Local Preserving Graphs Using Intra-Class Competitive Representation for Dimensionality Reduction of Hyperspectral Image

As a key technique in hyperspectral image pre-processing,dimensionality reduction has received a lot of attention.However,most of the graph-based dimensionality reduction methods only consider a single structure in the data and ignore the interfusion of multiple structures.In this paper,we propose two methods for combining intra-class competition for locally preserved graphs by constructing a new dictionary containing neighbourhood information.These two methods explore local information into the collaborative graph through competing constraints,thus effectively improving the overcrowded distribution of intra-class coefficients in the collaborative graph and enhancing the discriminative power of the algorithm.By classifying four benchmark hyperspectral data,the proposed methods are proved to be superior to several advanced algorithms,even under small-sample-size conditions.

Learning Noise-Assisted Robust Image Features for Fine-Grained Image Retrieval

Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fine-grained features by training deep models such that similar images are clustered,and dissimilar images are separated in the low embedding space.Previous works primarily focused on defining local structure loss functions like triplet loss,pairwise loss,etc.However,training via these approaches takes a long training time,and they have poor accuracy.Additionally,representations learned through it tend to tighten up in the embedded space and lose generalizability to unseen classes.This paper proposes a noise-assisted representation learning method for fine-grained image retrieval to mitigate these issues.In the proposed work,class manifold learning is performed in which positive pairs are created with noise insertion operation instead of tightening class clusters.And other instances are treated as negatives within the same cluster.Then a loss function is defined to penalize when the distance between instances of the same class becomes too small relative to the noise pair in that class in embedded space.The proposed approach is validated on CARS-196 and CUB-200 datasets and achieved better retrieval results(85.38%recall@1 for CARS-196%and 70.13%recall@1 for CUB-200)compared to other existing methods.

Intent Pattern Recognition of Lower-limb Motion Based on Mechanical Sensors

Based on the regularity nature of lower-limb motion,an intent pattern recognition approach for above-knee prosthesis is proposed in this paper. To remedy the defects of recognizer based on electromyogram(EMG), we develop a pure mechanical sensor architecture for intent pattern recognition of lower-limb motion. The sensor system is composed of an accelerometer, a gyroscope mounted on the prosthetic socket, and two pressure sensors mounted under the sole. To compensate the delay in the control of prosthesis, the signals in the stance phase are used to predict the terrain and speed in the swing phase. Specifically, the intent pattern recognizer utilizes intraclass correlation coefficient(ICC) according to the Cartesian product of walking speed and terrain. Moreover, the sensor data are fused via DempsterShafer's theory. And hidden Markov model(HMM) is used to recognize the realtime motion state with the reference of the prior step. The proposed method can infer the prosthesis user's intent of walking on different terrain, which includes level ground,stair ascent, stair descent, up and down ramp. The experiments demonstrate that the intent pattern recognizer is capable of identifying five typical terrain-modes with the rate of 95.8%. The outcome of this investigation is expected to substantially improve the control performance of powered above-knee prosthesis.

On Statistical Measures for Data Quality Evaluation

Most GIS databases contain data errors. The quality of the data sources such as traditional paper maps or more recent remote sensing data determines spatial data quality. In the past several decades, different statistical measures have been developed to evaluate data quality for different types of data, such as nominal categorical data, ordinal categorical data and numerical data. Although these methods were originally proposed for medical research or psychological research, they have been widely used to evaluate spatial data quality. In this paper, we first review statistical methods for evaluating data quality, discuss under what conditions we should use them and how to interpret the results, followed by a brief discussion of statistical software and packages that can be used to compute these data quality measures.

Adaptive inter-intradomain alignment network with class-aware sampling strategy for rolling bearing fault diagnosis

Existing unsupervised domain adaptation approaches primarily focus on reducing the data distribution gap between the source and target domains,often neglecting the influence of class information,leading to inaccurate alignment outcomes.Guided by this observation,this paper proposes an adaptive inter-intra-domain discrepancy method to quantify the intra-class and inter-class discrepancies between the source and target domains.Furthermore,an adaptive factor is introduced to dynamically assess their relative importance.Building upon the proposed adaptive inter-intradomain discrepancy approach,we develop an inter-intradomain alignment network with a class-aware sampling strategy(IDAN-CSS)to distill the feature representations.The classaware sampling strategy,integrated within IDAN-CSS,facilitates more efficient training.Through multiple transfer diagnosis cases,we comprehensively demonstrate the feasibility and effectiveness of the proposed IDAN-CSS model.

