深度学习在机械设备诊断中的应用

传统的机械设备状态监测是根据经验通过提取现场采集的振动信号特征值构建特征空间,采用多种方法对特征值进行聚类、分类,从而实现对设备状态的分类。但这种方法严重依赖于专家经验,并且效果受到信号噪声等众多因素的影响。分别在经典一维和二维卷积神经网络的的基础上,提出两种机械设备智能故障诊断方法,并通过凯斯西储大学轴承数据中心发布的数据集比较两种模型的性能,实验结果表明,基于一维卷积神经网络的智能诊断方法更适用于一维振动信号。将基于一维卷积神经网络的智能诊断方法应用于石化厂的机泵设备,证明其能实现特征自适应提取,可取得较好诊断效果。     

基于GST-ECNN的运动想象脑电信号识别方法

在对脑电信号的解码研究中,存在着现有时频分析方法对高频信号处理能力有限,多通道信号信息冗余,常用卷积神经网络分类器ReLU激活函数受学习速率的影响较大,对不同层采用相同的正则化很难获得满意结果等问题。为此,提出了一种基于广义S变换特征提取和增强卷积神经网络分类相结合的方法,同时提出一种结合Relief算法和向前选择搜索策略的包裹式方法进行通道选择。结果表明,提出的方法利用较少的信号通道,具有更强的特征提取和分类的能力,在第Ⅳ届BCI的数据集I上取得最高98.44±1.5%的分类准确率,高于其他现有算法。该方法良好的分类性能不仅减少了计算消耗,也有效提高了分类准确率,对脑电信号特征提取和分类具有一定的参考意义。     

IMAGE COMPRESSION SCHEME WITH EMBEDDED MULTILEVEL BLOCK TRUNCATION CODING BASED ON HUMAN VISUAL EFFECT

ABSTRACT

In this paper, we first propose a new embedded multilevel block truncation coding (BTC) technique. Unlike Differential pulse code modulation (DPCM), Vector quantization (VQ), and general multilevel BTC algorithms which determine the image quality at a time, the embedded multilevel BTC improves the image quality largely and progressively until obtaining an image with excellent quality. In order to reduce the bit rate efficiently, we propose a perception model and utilize it to develop a pruning algorithm. The pruning algorithm removes the useless information, which the human eyes are not sensitive, generated by the embedded multilevel BTC. The simulation results indicate that the bit rate with the proposed method is much less than that with the DPCM and general multilevel BTC under the same objective criterion, PSNR, or subjective criterion. This paper also shows that the computation complexity of the proposed method is much less than that with VQ under the same high quality reconstructed image.     

基于单幅户外彩色图像实现天气晴阴分类

提出了一种新颖的利用随机森林对单幅户外彩色图像进行晴阴分类的方法。首先定义了天空频率直方图特征和阴影能量特征,给出了其计算方法,并将透射率特征引入天气分类中,将这3种特征与已有特征共同组合构成候选天气特征集;其次定义了Fisher-Random Forest特征重要性计算方法对天气特征进行选择;最后将选择后的天气特征以向量形式输入到随机森林分类器实现对户外图像的晴阴分类。实验结果表明:与其他方法相比,该方法具有较高的准确性及较好的通用性。     

专业显示器性能测试方法研究

对2种应用广泛的专业显示器的时间稳定性、空间均匀性、色域、色品恒定性、通道独立性及色温6个方面的性能进行了测试,并比较了这2台显示器的显示性能的优劣。测试结果表明:在时间稳定性、色品恒定性及通道独立性方面,专业显示器B略优于专业显示器A;在空间均匀性方面,专业显示器A较好;而在其他特性方面,两者相差不大。总体来说,2种专业显示器的性能均比较稳定。     

Multiclass Stomach Diseases Classification Using Deep Learning Features Optimization

