改进ADASYN-SDA的入侵检测模型研究

针对传统入侵检测模型在高维数据且数据不均衡环境下检测性能较差的问题,提出了一种自适应过采样算法（ADASYN）与改进堆叠式降噪自编码器（SDA）结合的入侵检测模型。使用ADASYN算法进行数据过采样处理。使用Adam优化算法,以及Dropout正则化对SDA深度学习模型进行改进,提取出低维数、高鲁棒性的集成特征。在softmax分类器中进行入侵检测识别。实验结果表明,ADASYN-SDA模型相较于SDA、AE-DNN和MSVM模型,在平均准确率、检测率和误判率上均有一定程度的提高。     

基于深度自编码器的单样本人脸识别*

由于每个目标仅有一幅已知样本,无法描述目标的类内变化,诸多人脸识别算法在解决单样本人脸识别问题时识别性能较低.因此文中提出基于深度自编码器的单样本人脸识别算法.算法首先采用所有已知样本训练深度自编码器,得到广义深度自编码器,然后使用每个单样本目标的单个样本微调广义深度自编码器,得到特定类别的深度自编码器.识别时,将识别图像输入每个特定类别的深度自编码器,得到包含与测试图像相同类内变化的该类别的重构图像,使用重构图像训练Softmax回归模型,分类测试图像.在公共测试库上进行测试,并与其它算法在相同环境下进行对比,结果表明文中算法在获得更优识别率的同时,识别一幅图像所需平均时间更少.     

堆栈稀疏自编码器的风力机锥齿轮故障诊断

针对当前齿轮故障诊断存在着准确性不高、主观性强等问题,提出了一种基于堆栈稀疏自编码器(SSAE)和softmax分类器相结合的齿轮故障诊断方法。首先,运用时域分析以及样本熵方法对风力机锥齿轮振动信号进行特征提取,其次,将提取的特征输入到SSAE中进一步学习目标数据的深层本质特征,并进行特征降维,最后使用softmax分类器中进行分类识别。通过实验结果表明,和文中其他浅层学习模型相比,SSAE能够从齿轮振动信号中有效学习到所需的深层本质特征,拥有更高的识别准确率,因而证实了该方法优越性。     

An Overview and Perspectives On Bidirectional Intelligence: Lmser Duality,Double IA Harmony,and Causal Computation

Advances on bidirectional intelligence are overviewed along three threads, with extensions and new perspectives. The first thread is about bidirectional learning architecture, exploring five dualities that enable Lmser six cognitive functions and provide new perspectives on which a lot of extensions and particularlly flexible Lmser are proposed. Interestingly, either or two of these dualities actually takes an important role in recent models such as U-net, ResNet, and DenseNet. The second thread is about bidirectional learning principles unified by best yIng-yAng (IA) harmony in BYY system. After getting insights on deep bidirectional learning from a bird-viewing on existing typical learning principles from one or both of the inward and outward directions, maximum likelihood, variational principle, and several other learning principles are summarised as exemplars of the BYY learning, with new perspectives on advanced topics. The third thread further proceeds to deep bidirectional intelligence, driven by long term dynamics (LTD) for parameter learning and short term dynamics (STD) for image thinking and rational thinking in harmony. Image thinking deals with information flow of continuously valued arrays and especially image sequence, as if thinking was displayed in the real world, exemplified by the flow from inward encoding/cognition to outward reconstruction/transformation performed in Lmser learning and BYY learning. In contrast, rational thinking handles symbolic strings or discretely valued vectors, performing uncertainty reasoning and problem solving. In particular, a general thesis is proposed for bidirectional intelligence, featured by BYY intelligence potential theory (BYY-IPT) and nine essential dualities in architecture, fundamentals, and implementation, respectively. Then, problems of combinatorial solving and uncertainty reasoning are investigated from this BYY IPT perspective. First, variants and extensions are suggested for AlphaGoZero like searching tasks, such as traveling salesman problem (TSP) and attributed graph matching (AGM) that are turned into Go like problems with help of a feature enrichment technique. Second, reasoning activities are summarized under guidance of BYY IPT from the aspects of constraint satisfaction, uncertainty propagation, and path or tree searching. Particularly, causal potential theory is proposed for discovering causal direction, with two roads developed for its implementation.      

