scholarly journals Monitoring forest health using hyperspectral imagery: Does feature selection improve the performance of machine-learning techniques?

2020 ◽  
Author(s):  
Patrick Schratz ◽  
Jannes Muenchow ◽  
Eugenia Iturritxa ◽  
José Cortés ◽  
Bernd Bischl ◽  
...  
Keyword(s):  
Feature Selection ◽  
Predictive Performance ◽  
Environmental Modeling ◽  
Gradient Boosting ◽  
Support Vector ◽  
Substantial Impact ◽  
Feature Sets ◽  
Filter Methods ◽  
Extreme Gradient Boosting ◽  
Feature Importance

This study analyzed highly-correlated, feature-rich datasets from hyperspectral remote sensing data using multiple machine and statistical-learning methods.<br> The effect of filter-based feature-selection methods on predictive performance was compared.<br> Also, the effect of multiple expert-based and data-driven feature sets, derived from the reflectance data, was investigated.<br> Defoliation of trees (%) was modeled as a function of reflectance, and variable importance was assessed using permutation-based feature importance.<br> Overall support vector machine (SVM) outperformed others such as random forest (RF), extreme gradient boosting (XGBoost), lasso (L1) and ridge (L2) regression by at least three percentage points.<br> The combination of certain feature sets showed small increases in predictive performance while no substantial differences between individual feature sets were observed.<br> For some combinations of learners and feature sets, filter methods achieved better predictive performances than the unfiltered feature sets, while ensemble filters did not have a substantial impact on performance.<br><br> Permutation-based feature importance estimated features around the red edge to be most important for the models.<br> However, the presence of features in the near-infrared region (800 nm - 1000 nm) was essential to achieve the best performances.<br><br> More training data and replication in similar benchmarking studies is needed for more generalizable conclusions.<br> Filter methods have the potential to be helpful in high-dimensional situations and are able to improve the interpretation of feature effects in fitted models, which is an essential constraint in environmental modeling studies.

scholarly journals Monitoring forest health using hyperspectral imagery: Does feature selection improve the performance of machine-learning techniques?

2020 ◽  
Author(s):  
Patrick Schratz ◽  
Jannes Muenchow ◽  
Eugenia Iturritxa ◽  
José Cortés ◽  
Bernd Bischl ◽  
...  
Keyword(s):  
Feature Selection ◽  
Predictive Performance ◽  
Environmental Modeling ◽  
Gradient Boosting ◽  
Support Vector ◽  
Substantial Impact ◽  
Feature Sets ◽  
Filter Methods ◽  
Extreme Gradient Boosting ◽  
Feature Importance

This study analyzed highly-correlated, feature-rich datasets from hyperspectral remote sensing data using multiple machine and statistical-learning methods.<br> The effect of filter-based feature-selection methods on predictive performance was compared.<br> Also, the effect of multiple expert-based and data-driven feature sets, derived from the reflectance data, was investigated.<br> Defoliation of trees (%) was modeled as a function of reflectance, and variable importance was assessed using permutation-based feature importance.<br> Overall support vector machine (SVM) outperformed others such as random forest (RF), extreme gradient boosting (XGBoost), lasso (L1) and ridge (L2) regression by at least three percentage points.<br> The combination of certain feature sets showed small increases in predictive performance while no substantial differences between individual feature sets were observed.<br> For some combinations of learners and feature sets, filter methods achieved better predictive performances than the unfiltered feature sets, while ensemble filters did not have a substantial impact on performance.<br><br> Permutation-based feature importance estimated features around the red edge to be most important for the models.<br> However, the presence of features in the near-infrared region (800 nm - 1000 nm) was essential to achieve the best performances.<br><br> More training data and replication in similar benchmarking studies is needed for more generalizable conclusions.<br> Filter methods have the potential to be helpful in high-dimensional situations and are able to improve the interpretation of feature effects in fitted models, which is an essential constraint in environmental modeling studies.

scholarly journals Monitoring Forest Health Using Hyperspectral Imagery: Does Feature Selection Improve the Performance of Machine-Learning Techniques?

