基于改进Self-paced Ensemble算法的浏览器指纹识别

浏览器指纹技术凭借其无状态、跨域一致等优点,已经被许多网站应用到用户追踪、广告投放和安全验证等方面。浏览器指纹识别的过程是典型的不平衡数据的分类过程。针对当前浏览器指纹长期追踪过程中存在数据样本类不平衡导致指纹识别准确度低、长期追踪易失效等问题,提出了改进的Self-paced Ensemble(Improved SPE,ISPE)方法应用于浏览器指纹识别。对浏览器指纹样本欠采样过程和集成学习单个分类器的训练过程进行了改进,重点针对难以识别的浏览器指纹,添加类注意力机制并优化自协调因子,使分类器在训练和识别浏览器指纹的过程中更加注重边界样本的分类效果,从而提升总体的浏览器指纹识别准确度。在所收集的3 483条指纹和开源数据集中的15 000条指纹上进行了实验,结果表明,ISPE算法在浏览器指纹匹配识别的F1-score达到95.6%,相比Bi-RNN算法提高了16.8%。

DSP-TMM:A Robust Cluster Analysis Method Based on Diversity Self-Paced T-Mixture Model

In order to implement the robust cluster analysis,solve the problem that the outliers in the data will have a serious disturbance to the probability density parameter estimation,and therefore affect the accuracy of clustering,a robust cluster analysis method is proposed which is based on the diversity self-paced t-mixture model.This model firstly adopts the t-distribution as the submodel which tail is easily controllable.On this basis,it utilizes the entropy penalty expectation conditional maximal algorithm as a pre-clustering step to estimate the initial parameters.After that,this model introduces l2,1-norm as a self-paced regularization term and developes a new ECM optimization algorithm,in order to select high confidence samples from each component in training.Finally,experimental results on several real-world datasets in different noise environments show that the diversity self-paced t-mixture model outperforms the state-of-the-art clustering methods.It provides significant guidance for the construction of the robust mixture distribution model.

Issues and Limitations of Broad Band Remote Sensing of Kimberlite—A Case Example from Kimberlites of Dharwar Craton, India

Present study attempts to understand the potential of multispectral ASTER (Advanced space borne thermal emission and reflection radiometer) data for spatial mapping of kimberlite. Kimberlite is an economic rock known for hosting diamond. Kimberlite also has petrogenetic importance for giving us clue on the composition of lower part of the mantle. Kimberlites often contain serpentine, carbonate minerals;which have their diagnostic spectral signatures in short wave infrared (SWIR) domain. In the present study, attempt is made to delineate kimberlite from adjacent granite-granodiorite gneiss based on processing of the ASTER data as ASTER’s spectral channels can detect some of the diagnostic absorption features of kimberlites. But it has been observed that the kimberlites are difficult to be delineated by processing the ASTER data using correlative information of both sub-pixel and per-pixel mapping. Moreover, smaller spatial size of kimberlites with respect to pixel size of ASTER SWIR channels further obscures the spectral feature of kimberlite. Therefore, an attempt is also made to understand how intra pixel spectral mixing of kimberlite and granite granodiorite-gneiss modifies the diagnostic spectral feature of kimberlite. It is observed that spectral feature of kimberlites would be obscured when it is has very small spatial size (one-tenth of pixel) with respect to pixel size. Moreover, calcrete developed in the adjacent soil has identical absorption feature similar to the spectral features of kimberlites imprinted in the respective ASTER convolved spectral profiles. This also has resulted false-positives in ASTER image when we use spectral feature as a tool for spatial mapping of kimberlite. Therefore hyperspectral data with high spatial and spectral resolution is required for targeting kimberlites instead of using broad band spectral feature of kimberlites.

