EEG-Based Neonatal Sleep Stage Classification Using Ensemble Learning

Sleep stage classification can provide important information regarding neonatal brain development and maturation. Visual annotation, using polysomnography (PSG), is considered as a gold standard for neonatal sleep stage classification. However, visual annotation is time consuming and needs professional neurologists. For this reason, an internet of things and ensemble-based automatic sleep stage classification has been proposed in this study. 12 EEG features, from 9 bipolar channels, were used to train and test the base classifiers including convolutional neural network, support vector machine, and multilayer perceptron. Bagging and stacking ensembles are then used to combine the outputs for final classification. The proposed algorithm can reach a mean kappa of 0.73 and 0.66 for 2-stage and 3-stage (wake, active sleep, and quiet sleep) classification, respectively. The proposed network works as a semi-real time application because a smoothing filter is used to hold the sleep stage for 3 min. The high-performance parameters and its ability to work in semi real-time makes it a promising candidate for use in hospitalized newborn infants.     

DDoS Attack Detection via Multi-Scale Convolutional Neural Network

Distributed Denial-of-Service (DDoS) has caused great damage to the network in the big data environment. Existing methods are characterized by low computational efficiency, high false alarm rate and high false alarm rate. In this paper, we propose a DDoS attack detection method based on network flow grayscale matrix feature via multiscale convolutional neural network (CNN). According to the different characteristics of the attack flow and the normal flow in the IP protocol, the seven-tuple is defined to describe the network flow characteristics and converted into a grayscale feature by binary. Based on the network flow grayscale matrix feature (GMF), the convolution kernel of different spatial scales is used to improve the accuracy of feature segmentation, global features and local features of the network flow are extracted. A DDoS attack classifier based on multi-scale convolution neural network is constructed. Experiments show that compared with correlation methods, this method can improve the robustness of the classifier, reduce the false alarm rate and the missing alarm rate.     

应用卷积神经网络的锂电池极片涂布缺陷分类

目的 针对锂电池极片涂布缺陷种类多,传统方法分类检测精度不高,以及人工依赖性强等问题,提出一种基于卷积神经网络的锂电池极片涂布缺陷自动分类算法。方法 首先对网络结构以及模型参数进行优化,接着在网络中加入跳跃连接结构,将空洞卷积提取到的多尺度特征与高层特征进行融合以获取更多缺陷特征,并采用LeakyReLU(Leaky Rectified Linear Unit)激活函数保留图像中的负值特征信息,最后通过构建的数据集训练模型,实现锂电池极片涂布缺陷的准确分类。结果 实验结果表明,当前方法识别准确率能够达到99.34%,平均检测时间为51ms。结论 改进后的方法能够准确分类出锂电池极片18种涂布缺陷,满足工业生产中实时分类检测的要求。     

大数据下的深度学习研究

给出了大数据和机器学习的子领域——深度学习的概念,阐述了深度学习对获取大数据中的有价值信息的重要作用。描述了大数据下利用图像处理单元(GPU)进行并行运算的深度学习框架,对其中的大规模卷积神经网络(CNN)、大规模深度置信网络(DBN)和大规模递归神经网络(RNN)进行了重点论述。分析了大数据的容量、多样性、速率特征,介绍了大规模数据、多样性数据、高速率数据下的深度学习方法。展望了大数据背景下深度学习的发展前景,指出在不远的将来,大数据与深度学习融合的技术将会在计算机视觉、机器智能等多个领域获得突破性进展。     

基于均值特征和改进深度神经网络的说话人识别算法

为提高神经网络在说话人识别应用中的识别性能,提出基于高斯增值矩阵特征和改进深度卷积神经网络的说话人识别算法。算法首先通过最大后验概率提取基于梅尔频率倒谱系数（Mel Frequency Cepstrum Coefficient,MFCC）特征的高斯均值矩阵,并对特征进行噪声适应性补偿,以增强信号的帧间关联和说话人特征信息,然后采用改进的深度卷积神经网络进一步对准帧间信息,以提高说话人识别特征对背景噪声的适应性。实验结果表明,相比于高斯混合模型-通用背景模型等识别框架及传统MFCC等特征,该算法可取得更高的识别准确率和最小的识别均方误差。     