In the area of medical image processing, stomach cancer is one of the most important cancers which need to be diagnose at the early stage. In this paper, an optimized deep learning method is presented for multiple stomach disease classification. The proposed method work in few important steps—preprocessing using the fusion of filtering images along with Ant Colony Optimization (ACO), deep transfer learning-based features extraction, optimization of deep extracted features using nature-inspired algorithms, and finally fusion of optimal vectors and classification using Multi-Layered Perceptron Neural Network (MLNN). In the feature extraction step, pre-trained Inception V3 is utilized and retrained on selected stomach infection classes using the deep transfer learning step. Later on, the activation function is applied to Global Average Pool (GAP) for feature extraction. However, the extracted features are optimized through two different nature-inspired algorithms—Particle Swarm Optimization (PSO) with dynamic fitness function and Crow Search Algorithm (CSA). Hence, both methods’ output is fused by a maximal value approach and classified the fused feature vector by MLNN. Two datasets are used to evaluate the proposed method—CUI WahStomach Diseases and Combined dataset and achieved an average accuracy of 99.5%. The comparison with existing techniques, it is shown that the proposed method shows significant performance.     

Semi-GSGCN: Social Robot Detection Research with Graph Neural Network

Malicious social robots are the disseminators of malicious information on social networks, which seriously affect information security and network environments. Efficient and reliable classification of social robots is crucial for detecting information manipulation in social networks. Supervised classification based on manual feature extraction has been widely used in social robot detection. However, these methods not only involve the privacy of users but also ignore hidden feature information, especially the graph feature, and the label utilization rate of semi-supervised algorithms is low. Aiming at the problems of shallow feature extraction and low label utilization rate in existing social network robot detection methods, in this paper a robot detection scheme based on weighted network topology is proposed, which introduces an improved network representation learning algorithm to extract the local structure features of the network, and combined with the graph convolution network (GCN) algorithm based on the graph filter, to obtain the global structure features of the network. An end-to-end semi-supervised combination model (Semi-GSGCN) is established to detect malicious social robots. Experiments on a social network dataset (cresci-rtbust-2019) show that the proposed method has high versatility and effectiveness in detecting social robots. In addition, this method has a stronger insight into robots in social networks than other methods.     

A Framework of Deep Optimal Features Selection for Apple Leaf Diseases Recognition

Identifying fruit disease manually is time-consuming, expert-required, and expensive; thus, a computer-based automated system is widely required. Fruit diseases affect not only the quality but also the quantity. As a result, it is possible to detect the disease early on and cure the fruits using computer-based techniques. However, computer-based methods face several challenges, including low contrast, a lack of dataset for training a model, and inappropriate feature extraction for final classification. In this paper, we proposed an automated framework for detecting apple fruit leaf diseases using CNN and a hybrid optimization algorithm. Data augmentation is performed initially to balance the selected apple dataset. After that, two pre-trained deep models are fine-tuning and trained using transfer learning. Then, a fusion technique is proposed named Parallel Correlation Threshold (PCT). The fused feature vector is optimized in the next step using a hybrid optimization algorithm. The selected features are finally classified using machine learning algorithms. Four different experiments have been carried out on the augmented Plant Village dataset and yielded the best accuracy of 99.8%. The accuracy of the proposed framework is also compared to that of several neural nets, and it outperforms them all.     

Skin Lesion Segmentation and Classification Using Conventional and Deep Learning Based Framework

Background: In medical image analysis, the diagnosis of skin lesions remains a challenging task. Skin lesion is a common type of skin cancer that exists worldwide. Dermoscopy is one of the latest technologies used for the diagnosis of skin cancer. Challenges: Many computerized methods have been introduced in the literature to classify skin cancers. However, challenges remain such as imbalanced datasets, low contrast lesions, and the extraction of irrelevant or redundant features. Proposed Work: In this study, a new technique is proposed based on the conventional and deep learning framework. The proposed framework consists of two major tasks: lesion segmentation and classification. In the lesion segmentation task, contrast is initially improved by the fusion of two filtering techniques and then performed a color transformation to color lesion area color discrimination. Subsequently, the best channel is selected and the lesion map is computed, which is further converted into a binary form using a thresholding function. In the lesion classification task, two pre-trained CNN models were modified and trained using transfer learning. Deep features were extracted from both models and fused using canonical correlation analysis. During the fusion process, a few redundant features were also added, lowering classification accuracy. A new technique called maximum entropy score-based selection (MESbS) is proposed as a solution to this issue. The features selected through this approach are fed into a cubic support vector machine (C-SVM) for the final classification. Results: The experimental process was conducted on two datasets: ISIC 2017 and HAM10000. The ISIC 2017 dataset was used for the lesion segmentation task, whereas the HAM10000 dataset was used for the classification task. The achieved accuracy for both datasets was 95.6% and 96.7%, respectively, which was higher than the existing techniques.     

