurred in 40% of the pa-tients, with 1% mortality. The most frequent were ileus(13%) and wound infection(13%). Pseudomembra-nous colitis appeared in 4%. Increased postoperative complications were associated with delay in ileostomyclosure(P = 0.041). Male patients had more complica-tions(P = 0.042), mainly wound infections(P = 0.007). Pseudomembranous colitis was also associated with the delay in ileostomy closure(P = 0.003). End-to-end in-testinal anastomosis without resection was significantly associated with postoperative ileus(P = 0.037). CONCLUSION: Although closure of a protective il-eostomy is a fairly common surgical procedure, it has a high rate of complications, and this must be taken into account when the indication is made. The delay in stoma closure can increase the rate of complications in general, and specifically wound infections and colitis. | Ines Rubio-Perez Miguel Leon Daniel Pastor Joaquin Diaz Dominguez Ramon Cantero | 2014 | World Journal of Gastrointestinal Surgery2014，6，9： | 11 |
| 9 | GIS-based landslide susceptibility mapping using numerical risk factor bivariate model and its ensemble with linear multivariate regression and boosted regression tree algorithms显示文摘In this study, a novel approach of the landslide numerical risk factor(LNRF) bivariate model was used in ensemble with linear multivariate regression(LMR) and boosted regression tree(BRT) models, coupled with radar remote sensing data and geographic information system(GIS), for landslide susceptibility mapping(LSM) in the Gorganroud watershed, Iran. Fifteen topographic, hydrological, geological and environmental conditioning factors and a landslide inventory(70%, or 298 landslides) were used in mapping. Phased array-type L-band synthetic aperture radar data were used to extract topographic parameters. Coefficients of tolerance and variance inflation factor were used to determine the coherence among conditioning factors. Data for the landslide inventory map were obtained from various resources, such as Iranian Landslide Working Party(ILWP), Forestry, Rangeland and Watershed Organisation(FRWO), extensive field surveys, interpretation of aerial photos and satellite images, and radar data. Of the total data, 30% were used to validate LSMs, using area under the curve(AUC), frequency ratio(FR) and seed cell area index(SCAI).Normalised difference vegetation index, land use/land cover and slope degree in BRT model elevation, rainfall and distance from stream were found to be important factors and were given the highest weightage in modelling. Validation results using AUC showed that the ensemble LNRF-BRT and LNRFLMR models(AUC = 0.912(91.2%) and 0.907(90.7%), respectively) had high predictive accuracy than the LNRF model alone(AUC = 0.855(85.5%)). The FR and SCAI analyses showed that all models divided the parameter classes with high precision. Overall, our novel approach of combining multivariate and machine learning methods with bivariate models, radar remote sensing data and GIS proved to be a powerful tool for landslide susceptibility mapping. | Alireza ARABAMERI Biswajeet PRADHAN Khalil REZAE Masoud SOHRABI Zahra KALANTARI | 2019 | Journal of Mountain Science2019，16，3： | 11 |
| 10 | Typhoon disaster zoning and prevention criteria——A double layer nested multi-objective probability model and its application显示文摘For prevention and mitigation of typhoon disasters in China, in this paper a double layer nested multi-objective probability model of typhoon disaster zoning and prevention criteria is proposed. The multivariate compound extreme value distribution (MCEVD) is used to predict the joint probability of seven typhoon characteristics and corresponding typhoon induced disasters. Predicted results can be used for both typhoon disaster zoning and corresponding prevention criteria along China coast. | LIU DeFu PANG Liang XIE BoTao WU YuanKang | 2008 | Science China(Technological Sciences)2008，51，7： | 10 |
| 11 | Landsat TM/ETM+与HJ-1A/B CCD数据自动相对辐射处理及精度验证显示文摘全球地表覆盖遥感制图与关键技术研究项目要求对两个基准年度(2000年,2010年)的全球覆盖30 m分辨率遥感数据进行辐射处理,转换到地表反射率,数据以Landsat TM/ETM+为主,HJ-1A/B CCD数据为补充。海量数据中有些不适宜进行绝对大气校正,为了保证全球覆盖,对这些数据设计开发了一套自动的相对辐射处理及精度验证流程算法,利用相邻数据重叠区域进行相对辐射校正的方式,将数据由Oigital Number(DN)值直接转换为地表反射率,精度验证以MODIS地表反射率产品MOD09GA作为参考,比较对应波段数据的相对一致性,算法采用了图像分块处理技术及OpenMP加速技术提高效率,实际应用结果表明该算法流程可以满足项目对辐射处理精度、速度及自动化程度的要求。 | 胡昌苗 张微 冯峥 唐娉 | 2014 | 遥感学报2014，18，2： | 10 |