基于3D和1D多特征融合的语音情感识别算法

针对语音情感识别任务中特征提取单一、分类准确率低等问题,提出一种3D和1D多特征融合的情感识别方法,对特征提取算法进行改进。在3D网络,综合考虑空间特征学习和时间依赖性构造,利用双线性卷积神经网络（Bilinear Convolutional Neural Network,BCNN）提取空间特征,长短期记忆网络（Short-Term Memory Network,LSTM）和注意力（attention）机制提取显著的时间依赖特征。为降低说话者差异的影响,计算语音的对数梅尔特征（Log-Mel）和一阶差分、二阶差分特征合成3D Log-Mel特征集。在1D网络,利用一维卷积和LSTM的框架。最后3D和1D多特征融合得到判别性强的情感特征,利用softmax函数进行情感分类。在IEMOCAP和EMO-DB数据库上实验,平均识别率分别为61.22%和85.69%,同时与提取单一特征的3D和1D算法相比,多特征融合算法具有更好的识别性能。     

基于颜色空间变换和CNN的自适应去模糊方法

目的研究数字图像中的去模糊问题,从受损的模糊图像中恢复出清晰图像。方法针对现有图像去模糊算法无法保留图像高频信息及容易产生振铃效应等问题,提出一种基于Y通道反卷积和卷积神经网络的两阶段自适应去模糊算法(SDYCNN)。在第1阶段,将数字图像转换至YUV颜色空间,根据图像无参考质量评价分数与模糊核尺寸之间的对应关系,在Y通道内自适应确定模糊核尺寸并进行反卷积增强;第2阶段将第1阶段中的反卷积增强作为预处理方式,通过4层卷积神经网络建立反卷积增强后的图像与清晰图像之间的映射关系,实现图像去模糊。结果轻微模糊图像在第1阶段便能够得到较好的去模糊效果,严重模糊图像经过第1阶段的反卷积增强,也有助于神经网络中特征的快速提取。结论实验结果表明,该算法不仅对于模糊图像具有良好的恢复效果,运算效率也有显著提升。     

A serialized classification method for pulmonary nodules based on lightweight cascaded convolutional neural network-long short-term memory

Computer Assisted Diagnosis (CAD) is an effective method to detect lung cancer from computed tomography (CT) scans. The development of artificial neural network makes CAD more accurate in detecting pathological changes. Due to the complexity of the lung environment, the existing neural network training still requires large datasets, excessive time, and memory space. To meet the challenge, we analysis 3D volumes as serialized 2D slices and present a new neural network structure lightweight convolutional neural network (CNN)-long short-term memory (LSTM) for lung nodule classification. Our network contains two main components: (a) optimized lightweight CNN layers with tiny parameter space for extracting visual features of serialized 2D images, and (b) LSTM network for learning relevant information among 2D images. In all experiments, we compared the training results of several models and our model achieved an accuracy of 91.78% for lung nodule classification with an AUC of 93%. We used fewer samples and memory space to train the model, and we achieved faster convergence. Finally, we analyzed and discussed the feasibility of migrating this framework to mobile devices. The framework can also be applied to cope with the small amount of training data and the development of mobile health device in future.     

A Rub-Impact Recognition Method Based on Improved Convolutional Neural Network

Based on the theory of modal acoustic emission (AE), when the convolutional neural network (CNN) is used to identify rotor rub-impact faults, the training data has a small sample size, and the AE sound segment belongs to a single channel signal with less pixel-level information and strong local correlation. Due to the convolutional pooling operations of CNN, coarse-grained and edge information are lost, and the top-level information dimension in CNN network is low, which can easily lead to overfitting. To solve the above problems, we first propose the use of sound spectrograms and their differential features to construct multi-channel image input features suitable for CNN and fully exploit the intrinsic characteristics of the sound spectra. Then, the traditional CNN network structure is improved, and the outputs of all convolutional layers are connected as one layer constitutes a fused feature that contains information at each layer, and is input into the network’s fully connected layer for classification and identification. Experiments indicate that the improved CNN recognition algorithm has significantly improved recognition rate compared with CNN and dynamical neural network (DNN) algorithms.     

