- 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
-
SENSITIVITY ANALYSIS OF LIGHT INTERCEPTION TO GEOMETRICAL TRAITS OF APPLE TREES: AN IN SILICO STUDY BASED ON MAPPLET MODEL
摘要： The efficiency of light interception is a driving factor for plant transpiration and photosynthesis, and contributes greatly to plant growth. For a fruit tree, the efficiency of light interception is also a key factor to improve yield quality. Such efficiency is highly dependent on the tree geometrical and topological organisation which may vary between genotypes, or as a result of agronomic practices such as pruning. The purpose of this study was to use a functional-structural plant model, in order to find out the major geometrical traits that influence the efficiency of light interception in apple trees. MAppleT, an architectural model of apple tree, and VPlants, a software library that includes functionalities to simulate light environment, provided the basis for this work. The STAR, namely the silhouette to total area ratio of leaves, was used to evaluate the light interception efficiency. The general methodology contained three steps: (1) manipulation of a set of geometrical parameters in MAppleT, such as those related to internode elongation, leaf area expansion, and branching angle; (2) integration of the resulting tree architecture within the simulated light environment for calculation of STAR values at the whole tree scale; (3) analysis of the influence of the variation of each geometrical trait on the variance of STAR outputs. As expected, leaf area manipulation had the highest impact on STAR values. Interactions between input parameters were also found, and are illustrated in the case of leaf area versus internode length. This suggests that optimal combination(s) of the corresponding traits could be found, setting a target for genetic improvement, as well as physiological studies on real apple trees.
关键词： fruit trees,plant architecture,STAR,functional-structural plant modeling,virtual plants
更新于2025-09-23 15:23:52
-
[IEEE 2018 10th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS) - Beijing (2018.8.19-2018.8.20)] 2018 10th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS) - Instance Segmentation of Trees in Urban Areas from MLS Point Clouds Using Supervoxel Contexts and Graph-Based Optimization
摘要： In this paper, an instance segmentation method for tree extraction from MLS data sets in urban scenes is developed. The proposed method utilizes a supervoxel structure to organize the point clouds, and then extracts the detrended geometric features from the local context of supervoxels. Combined with the detrended features of the local context, the Random Forest (RF) classifier will be adopted to obtain the initial semantic labeling results of trees from point clouds. Afterwards, a local context-based regularization is iteratively performed to achieve global optimum on a global graphical model, in order to spatially smoothing the semantic labeling results. Finally, a graph-based segmentation is conducted to separate individual trees according to the semantic labeling results. The use of supervoxel structure can preserve the geometric boundaries of objects in the scene, and compared with point-based solutions, the supervoxel-based method can largely decrease the number of basic elements during the processing. Besides, the introduction of supervoxel contexts can extract the local information of an object making the feature extraction more robust and representative. Detrended geometric features can get over the redundant and in-salient information in the local context, so that discriminative features are obtained. Benefiting from the regularization process, the spatial smoothing is obtained based on initial labeling results from classic classifications such as RF classification. As a result, misclassification errors are removed to a large degree and semantic labeling results are thus smoothed. Based on the constructed global graphical model during the spatially smoothing process, a graph-based segmentation is applied to partition the graphical model for the clustering the instances of trees. The experiments on two test datasets have shown promising results, with an accuracy of the semantic labeling of trees reaching around 0.9. The segmentation of trees using graph-based algorithm also show acceptable results, with trees having simple structures and sparse distributions correctly separated, but for those cramped trees with complex structures, the points are over- or under-segmented.
