Proposed Sampling Strategy Research Articles

Targeted Sampling Dynamic Window Approach: A Path-Aware Dynamic Window Approach Sampling Strategy for Omni-Directional Robots

Abstract This paper describes a sampling strategy for the dynamic window approach (DWA), a local path planner, for omni-directional robot motion planning. An efficient local planner allows the robot to quickly respond to dynamic obstacles and ensures that commanded velocities meet the dynamic constraints of the robot. While typical DWA implementations sample the velocity space evenly, we propose that targeted sampling (TS) will result in a more fine-grained search of the relevant velocity space, leading to better control and performance in space-constrained environments. Our TS-DWA strategy is informed by the global planned path, allowing us to sample more velocities in the general path direction. We employ a polar velocity generator to selectively sample velocities and couple angular velocity samples to the path curvature. A bias for angular velocity is added for robots with a preferred heading, such as robots with forward-mounted sensors, to quickly turn toward the desired direction for better sensing. The strategy is implemented as a robot operating system (ROS) navigation stack local_planner plugin and tested in simulation with Gazebo using an omni-directional robot platform. Experiments show that as the space around the simulated robot gets smaller, our proposed sampling strategy results in more successful navigation trials to the goal in space-constrained environments compared to other commonly used methods like DWA and timed-elastic-band, where planning fails or oscillates. TS-DWA was also deployed on the Vision60 quadrupedal robot to demonstrate navigation through narrow corridors in the real world.

Survival Prediction via Deep Attention-Based Multiple-Instance Learning Networks with Instance Sampling

Survival prediction via training deep neural networks with giga-pixel whole-slide images (WSIs) is challenging due to the lack of time annotation at the pixel level or patch (instance). Multiple instance learning (MIL), as a typical weakly supervised learning method, aims to resolve this challenge by using only the slide-level time. The attention-based MIL method leverages and enhances performance by weighting the instances based on their contribution to predicting the outcome. A WSI typically contains hundreds of thousands of image patches. Training a deep neural network with thousands of image patches per slide is computationally expensive and time-consuming. To tackle this issue, we propose an adaptive-learning strategy where we sample a subset of informative instances/patches more often to train the deep survival neural networks. We also present other sampling strategies and compare them with our proposed sampling strategy. Using both real-world and synthesized WSIs for survival, we show that sampling strategies significantly can significantly reduce computing time while result in no or negligible performance loss. We also discuss the benefits of each instance sampling strategy in different scenarios.

Camera-aware re-identification feature for multi-target multi-camera tracking

Multi-target multi-camera tracking is an important research topic in intelligent surveillance to achieve re-identification (Re-ID) of moving targets across different cameras. However, Re-ID faces significant challenges owing to variations in cameras/viewpoints, making it difficult to learn discriminative feature representations for targets captured from different cameras/viewpoints. A new pipeline is introduced by balancing the across-cameras sample feature space in camera-aware Re-ID framework. Specifically, different sampling strategies play a crucial role on the performance under the same baseline and identify the feature discrepancy between cameras/viewpoints as a crucial factor. This proposed sampling strategy is called camera equalization sampling to learn enhanced feature disparities, which balances cameras under identity rather than randomly sampling in a batch. The sampled images are combined with non visual cues(cameras position encoding) to reduce intra class variance. For the mechanism of camera equalization sampling, the improved camera centric loss function can better reduce the negative impact of individual samples and provide stable learnable features.Our proposed method consists of three modules. (i) Camera equalization (CE) ensures that each batch collects at least one image from each camera for every identity, thereby enabling robust features. (ii) Camera position embedding (CPE) mitigates the scene bias caused by different cameras/viewpoints by encoding camera indices. (iii) Camera Center triplet loss(CCL) based on CE improves higher robustness to outliers and noisy labels. We demonstrated the proposed method's effectiveness on popular datasets such as DukeMTMC-reID, Market-1501, and MSMT17, achieving state-of-the-art performance.