A DDoS Attack Information Fusion Method Based on CNN for Multi-Element Data

Traditional distributed denial of service (DDoS) detection methods need a lot of computing resource, and many of them which are based on single element have high missing rate and false alarm rate. In order to solve the problems, this paper proposes a DDoS attack information fusion method based on CNN for multi-element data. Firstly, according to the distribution, concentration and high traffic abruptness of DDoS attacks, this paper defines six features which are respectively obtained from the elements of source IP address, destination IP address, source port, destination port, packet size and the number of IP packets. Then, we propose feature weight calculation algorithm based on principal component analysis to measure the importance of different features in different network environment. The algorithm of weighted multi-element feature fusion proposed in this paper is used to fuse different features, and obtain multi-element fusion feature (MEFF) value. Finally, the DDoS attack information fusion classification model is established by using convolutional neural network and support vector machine respectively based on the MEFF time series. Experimental results show that the information fusion method proposed can effectively fuse multi-element data, reduce the missing rate and total error rate, memory resource consumption, running time, and improve the detection rate.     

Improved cuckoo search with particle swarm optimization for classification of compressed images

The need for a general purpose Content Based Image Retrieval (CBIR) system for huge image databases has attracted information-technology researchers and institutions for CBIR techniques development. These techniques include image feature extraction, segmentation, feature mapping, representation, semantics, indexing and storage, image similarity-distance measurement and retrieval making CBIR system development a challenge. Since medical images are large in size running to megabits of data they are compressed to reduce their size for storage and transmission. This paper investigates medical image retrieval problem for compressed images. An improved image classification algorithm for CBIR is proposed. In the proposed method, RAW images are compressed using Haar wavelet. Features are extracted using Gabor filter and Sobel edge detector. The extracted features are classified using Partial Recurrent Neural Network (PRNN). Since training parameters in Neural Network are NP hard, a hybrid Particle Swarm Optimization (PSO) – Cuckoo Search algorithm (CS) is proposed to optimize the learning rate of the neural network.     

An Optimized Approach to Vehicle-Type Classification Using a Convolutional Neural Network

Vehicle type classification is considered a central part of an intelligent traffic system. In recent years, deep learning had a vital role in object detection in many computer vision tasks. To learn high-level deep features and semantics, deep learning offers powerful tools to address problems in traditional architectures of handcrafted feature-extraction techniques. Unlike other algorithms using handcrated visual features, convolutional neural network is able to automatically learn good features of vehicle type classification. This study develops an optimized automatic surveillance and auditing system to detect and classify vehicles of different categories. Transfer learning is used to quickly learn the features by recording a small number of training images from vehicle frontal view images. The proposed system employs extensive data-augmentation techniques for effective training while avoiding the problem of data shortage. In order to capture rich and discriminative information of vehicles, the convolutional neural network is fine-tuned for the classification of vehicle types using the augmented data. The network extracts the feature maps from the entire dataset and generates a label for each object (vehicle) in an image, which can help in vehicle-type detection and classification. Experimental results on a public dataset and our own dataset demonstrated that the proposed method is quite effective in detection and classification of different types of vehicles. The experimental results show that the proposed model achieves 96.04% accuracy on vehicle type classification.     

