Presentation attack detection based on two-stream vision transformers with self-attention fusion

Aiming at the performance degradation of the existing presentation attack detection methods due to the illumination variation, a two-stream vision transformers framework (TSViT) based on transfer learning in two complementary spaces is proposed in this paper. The face images of RGB color space and multi-scale retinex with color restoration (MSRCR) space are fed to TSViT to learn the distinguishing features of presentation attack detection. To effectively fuse features from two sources (RGB color space images and MSRCR images), a feature fusion method based on self-attention is built, which can effectively capture the complementarity of two features. Experiments and analysis on Oulu-NPU, CASIA-MFSD, and Replay-Attack databases show that it outperforms most existing methods in intra-database testing and achieves good generalization performance in cross-database testing.     

基于信息熵抑制的大数据特征隐匿性加密仿真

针对传统大数据特征加密方法中大数据精度较差、加密耗时较长的问题,提出基于信息熵抑制的大数据特征隐匿性加密方法。分析信息熵抑制相关理论,采用信息熵映射函数对大数据分类,将信息熵抑制过程转化为计算2个文件相似性的过程,并根据余弦相似度公式以及Hamming距离值计算数据相似度,完成数据消冗。在完成数据消冗的基础上,分析分组密码方法和ECC加密方法,结合两种方法得到大数据特征隐匿性加密处理计算公式,实现基于信息熵抑制的大数据特征隐匿性加密。实验研究结果表明,所提方法能够有效去除冗余数据,提升大数据精度,加快数据加密的处理速度,高效完成大数据加密过程。     

A deep neural network based classifier for brain tumor diagnosis

Classification process plays a key role in diagnosing brain tumors. Earlier research works are intended for identifying brain tumors using different classification techniques. However, the False Alarm Rates (FARs) of existing classification techniques are high. To improve the early-stage brain tumor diagnosis via classification the Weighted Correlation Feature Selection Based Iterative Bayesian Multivariate Deep Neural Learning (WCFS-IBMDNL) technique is proposed in this work. The WCFS-IBMDNL algorithm considers medical dataset for classifying the brain tumor diagnosis at an early stage. At first, the WCFS-IBMDNL technique performs Weighted Correlation-Based Feature Selection (WC-FS) by selecting subsets of medical features that are relevant for classification of brain tumors. After completing the feature selection process, the WCFS-IBMDNL technique uses Iterative Bayesian Multivariate Deep Neural Network (IBMDNN) classifier for reducing the misclassification error rate of brain tumor identification. The WCFS-IBMDNL technique was evaluated in JAVA language using Disease Diagnosis Rate (DDR), Disease Diagnosis Time (DDT), and FAR parameter through the epileptic seizure recognition dataset.     

基于特征选择和深度信念网络的文本情感分类算法

由于人类语言的复杂性，文本情感分类算法大多都存在因为冗余而造成的词汇量过大的问题。深度信念网络（DBN）通过学习输入语料中的有用信息以及它的几个隐藏层来解决这个问题。然而对于大型应用程序来说，DBN是一个耗时且计算代价昂贵的算法。针对这个问题，提出了一种半监督的情感分类算法，即基于特征选择和深度信念网络的文本情感分类算法（FSDBN）。首先使用特征选择方法（文档频率（DF）、信息增益（IG）、卡方统计（CHI）、互信息（MI））过滤掉一些不相关的特征从而使词汇表的复杂性降低；然后将特征选择的结果输入到DBN中，使得DBN的学习阶段更加高效。将所提算法应用到中文以及维吾尔语中，实验结果表明在酒店评论数据集上，FSDBN在准确率方面比DBN提高了1.6%，在训练时间上比DBN缩短一半。     

Parameter identification of proton exchange membrane fuel cell via Levenberg-Marquardt backpropagation algorithm

It is essential to develop an accurate model of proton exchange membrane fuel cell (PEMFC) for a reliable operation and analysis, in which unknown parameters usually need to be determined. The inherent nonlinear, strong coupling, and diversification of PEMFC model seriously hinder traditional methods to identify the parameters. For the sake of overcoming these thorny obstacles, Levenberg-Marquardt backpropagation (LMBP) algorithm based on artificial neural networks (ANNs) is proposed for PEMFC parameter identification. Furthermore, the performance of LMBP is thoroughly evaluated and compared with four typical meta-heuristic algorithms under three cases. Simulation results indicate that LMBP performs a higher accuracy and faster speed for parameter identification. In particular, accuracy and convergence speed can achieve as much as 99.8% and 95.9% growth via LMBP, respectively.     

Tuning of Active Disturbance Rejection Control with application to power plant furnace regulation

Active Disturbance Rejection Control (ADRC) is emerging as a promising solution in dealing with the unmeasurable disturbances and unknown uncertainties, which are treated in a lumped manner and augmented as an extended state variable. Subsequently, an extended state observer (ESO) is designed to estimate and cancel the combined uncertain term in real time, modifying the uncertain plant to behave like a nominal model consisting of integrators. In the original ADRC formulation, the plant model is assumed to be of delay-free and its order is assumed to be equal to that of the real plant. However, a low-order ADRC is preferred and received a wide acceptance in practice because of its simplicity. Currently, the feasibility of such practice is not clearly revealed as well as its potential dangers. To this end, this paper analyzes the control mechanism from the perspective of the modified plant, which, in turn, would give guidance to parameter tuning. The effect of each parameter on the compensation efficiency and stability conditions of the modified plant is analyzed, based on which a complete tuning procedure for ADRC is developed where the initial settings is derived from the existing PI controller parameters. Finally, the proposed tuning method is experimentally used for a furnace pressure regulation of a 1000MW power plant, validating the feasibility of the low-order ADRC, even in the absence of both dynamic model and the information on the model order.     

Facial expression recognition of intercepted video sequences based on feature point movement trend and feature block texture variation

Facial Expression Recognition (FER) is an important subject of human–computer interaction and has long been a research area of great interest. Accurate Facial Expression Sequence Interception (FESI) and discriminative expression feature extraction are two enormous challenges for the video-based FER. This paper proposes a framework of FER for the intercepted video sequences by using feature point movement trend and feature block texture variation. Firstly, the feature points are marked by Active Appearance Model (AAM) and the most representative 24 of them are selected. Secondly, facial expression sequence is intercepted from the face video by determining two key frames whose emotional intensities are minimum and maximum, respectively. Thirdly, the trend curve which represents the Euclidean distance variations between any two selected feature points is fitted, and the slopes of specific points on the trend curve are calculated. Finally, combining Slope Set which is composed by the calculated slopes with the proposed Feature Block Texture Difference (FBTD) which refers to the texture variation of facial patch, the final expressional feature are formed and inputted to One-dimensional Convolution Neural Network (1DCNN) for FER. Five experiments are conducted in this research, and three average FER rates 95.2%, 96.5%, and 97% for Beihang University (BHU) facial expression database, MMI facial expression database, and the combination of two databases, respectively, have shown the significant advantages of the proposed method over the existing ones.