Communication modulation signal recognition based on the deep multi-hop neural network

Automatic modulation classification (AMC) is one of the core technologies in non-cooperative communication. In the complex wireless environment, it is not easy to quickly and accurately recognize the modulation styles of signals by conventional methods. The deep learning method (DLM) can deal with the problem and achieve good effects. In conventional DLMs, the length of input data is fixed. However, the signal length in communication is changing, which may not make full use of the DLMs’ input signal information to improve the recognition accuracy. In this paper, the deep multi-hop convolutional neural network (CNN) is employed to learn the time-domain signal features with different lengths. The proposed network includes the multi-hop connection rate and the receptive field extension scope to dispose of the limitation. The experiment shows that the proposed network can achieve better recognition results under the sparse multi-hop network structure. The reception field extension scope is also conducive to further improve the recognition effects. Finally, the proposed network has shorter training time and smaller parameters, which is more convenient for training the network and deploying in the existing communication system.     

用改进的BP网络预测油气

人工神经网络在地球物理领域中，尤其在模式识别和油气预测方面得到了较好的应用．前向网络的重要特性是能够总结、归纳已知样本隐含的函数关系．然而其推广性能有待进一步研究．本文强调了该问题的重要性并提出了改善网络推广性能的技术，即在网络学习过程中，不仅让总误差下降，还尽可能使建立的“隐函数”平滑．计算实例表明，本文的算法可以明显地改善网络的推广性能．最后给出了用该技术在辽河油田进行油气预测的实例     

A qualitatively analyzable two-stage ensemble model based on machine learning for credit risk early warning: Evidence from Chinese manufacturing companies

Constructing ensemble models has become a common method for corporate credit risk early warning, while as to deep learning model with better predictive ability, there have been no fixed theoretical models formed in corporate credit risk early warning, as such models often fail to conduct further qualitative analysis of the results. Thus, this article builds a new two-stage ensemble model using a variety of machine learning methods represented by deep learning for corporate credit risk early warning, which can not only effectively improve the prediction performance of the model, but also qualitatively analyze the source of corporate credit risk from multiple angles according to the results. At first stage, the improved entropy method is used to re-assign the instance weight in correlation degree based on grey correlation analysis. At second stage, this study adopts Bagging method to integrate multiple one-dimensional convolutional neural networks, and borrows idea of N-fold cross validation to expand the difference of the base classifier. Empirically, this article selects listed companies in Chinese manufacturing industry between 2012 and 2021 as datasets, including 467 samples with 51 financial indicators. The new ensemble model has the highest F1-score (87.29%) and G-mean (89.47%) among comparative models, and qualitatively analyzes corporate risk sources. Further, it also analyzes how to increase early warning effect from the angles of indicator number and time span.     

IGCNN-FC: Boosting interpretability and generalization of convolutional neural networks for few chest X-rays analysis

Computer-aided diagnosis (CAD) with convolutional neural networks (CNNs) has been widely applied to assist doctors in medical image analysis. However, most of them often encounter two obstacles: (1) Data scarcity, because the advanced performance of CNNs heavily depends on a large amount of data, especially high-quality annotated ones. (2) Interpretability, CNNs cannot directly provide evidence related to the decision-making process to support their diagnosis results. To overcome these two obstacles, we propose an interpretable deep learning framework based on CNNs. Specifically, we introduce a multi-scale loss-based attention to leverage the mid- and high-level features to mine significant features for decision-making. Additionally, to better explore the semantic knowledge from training data, we utilize the mixup method to produce more annotated training images. Moreover, to boost model generalization capability, we employ the self-distillation to learn the knowledge generated from previous training epochs. Experiments on two benchmark Chest X-ray datasets demonstrate the effectiveness of the proposed framework with superior performance over recent SOTA methods, with boosting model interpretability.     

Efficient quantum feature extraction for CNN-based learning

Hybrid quantum-classical algorithms provide a promising way to harness the power of current quantum devices. In this framework, parametrized quantum circuits (PQCs) which consist of layers of parametrized unitaries can be considered as a kind of quantum neural networks. Recent works have begun to explore the potential of PQCs as general function approximators. In this work, we propose a quantum-classical deep network structure to enhance model discriminability of convolutional neural networks (CNNs). In CNNs, the convolutional layer uses linear filters to scan the input data followed by a nonlinear operation. Instead, we build PQCs, which are more potent function approximators, with more complex structures to capture the features within the receptive field. The feature maps are obtained by sliding the PQCs over the input in a similar way as CNN. We also give a training algorithm for the proposed model. Through numerical simulation, the proposed hybrid models demonstrate reasonable classification performance on MNIST and Fashion-MNIST (4-classes). In addition, we compare the performance of models in different settings. The results demonstrate that the model with high-expressibility ansaetze achieves lower cost and higher accuracy, but exhibits a “saturation” phenomenon.     