Towards Food Image Retrieval via Generalization-Oriented Sampling and Loss Function Design

Food computing has increasingly received widespread attention in the multimedia field. As a basic task of food computing, food image retrieval has wide applications, that is, food image retrieval can help users to find the desired food from a large number of food images. Besides, the retrieved information can be applied to establish a richer database for the subsequent food content-related recommendation. Food image retrieval aims to achieve better performance on novel categories. Thus, it is worth studying to transfer the embedding ability from the training set to the unseen test set, that is, the generalization of the model. Food is influenced by various factors, such as culture and geography, leading to great differences between domains, such as Asian food and western food. Therefore, it is challenging to study the generalization of the model in food image retrieval. In this article, we improve the classical metric learning framework and propose a generalization-oriented sampling strategy, which boosts the generalization of the model by maximizing the intra-class distance from a proportion of positive pairs to avoid the excessive distance compression in the embedding space. Considering that the existing optimization process is in an opposite direction to our proposed sampling strategy, we further propose an adaptive gradient assignment policy named gradient-adaptive optimization , which can alleviate the intra-class distance compression during optimization by assigning different gradients to different samples. Extensive evaluation on three popular food image datasets demonstrates the effectiveness of the proposed method. We also experiment on three popular general datasets to prove that solving the problem from the generalization can also improve the performance of general image retrieval. Code is available at https://github.com/Jiajun-ISIA/Generalization-oriented-Sampling-and-Loss .

Improved instance segmentation for slender urban road facility extraction using oblique aerial images

Slender urban road facilities (SURFs) with extreme aspect ratios are essential roles of the road network and exist everywhere in urban scenarios, such as street lamps, traffic lights, and monitors. Their information provides important knowledge for road safety, traffic control, urban planning, city management, etc. With low cost and high-efficiency benefits, oblique aerial images are easily captured to cover large-scale areas, which can be appropriately used to survey SURFs in urban areas automatically. Meanwhile, instance segmentation methods are frequently applied, predicting bounding boxes and semantic masks of objects simultaneously, yet a minority is delicately designed for SURFs. This research aims to propose an instance segmentation method to automatically extract SURFs from oblique aerial imagery, enhancing both the predicted bounding box and the segmented binary mask. First, we design a dense anchor ratio with an IoU-balanced sampling strategy (DASS) for proposal generation by statistical analysis to improve the predicted bounding box. The proposed sampling strategy can better cover the shape of slender proposals and alleviate the imbalance problem between the target objects and background. Regarding the typical instance segmentation architectures, the binary mask is segmented coarsely due to the downsampling operations. Second, we propose balanced fine-grained features (BFGF) merged into the instance segmentation process via a three-stage architecture, effectively improving the detector’s performance. Specifically, before feature incorporation, the multi-level feature pyramid is refined by rescaling and integrating to obtain balanced features. Moreover, to evaluate the proposed approaches, we contribute an Urban Road Facilities Dataset for our task, URFD, which contains 1075 images and 1378 instances labeled manually and enriches the open resource dataset. By comparative experiments, the proposed method performs superiority in SURF instance segmentation, obtaining an mAP of 0.888 of the predicted bounding box and an mAP of 0.876 of the segmented binary mask.

Objective evaluation-based efficient learning framework for hyperspectral image classification

ABSTRACT Deep learning techniques with remarkable performance have been successfully applied to hyperspectral image (HSI) classification. Due to the limited availability of training data, earlier studies primarily adopted the patch-based classification framework, which divides images into overlapping patches for training and testing. However, this framework results in redundant computations and possible information leakage. This study proposes an objective evaluation-based efficient learning framework for HSI classification. It consists of two main parts: (i) a leakage-free balanced sampling strategy and (ii) an efficient fully convolutional network (EfficientFCN) optimized for the accuracy-efficiency trade-off. The leakage-free balanced sampling strategy first generates balanced and non-overlapping training and test data by partitioning the HSI and its ground truth image into non-overlapping windows. Then, the generated training and test data are used to train and test the proposed EfficientFCN. EfficientFCN exhibits a pixel-to-pixel architecture with modifications for faster inference speed and improved parameter efficiency. Experimental results demonstrate that the proposed sampling strategy can provide objective performance evaluation. EfficientFCN outperforms many state-of-the-art approaches concerning the speed-accuracy trade-off. For instance, compared to the recent efficient models EfficientNetV2 and ConvNeXt, EfficientFCN achieves 0.92% and 3.42% superior accuracy and 0.19s and 0.16s faster inference time, respectively, on the Houston dataset. Code is available at https://github.com/xmzhang2018.