基于流形正则化的批量分层编码极限学习机

针对极限学习机在处理高维数据时存在内存能耗大、分类准确率低、泛化性差等问题,提出了一种批量分层编码极限学习机算法。首先通过对数据集分批处理,以减小数据维度,降低输入复杂性;然后采用多层自动编码器结构对各批次数据进行无监督编码,以实现深层特征提取;最后利用流形正则化思想构建含有继承因子的流形分类器,以保持数据的完整性,提高算法的泛化性能。实验结果表明,该方法实现简单,在NORB,MNIST和USPS数据集上的分类准确率分别可以达到92.16%、99.35%和98.86%,与其它极限学习机算法对比,在降低计算复杂度和减少CPU内存消耗上具有较明显的优势。     

Bridging semantic gap between high-level and low-level features in content-based video retrieval using multi-stage ESN–SVM classifier

Content-based video retrieval system aims at assisting a user to retrieve targeted video sequence in a large database. Most of the search engines use textual annotations to retrieve videos. These types of engines offer a low-level abstraction while the user seeks high-level semantics. Bridging this type of semantic gap in video retrieval remains an important challenge. In this paper, colour, texture and shapes are considered to be low-level features and motion is a high-level feature. Colour histograms convert the RGB colour space into YcbCr and extract hue and saturation values from frames. After colour extraction, filter mask is applied and gradient value is computed. Gradient and threshold values are compared to draw the edge map. Edges are smoothed for sharpening to remove the unnecessary connected components. These diverse shapes are then extracted and stored in shape feature vectors. Finally, an SVM classifier is used for classification of low-level features. For high-level features, depth images are extracted for motion feature identification and classification is done via echo state neural networks (ESN). ESN are a supervised learning technique and follow the principle of recurrent neural networks. ESN are well known for time series classification and also proved their effective performance in gesture detection. By combining the existing algorithms, a high-performance multimedia event detection system is constructed. The effectiveness and efficiency of proposed event detection mechanism is validated using MSR 3D action pair dataset. Experimental results show that the detection accuracy of proposed combination is better than those of other algorithms     

基于流形学习和K-最近邻分类器的旋转机械故障诊断方法

针对旋转机械故障诊断需人工干预、精度低、故障样本难以获取等问题,提出基于流形学习和K-最近邻分类器（KNNC）的故障诊断模型。提取振动信号多域信息熵以全面反映设备运行状态并构造高维特征集;利用正交邻域保持嵌入(ONPE)非线性流形学习算法的二次特征提取特性进行维数约简使特征具有更好的聚类特性;基于改进的更适用于小样本分类KNNC进行模式识别,用轴承故障诊断案例证明该模型的有效性。     

基于k-Means算法的彩色QR码识别

为了降低彩色QR码解码过程中出现的混叠效应,提高彩色QR码解码的正确率,提出一种基于HSV颜色模型的k-Means聚类算法。为了选择适合彩色QR码的颜色空间模型,通过实验验证了在RGB,Lab,HSV 3个颜色模型下k-Means聚类算法的效果。在HSV颜色模型下,根据等欧氏距离的原则建立彩色编码模块的配色模型,最大程度地减小解码中颜色的混叠效应。彩色QR码解码预处理阶段,利用基于HSV颜色模型的光线补偿的k-Means聚类算法对彩色编码模块进行颜色分离,以提高解码的精度。研究结果表明:在HSV颜色模型下,k-Means聚类效果最好,图像区域分类效果最清晰;所建立的配色模型可以最优地为彩色编码模块配色;基于HSV颜色模型的光线补偿的k-Means聚类算法可以提高彩色QR码解码的正确率。因此,建立合理的配色模型进行彩色编码模块的颜色设置,同时采用基于HSV颜色模型的光线补偿的k-Means聚类算法进行颜色分割,可以大幅度地降低彩色QR码编码模块之间的混叠效应,从而显著提高彩色QR码解码的正确率。     