Deep forest

Current deep-learning models are mostly built upon neural networks, i.e. multiple layers of parameterized differentiable non-linear modules that can be trained by backpropagation. In this paper, we explore the possibility of building deep models based on non-differentiable modules such as decision trees. After a discussion about the mystery behind deep neural networks, particularly by contrasting them with shallow neural networks and traditional machine-learning techniques such as decision trees and boosting machines, we conjecture that the success of deep neural networks owes much to three characteristics, i.e. layer-by-layer processing, in-model feature transformation and sufficient model complexity. On one hand, our conjecture may offer inspiration for theoretical understanding of deep learning; on the other hand, to verify the conjecture, we propose an approach that generates deep forest holding these characteristics. This is a decision-tree ensemble approach, with fewer hyper-parameters than deep neural networks, and its model complexity can be automatically determined in a data-dependent way. Experiments show that its performance is quite robust to hyper-parameter settings, such that in most cases, even across different data from different domains, it is able to achieve excellent performance by using the same default setting. This study opens the door to deep learning based on non-differentiable modules without gradient-based adjustment, and exhibits the possibility of constructing deep models without backpropagation.     

钢板表面缺陷深度主动学习高效分类方法

针对钢板表面缺陷图像分类传统深度学习算法中需要大量标签数据的问题,提出一种基于主动学习的高效分类方法。该方法包含一个轻量级的卷积神经网络和一个基于不确定性的主动学习样本筛选策略。神经网络采用简化的convolutional base进行特征提取,然后用全局池化层替换掉传统密集连接分类器中的隐藏层来减轻过拟合。为了更好的衡量模型对未标签图像样本所属类别的不确定性,首先将未标签图像样本传入到用标签图像样本训练好的模型,得到模型对每一个未标签样本关于标签的概率分布(probability distribution over classes, PDC),然后用此模型对标签样本进行预测并得到模型对每个标签的平均PDC。将两类分布的KL-divergence值作为不确定性指标来筛选未标签图像进行人工标注。根据在NEU-CLS开源缺陷数据集上的对比实验,该方法可以通过44%的标签数据实现97%的准确率,极大降低标注成本。     

Knowledge graph embedding model with attention-based high-low level features interaction convolutional network

Knowledge graphs are sizeable graph-structured knowledge with both abstract and concrete concepts in the form of entities and relations. Recently, convolutional neural networks have achieved outstanding results for more expressive representations of knowledge graphs. However, existing deep learning-based models exploit semantic information from single-level feature interaction, potentially limiting expressiveness. We propose a knowledge graph embedding model with an attention-based high-low level features interaction convolutional network called ConvHLE to alleviate this issue. This model effectively harvests richer semantic information and generates more expressive representations. Concretely, the multilayer convolutional neural network is utilized to fuse high-low level features. Then, features in fused feature maps interact with other informative neighbors through the criss-cross attention mechanism, which expands the receptive fields and boosts the quality of interactions. Finally, a plausibility score function is proposed for the evaluation of our model. The performance of ConvHLE is experimentally investigated on six benchmark datasets with individual characteristics. Extensive experimental results prove that ConvHLE learns more expressive and discriminative feature representations and has outperformed other state-of-the-art baselines over most metrics when addressing link prediction tasks. Comparing MRR and Hits@1 on FB15K-237, our model outperforms the baseline ConvE by 13.5% and 16.0%, respectively.     

增强现实技术在解剖学中的应用以及系统评价

传统意义上的解剖学学习依赖于传统技术,例如人体尸体解剖和教科书的使用。随着技术的飞速发展,学习解剖学的方法有了革命性的发展。当前,解剖学教育中采用了许多新的技术和方法,尤其是增强现实技术引起了人们极大的兴趣,但对于这种技术的有效性的评估文献很少。因此,该研究的目的是通过荟萃分析,了解增强现实技术是否是解剖学领域的最佳工具结果提示:在与增强现实技术相关的31篇文章中,有30篇表示赞成,1篇表示中立,没有任何文章反对使用此技术。因此,可以将增强现实技术应用于解剖学教学过程中。     