基于环形特征的卷积神经网络轮毂识别

针对实际生产中不同种类轮毂的混流生产问题,提出了一种基于环形特征的卷积神经网络轮毂识别算法。将直角坐标下的环形轮毂映射到极坐标中,归一化为标准形式的矩形,提取轮毂图像的环形特征信息,减少冗余特征产生的影响;设计了一种改进的VGG网络架构,利用深度可分离卷积打破输出通道维度与卷积核大小的联系,在不损失网络性能的同时降低了计算量,能够在实际生产中轮毂识别任务在有限的算力情况下实时进行计算;从有效性和实时性两个方面对轮毂识别算法进行评估,且通过Inception V3、SVM、KNN等模型的对比实验,验证了该算法可以实时地对轮毂自适应分类。实验表明: 该方法对轮毂图像的处理精度达到99%以上,单幅图像平均处理时间降低至11.78ms。     

Enhancing Blockchain Security Using Ripple Consensus Algorithm

In the development of technology in various fields like big data analysis, data mining, big data, cloud computing, and blockchain technology, security become more constrained. Blockchain is used in providing security by encrypting the sharing of information. Blockchain is applied in the peer-to-peer (P2P) network and it has a decentralized ledger. Providing security against unauthorized breaches in the distributed network is required. To detect unauthorized breaches, there are numerous techniques were developed and those techniques are inefficient and have poor data integrity. Hence, a novel technique needs to be implemented to tackle the new breaches in the distributed network. This paper, proposed a hybrid technique of two fish with a ripple consensus algorithm (TF-RC). To improve the detection time and security, this paper uses efficient transmission of data in the distributed network. The experimental analysis of TF-RC by using the metric measures of performance in terms of latency, throughput, energy efficiency and it produced better performance.     

基于时间序列单维卷积神经网络的水泥熟料游离钙软测量方法

水泥熟料游离钙(fCaO)含量对水泥质量和生产能耗有着重要影响,现阶段主要通过化学分析的方法离线测得水泥熟料fCaO含量,但是该方法对于烧成系统操作指导具有明显的滞后性。针对熟料fCaO无法在线实时监测的问题,提出基于多变量时间序列单维卷积神经网络(TS-CNN)熟料fCaO软测量建模方法。该方法利用影响熟料fCaO的多个过程变量历史时间段的时间序列作为输入,结合水泥数据特性,采用单维卷积池化的方式提取各过程变量特征,同时降低网络的复杂度,最后经全连接层整合提取的局部信息。通过实验对比,结果表明基于TS-CNN的软测量方法预测精度更高、泛化能力更强。     

基于多级特征融合的体素三维目标检测网络

目的 为精确分析点云场景中待测目标的位置和类别信息,提出一种基于多级特征融合的体素三维目标检测网络。方法 以2阶段检测算法Voxel?RCNN作为基线模型,在检测一阶段,增加稀疏特征残差密集融合模块,由浅入深地对逐级特征进行传播和复用,实现三维特征充分的交互融合。在二维主干模块中增加残差轻量化高效通道注意力机制,显式增强通道特征。提出多级特征及多尺度核自适应融合模块,自适应地提取各级特征的关系权重,以加权方式实现特征的强融合。在检测二阶段,设计三重特征融合策略,基于曼哈顿距离搜索算法聚合邻域特征,并嵌入深度融合模块和CTFFM融合模块提升格点特征质量。结果 实验于自动驾驶数据集KITTI中进行模拟测试,相较于基线网络,在3种难度等级下,一阶段检测模型的行人3D平均精度提升了3.97%,二阶段检测模型的骑行者3D平均精度提升了3.37%。结论 结果证明文中方法能够显著提升目标检测性能,且各模块具有较好的移植性,可灵活嵌入到体素类三维检测模型中,带来相应的效果提升。     