MvLognCorrEst: an R package for sampling from multivariate lognormal distributions and estimating correlations from uncomplete correlation matrix

Background and ObjectivePharmacometrics (PMX) is a quantitative discipline which supports decision-making processes in all stages of drug development. PMX leverages Modeling and Simulations (M&S), which represents a powerful tool to characterize and predict the behavior and the effect of a drug. M&S-based methods, such as Sensitivity Analysis (SA) and Global Sensitivity Analysis (GSA), are gaining interest in PMX as they allow the evaluation of model-informed inference quality. Simulations should be correctly designed to obtain reliable results. Neglecting correlations between model parameters can significantly alter the results of simulations. However, the introduction of a correlation structure between model parameters can cause some issues. Sampling from a multivariate lognormal distribution, which is the typically distribution assumed for PMX model parameters, is not straightforward when a correlation structure is introduced. Indeed, correlations need to respect some constraints which depend by the CVs (i.e., coefficients of variation) of lognormal variables. In addition, when correlation matrices have some unspecified values, they should be properly fixed preserving the positive semi-definiteness of the correlation structure. In this paper, we present mvLognCorrEst, an R package developed to address these issues. MethodsThe proposed sampling strategy was based on reconducting the extraction from the multivariate lognormal distribution of interest to the underlying Normal distribution. However, with high lognormal CVs, a positive semi-definite Normal covariance matrix cannot be obtained due to the violation of some theoretical constraints. In these cases, the Normal covariance matrix was approximated to its nearest positive definite matrix using Frobenius norm as matrix distance. For the estimation of unknown correlations terms, the graph theory was used to represent the correlation structure as weighed undirected graph. Plausible value ranges for the unspecified correlations were derived considering the paths between variables. Then, their estimation was performed by solving a constrained optimization problem. Results: Package functions are presented and applied on a real case study, that is the GSA of a PMX model that has been recently developed to support preclinical oncological studies. ConclusionsmvLognCorrEst package is an R tool to support simulation-based analysis for which sampling from multivariate lognormal distributions with correlated variables and/or estimation of partially defined correlation matrix are required.

Sequential Ensemble Monte Carlo Sampler for On-Line Bayesian Inference of Time-Varying Parameter in Engineering Applications

Abstract Several on-line identification approaches have been proposed to identify parameters and evolution models of engineering systems and structures when sequential datasets are available via Bayesian inference. In this work, a robust and “tune-free” sampler is proposed to extend one of the sequential Monte Carlo implementations for the identification of time-varying parameters which can be assumed constant within each set of data collected but might vary across different sequences of datasets. The proposed approach involves the implementation of the affine-invariant Ensemble sampler in place of the Metropolis–Hastings sampler to update the samples. An adaptive-tuning algorithm is also proposed to automatically tune the step-size of the affine-invariant ensemble sampler which, in turn, controls the acceptance rate of the samples across iterations. Furthermore, a numerical investigation behind the existence of inherent lower and upper bounds on the acceptance rate, making the algorithm robust by design, is also conducted. The proposed method allows for the off-line and on-line identification of the most probable models under uncertainty. The proposed sampling strategy is first verified against the existing sequential Monte Carlo sampler in a numerical example. Then, it is validated by identifying the time-varying parameters and the most probable model of a nonlinear dynamical system using experimental data.