Distributed estimation of unmanned surface vessel based on Kalman-consensus filter and convolutional neural network

The distributed estimation has important research significance in unmanned systems. This paper investigates the distributed estimation of unmanned surface vessel (USV) via multi-sensor collaboration and 3D object recognition, in which a Knowledge Graph (KG) is constructed to store and represent the estimation results. Kalman-consensus Filter (KCF) and convolutional neural network (CNN) are used to estimate the optimal states of objects, and recognise multiple classes of objects without designing detectors for each class of objects, respectively. The recognition efficiency is improved by dividing the data into pixel blocks whose value is the number of detection points, and a point cloud dataset in different locations and rotations is also provided. Experiments are proposed to show that our method can help the USV accurately perceive entities in the environment, which validates the effectiveness of the proposed algorithm.     

Semisupervised SAR image change detection based on a siamese variational autoencoder

In synthetic aperture radar (SAR) image change detection, the deep learning has attracted increasingly more attention because the difference images (DIs) of traditional unsupervised technology are vulnerable to speckle noise. However, most of the existing deep networks do not constrain the distributional characteristics of the hidden space, which may affect the feature representation performance. This paper proposes a variational autoencoder (VAE) network with the siamese structure to detect changes in SAR images. The VAE encodes the input as a probability distribution in the hidden space to obtain regular hidden layer features with a good representation ability. Furthermore, subnetworks with the same parameters and structure can extract the spatial consistency features of the original image, which is conducive to the subsequent classification. The proposed method includes three main steps. First, the training samples are selected based on the false labels generated by a clustering algorithm. Then, we train the proposed model with the semisupervised learning strategy, including unsupervised feature learning and supervised network fine-tuning. Finally, input the original data instead of the DIs in the trained network to obtain the change detection results. The experimental results on four real SAR datasets show the effectiveness and robustness of the proposed method.     

Multimodal negative sentiment recognition of online public opinion on public health emergencies based on graph convolutional networks and ensemble learning

To improve the effect of multimodal negative sentiment recognition of online public opinion on public health emergencies, we constructed a novel multimodal fine-grained negative sentiment recognition model based on graph convolutional networks (GCN) and ensemble learning. This model comprises BERT and ViT-based multimodal feature representation, GCN-based feature fusion, multiple classifiers, and ensemble learning-based decision fusion. Firstly, the image-text data about COVID-19 is collected from Sina Weibo, and the text and image features are extracted through BERT and ViT, respectively. Secondly, the image-text fused features are generated through GCN in the constructed microblog graph. Finally, AdaBoost is trained to decide the final sentiments recognized by the best classifiers in image, text, and image-text fused features. The results show that the F1-score of this model is 84.13% in sentiment polarity recognition and 82.06% in fine-grained negative sentiment recognition, improved by 4.13% and 7.55% compared to the optimal recognition effect of image-text feature fusion, respectively.     

科学基金资助F0701的科学计量分析

2018年,科学基金信息科学领域增设“教育信息科学与技术”申请代码(F0701)资助教育科学基础研究。基于首批F0701科学基金申请与资助项目数据的科学计量分析显示：申请项目涵盖了个性化教学、教育大数据、机器学习、增强现实、教育机器人、学习评测、交互学习、数字资源、协同学习、资源配置等十个主题聚类。研究发现,目前的教育信息科学与技术研究仍处于技术迁移期,主要以信息领域向教育领域渗透的研究工作为主,但对教育领域的重大关键科学问题缺乏深刻凝练,深度交叉融合不足。建议研究者加强对自然科学研究范式的运用、增强研究团队的交叉融合、提高凝练科学问题的能力;建议科学基金进一步充实完善申请代码,引导评审专家根据本领域项目申请的特点进行评估,提高资助率并加大支持力度,促进我国教育信息科学与技术领域整体研究水平的提升。     

基于深度学习的学术文本段落结构功能识别研究

【目的/意义】在学术大数据的应用背景下,对学术文本更加细粒度、语义化的分析挖掘日益迫切,学术文本结构功能识别成为科研领域的一个研究热点。【方法/过程】本文从段落的层次来识别章节结构功能,提出利用结合卷积神经网络和循环神经网络的特征对学术文本段落进行表达,然后进行分类。【结果/结论】文本提出的深度学习方法在整体分类结果上优于传统的机器学习方法,同时极大的减少了传统特征工程的人力需求。     

Towards understanding residual and dilated dense neural networks via convolutional sparse coding