2021 ◽  
Vol 13 (23) ◽  
pp. 4832
Author(s):  
Patrick Schratz ◽  
Jannes Muenchow ◽  
Eugenia Iturritxa ◽  
José Cortés ◽  
Bernd Bischl ◽  
...  
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Predictive Performance ◽  
Environmental Modeling ◽  
Gradient Boosting ◽  
Support Vector ◽  
Substantial Impact ◽  
Feature Sets ◽  
Filter Methods ◽  
Extreme Gradient Boosting

This study analyzed highly correlated, feature-rich datasets from hyperspectral remote sensing data using multiple statistical and machine-learning methods. The effect of filter-based feature selection methods on predictive performance was compared. In addition, the effect of multiple expert-based and data-driven feature sets, derived from the reflectance data, was investigated. Defoliation of trees (%), derived from in situ measurements from fall 2016, was modeled as a function of reflectance. Variable importance was assessed using permutation-based feature importance. Overall, the support vector machine (SVM) outperformed other algorithms, such as random forest (RF), extreme gradient boosting (XGBoost), and lasso (L1) and ridge (L2) regressions by at least three percentage points. The combination of certain feature sets showed small increases in predictive performance, while no substantial differences between individual feature sets were observed. For some combinations of learners and feature sets, filter methods achieved better predictive performances than using no feature selection. Ensemble filters did not have a substantial impact on performance. The most important features were located around the red edge. Additional features in the near-infrared region (800–1000 nm) were also essential to achieve the overall best performances. Filter methods have the potential to be helpful in high-dimensional situations and are able to improve the interpretation of feature effects in fitted models, which is an essential constraint in environmental modeling studies. Nevertheless, more training data and replication in similar benchmarking studies are needed to be able to generalize the results.

scholarly journals Interpretable Machine Learning for Early Neurological Deterioration Prediction in Atrial Fibrillation-Related Stroke

2021 ◽  
Author(s):  
Seong Hwan Kim ◽  
Eun-Tae Jeon ◽  
Sungwook Yu ◽  
Kyungmi O ◽  
Chi Kyung Kim ◽  
...  
Keyword(s):  
Machine Learning ◽  
Atrial Fibrillation ◽  
Neurological Deterioration ◽  
Gradient Boosting ◽  
Support Vector ◽  
Light Gradient ◽  
Interpretable Machine Learning ◽  
Extreme Gradient Boosting ◽  
Early Neurological Deterioration ◽  
Feature Importance

Abstract We aimed to develop a novel prediction model for early neurological deterioration (END) based on an interpretable machine learning (ML) algorithm for atrial fibrillation (AF)-related stroke and to evaluate the prediction accuracy and feature importance of ML models. Data from multi-center prospective stroke registries in South Korea were collected. After stepwise data preprocessing, we utilized logistic regression, support vector machine, extreme gradient boosting, light gradient boosting machine (LightGBM), and multilayer perceptron models. We used the Shapley additive explanations (SHAP) method to evaluate feature importance. Of the 3,623 stroke patients, the 2,363 who had arrived at the hospital within 24 hours of symptom onset and had available information regarding END were included. Of these, 318 (13.5%) had END. The LightGBM model showed the highest area under the receiver operating characteristic curve (0.778, 95% CI, 0.726 - 0.830). The feature importance analysis revealed that fasting glucose level and the National Institute of Health Stroke Scale score were the most influential factors. Among ML algorithms, the LightGBM model was particularly useful for predicting END, as it revealed new and diverse predictors. Additionally, the SHAP method can be adjusted to individualize the features’ effects on the predictive power of the model.

scholarly journals Techniques for Detecting Malware Traffic: A Comprehensive Approach to Feature Selection and Classification

2021 ◽  
Vol 9 (12) ◽  
pp. 1-10
Author(s):  
Harsha A K
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Random Forest ◽  
Learning Algorithms ◽  
Malware Detection ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Support Vector ◽  
Steady Increase ◽  
Extreme Gradient Boosting