Research on image reconstruction algorithms based on autoencoder neural network of Restricted Boltzmann Machine (RBM)

Aiming at the problem of low quality in image reconstruction of traditional image reconstruction algorithm of electromagnetic tomography(EMT), an EMT image reconstruction algorithm based on autoencoder neural network of Restricted Boltzmann Machine (RBM) is proposed. Firstly, the basic principles of EMT system and autoencoder neural network are analyzed. Autoencoder neural network is a deep learning model, which contains two parts: encoder and decoder. The encoding process of the encoder is equivalent to the object field detection process in the EMT system; the decoding process of the decoder is equivalent to the image reconstruction process. On this basis, an autoencoder neural network model is built. In this model, the RBM is used for layer by layer pre-training to obtain the initial weight and offset, and the global weight and offset are adjusted by BP algorithm. The parameter file generated in the trained autoencoder neural network is used to construct a decoder. Finally, the detected voltage value output by the EMT system is input into the decoder network to obtain the reconstructed image of the EMT. Furthermore, data with Gaussian noise and data regarding flow pattern not in training dataset are used to test the generalization ability and practicability of the network, respectively. The experimental results show that the method in this paper is a kind of EMT image reconstruction method with higher accuracy, which also provides a new means for EMT image reconstruction.     

Latent Space Representational Learning of Deep Features for Acute Lymphoblastic Leukemia Diagnosis

Acute Lymphoblastic Leukemia (ALL) is a fatal malignancy that is featured by the abnormal increase of immature lymphocytes in blood or bone marrow. Early prognosis of ALL is indispensable for the effectual remediation of this disease. Initial screening of ALL is conducted through manual examination of stained blood smear microscopic images, a process which is time-consuming and prone to errors. Therefore, many deep learning-based computer-aided diagnosis (CAD) systems have been established to automatically diagnose ALL. This paper proposes a novel hybrid deep learning system for ALL diagnosis in blood smear images. The introduced system integrates the proficiency of autoencoder networks in feature representational learning in latent space with the superior feature extraction capability of standard pretrained convolutional neural networks (CNNs) to identify the existence of ALL in blood smears. An augmented set of deep image features are formed from the features extracted by GoogleNet and Inception-v3 CNNs from a hybrid dataset of microscopic blood smear images. A sparse autoencoder network is designed to create an abstract set of significant latent features from the enlarged image feature set. The latent features are used to perform image classification using Support Vector Machine (SVM) classifier. The obtained results show that the latent features improve the classification performance of the proposed ALL diagnosis system over the original image features. Moreover, the classification performance of the system with various sizes of the latent feature set is evaluated. The retrieved results reveal that the introduced ALL diagnosis system superiorly compete the state of the art.     

基于自编码神经网络的手写体数字识别中 关于特征表达的研究

研究多种改良的自编码神经网络（Autoencoder）,如稀疏（Sparse）、噪声（Denoising）、权值对称（Tied Weight）。 探究这些自编码神经网络的改良在图像特征表达中的原理。将方法应用到手写体数字的识别中,通过设置各种改良自编码神 经网络的参数取值并且对比各种改良自编码神经网络的特征表达效果,证明改良自编神经网络的理论原理。实验证明稀疏和 噪声对于自编码神经网络性能具有较大提升。     

A novel method for aeroengine performance model reconstruction based on CDAE model

Aeroengine is a complex multi-module system. Due to the limitation of sensor cost and sensor installation conditions, it is usually impossible to install a large number of sensors to measure the physical parameters of the aeroengine modules to establish the accurate module characteristic models to achieve the purpose of module performance evaluation. To address this issue, the high-dimensional physical field reconstruction strategy base on limited measurement data is developed, which is of great significance to the modeling of module characteristics. A reconstruction framework of a high-dimensional physical field based on limited measurement data is built. The mapping relationship between limited measurement data and high-dimensional physical field data is established, and the relevant learning strategies based on the deep learning network are designed. To verify the effectiveness of the proposed method, the simulation dataset generated by the multi-component closed-loop simulation system and the aeroengine service dataset are used for experimental verification, and the mean and variance of mean square error are used as evaluation indexes. Experimental results show that the proposed method can obtain high-dimensional physical field distribution based on limited measurement data.