Improving the Performance of Automated Rooftop Extraction through Geospatial Stratified and Optimized Sampling

Accurate and timely access to building rooftop information is very important for urban management. The era of big data brings new opportunities for rooftop extraction based on deep learning and high-resolution satellite imagery. However, collecting representative datasets from such big data to train deep learning models efficiently is an essential problem that still needs to be explored. In this study, geospatial stratified and optimized sampling (GSOS) based on geographical priori information and optimization of sample spatial location distribution is proposed to acquire representative samples. Specifically, the study area is stratified based on land cover to divide the rooftop-dense stratum and the rooftop-sparse stratum. Within each stratum, an equal amount of samples is collected and their spatial locations are optimized. To evaluate the effectiveness of the proposed strategy, several qualitive and quantitative experiments are conducted. As a result, compared with other common sampling approaches (e.g., random sampling, stratified random sampling, and optimized sampling), GSOS is superior in terms of the abundance and types of collected samples. Furthermore, two quantitative metrics, the F1-score and Intersection over Union (IoU), are reported for rooftop extraction based on deep learning methods and different sampling methods, in which the results based on GSOS are on average 9.88% and 13.20% higher than those based on the other sampling methods, respectively. Moreover, the proposed sampling strategy is able to obtain representative training samples for the task of building rooftop extractions and may serve as a viable method to alleviate the labour-intensive problem in the construction of rooftop benchmark datasets.

A Novel Surrogate Model-Based Solving Framework for the Black-Box Dynamic Co-Design and Optimization Problem in the Dynamic System

When encountering the black-box dynamic co-design and optimization (BDCDO) problem in the multidisciplinary dynamic system, the finite difference technique is inefficient or even infeasible to provide approximate numerical gradient information for the optimization algorithm since it requires numerous original expensive evaluations. Therefore, a solving framework based on the surrogate model of the state equation is introduced to optimize BDCDO. To efficiently construct the surrogate model, a sequential sampling method is presented on the basis of the successive relative improvement ratio. Meanwhile, a termination criterion is suggested to quantify the convergence of the solution. Ultimately, the newly proposed sampling strategy and termination criterion are incorporated into the BDCDO solving framework to optimize two numerical examples and two engineering examples. The results demonstrate that the framework integrating the proposed sampling strategy and termination criterion has the best performance in terms of the accuracy, efficiency, and computational budget compared to the existing methods.

Adaptive sampling strategy for characterizing spatial distribution of soil liquefaction potential using cone penetration test

Characterizing spatial distribution of soil liquefaction potential is critical for assessing liquefaction-related hazards (e.g. building damages caused by liquefaction-induced differential settlement). However, in engineering practice, soil liquefaction potential is usually measured at limited locations in a specific site using in situ tests, e.g. cone penetration tests (CPTs), due to the restrictions of time, cost and access to subsurface space. In these cases, liquefaction potential of soil at untested locations requires to be interpreted from limited measured data points using proper interpolation method, leading to remarkable statistical uncertainty in liquefaction assessment. This underlines an important question of how to optimize the locations of CPT soundings and determine the minimum number of CPTs for achieving a target reliability level of liquefaction assessment. To tackle this issue, this study proposes a smart sampling strategy for determining the minimum number of CPTs and their optimal locations in a self-adaptive and data-driven manner. The proposed sampling strategy leverages on information entropy and Bayesian compressive sampling (BCS). Both simulated and real CPT data are used to demonstrate the proposed method. Illustrative examples indicate that the proposed method can adaptively and sequentially select the required number and optimal locations of CPTs.

Machine learning with a susceptibility index-based sampling strategy for landslide susceptibility assessment