Abstract: Since the advent of encryption, there has been a steady increase in malware being transmitted over encrypted networks. Traditional approaches to detect malware like packet content analysis are inefficient in dealing with encrypted data. In the absence of actual packet contents, we can make use of other features like packet size, arrival time, source and destination addresses and other such metadata to detect malware. Such information can be used to train machine learning classifiers in order to classify malicious and benign packets. In this paper, we offer an efficient malware detection approach using classification algorithms in machine learning such as support vector machine, random forest and extreme gradient boosting. We employ an extensive feature selection process to reduce the dimensionality of the chosen dataset. The dataset is then split into training and testing sets. Machine learning algorithms are trained using the training set. These models are then evaluated against the testing set in order to assess their respective performances. We further attempt to tune the hyper parameters of the algorithms, in order to achieve better results. Random forest and extreme gradient boosting algorithms performed exceptionally well in our experiments, resulting in area under the curve values of 0.9928 and 0.9998 respectively. Our work demonstrates that malware traffic can be effectively classified using conventional machine learning algorithms and also shows the importance of dimensionality reduction in such classification problems. Keywords: Malware Detection, Extreme Gradient Boosting, Random Forest, Feature Selection.

scholarly journals Evaluating Variable Selection and Machine Learning Algorithms for Estimating Forest Heights by Combining Lidar and Hyperspectral Data

2020 ◽  
Vol 9 (9) ◽  
pp. 507
Author(s):  
Sanjiwana Arjasakusuma ◽  
Sandiaga Swahyu Kusuma ◽  
Stuart Phinn
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Learning Algorithms ◽  
Principal Component ◽  
Hyperspectral Data ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Support Vector ◽  
Forest Height ◽  
Extreme Gradient Boosting

Machine learning has been employed for various mapping and modeling tasks using input variables from different sources of remote sensing data. For feature selection involving high- spatial and spectral dimensionality data, various methods have been developed and incorporated into the machine learning framework to ensure an efficient and optimal computational process. This research aims to assess the accuracy of various feature selection and machine learning methods for estimating forest height using AISA (airborne imaging spectrometer for applications) hyperspectral bands (479 bands) and airborne light detection and ranging (lidar) height metrics (36 metrics), alone and combined. Feature selection and dimensionality reduction using Boruta (BO), principal component analysis (PCA), simulated annealing (SA), and genetic algorithm (GA) in combination with machine learning algorithms such as multivariate adaptive regression spline (MARS), extra trees (ET), support vector regression (SVR) with radial basis function, and extreme gradient boosting (XGB) with trees (XGbtree and XGBdart) and linear (XGBlin) classifiers were evaluated. The results demonstrated that the combinations of BO-XGBdart and BO-SVR delivered the best model performance for estimating tropical forest height by combining lidar and hyperspectral data, with R2 = 0.53 and RMSE = 1.7 m (18.4% of nRMSE and 0.046 m of bias) for BO-XGBdart and R2 = 0.51 and RMSE = 1.8 m (15.8% of nRMSE and −0.244 m of bias) for BO-SVR. Our study also demonstrated the effectiveness of BO for variables selection; it could reduce 95% of the data to select the 29 most important variables from the initial 516 variables from lidar metrics and hyperspectral data.

scholarly journals Mapping of the Canopy Openings in Mixed Beech–Fir Forest at Sentinel-2 Subpixel Level Using UAV and Machine Learning Approach

2020 ◽  
Vol 12 (23) ◽  
pp. 3925
Author(s):  
Ivan Pilaš ◽  
Mateo Gašparović ◽  
Alan Novkinić ◽  
Damir Klobučar
Keyword(s):  
Machine Learning ◽  
Forest Canopy ◽  
Vegetation Index ◽  
Predictive Performance ◽  
Spatial Extent ◽  
Gradient Boosting ◽  
Support Vector ◽  
Stochastic Gradient Boosting ◽  
Extreme Gradient Boosting ◽  
Sentinel 2