Impact of drivers'attributes on children injury severities in traffic crashes

Every year,a substantial number of children sustain injuries and fatalities in motor vehicle crashes in Wyoming.Understanding the factors contributing to child injury is crucial for the development of appropriate mitigation measures that aid in alleviating the severity of such injuries.In this study,a hierarchical Bayesian binary logit regression model was developed to investigate the factors that contribute to children’s injuries resulting from crashes while accounting for possible intra-class correlation effects(those of unobserved factors common to children involved in the same crash).A strong correlation among crashes justified the use of the hierarchical Bayesian logit model.As per the modeling results,the children’s ages,safety restraint types,vehicle types,drivers’ages,alcohol/drug involvement,drivers’seat belt use habits,drivers’actions,manners of collision and environmental conditions contributed to child injury risk.The child’s age was found to be inversely related to the risk of injury.Similarly,among safety restraint types,rear-facing car seats and forward-facing car seats were found to reduce injury likelihoods in crashes.When it comes to the drivers’characteristics,the probability of incurring injuries among the child population increased in the presence of young,unbuckled and impaired drivers.Furthermore,improper driving actions,such as running off the road,raised the risk of incurring injuries to children.The findings of this study may be beneficial to authorities regarding developing and implementing road safety programs aimed at ameliorating child injury concerns.

基于对应分析的冗余模糊C均值聚类算法研究

针对模糊C均值聚类(FCM)算法聚类原型最适合于球状类型簇的特点,提出了基于类间分离度和类内紧缩度加权的冗余聚类中心的FCM算法,即先将大簇或者延伸形状的簇(非凸)采用加权FCM算法分割成多个小类(冗余类),从而规避FCM算法对初始聚类中心敏感的弱点.由于隶属度划分矩阵的元素是每个样本隶属于各冗余类的隶属度值,因此将其作为各冗余类的类特征,通过对应分析得到冗余类的新特征,再次采用加权FCM算法进行冗余类合并,最后达到分类效果.以代表曲线分割和曲面分割分类问题的3个典型数据集为算例,结果表明该方法能够识别不规则的簇,解决了FCM算法对初始聚类中心敏感的缺陷.

面向类内差距表情的深度学习识别

目的为解决真实环境中由类内差距引起的面部表情识别率低及室内外复杂环境对类内差距较大的面部表情识别难度大等问题,提出一种利用生成对抗网络(generative adversarial network,GAN)识别面部表情的方法。方法在GAN生成对抗的思想下,构建一种IC-GAN(intra-class gap GAN)网络结构,使用卷积组建编码器、解码器对自制混合表情图像进行更深层次的特征提取,使用基于动量的Adam(adaptive moment estimation)优化算法进行网络权重更新,重点针对真实环境面部表情识别过程中的类内差距较大的表情进行识别,使其更好地适应类内差异较大的任务。结果基于Pytorch环境,在自制的面部表情数据集上进行训练,在面部表情验证集上进行测试,并与深度置信网络(deep belief network,DBN)和GoogLeNet网络进行对比实验,最终IC-GAN网络的识别结果比DBN网络和GoogLeNet网络分别提高11%和8.3%。结论实验验证了IC-GAN在类内差距较大的面部表情识别中的精度,降低了面部表情在类内差距较大情况下的误识率,提高了系统鲁棒性,为面部表情的生成工作打下了坚实的基础。

Reliability of the measurement of glenoid bone defect in anterior shoulder instability

Background:The size of the glenoid bone defect is an important index in selecting the appropriate treatment for anterior shoulder instability.However,the reliability of glenoid bone defect measurement is controversial.The purpose of the present study was to investigate the reliabilities of measurements of the glenoid bone defect on computed tomography and to explore the predisposing factors leading to inconsistency of these measurements.Methods:The study population comprised 69 consecutive patients who underwent surgery for recurrent anterior shoulder dislocation in Peking University Fourth School of Clinical Medicine from March 2016 to January 2017.The glenoid bone defect was measured by three surgeons on‘self-confirmed’and‘designated’3-D en-face views,and repeated after an interval of 3 months.Measurements included the ratio of the defect area to the best-fit circle area,and the ratio of the defect width to the diameter of the best-fit circle.The inter-and intra-observer reliabilities of the measurements were evaluated using intraclass correlation coefficients(ICCs).The maximum absolute inter-and intra-observer differences and the cumulative percentages of cases with inter-and intraobserver differences greater than these respective levels were calculated.Results:Almost all linear defect values were bigger than the areal defect values.The inter-observer ICCs for the areal defect were 0.557 and 0.513 in the‘self-confirmed’group and 0.549 and 0.431 in the‘designated’group.The inter-observer reliabilities for the linear defect were moderate or fair in the‘self-confirmed’group(ICC=0.446,0.374)and‘designated’group(ICC=0.402,0.327).The ICCs for intra-observer measurements were higher than those for inter-observer measurements.The respective maximum interand intra-observer absolute differences were 13.9%and 13.2%in the‘self-confirmed’group,and 15.8%and 9.8%in the‘designated’group.Conclusions:The areal measurement of the glenoid bone defect is more reliable than the linear measurement.The reliability of the glenoid defect areal measurement is moderate or worse,suggesting that a more accurate and objective measurement method is needed in both en-face view and best-fit circle determination.Subjective factors affecting the glenoid bone loss measurement should be minimized.