Multi-Label Learning Based on Transfer Learning and Label Correlation

In recent years,multi-label learning has received a lot of attention.However,most of the existing methods only consider global label correlation or local label correlation.In fact,on the one hand,both global and local label correlations can appear in real-world situation at same time.On the other hand,we should not be limited to pairwise labels while ignoring the high-order label correlation.In this paper,we propose a novel and effective method called GLLCBN for multi-label learning.Firstly,we obtain the global label correlation by exploiting label semantic similarity.Then,we analyze the pairwise labels in the label space of the data set to acquire the local correlation.Next,we build the original version of the label dependency model by global and local label correlations.After that,we use graph theory,probability theory and Bayesian networks to eliminate redundant dependency structure in the initial version model,so as to get the optimal label dependent model.Finally,we obtain the feature extraction model by adjusting the Inception V3 model of convolution neural network and combine it with the GLLCBN model to achieve the multi-label learning.The experimental results show that our proposed model has better performance than other multi-label learning methods in performance evaluating.

Drainage Network and Lineament Analysis:An Approach for Potwar Plateau(Northern Pakistan)

Drainage responds rapidly to tectonic changes and thus it is a potential parameter for teetonogeomorphological analysis. Drainage network of Potwar is a good geological record of movement, displacements, regional uplifts and erosion of the tectonic units. This study focuses on utilizing drainage network extracted from Shuttle Radar Digital Elevation Data （SRTM-DEM） in order to constrain the structure of the Potwar Plateau. SWAN syncline divides Potwar into northern Potwar deformed zone （NPDZ） and southern Potwar platform zone （SPPZ）. We extracted the drainage network from DEM and analyzed 112 streams using stream power law. Spatial distribution of concavity and steepness indices were used to prepare uplift rate map for the area. DEM was further utilized to extract lineaments to study the mutual relationship between lineaments and drainage patterns. We compared the local correlation between the extracted lineaments and drainage network of the area that gives us quantitative information and shows promising prospects. The streams in the NPDZ indicate high steepness values as compared to the streams in the SPPZ. The spatial distribution of geomorphic parameters distinctive deformation and uplift rates suggest the among eastern, central and western parts. The local correlation between drainage network and lineaments from DEM is strongly positive in the area within I km of radius.

RESEARCH ON THE LOCAL CORRECTION MODEL OF ATMOSPHERIC DRY DELAY IN GPS REMOTE SENSING WATER VAPOR

The precision of atmospheric dry delay model is closely correlated with the accuracy of GPS water vapor in the process of GPS (Global Position System) remote sensing. Radiosonde data (from 1996 to 2001) at Qingyuan are used to calculate the exact values of the atmospheric dry delay. Base on these calculations and the surface meteorological parameters, the local year and month correction models of dry delay at the zenith angle of 0° are established by statistical methods. The analysis result shows that the local model works better and is slight more sensitive to altitude angle than universal models and that it is not necessary to build models for each month due to the slight difference between year model and month model. Furthermore, when the altitude angle is less than 75°, the difference between curve path and straight path increases rapidly with altitude angle’s decrease.

PRODUCT IMAGE RETRIEVAL BASED ON CO-FEATURES OF THE OBJECT

In this paper, we propose a product image retrieval method based on the object contour corners, image texture and color. The product image mainly highlights the object and its background is very simple. According to these characteristics, we represent the object using its contour, and detect the corners of contour to reduce the number of pixels. Every corner is described using its approximate curvature based on distance. In addition, the Block Difference of Inverse Probabilities (BDIP) and Block Variation of Local Correlation (BVLC) texture features and color moment are extracted from image's HIS color space. Finally, dynamic time warping method is used to match features with different length. In order to demonstrate the effect of the proposed method, we carry out experiments in Mi-crosoft product image database, and compare it with other feature descriptors. The retrieval precision and recall curves show that our method is feasible.

Meso-mechanical Interfacial Behavior of Elbow Steel Fiber Reinforced Concrete

The strain distributions near the interface when the elbow steel fiber is pulled out from the half-mould concrete matrix are directly measured using a combined method of single fiber pull-out test and digital image correlation. Meanwhile, the real-time processes of the bonding, debonding and sliding at the interface are observed. The micro-mechanism of the strain localization in the failure process of interface when debonding occurs and the strengthening mechanism at the imbedded fiber are discussed. The experimental results show that the meso-scale strain localization gives rise to the localization of shear damage near the fiber interface. This strain localization characterized by the debonding process near the interface occurs, develops and moves gradually at an apparently regular interval. At the elbow part of the imbedded fiber, the peak value of the shearing stress occurs. But the primary debonding does not occur at this place because the strength of the shear damage is increased at the local area of the elbow part in the concrete, displaying an apparent reinforced effect at the end of the fiber.