| 12 | Integrated metabolomic profiling for analysis of antilipidemic effects of Polygonatum kingianum extract on dyslipidemia in rats显示文摘AIM To identify the effects and mechanism of action of Polygonatum kingianum(P. kingianum) on dyslipidemia in rats using an integrated untargeted metabolomic method.METHODS A rat model of dyslipidemia was induced with a high-fat diet(HFD) and rats were given P. kingianum [4 g/(kg·d)] intragastrically for 14 wk. Changes in serum and hepatic lipid parameters were evaluated. Metabolites in serum, urine and liver samples were profiled using ultra-highperformance liquid chromatography/mass spectrometry followed by multivariate statistical analysis to identify potential biomarkers and metabolic pathways.RESULTS P. kingianum significantly inhibited the HFD-induced increase in total cholesterol and triglyceride in the liver and serum. P. kingianum also significantly regulated metabolites in the analyzed samples toward normal status. Nineteen, twenty-four and thirty-eight potential biomarkers were identified in serum, urine and liver samples, respectively. These biomarkers involved biosynthesis of phenylalanine, tyrosine, tryptophan, valine, leucine and isoleucine, along with metabolism of tryptophan, tyrosine, phenylalanine, starch, sucrose, glycerophospholipid, arachidonic acid, linoleic acid, nicotinate, nicotinamide and sphingolipid.CONCLUSION P. kingianum alleviates HFD-induced dyslipidemia by regulating many endogenous metabolites in serum, urine and liver samples. Collectively, our findings suggest that P. kingianum may be a promising lipid regulator to treat dyslipidemia and associated diseases. | Xing-Xin Yang Jia-Di Wei Jian-Kang Mu Xin Liu Jin-Cai Dong Lin-Xi Zeng Wen Gu Jing-Ping Li Jie Yu | 2018 | World Journal of Gastroenterology2018，24，48： | 8 |
| 13 | 生猪养殖户安全生产行为及其影响因素分析显示文摘本文将生猪养殖户的饲料使用、添加剂使用、兽药使用以及病死猪处理等行为视为一个整体进行分析,采用multivariate probit模型,综合考察影响生猪养殖户安全生产行为的因素。结果显示,养殖年限对养殖户的生产行为具有显著的负向影响;养殖规模和专业化程度对养殖户不同生产行为的影响程度不同:养殖规模对遵守休药期以及病死猪无害化处理的行为具有正向影响,但时饲料和添加剂的使用行为影响不显著;专业化有助于规范养殖户添加剂的使用行为和病死猪的处理行为,但对饲料和兽药的使用行为影响甚微。由此提出,有针对性地加强对养殖户的宣传教育,发展适度规模经营,推广病死猪处理技术以及增强对养殖户的技术指导等,是保障猪肉质量安全的有效途径。 | 钟颖琦 黄祖辉 吴林海 | 2016 | 中国畜牧杂志2016，52，20： | 8 |
| 14 | Vegetation-environment relationships in the forests of Chitral district Hindukush range of Pakistan显示文摘We investigated the composition of plant communities to quantify their relationships with environmental parameters in the Chitral Hindukush range of Pakistan. We sampled tree vegetation using the Point Centered Quarter (PCQ) method while understory vegetation was sampled in 1.5-m circular quadrats. Cedrus deodara is the national symbol of Pakistan and was dominant in the sampled communities. Because environmental variables determine vegetation types, we analyzed and evaluated edaphic and topographic factors. DCA-Ordination showed the major gradient as an amalgam of elevation (p<0.05) and slope (p<0.01) as the topographic factors correlated with species distribution. Soil variables were the factors of environmental significance along DCA axes. However, among these factors, Mg2+ , K + and N2+ contributed not more than 0.054% 0.20% and 0.073%, respectively, to variation along the first ordination axis. We conclude that the principal reason for weak or no correlation with many edaphic variables was the anthropogenic disturbance of vegetation. The understory vegetation was composed of perennial herbs in most communities and was most dense under the tree canopy. The understory vegetation strongly regulates tree seedling growth and regeneration patterns. We recommend further study of the understory vegetation using permanent plots to aid development of forest regeneration strategies. | Nasrullah Khan Syed Shahid Shaukat Moinuddin Ahmed Muhammad Faheem Siddiqui | 2013 | Journal of Forestry Research2013，24，2： | 8 |