The past landslides from landslide inventory are essential for machine learning (ML)-based landslide susceptibility assessment (LSA). They determine not only the positive samples (characterized by the past landslides) but also the negative samples (randomly generated based on past landslides) for training and validating the ML models. However, the number of past landslides is often limited because of the constraints of time, budget, and resources available, etc. In other words, the available data for establishing landslide susceptibility ML models are limited, which indicates that the accuracy and reliability of the corresponding models are insufficient. This article, therefore, proposes using a new landslide susceptibility index-based sampling strategy to enhance the positive and negative samples for model training and validation to reach an improved ML-based LSA. To realize this idea, landslide susceptibility analysis based on initial datasets compiled from landslide inventory by using three ML models, i.e., random forest (RF), gradient boosting decision tree (GBDT) and support vector machine (SVM), are first conducted to obtain the initial landslide susceptibility indices at different space locations. Then, the landslide susceptibility indices are analyzed with the proposed sampling strategy which considers directly the grid units with very high and very low landslide susceptibility indices as potential positive and negative samples, respectively, to enrich the initial dataset; and the number of these positive/negative samples is determined by a Bayesian optimization algorithm. Thereafter, the ML models are updated with the enriched datasets. Finally, to verify the effectiveness of the proposed strategy, the improved models are applied to assess the landslide susceptibility of Taojiang County, China, and the results are compared with those from initial corresponding models without updating. The results show that compared with the initial RF, GBDT and SVM models, the corresponding improved models have a better performance in accuracy, precision, recall rate, and specificity. In particular, the AUC values of the three models are increased by 11.94%, 10.72% and 0.57%, respectively.

Sample design optimization for soil mapping using improved artificial neural networks and simulated annealing

Optimization of the sampling design is significant for generating accurate soil maps based on samples. Simulated annealing (SA) with the mean squared prediction error (MSE) as objective function has been proven as an effective method for sampling optimization with prior samples for the MSE calculation. In this study, an improved artificial neural network (the improved ANN) was developed firstly and then utilized to calculate the objective function of SA for sampling optimization (named as the improved ANN_SA). The proposed approach was evaluated to generate optimized samples with a series of samples sizes (from 10 to 500 points) for mapping soil organic matter (SOM) content from the existing 5054 samples in a study area with 1067 km2 in Jiangsu Province, China. A commonly-used sampling optimization using SA with the objective function calculated by regression kriging (named as RK_SA) was taken as a reference method. The two sampling optimization approaches were compared in mapping SOM using three prediction methods, the improved ANN, regression kriging (RK) and random forest. The results showed that the proposed sampling optimization approach generally achieved more accurate prediction over different sampling sizes. The maximum improvement of prediction accuracy by using the proposed sampling strategy vs. the reference strategy was 12.5%, 53.6%, and 15.5% when using the improved ANN, RK, and random forest as soil mapping methods, respectively. Moreover, the improved ANN and random forest generated more accurate soil predictions than RK with the proposed sampling optimization approach. The superiority of the proposed sampling optimization was more obvious in low sampling densities (smaller than 0.3 points/km2). We conclude that the improved ANN_SA sampling is a potential effective sampling optimization approach, and machine learning is a promising method for soil mapping when using this sampling approach.

Integrating Algorithmic Sampling-Based Motion Planning with Learning in Autonomous Driving

Sampling-based motion planning (SBMP) is a major algorithmic trajectory planning approach in autonomous driving given its high efficiency and outstanding performance in practice. However, driving safety still calls for further refinement of SBMP. In this article we organically integrate algorithmic motion planning with learning models to improve SBMP in highway traffic scenarios from the following two perspectives. First, given the number of points to be sampled, we develop a new model to sample “important” points for SBMP by predicting the intention of surrounding vehicles and learning the distribution of human drivers’ trajectory. Second, we empirically study the relationship between the number of sample points and the environment, which is largely ignored in conventional SBMP. Then, we provide a guideline to select the appropriate number of points to be sampled under different scenarios to guarantee efficiency. The simulation experiments are conducted based on the vehicle trajectory dataset NGSIM. The results show that the proposed sampling strategy outperforms existing sampling strategies in terms of the computing time, traveling time, and smoothness of the trajectory.

