- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Analysis of NIR spectroscopic data using decision trees and their ensembles
摘要： Decision trees and their ensembles became quite popular for data analysis during the past decade. One of the main reasons for that is current boom in big data, where traditional statistical methods (such as, e.g., multiple linear regression) are not very efficient. However, in chemometrics these methods are still not very widespread, first of all because of several limitations related to the ratio between number of variables and observations. This paper presents several examples on how decision trees and their ensembles can be used in analysis of NIR spectroscopic data both for regression and classification. We will try to consider all important aspects including optimization and validation of models, evaluation of results, treating missing data and selection of most important variables. The performance and outcome of the decision tree-based methods are compared with more traditional approach based on partial least squares.
关键词： Decision trees,Classification and regression trees,Random forests,NIR spectroscopy
更新于2025-09-23 15:23:52
-
[IEEE 2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP) - Aristi Village, Zagorochoria, Greece (2018.6.10-2018.6.12)] 2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP) - Quantitative Evaluation of Salient Deep Neural Network Features Using Random Forests
摘要： The Deep Neural Networks and Deep Convolutional Neural Network have the property of providing multi-scale features at different layers of the network. Combination of these large number of features is one of the attributed reasons for the performance of the Neural Network (NN) on vision problems. This work uses Random Forests to identify robust features at various layers of the NN and evaluates the classification performance of these features in isolation. We propose a method for evaluation of parts of an already trained network using the selection by entropy maximization property of the Random Forests. We define measures for saliency in terms of contribution to the final classification, and evaluate the feature saliency. Simultaneously, a measure to identify the imperativeness of network features for classification is also formalized. The experiments made on a Hand dataset and the MNIST dataset, quantitatively validate various intuitions like the discriminatory nature of the outer layer features.
关键词： Random Forests,Feature Evaluation,CNN,Feature Selection
更新于2025-09-23 15:23:52
-
On the Synergistic Use of Optical and SAR Time-Series Satellite Data for Small Mammal Disease Host Mapping
摘要： (1) Background: Echinococcus multilocularis (Em), a highly pathogenic parasitic tapeworm, is responsible for a significant burden of human disease. In this study, optical and time-series Synthetic Aperture Radar (SAR) data is used synergistically to model key land cover characteristics driving the spatial distributions of two small mammal intermediate host species, Ellobius tancrei and Microtus gregalis, which facilitate Em transmission in a highly endemic area of Kyrgyzstan. (2) Methods: A series of land cover maps are derived from (a) single-date Landsat Operational Land Imager (OLI) imagery, (b) time-series Sentinel-1 SAR data, and (c) Landsat OLI and time-series Sentinel-1 SAR data in combination. Small mammal distributions are analyzed in relation to the surrounding land cover class coverage using random forests, before being applied predictively over broader areas. A comparison of models derived from the three land cover maps are made, assessing their potential for use in cloud-prone areas. (3) Results: Classification accuracies demonstrated the combined OLI-SAR classification to be of highest accuracy, with the single-date OLI and time-series SAR derived classifications of equivalent quality. Random forest analysis identified statistically significant positive relationships between E. tancrei density and agricultural land, and between M. gregalis density and water and bushes. Predictive application of random forest models identified hotspots of high relative density of E. tancrei and M. gregalis across the broader study area. (4) Conclusions: This offers valuable information to improve the targeting of limited-resource disease control activities to disrupt disease transmission in this area. Time-series SAR derived land cover maps are shown to be of equivalent quality to those generated from single-date optical imagery, which enables application of these methods in cloud-affected areas where, previously, this was not possible due to the sparsity of cloud-free optical imagery.