Colour image coding scheme using absolute moment block truncation coding and block prediction technique

Abstract

A predictive colour image compression scheme based on absolute moment block truncation coding is proposed. In this scheme, the high correlations among neighbouring image blocks are exploited by using the similar block prediction technique. In addition, the bit plane omission technique and the coding of quantisation levels are used to cut down the storage cost of smooth blocks and complex blocks respectively. According to the experimental results, the proposed scheme provides better performance than the comparative schemes based on block truncation coding. It provides better image qualities of compressed images at low bit rates. Meanwhile, it consumes very little computational cost. In other words, the proposed scheme is quite suitable for real time multimedia applications.     

Ozone Depletion Identification in Stratosphere Through Faster Region-Based Convolutional Neural Network

The concept of classification through deep learning is to build a model that skillfully separates closely-related images dataset into different classes because of diminutive but continuous variations that took place in physical systems over time and effect substantially. This study has made ozone depletion identification through classification using Faster Region-Based Convolutional Neural Network (F-RCNN). The main advantage of F-RCNN is to accumulate the bounding boxes on images to differentiate the depleted and non-depleted regions. Furthermore, image classification’s primary goal is to accurately predict each minutely varied case’s targeted classes in the dataset based on ozone saturation. The permanent changes in climate are of serious concern. The leading causes beyond these destructive variations are ozone layer depletion, greenhouse gas release, deforestation, pollution, water resources contamination, and UV radiation. This research focuses on the prediction by identifying the ozone layer depletion because it causes many health issues, e.g., skin cancer, damage to marine life, crops damage, and impacts on living being’s immune systems. We have tried to classify the ozone images dataset into two major classes, depleted and non-depleted regions, to extract the required persuading features through F-RCNN. Furthermore, CNN has been used for feature extraction in the existing literature, and those extricated diverse RoIs are passed on to the CNN for grouping purposes. It is difficult to manage and differentiate those RoIs after grouping that negatively affects the gathered results. The classification outcomes through F-RCNN approach are proficient and demonstrate that general accuracy lies between 91% to 93% in identifying climate variation through ozone concentration classification, whether the region in the image under consideration is depleted or non-depleted. Our proposed model presented 93% accuracy, and it outperforms the prevailing techniques.     

基于颜色信息与空间特征的自适应商标检索算法

目的为了增强商标检索技术对商标特征的描述能力,改善其在外来干扰下的检索精度与鲁棒性。方法提出一种基于颜色与空间特征自适应结合的商标检索算法。首先,引入主颜色描述符(DCD),将其作为颜色特征检测器,并在颜色特征提取时嵌入k-均值聚类算子,增强颜色区域,准确提取颜色特征。随后,每个商标被量化为8个显色的最大值,以便提取每个颜色分量中的空间分布信息。然后,通过利用不同的权重来平衡颜色与空间特征的重要性,定义一种基于模糊直方图分析技术,计算每个商标自适应系数,以准确描述彩色商标的图像特征。最后,通过Euclidean距离进行相似度量,输出检索到的商标。结果实验结果表明,与当前商标检索方法相比,所提算法具有更高的检索精度与鲁棒性,呈现出更理想的P-R曲线,在召回率为0.7时,其检索准确率仍可达到90%。结论文中检索方法具有较高的检索精度,在包装商标检测、商标版权保护等领域中具有良好的应用价值。     

Efficient heart disease prediction‐based on optimal feature selection using DFCSS and classification by improved Elman‐SFO