Switching: understanding the class-reversed sampling in tail sample memorization

Long-tailed visual recognition poses significant challenges to traditional machine learning and emerging deep networks due to its inherent class imbalance. Existing reweighting and re-sampling methods, although effective, lack a fundamental theory while leaving the paradoxical effects of long tail unsolved, where network failing with head classes under-represented and tail classes overfitted. In this paper, we investigate long-tailed recognition from a memorization-generalization point of view, which not only unravels the whys of previous methods, but also derives a new principled solution. Specifically, we first empirically identify the regularity of classes under long-tailed distributions, finding that long-tailed challenge is essentially a trade-off between the representation of high-regularity head classes and generalization to low-regularity tail classes. To memorize tail samples without seriously damaging the representation of head samples, we propose a simple yet effective sampling strategy for ordinary mini-batch SGD optimization process, Switching, which switches from instance-balanced sampling to class-reversed sampling for only once at small learning rate. By theoretical analysis, we show that the upper bound on the generalization error of the proposed sampling strategy is lower than instance-balanced sampling conditionally. In our experiments, the proposed method can reach feasible performance more efficiently than current methods. Further experiments validate the superiority of the proposed Switching strategy, implying that the long-tailed learning trade-off could be parsimoniously tackled only in the memorization stage with a small learning rate and over-exposure of tail samples.

Two-phase stratified sampling and analysis for predicting binary outcomes.

The two-phase study design is a cost-efficient sampling strategy when certain data elements are expensive and, thus, can only be collected on a sub-sample of subjects. To date guidance on how best to allocate resources within the design has assumed that primary interest lies in estimating association parameters. When primary interest lies in the development and evaluation of a risk prediction tool, however, such guidance may, in fact, be detrimental. To resolve this, we propose a novel strategy for resource allocation based on oversampling cases and subjects who have more extreme risk estimates according to a preliminary model developed using fully observed predictors. Key to the proposed strategy is that it focuses on enhancing efficiency regarding estimation of measures of predictive accuracy, rather than on efficiency regarding association parameters which is the standard paradigm. Towards valid estimation and inference for accuracy measures using the resultant data, we extend an existing semiparametric maximum likelihood ethod for estimating odds ratio association parameters to accommodate the biased sampling scheme and data incompleteness. Motivated by our sampling design, we additionally propose a general post-stratification scheme for analyzing general two-phase data for estimating predictive accuracy measures. Through theoretical calculations and simulation studies, we show that the proposed sampling strategy and post-stratification scheme achieve the promised efficiency improvement. Finally, we apply the proposed methods to develop and evaluate a preliminary model for predicting the risk of hospital readmission after cardiac surgery using data from the Pennsylvania Health Care Cost Containment Council.

A hybrid sequential sampling strategy for sparse polynomial chaos expansion based on compressive sampling and Bayesian experimental design

Sparse representation of Polynomial Chaos Expansion (PCE) has been widely used in the field of Uncertainty Quantification (UQ) due to its simple model structure and low computational cost. The sample quality is a crucial issue that affects the precision of sparse PCE model. In this paper, a hybrid sequential sampling strategy is proposed to collect samples with high quality and in relatively small quantities for training PCE model. To achieve fast convergence rate and modelling stability, the proposed strategy takes into account both input information and target model feature by combining compressive sampling and Bayesian experimental design. First, a sequential sampling framework is established to collect samples that approximately match the coherence-optimal distribution, which is derived from the compressive sampling theory, during the iteration process. Then, by resorting to the Bayesian Compressive Sensing (BCS) method and information theory, favourable sampling points in each iteration are determined according to the modelling results, substituting for randomly selecting sampling points. The performance of the proposed sampling strategy is evaluated on several analytical functions through comparison with three input-dependent only sampling methods and two output-dependent only sampling methods. Results show that the proposed strategy outperforms the input-dependent only methods and has no worse performance than the output-dependent only methods in convergence rate and computational stability in most circumstances. The proposed strategy is further applied to two engineering cases for global sensitivity analysis of structural static and dynamic properties. It is illustrated that with automatically collected samples and observations, the PCE models can be obtained with desired accuracy, and the sensitivity analysis can be pursued with low computational cost and high precision.