关键词： Echinococcus multilocularis,random forests,spatial epidemiology,SAR,land cover,Ellobius tancrei,Microtus gregalis,time-series,Sentinel
更新于2025-09-23 15:23:52
-
Low-Dose Computed Tomography Image Super-Resolution Reconstruction via Random Forests
摘要： Aiming at reducing computed tomography (CT) scan radiation while ensuring CT image quality, a new low-dose CT super-resolution reconstruction method based on combining a random forest with coupled dictionary learning is proposed. The random forest classifier finds the optimal solution of the mapping relationship between low-dose CT (LDCT) images and high-dose CT (HDCT) images and then completes CT image reconstruction by coupled dictionary learning. An iterative method is developed to improve robustness, the important coefficients for the tree structure are discussed and the optimal solutions are reported. The proposed method is further compared with a traditional interpolation method. The results show that the proposed algorithm can obtain a higher peak signal-to-noise ratio (PSNR) and structural similarity index measurement (SSIM) and has better ability to reduce noise and artifacts. This method can be applied to many different medical imaging fields in the future and the addition of computer multithreaded computing can reduce time consumption.
关键词： super-resolution,coupled dictionary learning,random forests,low-dose CT
更新于2025-09-23 15:22:29
-
Estimating spatial variation in Alberta forest biomass from a combination of forest inventory and remote sensing data
摘要： Uncertainties in the estimation of tree biomass carbon storage across large areas pose challenges for the study of forest carbon cycling at regional and global scales. In this study, we attempted to estimate the present above-ground biomass (AGB) in Alberta, Canada, by taking advantage of a spatially explicit data set derived from a combination of forest inventory data from 1968 plots and space-borne light detection and ranging (lidar) canopy height data. Ten climatic variables, together with elevation, were used for model development and assessment. Four approaches, including spatial interpolation, non-spatial and spatial regression models, and decision-tree-based modeling with random forests algorithm (a machine-learning technique), were compared to find the “best” estimates. We found that the random forests approach provided the best accuracy for biomass estimates. Non-spatial and spatial regression models gave estimates similar to random forests, while spatial interpolation greatly overestimated the biomass storage. Using random forests, the total AGB stock in Alberta forests was estimated to be 2.26 × 109 Mg (megagram), with an average AGB density of 56.30 ± 35.94 Mg ha?1. At the species level, three major tree species, lodgepole pine, trembling aspen and white spruce, stocked about 1.39 × 109 Mg biomass, accounting for nearly 62 % of total estimated AGB. Spatial distribution of biomass varied with natural regions, land cover types, and species. Furthermore, the relative importance of predictor variables on determining biomass distribution varied with species. This study showed that the combination of ground-based inventory data, spaceborne lidar data, land cover classification, and climatic and environmental variables was an efficient way to estimate the quantity, distribution and variation of forest biomass carbon stocks across large regions.
关键词： random forests,remote sensing,lidar,forest biomass,carbon storage,Alberta
更新于2025-09-23 15:21:01
-
[IEEE 2020 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus) - St. Petersburg and Moscow, Russia (2020.1.27-2020.1.30)] 2020 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus) - Investigation of an UWB Antipodal Tapered Slot Antenna Element Based on Substrate Integrated Waveguide in an Antenna Array
摘要： In 2008, the first commercial wave farm came online in Portugal. As with other types of renewable energy, the electricity obtained from waves has the drawback of intermittency. Knowing a few hours ahead how much energy waves will hold can contribute to a better management of the electricity grid. In this work, three types of statistical models have been used to create up to 24-h forecasts of the zonal and meridional components of wave energy flux (WEF) levels at three directional buoys located off the coast in the Bay of Biscay. Each model’s performance has been compared at a 95% confidence level with the simplest prediction (persistence of levels), along with the forecasts provided by the physics-based WAve Modeling (WAM) wave model at the nearest grid point. The results indicate that for forecasting horizons between 3 and roughly 16 h ahead, the statistical models built on random forests (RFs) outperform the rest, including WAM and persistence.