| 15 | Property and provenance study of fancy celadon samples excavated from the Noble Burials of the Yue State at Hongshan, China显示文摘The Noble Burials of the Yue State at Hongshan in Wuxi City with many fancy burial objects were excavated by Archaeology Institute of Jiangsu Province and Xishan District Committee for Administration of Cultural Relics of China. It was appraised as one of the ten major archaeological excavations in 2004. Some precious ceramic samples excavated from this site are very important for studying the development history of Chinese ceramics, especially for studying the origin of porcelain. With the cooperation of Archaeology Institute of Nanjing Museum, the ceramic samples excavated from the Noble Burials of the Yue State at Hongshan were collected and systematically analyzed. Compared with the celadon samples produced in Yue-kiln site during later Eastern Han Dynasty (25–220 A.D.), some important topics such as the provenance and properties of the ceramic samples excavated from the Noble Burials of the Yue State at Hongshan were deeply studied. | WU Juan1, WU JunMing1 , LI QiJiang1, ZHANG MaoLin1, LI JiaZhi2, LU XiaoKe2 & DENG ZeQun2 1 Jingdezhen Ceramics Institute, Jingdezhen 333001, China 2 Shanghai Institute of Ceramics, Chinese Academy of Sciences, Shanghai 200050, China | 2010 | Science China(Technological Sciences)2010，53，2： | 7 |
| 16 | Multi-layer Contribution Propagation Analysis for Fault Diagnosis显示文摘The recent development of feature extraction algorithms with multiple layers in machine learning and pattern recognition has inspired many applications in multivariate statistical process monitoring. In this work, two existing multi-layer linear approaches in fault detection are reviewed and a new one with extra layer is proposed in analogy. To provide a general framework for fault diagnosis in succession, this work also proposes the contribution propagation analysis which extends the original definition of contribution of variables in multivariate statistical process monitoring. In fault diagnosis stage, the proposed contribution propagation analysis for multilayer linear feature extraction algorithms is compared with the fault diagnosis results of original contribution plots associated with single layer feature extraction approach. Plots of variable contributions obtained by the aforementioned approaches on the data sets collected from a simulated benchmark case study(Tennessee Eastman process) as well as an industrial scale multiphase flow facility are presented as a demonstration of the usage and performance of the contribution propagation analysis on multi-layer linear algorithms. | Ruo-Mu Tan Yi Cao | 2019 | International Journal of Automation and computing2019，16，1： | 6 |
| 17 | Geochemistry and multivariate statistical evaluation of major oxides, trace and rare earth elements in coal occurrences and deposits around Kogi east, Northern Anambra Basin, Nigeria显示文摘The Cretaceous Mamu Formation coal samples located within the Northern Anambra Basin were collected, analysed and interpreted using multivariate statistical approach to determine the major, trace and rare elements association with a view to determine the source of the terrestrial rocks, palaeoweathering/climatic conditions and tectonic setting. The dominant oxides such as SiO2, A12O3, Fe2O3, TiO2 and CaO were identified in the coal to suggest terrigenous origin. The ratio of SiO2/Al2O3 of 4.8 suggests that the coal was formed from low land peat associated with freshwater continental marine or blackish water with low salinity as indicated by Sr/Ba and CaO + MgO/K2O + Na2。ratios. The major oxides also revealed stable condition of deposition, low degree of tectonic setting but constant subsidence in the basin. The condition of deposition was acidic in nature as indicated by TiO2/Zr plot. Based on the abundance of Zr, Zn, Ba, Ni, Co, Sr, V, and Y, moderate salinity, sub-oxic to oxic bottom water condition was prevalent and also indication of marine influence. Based on the ratios of La/Yb;La/Sm and Gd/Yb, LREE has higher enrichment than HREE. Humid climatic conditions were observed at the coal formation stage while weak laterization to kaolinization was also evidence. | E.G.Ameh | 2019 | International Journal of Coal Science & Technology2019，6，2： | 6 |