Convolutional neural network (CNN) and its variants have led to many state-of-the-art results in various fields. However, a clear theoretical understanding of such networks is still lacking. Recently, a multilayer convolutional sparse coding (ML-CSC) model has been proposed and proved to equal such simply stacked networks (plain networks). Here, we consider the initialization, the dictionary design and the number of iterations to be factors in each layer that greatly affect the performance of the ML-CSC model. Inspired by these considerations, we propose two novel multilayer models: the residual convolutional sparse coding (Res-CSC) model and the mixed-scale dense convolutional sparse coding (MSD-CSC) model. They are closely related to the residual neural network (ResNet) and the mixed-scale (dilated) dense neural network (MSDNet), respectively. Mathematically, we derive the skip connection in the ResNet as a special case of a new forward propagation rule for the ML-CSC model. We also find a theoretical interpretation of dilated convolution and dense connection in the MSDNet by analyzing the MSD-CSC model, which gives a clear mathematical understanding of each. We implement the iterative soft thresholding algorithm and its fast version to solve the Res-CSC and MSD-CSC models. The unfolding operation can be employed for further improvement. Finally, extensive numerical experiments and comparison with competing methods demonstrate their effectiveness.     

基于惯性动作捕捉的人体运动姿态分析

人体运动姿态编辑的自由性是以人体运动规律为依据,利用最小二乘法数学理论对获取到的动画数据.bvh格式文件,从运动学和时空学两方面进行分析,通过拟合人体运动曲线,得到人体运动规律参数。实验证明,该方法可以精确地分析人体的三维运动姿态,并可将其结果应用于医学研究、视频监控和体育教学研究等领域。     

BP神经网络在智能雨刮器上的应用及MATLAB仿真研究

在分析了传统雨刮器缺点的基础上,提出了一种基于BP神经网络的模式识别模型,用专家的经验数据训练它,并测试了它;给出了BP神经网络的学习过程及算法。结果表明这个基于BP神经网络的模型不使用精确的数学模型即可有效处理智能雨刮器系统的不可靠性和非线性。     

面向语义缺失场景的社交媒体中热门新闻识别方法研究

[目的/意义]对社交媒体中热门新闻的及时识别,有助于加速正面资讯的投送或抑制负面资讯的扩散。当前,基于自然语言处理的传统识别方法正面临社交媒体新生态的挑战：大量新闻内容以图片、音视频形式存在,缺乏用于语义及情感分析的文本。[方法/过程]对此,本文首先将社交网络划分为众多社群,并按其层次结构组织为贝叶斯网络。接着,面向社群构建基于卷积神经网络的热门新闻识别模型,模型综合考虑新闻传播的宏观统计规律及微观传播过程,以提取社群内热门新闻传播的特征。最后,利用贝叶斯推理并结合局部性的模型识别结果进行全局性热度预测。[结果/结论]实验表明,本方法在语义缺失场景下可有效识别热门新闻,其准确度强于基于语义信息的机器学习方法,模型具有良好的时效性、可扩展性和适用性。该研究有助于社交媒体的监管机构及时识别出各类不含语义信息且迅速扩散的热点内容。     

Automatic segmentation of intracerebral hemorrhage in CT images using encoder–decoder convolutional neural network

Intracerebral hemorrhage (ICH) is the most serious type of stroke, which results in a high disability or mortality rate. Therefore, accurate and rapid ICH region segmentation is of great significance for clinical diagnosis and treatment of ICH. In this paper, we focus on deep neural networks to automatically segment ICH regions. Firstly, we propose an encoder-decoder convolutional neural network (ED-Net) architecture to comprehensively utilizing both the low-level and high-level semantic information. Specifically, the encoder is used to extract multi-scale semantic feature information, while the decoder integrates them to form a unified ICH feature representation. Secondly, we introduce a synthetic loss function by paying more attention to the small ICH regions to overcome the data imbalanced problem. Thirdly, to improve the clinical adaptability of the proposed model, we collect 480 patient cases with ICH from four hospitals to construct a multi-center dataset, in which each case contains the first and review CT scans. In particular, CT scans of different patients are diverse, which greatly increases the difficulty of segmentation. Finally, we evaluate ED-Net on the multi-center ICH clinical dataset from different model parameters and different loss functions. We also compare the results of ED-Net with nine state-of-the-art methods in the literature. Both quantitative and visual results have shown that ED-Net outperforms other methods by providing more accurate and stable performance.