PSO-Gabor-CNN算法在印刷品套印缺陷的检测

目的二维Gabor滤波器含有多个参数,在印刷品套印缺陷检测中,二维Gabor滤波器使用不同参数增强图像特征的效果差别较大,为了获得二维Gabor在某印刷品套印缺陷检测下的优化参数。方法在印刷品套印缺陷检测中,提出一种PSO-Gabor-CNN算法,采用Sobel算子对印刷品图像进行边缘检测,以粒子群算法(PSO)对二维Gabor滤波器的中心最大频率kmax、带宽σ、模板窗口window进行参数寻优,处理后的图像与模板图像采用加权欧式距离进行评价。然后用优化后的Gabor滤波器对图像进行滤波,最后采用卷积神经网络(CNN)对印刷品套印缺陷进行检测和分类。结果通过粒子群算法,确定了二维Gabor中心最大频率kmax为6.0476、带宽σ为0.1444、模板窗口window为27×27取得最佳效果,此时加权欧式距离为1.1927×10-33。卷积神经网络经过70次训练的均方误差为0.0035,测试样本正确率为96.93%。该方法与无数据预处理的BP神经网络(BPNN)、Sobel预处理的BP神经网络(Sobel-BPNN)、无数据预处理的卷积神经网络(CNN)、Sobel预处理的卷积神经网络(Sobel-CNN)对比,表现出了较好的识别效果。结论该方法可以获取二维Gabor滤波器的较优参数,从而获得较好的滤波效果,将其应用于套印缺陷检测,具有一定的应用价值。     

Data Augmentation Using Contour Image for Convolutional Neural Network

With the development of artificial intelligence-related technologies such as deep learning, various organizations, including the government, are making various efforts to generate and manage big data for use in artificial intelligence. However, it is difficult to acquire big data due to various social problems and restrictions such as personal information leakage. There are many problems in introducing technology in fields that do not have enough training data necessary to apply deep learning technology. Therefore, this study proposes a mixed contour data augmentation technique, which is a data augmentation technique using contour images, to solve a problem caused by a lack of data. ResNet, a famous convolutional neural network (CNN) architecture, and CIFAR-10, a benchmark data set, are used for experimental performance evaluation to prove the superiority of the proposed method. And to prove that high performance improvement can be achieved even with a small training dataset, the ratio of the training dataset was divided into 70%, 50%, and 30% for comparative analysis. As a result of applying the mixed contour data augmentation technique, it was possible to achieve a classification accuracy improvement of up to 4.64% and high accuracy even with a small amount of data set. In addition, it is expected that the mixed contour data augmentation technique can be applied in various fields by proving the excellence of the proposed data augmentation technique using benchmark datasets.     

基于深度神经网络的货架商品识别方法

目的为快速统计货架商品信息,提出一种基于深度神经网络的货架商品自动识别方法。方法摄像头采集的货架商品图像经过深度神经网络算法处理,得到了图像中商品的SKU和位置。针对货架商品识别这种密集检测场景,文中方法改进了通用深度神经网络目标检测算法,将算法分为检测和分类2个阶段且重新设计了部分网络结构。最后,将文中方法和传统货架商品识别方法以及通用深度神经网络目标检测方法进行了比较。结果实验证明该方法的检测阶段的模型平均正确率达到96.5%,分类阶段的分类准确率达到99.9%。整图测试的查准率为97.56%,查全率为99.26%。结论相较于以往使用传统的目标检测模型进行货架商品识别以及使用SIFT等人工算子提取特征并分类识别商品具体SKU,文中方法的商品检出率和分类准确率都有了大幅度的提升,具有很好的应用潜力。     

基于卷积神经网络和Transformer网络的鸟声识别

针对传统鸟声识别算法中特征提取方式单一、分类识别准确率低等问题,提出一种结合卷积神经网络和Transformer网络的鸟声识别方法。该方法综合考虑网络局部特征学习和全局上下文依赖性构造,从原始鸟声音频信号中提取短时傅里叶变换(Short Time Fourier Transform,STFT)语谱图特征,将其输入到卷积神经网络(ConvolutionalNeural Network,CNN)中提取局部频谱特征信息,同时提取鸟声信号的对数梅尔特征及一阶差分、二阶差分特征用于合成梅尔频率倒谱系数(Mel Frequency Cepstrum Coefficient,MFCC)混合特征向量,将其输入到Transformer网络中获取全局序列特征信息,最后融合所提取的特征可得到更丰富的鸟声特征参数,通过Softmax分类器得到鸟声识别结果。在Birdsdata和xeno-canto鸟声数据集上进行实验,平均识别准确率分别达到了97.81%和89.47%。实验结果表明该方法相较于其他现有的鸟声识别模型具有更高的识别准确率。