| 18 | Determining the spatial distribution of soil properties using the environmental covariates and multivariate statistical analysis: a case study in semi-arid regions of Iran显示文摘Natural soil-forming factors such as landforms, parent materials or biota lead to high variability in soil properties. However, there is not enough research quantifying which environmental factor(s) can be the most relevant to predicting soil properties at the catchment scale in semi-arid areas. Thus, this research aims to investigate the ability of multivariate statistical analyses to distinguish which soil properties follow a clear spatial pattern conditioned by specific environmental characteristics in a semi-arid region of Iran. To achieve this goal, we digitized parent materials and landforms by recent orthophotography. Also, we extracted ten topographical attributes and five remote sensing variables from a digital elevation model(DEM) and the Landsat Enhanced Thematic Mapper(ETM), respectively. These factors were contrasted for 334 soil samples(depth of 0–30 cm). Cluster analysis and soil maps reveal that Cluster 1 comprises of limestones, massive limestones and mixed deposits of conglomerates with low soil organic carbon(SOC) and clay contents, and Cluster 2 is composed of soils that originated from quaternary and early quaternary parent materials such as terraces, alluvial fans, lake deposits, and marls or conglomerates that register the highest SOC content and the lowest sand and silt contents. Further, it is confirmed that soils with the highest SOC and clay contents are located in wetlands, lagoons, alluvial fans and piedmonts, while soils with the lowest SOC and clay contents are located in dissected alluvial fans, eroded hills, rock outcrops and steep hills. The results of principal component analysis using the remote sensing data and topographical attributes identify five main components, which explain 73.3% of the total variability of soil properties. Environmental factors such as hillslope morphology and all of the remote sensing variables can largely explain SOC variability, but no significant correlation is found for soil texture and calcium carbonate equivalent contents. Therefore, we conclude that SOC can be considered as the best-predicted soil property in semi-arid regions. | Mojtaba ZERAATPISHEH Shamsollah AYOUBI Magboul SULIEMAN JesusRODRIGO-COMINO | 2019 | Journal of Arid Land2019，11，4： | 5 |
| 19 | Artificial neural network models predicting the leaf area index:a case study in pure even-aged Crimean pine forests from Turkey显示文摘Background: Leaf Area Index(LAI) is an important parameter used in monitoring and modeling of forest ecosystems. The aim of this study was to evaluate performance of the artificial neural network(ANN) models to predict the LAI by comparing the regression analysis models as the classical method in these pure and even-aged Crimean pine forest stands.Methods: One hundred eight temporary sample plots were collected from Crimean pine forest stands to estimate stand parameters. Each sample plot was imaged with hemispherical photographs to detect the LAI. The partial correlation analysis was used to assess the relationships between the stand LAI values and stand parameters, and the multivariate linear regression analysis was used to predict the LAI from stand parameters. Different artificial neural network models comprising different number of neuron and transfer functions were trained and used to predict the LAI of forest stands.Results: The correlation coefficients between LAI and stand parameters(stand number of trees, basal area, the quadratic mean diameter, stand density and stand age) were significant at the level of 0.01. The stand age, number of trees, site index, and basal area were independent parameters in the most successful regression model predicted LAI values using stand parameters(/?;adj = 0.5431). As corresponding method to predict the interactions between the stand LAI values and stand parameters, the neural network architecture based on the RBF 4-19-1 with Gaussian activation function in hidden layer and the identity activation function in output layer performed better in predicting LAI(SSE(12.1040), MSE(0.1223), RM5 E(0.3497), AIC(0.1040), BIC(-777310) and R2(0.6392)) compared to the other studied techniques.Conclusion: The ANN outperformed the multivariate regression techniques in predicting LAI from stand parameters. The ANN models, developed in this study, may aid in making forest management planning in study forest stands. | ilker Ercanli Alkan Gunlu Muammer Senyurt Sedat Keles | 2018 | Forest Ecosystems2018，5，4： | 4 |
| 20 | LAGRANGE REPRESENTATION OF MULTIVARIATE INTERPOLATION显示文摘This paper gives a set of linearly independent interpolating functionals and a correspon-ding set of fundamental Lagrange polynomials for the multivariate extension (the liftedmultivariate map) of univariate generalized Hermite interpolation operator. | 梁学章 | 1989 | Science China Mathematics1989，32，4： | 4 |
您所在的机构暂未开通此部分的功能，请联系管理员