The Effects of Externally Paced Exercise on Executive Function and Stress in College-Aged Students

Purpose The purpose of the study was to investigate the acute effect of a beginner martial art class and aerobic exercise on executive function(EF)in college-aged young adults.There is overwhelming evidence that demonstrates acute as well as long-term aerobic exercise improves EF.Nevertheless,there is limited research comparing externally paced exercise(EPE)to self-paced exercise(SPE)such as walking on improving EF.EPE requires greater cortical demand than SPE to execute a motor plan.Methods Eight men and eight women,aged 24.2±2.8 years,participated in a Repeated Measures Crossover Design.Pre-and post-testing of EF with the Stroop and Tower of London(ToL)and stress level were measured after each of the two 1-h conditions:the SPE consisted of a walk(aerobic exercise)and the EPE was a beginner martial art class.Results There were significant main effects for the martial art class for the Stroop’s mean reaction time for congruent trials(P=0.01)with a large-effect size.The mean reaction time for incongruent trials was significant(P=0.05)with a medium-effect size.The ToL’s mean solution time(P=0.003)and mean execution time(P=0.002)were also significant with large-effect sizes.Stress levels were not significantly improved following either condition.Conclusion The martial art class significantly improved all the major domains of EF,while aerobic exercise of a similar intensity did not demonstrate any measured significant changes.The physiological benefits of physical exercise are well documented;however,the cognitive enhancing capability of EPE should also be appreciated given the results of this study.

Crop type mapping using LiDAR,Sentinel-2 and aerial imagery with machine learning algorithms

LiDAR data are becoming increasingly available,which has opened up many new applications.One such application is crop type mapping.Accurate crop type maps are critical for monitoring water use,estimating harvests and in precision agriculture.The traditional approach to obtaining maps of cultivated fields is by manually digitizing the fields from satellite or aerial imagery and then assigning crop type labels to each field-often informed by data collected during ground and aerial surveys.However,manual digitizing and labeling is time-consuming,expensive and subject to human error.Automated remote sensing methods is a cost-effective alternative,with machine learning gaining popularity for classifying crop types.This study evaluated the use of LiDAR data,Sentinel-2 imagery,aerial imagery and machine learning for differentiating five crop types in an intensively cultivated area.Different combinations of the three datasets were evaluated along with ten machine learning.The classification results were interpreted by comparing overall accuracies,kappa,standard deviation and f-score.It was found that LiDAR data successfully differentiated between different crop types,with XGBoost providing the highest overall accuracy of 87.8%.Furthermore,the crop type maps produced using the LiDAR data were in general agreement with those obtained by using Sentinel-2 data,with LiDAR obtaining a mean overall accuracy of 84.3%and Sentinel-2 a mean overall accuracy of 83.6%.However,the combination of all three datasets proved to be the most effective at differentiating between the crop types,with RF providing the highest overall accuracy of 94.4%.These findings provide a foundation for selecting the appropriate combination of remotely sensed data sources and machine learning algorithms for operational crop type mapping.

Seasonal effects of impervious surface estimation in subtropical monsoon regions

Accurate impervious surface estimation(ISE)is challenging due to the diversity of land covers and the vegetation phenology and climate.This study investigates the variation of impervious surfaces estimated from different seasons of satellite images and the seasonal sensitivity of different methods.Four Landsat ETM?images of four different seasons and two popular methods(i.e.artificial neural network(ANN)and support vector machine(SVM))are employed to estimate the impervious surface on the pixel level.Results indicate that winter(dry season)is the best season to estimate impervious surface even though plants are not in their growing season.Less cloud and less variable source areas(VSA)(seasonal water body)become the major advantages of winter for the ISE,as cloud is easily confusedwith bright impervious surfaces,andwater in VSA is confusedwith dark impervious surfaces due to their similar spectral reflectance.For the seasonal sensitivity of methods,ANN appears more stable as its accuracy varied less than that obtained with SVM.However,both the methods showed a general consistency of the seasonal changes of the accuracy,indicating that winter time is the best season for impervious surfaces estimation with optical satellite images in subtropical monsoon regions.