关键词： Applied physics,forecasting,random forests (RFs),wave energy flux (WEF),fluid mechanics,Bay of Biscay
更新于2025-09-23 15:19:57
-
[IEEE 2018 24th International Conference on Pattern Recognition (ICPR) - Beijing, China (2018.8.20-2018.8.24)] 2018 24th International Conference on Pattern Recognition (ICPR) - Automatic Inspection of Aerospace Welds Using X-Ray Images
摘要： The non-destructive testing (NDT) of components is very important to the aerospace industry. Welds in these components may contain porosities and other defects. These reduce the fatigue life of components and may result in catastrophic accidents if they end up in the aircraft. Currently such welds are inspected by humans studying radiographs of the welds. We describe an automatic system for detecting defects in welds, with the aim of creating a triage system to reduce the workload on human inspectors. Given an X-ray image of the aerospace weld, the system locates the weld line, then analyses the region around the line to identify abnormalities. Our results show that the weld can be precisely extracted from X-ray images and the defect detection operation can identify 83% of defects with fewer than 3 false positives per image, and thus may be useful for prompting human inspectors to reduce their workload.
关键词： weld,NDT,random forests,NDE,defect detection,Non-destructive evaluation/testing
更新于2025-09-04 15:30:14
-
A new thermal infrared and visible spectrum images-based pedestrian detection system
摘要： In this paper, we propose a hybrid system for pedestrian detection, in which both thermal and visible images of the same scene are used. The proposed method is achieved in two basic steps: (1) Hypotheses generation (HG) where the locations of possible pedestrians in an image are determined and (2) hypotheses verification (HV), where tests are done to check the presence of pedestrians in the generated hypotheses. HG step segments the thermal image using a modified version of OTSU thresholding technique. The segmentation results are mapped into the corresponding visible image to obtain the regions of interests (possible pedestrians). A post-processing is done on the resulting regions of interests to keep only significant ones. HV is performed using random forest as classifier and a color-based histogram of oriented gradients (HOG) together with the histograms of oriented optical flow (HOOF) as features. The proposed approach has been tested on OSU Color-Thermal, INO Video Analytics and LITIV data sets and the results justify its effectiveness.
关键词： Thermal images,Random forests,Local binary pattern (LBP),Pedestrian detection,Histograms of oriented optical flow (HOOF),Support vector machines (SVMs),Visible images,Histogram of oriented gradients (HOG)
更新于2025-09-04 15:30:14
-
A near-infrared spectroscopy routine for unambiguous identification of cryptic ant species
摘要： Species identification—of importance for most biological disciplines—is not always straightforward as cryptic species hamper traditional identification. Fibre-optic near-infrared spectroscopy (NIRS) is a rapid and inexpensive method of use in various applications, including the identification of species. Despite its efficiency, NIRS has never been tested on a group of more than two cryptic species, and a working routine is still missing. Hence, we tested if the four morphologically highly similar, but genetically distinct ant species Tetramorium alpestre, T. caespitum, T. impurum, and T. sp. B, all four co-occurring above 1,300 m above sea level in the Alps, can be identified unambiguously using NIRS. Furthermore, we evaluated which of our implementations of the three analysis approaches, partial least squares regression (PLS), artificial neural networks (ANN), and random forests (RF), is most efficient in species identification with our data set. We opted for a 100% classification certainty, i.e., a residual risk of misidentification of zero within the available data, at the cost of excluding specimens from identification. Additionally, we examined which strategy among our implementations, one-vs-all, i.e., one species compared with the pooled set of the remaining species, or binary-decision strategies, worked best with our data to reduce a multi-class system to a two-class system, as is necessary for PLS. Our NIRS identification routine, based on a 100% identification certainty, was successful with up to 66.7% of unambiguously identified specimens of a species. In detail, PLS scored best over all species (36.7% of specimens), while RF was much less effective (10.0%) and ANN failed completely (0.0%) with our data and our implementations of the analyses. Moreover, we showed that the one-vs-all strategy is the only acceptable option to reduce multi-class systems because of a minimum expenditure of time. We emphasise our classification routine using fibre-optic NIRS in combination with PLS and the one-vs-all strategy as a highly efficient pre-screening identification method for cryptic ant species and possibly beyond.
关键词： Random forests,Ants,Species identification tool,One-vs-all strategy,Formicidae,Neural networks,Cryptic-species complex,Partial least squares regression,Tetramorium
更新于2025-09-04 15:30:14