The presented study demonstrates a bi-sensor approach suitable for rapid and precise up-to-date mapping of forest canopy gaps for the larger spatial extent. The approach makes use of Unmanned Aerial Vehicle (UAV) red, green and blue (RGB) images on smaller areas for highly precise forest canopy mask creation. Sentinel-2 was used as a scaling platform for transferring information from the UAV to a wider spatial extent. Various approaches to an improvement in the predictive performance were examined: (I) the highest R2 of the single satellite index was 0.57, (II) the highest R2 using multiple features obtained from the single-date, S-2 image was 0.624, and (III) the highest R2 on the multitemporal set of S-2 images was 0.697. Satellite indices such as Atmospherically Resistant Vegetation Index (ARVI), Infrared Percentage Vegetation Index (IPVI), Normalized Difference Index (NDI45), Pigment-Specific Simple Ratio Index (PSSRa), Modified Chlorophyll Absorption Ratio Index (MCARI), Color Index (CI), Redness Index (RI), and Normalized Difference Turbidity Index (NDTI) were the dominant predictors in most of the Machine Learning (ML) algorithms. The more complex ML algorithms such as the Support Vector Machines (SVM), Random Forest (RF), Stochastic Gradient Boosting (GBM), Extreme Gradient Boosting (XGBoost), and Catboost that provided the best performance on the training set exhibited weaker generalization capabilities. Therefore, a simpler and more robust Elastic Net (ENET) algorithm was chosen for the final map creation.

scholarly journals HMMPred: Accurate Prediction of DNA-Binding Proteins Based on HMM Profiles and XGBoost Feature Selection

2020 ◽  
Vol 2020 ◽  
pp. 1-10 ◽  
Author(s):  
Xiuzhi Sang ◽  
Wanyue Xiao ◽  
Huiwen Zheng ◽  
Yang Yang ◽  
Taigang Liu
Keyword(s):  
Feature Selection ◽  
Dna Binding ◽  
Binding Proteins ◽  
Biological Activities ◽  
Dna Binding Proteins ◽  
Gradient Boosting ◽  
Support Vector ◽  
Svm Classifier ◽  
Cross Covariance ◽  
Extreme Gradient Boosting

Prediction of DNA-binding proteins (DBPs) has become a popular research topic in protein science due to its crucial role in all aspects of biological activities. Even though considerable efforts have been devoted to developing powerful computational methods to solve this problem, it is still a challenging task in the field of bioinformatics. A hidden Markov model (HMM) profile has been proved to provide important clues for improving the prediction performance of DBPs. In this paper, we propose a method, called HMMPred, which extracts the features of amino acid composition and auto- and cross-covariance transformation from the HMM profiles, to help train a machine learning model for identification of DBPs. Then, a feature selection technique is performed based on the extreme gradient boosting (XGBoost) algorithm. Finally, the selected optimal features are fed into a support vector machine (SVM) classifier to predict DBPs. The experimental results tested on two benchmark datasets show that the proposed method is superior to most of the existing methods and could serve as an alternative tool to identify DBPs.

scholarly journals Big Data Analytics for Short and Medium-Term Electricity Load Forecasting Using an AI Techniques Ensembler

Energies ◽  
2020 ◽  
Vol 13 (19) ◽  
pp. 5193
Author(s):  
Nasir Ayub ◽  
Muhammad Irfan ◽  
Muhammad Awais ◽  
Usman Ali ◽  
Tariq Ali ◽  
...  
Keyword(s):  
Feature Selection ◽  
Load Forecasting ◽  
Energy Generation ◽  
Supervised Machine Learning ◽  
Gradient Boosting ◽  
Support Vector ◽  
Hybrid Techniques ◽  
Extreme Gradient Boosting ◽  
Electricity Load ◽  
Electricity Load Forecasting

Electrical load forecasting provides knowledge about future consumption and generation of electricity. There is a high level of fluctuation behavior between energy generation and consumption. Sometimes, the energy demand of the consumer becomes higher than the energy already generated, and vice versa. Electricity load forecasting provides a monitoring framework for future energy generation, consumption, and making a balance between them. In this paper, we propose a framework, in which deep learning and supervised machine learning techniques are implemented for electricity-load forecasting. A three-step model is proposed, which includes: feature selection, extraction, and classification. The hybrid of Random Forest (RF) and Extreme Gradient Boosting (XGB) is used to calculate features’ importance. The average feature importance of hybrid techniques selects the most relevant and high importance features in the feature selection method. The Recursive Feature Elimination (RFE) method is used to eliminate the irrelevant features in the feature extraction method. The load forecasting is performed with Support Vector Machines (SVM) and a hybrid of Gated Recurrent Units (GRU) and Convolutional Neural Networks (CNN). The meta-heuristic algorithms, i.e., Grey Wolf Optimization (GWO) and Earth Worm Optimization (EWO) are applied to tune the hyper-parameters of SVM and CNN-GRU, respectively. The accuracy of our enhanced techniques CNN-GRU-EWO and SVM-GWO is 96.33% and 90.67%, respectively. Our proposed techniques CNN-GRU-EWO and SVM-GWO perform 7% and 3% better than the State-Of-The-Art (SOTA). In the end, a comparison with SOTA techniques is performed to show the improvement of the proposed techniques. This comparison showed that the proposed technique performs well and results in the lowest performance error rates and highest accuracy rates as compared to other techniques.