Consideration of the Local Correlation of Learning Behaviors to Predict Dropouts from MOOCs

Recently, Massive Open Online Courses(MOOCs) have become a major online learning methodology for millions of people worldwide. However, the dropout rates from several current MOOCs are high. Usually, dropout prediction aims to predict whether a learner will exhibit learning behaviors during several consecutive days in the future. Therefore, the information related to the learning behaviors of a learner in several consecutive days should be considered. After in-depth analysis of the learning behavior patterns of the MOOC learners, this study reports that learners often exhibit similar learning behaviors on several consecutive days, i.e., the learning status of a learner for the subsequent day is likely to be similar to that for the previous day. Based on this characteristic of MOOC learning,this study proposes a new simple feature matrix for keeping information related to the local correlation of learning behaviors and a new Convolutional Neural Network(CNN) model for predicting the dropout. Extensive experimental validations illustrate that the local correlation of learning behaviors should not be neglected. The proposed CNN model considers this characteristic and improves the dropout prediction accuracy. Furthermore, the proposed model can be used to predict dropout temporally and early when sufficient data are collected.

Detection of Geochemical Element Assemblage Anomalies Using a Local Correlation Approach

As direct prospecting data,geochemical data play an important role in modelling prospect potential.Geochemical element assemblage anomalies are usually reflected by the correlation between elements.Correlation coefficients are computed from the values of two elements,which reflect only the correlation at a global level.Thus,the spatial details of the correlation structure are ignored.In fact,an element combination anomaly often exists in geological backgrounds,such as on a fault zone or within a lithological unit.This anomaly may cause some combination of anomalies that are submerged inside the overall area and thus cannot be effectively extracted.To address this problem,we propose a local correlation coefficient based on spatial neighbourhoods to reflect the global distribution of elements.In this method,the sampling area is first divided into a set of uniform grid cells.A moving window with a size of 3×3 is defined with an integer of 3 to represent the sampling unit.The local correlation in each unit is expressed by the Pearson correlation coefficient.The whole area is scanned by the moving window,which produces a correlation coefficient matrix,and the result is portrayed with a thermal diagram.The local correlation approach was tested on two selected geochemical soil survey sites in Xiao Mountain,Henan Province.The results show that the areas of high correlation are mainly distributed in the fault zone or the known mineral spots.Therefore,the local correlation method is effective in extracting geochemical element combination anomalies.

A New UWB Receiver in the Indoor Multipath Environment

In the literatures about Ultra Wide Band （UWB） to date, the receiver structure is mainly based on Rake receiver. But due to the wave distortion caused by overlapped between the received and the sent pulses, a lot of energy in demodulator will be lost. In this paper, a new receiver is developed by adopting maximum likelihood algorithm, in which RAKE structure is not needed and can also be implemented easily. The simulation showed that this method has BER advantage over the traditional RAKE receiver with maximal ratio combining at high SNR, and over the autocorrelation receiver as well.

Study of closed orbit response to magnet vibrations at the SSRF storage ring

This paper presents the analytical and simulation responses of the closed orbit distortion in the SSRF storage ring to random and plane wave like magnet vibrations respectively. It is shown that the use of girder is very beneficial in the view of suppressing this response function. Effect of the independently supported gradient bending magnets to the closed orbit response is given. An analytic formula is written to give a rough estimate of the closed orbit distortion due to ground motion, taking into account the closed orbit response function and girder transfer function. As an example, the result of SSRF case is given.

KDLPCCA-Based Projection for Feature Extraction in SSVEP-Based Brain-Computer Interfaces

An electroencephalogram(EEG)signal projection using kernel discriminative locality preserving canonical correlation analysis(KDLPCCA)-based correlation with steady-state visual evoked potential(SSVEP)templates for frequency recognition is presented in this paper.With KDLPCCA,not only a non-linear correlation but also local properties and discriminative information of each class sample are considered to extract temporal and frequency features of SSVEP signals.The new projected EEG features are classified with classical machine learning algorithms,namely,K-nearest neighbors(KNNs),naive Bayes,and random forest classifiers.To demonstrate the effectiveness of the proposed method,16-channel SSVEP data corresponding to 4 frequencies collected from 5 subjects were used to evaluate the performance.Compared with the state of the art canonical correlation analysis(CCA),experimental results show significant improvements in classification accuracy and information transfer rate(ITR),achieving 100%and 240 bits/min with 0.5 s sample block.The superior performance demonstrates that this method holds the promising potential to achieve satisfactory performance for high-accuracy SSVEP-based brain-computer interfaces.