关键词： local context,urban areas,supervoxels,MLS,Instance segmentation,graph-based segmentation,trees
更新于2025-09-23 15:22:29
-
[IEEE 2019 29th Australasian Universities Power Engineering Conference (AUPEC) - Nadi, Fiji (2019.11.26-2019.11.29)] 2019 29th Australasian Universities Power Engineering Conference (AUPEC) - Adaptive Boosting and Bootstrapped Aggregation based Ensemble Machine Learning Methods for Photovoltaic Systems Output Current Prediction
摘要： Photovoltaics output current prediction received great deal of attention in recent years, due to the high penetration level of PV utilization. The intermittent nature of PV systems, in addition to the fast-varying irradiance levels, provoked the need for fast, accurate and reliable forecasting techniques. Machine Learning (ML) methods have been proven to effectively solve regression-based prediction problems. ML methods that utilize multiple models to construct decision trees are called Ensemble Machine Learning (EML) algorithms. This paper presents a comparison study of two EML methods namely; AdaBoost and Random Forest for photovoltaics application. A dataset of fast varying environmental conditions has been employed and the terminal current of the experimental setup has been augmented based on the mathematical model and the use of an evolutionary algorithm. The mathematical model has been examined for several irradiance and temperature levels and adjusted based on the manufacturer datasheet. Random Forest overall absolute error distribution had the lowest mean and standard deviation. Results shows the superior performance of Random Forest over AdaBoost in terms of absolute error, on the contrary, AdaBoost absolute error distribution is scattered with larger quartiles limits. Random Forest overall absolute error distribution had the lowest mean of 0.27% with a standard deviation of 0.91%, however, AdaBoost absolute error mean was as high as 34.5% with a standard deviation of 15.8% relative to the mathematical model. Accurate predictions can be integrated in an EML based maximum power point tracking (MPPT) scheme.
关键词： ensemble machine learning,adaptive boosting,photovoltaics,regression decision trees,single diode model
更新于2025-09-23 15:21:01
-
Joint Image Compression and Encryption Using IWT with SPIHT, Kd-Tree and Chaotic Maps
摘要： Confidentiality and efficient bandwidth utilization require a combination of compression and encryption of digital images. In this paper, a new method for joint image compression and encryption based on set partitioning in hierarchical trees (SPIHT) with optimized Kd-tree and multiple chaotic maps was proposed. First, the lossless compression and encryption of the original images were performed based on integer wavelet transform (IWT) with SPIHT. Wavelet coefficients undergo diffusions and permutations before encoded through SPIHT. Second, maximum confusion, diffusion and compression of the SPIHT output were performed via the modified Kd-tree, wavelet tree and Huffman coding. Finally, the compressed output was further encrypted with varying parameter logistic maps and modified quadratic chaotic maps. The performance of the proposed technique was evaluated through compression ratio (CR) and peak-signal-to-noise ratio (PSNR), key space and histogram analyses. Moreover, this scheme passes several security tests, such as sensitivity, entropy and differential analysis tests. According to the theoretical analysis and experimental results, the proposed method is more secure and decreases the redundant information of the image more than the existing techniques for hybrid compression and encryption.
关键词： k-dimensional tree,chaotic maps,set partition in hierarchical trees,integer wavelet transform,encryption,image compression
更新于2025-09-23 15:21:01
-
[IEEE 2019 International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON) - Novosibirsk, Russia (2019.10.21-2019.10.27)] 2019 International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON) - The Use of Spread Spectrum Signals to Increase the Noise Immunity of Optical Communication Systems Based on the Effect of LED Reversibility
摘要： Data mining applications are becoming a more common tool in understanding and solving educational and administrative problems in higher education. In general, research in educational mining focuses on modeling student’s performance instead of instructors’ performance. One of the common tools to evaluate instructors’ performance is the course evaluation questionnaire to evaluate based on students’ perception. In this paper, four different classi?cation techniques—decision tree algorithms, support vector machines, arti?cial neural networks, and discriminant analysis—are used to build classi?er models. Their performances are compared over a data set composed of responses of students to a real course evaluation questionnaire using accuracy, precision, recall, and speci?city performance metrics. Although all the classi?er models show comparably high classi?cation performances, C5.0 classi?er is the best with respect to accuracy, precision, and speci?city. In addition, an analysis of the variable importance for each classi?er model is done. Accordingly, it is shown that many of the questions in the course evaluation questionnaire appear to be irrelevant. Furthermore, the analysis shows that the instructors’ success based on the students’ perception mainly depends on the interest of the students in the course. The ?ndings of this paper indicate the effectiveness and expressiveness of data mining models in course evaluation and higher education mining. Moreover, these ?ndings may be used to improve the measurement instruments.