Landslide Susceptibility Analysis using Gradient Boosting Models: A Case Study in Penang Island, Malaysia

2021 ◽  
pp. 22-37
Author(s):  
Han Gao ◽  
Pei Shan Fam ◽  
Lea Tien Tay ◽  
Heng Chin Low
Keyword(s):  
Feature Selection ◽  
Landslide Susceptibility ◽  
Roc Curves ◽  
Spatial Prediction ◽  
Prediction Performance ◽  
Gradient Boosting ◽  
Support Vector ◽  
Prediction Ability ◽  
Light Gradient ◽  
Extreme Gradient Boosting

Tree-based gradient boosting (TGB) models gain popularity in various areas due to their powerful prediction ability and fast processing speed. This study aims to compare the landslide spatial prediction performance of TGB models and non-tree-based machine learning (NML) models in Penang Island, Malaysia. Two specific instances of TGB models, eXtreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM) and two specific instances of NML models, artificial neural network (ANN) and support vector machine (SVM), are applied to make predictions of landslide susceptibility. Feature selection and oversampling techniques are considered to improve the prediction performance as well. The results are analyzed and discussed mainly based on receiver operating characteristic (ROC) curves as well as the area under the curves (AUC). The results show that TGB models give better prediction performance compared to NML models, no matter what the sample size is. The TGB models’ performances are improved when training with the dataset considering either feature selection or oversampling techniques. The highest AUC value of 0.9525 is obtained from the combination of XGBoost and SMOTE. The landslide susceptibility maps (LSMs) produced by XGBoost and LightGBM can provide valuable information in landslide management and mitigation in Penang Island, Malaysia.

scholarly journals Improvement of Prediction Performance With Conjoint Molecular Fingerprint in Deep Learning

2020 ◽  
Vol 11 ◽  
Author(s):  
Liangxu Xie ◽  
Lei Xu ◽  
Ren Kong ◽  
Shan Chang ◽  
Xiaojun Xu
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Molecular Descriptor ◽  
Predictive Performance ◽  
Gradient Boosting ◽  
Support Vector ◽  
Quantitative Structure ◽  
Structure Activity ◽  
Extreme Gradient Boosting ◽  
The Impact

The accurate predicting of physical properties and bioactivity of drug molecules in deep learning depends on how molecules are represented. Many types of molecular descriptors have been developed for quantitative structure-activity/property relationships quantitative structure-activity relationships (QSPR). However, each molecular descriptor is optimized for a specific application with encoding preference. Considering that standalone featurization methods may only cover parts of information of the chemical molecules, we proposed to build the conjoint fingerprint by combining two supplementary fingerprints. The impact of conjoint fingerprint and each standalone fingerprint on predicting performance was systematically evaluated in predicting the logarithm of the partition coefficient (logP) and binding affinity of protein-ligand by using machine learning/deep learning (ML/DL) methods, including random forest (RF), support vector regression (SVR), extreme gradient boosting (XGBoost), long short-term memory network (LSTM), and deep neural network (DNN). The results demonstrated that the conjoint fingerprint yielded improved predictive performance, even outperforming the consensus model using two standalone fingerprints among four out of five examined methods. Given that the conjoint fingerprint scheme shows easy extensibility and high applicability, we expect that the proposed conjoint scheme would create new opportunities for continuously improving predictive performance of deep learning by harnessing the complementarity of various types of fingerprints.

Sign in / Sign up

Export Citation Format

Share Document