Efficient Fourier Single-Pixel Imaging with Gaussian Random Sampling

Fourier single-pixel imaging (FSI) is a branch of single-pixel imaging techniques. It allows any image to be reconstructed by acquiring its Fourier spectrum by using a single-pixel detector. FSI uses Fourier basis patterns for structured illumination or structured detection to acquire the Fourier spectrum of image. However, the spatial resolution of the reconstructed image mainly depends on the number of Fourier coefficients sampled. The reconstruction of a high-resolution image typically requires a number of Fourier coefficients to be sampled. Consequently, a large number of single-pixel measurements lead to a long data acquisition time, resulting in imaging of a dynamic scene challenging. Here we propose a new sampling strategy for FSI. It allows FSI to reconstruct a clear and sharp image with a reduced number of measurements. The key to the proposed sampling strategy is to perform a density-varying sampling in the Fourier space and, more importantly, the density with respect to the importance of Fourier coefficients is subject to a one-dimensional Gaussian function. The final image is reconstructed from the undersampled Fourier spectrum through compressive sensing. We experimentally demonstrate the proposed method is able to reconstruct a sharp and clear image of 256 × 256 pixels with a sampling ratio of 10%. The proposed method enables fast single-pixel imaging and provides a new approach for efficient spatial information acquisition.

Remote Sensing-Guided Spatial Sampling Strategy over Heterogeneous Surface Ground for Validation of Vegetation Indices Products with Medium and High Spatial Resolution

Remote sensing (RS)-derived vegetation indices (VIs) with medium and high spatial resolution have emerged as a promising dataset for fine-scale ecosystem modeling and agricultural monitoring at local or global scales. Before they can be used as reliable inputs for other research, conducting in situ measurements for validation is very critical. However, the spatial heterogeneity due to the diversity of land cover and its spatial organization in the landscape increases the uncertainty of validation, so design of optimal sampling is an important basis for the reliability of the validation. In this paper, we propose an integrative stratified sampling strategy (INTEG-STRAT) based on normalized difference vegetation index (NDVI) data as prior knowledge. The basic idea is to realize a sampling optimization by determining the optimal combination of the spatial sampling method (e.g., simple random sampling (SRS), spatial system sampling (SYS), stratified sampling, generalized random tessellation stratified (GRTS), balanced acceptance sampling (BAS)) and spatial stratification scheme with an objective rule. The objective rule in this paper is to minimize the root mean square error (RMSE) of 10-fold cross validation between estimated values (sample are not included) and the corresponding values on prior knowledge. Relative precision, correlation coefficient, and RMSE are used to compare the effectiveness of the proposed sampling strategy with each sampling method without considering sampling optimization. After comparing, we find that the INTEG-STRAT requires fewer samples to become stable and has higher accuracy. At site 1, when the correlation coefficient between NDVI image and the simulated NDVI surface reached 80%, INTEG-STRAT needed only 70 sampling points while other methods require more sampling points. At the same time, INTEG-STRAT strategy has a smaller RMSE between the estimated values and the corresponding values on prior knowledge image. In general, INTEG-STRAT is an effective method in the selection of representative samples to support the validation of vegetation indices products with medium and high spatial resolution.

FB2Droid: A Novel Malware Family-Based Bagging Algorithm for Android Malware Detection

As the number of Android malware applications continues to grow at a high rate, detecting malware to protect the system security and user privacy is becoming increasingly urgent. Each malware application belongs to a specific family, and there is a gap in the number of malware families. The accuracy of detection can be improved if malware family information is well utilized and certain strategies are adopted to balance the variability among samples. In addition, the performance of a base classifier is limited. If an ensemble classifier or an ensemble method can be adopted, the detection effect can be further improved. Therefore, this paper proposes a novel malware family-based bagging algorithm for Android malware detection, called FB2Droid, to perform malware detection. First, five features are extracted from the Android application package. Then, the relief feature selection algorithm is used for feature selection. Next, we designed two different sampling strategies based on different families of malware to alleviate the sample imbalance in the dataset. Combined with the two sampling strategies, the traditional bagging algorithm is improved to integrate the classifier. In the experiment, several classifiers were used to evaluate the proposed scheme. The experimental results show that the proposed sampling strategy and the improved bagging algorithm can effectively improve the detection accuracy of these classifiers.