Prediction of cardiovascular disease (CVD) is a critical challenge in the area of clinical data analysis. In this study, an efficient heart disease prediction is developed based on optimal feature selection. Initially, the data pre‐processing process is performed using data cleaning, data transformation, missing values imputation, and data normalisation. Then the decision function‐based chaotic salp swarm (DFCSS) algorithm is used to select the optimal features in the feature selection process. Then the chosen attributes are given to the improved Elman neural network (IENN) for data classification. Here, the sailfish optimisation (SFO) algorithm is used to compute the optimal weight value of IENN. The combination of DFCSS–IENN‐based SFO (IESFO) algorithm effectively predicts heart disease. The proposed (DFCSS–IESFO) approach is implemented in the Python environment using two different datasets such as the University of California Irvine (UCI) Cleveland heart disease dataset and CVD dataset. The simulation results proved that the proposed scheme achieved a high‐classification accuracy of 98.7% for the CVD dataset and 98% for the UCI dataset compared to other classifiers, such as support vector machine, K‐nearest neighbour, Elman neural network, Gaussian Naive Bayes, logistic regression, random forest, and decision tree.Inspec keywords: cardiovascular system, medical diagnostic computing, feature extraction, regression analysis, data mining, learning (artificial intelligence), Bayes methods, neural nets, support vector machines, diseases, pattern classification, data handling, decision trees, cardiology, data analysis, feature selectionOther keywords: efficient heart disease prediction‐based, optimal feature selection, improved Elman‐SFO, cardiovascular disease, clinical data analysis, data pre‐processing process, data cleaning, data transformation, values imputation, data normalisation, decision function‐based chaotic salp swarm algorithm, optimal features, feature selection process, improved Elman neural network, data classification, sailfish optimisation algorithm, optimal weight value, DFCSS–IENN‐based SFO algorithm, DFCSS–IESFO, California Irvine Cleveland heart disease dataset, CVD dataset, high‐classification accuracy     

基于双分支特征提取的轻量级图像分割算法

目的 为了提升彩色图像的分割精度，解决彩色图像分割中存在庞大计算成本和冗余参数的问题，本文提出一种双分支特征提取网络来解决上述问题。方法 双分支特征提取网络主要由语义信息分支和空间细节分支组成。语义信息分支通过在非对称残差模块中设置不同的空洞卷积率来获取输入图像不同尺度的上下文信息。空间细节分支是一个浅层且简单的网络，用于建立每个像素间的局部依赖关系以保留细节。在双分支之后连接一个特征聚合模块来有效地结合这2个分支的输出。结果 在没有任何预训练和后处理的情况下，在单块RTX2080Ti GPU上仅用0.91 M参数在Cityscapes数据集上以97帧/s的速度实现75.1%的分割准确性，在Camvid数据集上以107帧/s的推理速度取得了70.5%的分割效果。结论 通过大量实验证明，本文模型在分割准确性和效率之间取得了较好的平衡。     

A HEVC Video Steganalysis Algorithm Based on PU Partition Modes

Steganalysis is a technique used for detecting the existence of secret information embedded into cover media such as images and videos. Currently, with the higher speed of the Internet, videos have become a kind of main methods for transferring information. The latest video coding standard High Efficiency Video Coding (HEVC) shows better coding performance compared with the H.264/AVC standard published in the previous time. Therefore, since the HEVC was published, HEVC videos have been widely used as carriers of hidden information.
In this paper, a steganalysis algorithm is proposed to detect the latest HEVC video steganography method which is based on the modification of Prediction Units (PU) partition modes. To detect the embedded data, All the PU partition modes are extracted from P pictures, and the probability of each PU partition mode in cover videos and stego videos is adopted as the classification feature. Furthermore, feature optimization is applied, that the 25-dimensional steganalysis feature has been reduced to the 3-dimensional feature. Then the Support Vector Machine (SVM) is used to identify stego videos. It is demonstrated in experimental results that the proposed steganalysis algorithm can effectively detect the stego videos, and much higher classification accuracy has been achieved compared with state-of-the-art work.