关键词： linear discriminant analysis,Arti?cial neural networks,support vector machines,decision trees,classi?cation algorithms,performance evaluation
更新于2025-09-23 15:19:57
-
Potential use of hyperspectral data to classify forest tree species
摘要： Background: Remote sensing techniques and data are becoming increasingly popular in forest management, e.g. for change detection and health condition analysis. Tree species recognition is a fundamental issue in taking forest inventories, especially in carbon budget modelling. Hyperspectral imagery provides an accurate classification results for large areas based on a relatively small amount of training data. Results: A hyperspectral image of a forest stand in north-eastern Poland taken using an AISA (Airborne Imaging Spectrometer for Application) Eagle camera was transformed to extract the most valuable spectral differences and was classified into seven tree types (birch, European beech, oak, hornbeam, European larch, Scots pine, and Norway spruce) using nine classification algorithms. The highest overall accuracy and kappa coefficient were 90.3% and 0.9 respectively using three minimum noise fraction bands and maximum likelihood classifier. Conclusions: Hyperspectral imaging of forests can be used to classify major forest tree species with a good degree of accuracy. It is time-efficient and user-friendly; however, the data and software required means that this approach is still expensive at present.
关键词： Trees,AISA,Hyperspectral classification,Minimum noise fraction
更新于2025-09-19 17:15:36
-
Numerical optimization design for waveguide bends with low-loss and wide-bandwidth in two-dimensional photonic crystal slabs
摘要： In this article, the attitude control problem of a new-designed aerial trees-pruning robot is addressed. During the tree cutting process, the aerial trees-pruning robot will be disturbed by unknown external disturbances. At the same time, the model uncertainties will also affect the attitude controller. To overcome the above problems, an attitude controller is designed with a nonsingular fast terminal sliding mode method. First, the extended state observer is designed to estimate the modeling uncertainties and unknown disturbances. Then, the extended state observer-based nonsingular fast terminal sliding mode controller can make the tracking error of the attitude converge to zero in a finite time. Finally, a control allocation matrix switching strategy is proposed to solve the problem of the change of the aerial robot model in the cutting process. The final simulation and experimental results show that the extended state observer-based nonsingular fast terminal sliding mode controller designed in this article has good attitude control performance and can effectively overcome the modeling uncertainties and unknown disturbances. The attitude controller and control allocation matrix switching strategy ensure that the attitude angles of the aerial robot can quickly track the reference signals.
关键词： nonsingular fast terminal sliding mode,attitude controller,extended state observer,Aerial trees-pruning robot,control allocation
更新于2025-09-19 17:13:59
-
A plasmonic ellipse resonator possessing hybrid modes for ultracompact chipscale application
摘要： Data mining methods based on machine learning play an increasingly important role in drug design and discovery. In the current work, eight machine learning methods including decision trees, k- Nearest neighbor, support vector machines, random forests, extremely randomized trees, AdaBoost, gradient boosting trees, and XGBoost were evaluated comprehensively through a case study of ACC inhibitor data sets. Internal and external data sets were employed for cross- validation of the eight machine learning methods. Results showed that the extremely randomized trees model performed best and was adopted as the first step of virtual screening. Together with structure- based virtual screening in the second step, this combined strategy obtained desirable results. This work indicates that the combination of machine learning methods with traditional structure- based virtual screening can effectively strengthen the ability in finding potential hits from large compound database for a given target.
关键词： molecular docking,machine learning,extremely randomized trees,ACC inhibitors
更新于2025-09-11 14:15:04
-
Effective Raman spectra identification with tree-based methods
摘要： Treatment of spectral information is an essential tool for the examination of various cultural heritage materials. Raman spectroscopy has become an everyday practice for compound identification due to its non-intrusive nature, but often it can be a complex operation. Spectral identification and analysis on artists’ materials is being done with the aid of already existing spectral databases and spectrum matching algorithms. We demonstrate that with a machine learning method called Extremely Randomised Trees, we can learn a model in a supervised learning fashion, able to accurately match an entire-spectrum range into its respective mineral. Our approach was tested and was found to outperform the state-of-the-art methods on the corrected RRUFF dataset, while maintaining low computational complexity and inherently supporting parallelisation.
关键词： Randomised trees,Random forest,Mineral identification,Raman spectroscopy,Machine learning,Classification,Raman spectra identification
更新于2025-09-10 09:29:36