Sentiment Classification Based on Piecewise Pooling Convolutional Neural Network

Recently, the effectiveness of neural networks, especially convolutional neural networks, has been validated in the field of natural language processing, in which, sentiment classification for online reviews is an important and challenging task. Existing convolutional neural networks extract important features of sentences without local features or the feature sequence. Thus, these models do not perform well, especially for transition sentences. To this end, we propose a Piecewise Pooling Convolutional Neural Network (PPCNN) for sentiment classification. Firstly, with a sentence presented by word vectors, convolution operation is introduced to obtain the convolution feature map vectors. Secondly, these vectors are segmented according to the positions of transition words in sentences. Thirdly, the most significant feature of each local segment is extracted using max pooling mechanism, and then the different aspects of features can be extracted. Specifically, the relative sequence of these features is preserved. Finally, after processed by the dropout algorithm, the softmax classifier is trained for sentiment classification. Experimental results show that the proposed method PPCNN is effective and superior to other baseline methods, especially for datasets with transition sentences.     

Fine-Grained Features for Image Captioning

Image captioning involves two different major modalities (image and sentence) that convert a given image into a language that adheres to visual semantics. Almost all methods first extract image features to reduce the difficulty of visual semantic embedding and then use the caption model to generate fluent sentences. The Convolutional Neural Network (CNN) is often used to extract image features in image captioning, and the use of object detection networks to extract region features has achieved great success. However, the region features retrieved by this method are object-level and do not pay attention to fine-grained details because of the detection model’s limitation. We offer an approach to address this issue that more properly generates captions by fusing fine-grained features and region features. First, we extract fine-grained features using a panoramic segmentation algorithm. Second, we suggest two fusion methods and contrast their fusion outcomes. An X-linear Attention Network (X-LAN) serves as the foundation for both fusion methods. According to experimental findings on the COCO dataset, the two-branch fusion approach is superior. It is important to note that on the COCO Karpathy test split, CIDEr is increased up to 134.3% in comparison to the baseline, highlighting the potency and viability of our method.     

基于语义分割的实时车道线检测方法

车道线识别是自动驾驶环境感知的一项重要任务。近年来,基于卷积神经网络的深度学习方法在目标检测和场景分割中取得了很好的效果。本文借鉴语义分割的思想,设计了一个基于编码解码结构的轻量级车道线分割网络。针对卷积神经网络计算量大的问题,引入深度可分离卷积来替代普通卷积以减少卷积运算量。此外,提出了一种更高效的卷积结构LaneConv和LaneDeconv来进一步提高计算效率。为了获取更好的车道线特征表示能力,在编码阶段本文引入了一种将空间注意力和通道注意力串联的双注意力机制模块(CBAM)来提高车道线分割精度。在Tusimple车道线数据集上进行了大量实验,结果表明,本文方法能够显著提升车道线的分割速度,且在各种条件下都具有良好的分割效果和鲁棒性。与现有的车道线分割模型相比,本文方法在分割精度方面相似甚至更优,而在速度方面则有明显提升。

     

Lymph node detection method based on multisource transfer learning and convolutional neural network

Recently years, convolutional neural networks (CNNs) have proven to be powerful tools for a broad range of computer vision tasks. However, training a CNN from scratch is difficult because it requires a large amount of labeled training data, which remains a challenge in medical imaging domain. To this end, deep transfer learning (TL) technique is widely used for many medical image tasks. In this paper, we propose a novel multisource transfer learning CNN model for lymph node detection. The mechanism behind it is straightforward. Point-wise (1 × 1) convolution is used to fuse multisource transfer learning knowledge. Concretely, we view the transferred features as priori domain knowledge and 1 × 1 convolutional operation is implemented after pre-trained convolution layers to adaptively combine the transfer information for target task. In order to learn non-linear transferred features and prevent over-fitting, we present an encode process for the pre-trained convolution kernels. At last, based on convolutional factorization technique, we train the proposed CNN model and the encoder process jointly, which improves the feasibility of our approach. The effectiveness of the proposed method is verified on lymph node (LN) dataset: 388 mediastinal LNs labeled by radiologists in 90 patient CT scans, and 595 abdominal LNs in 86 patient CT scans for LN detection. Our method demonstrates sensitivities of about 85%/71% at 3 FP/vol. and 92%/85% at 6 FP/vol. for mediastinum and abdomen respectively, which compares favorably to previous methods.     

基于卷积神经网络的生物式水质监测方法

生物式水质监测通常是先通过提取水生物在不同环境下的应激反应特征,再进行特征分类,从而识别水质。针对水质监测问题,提出一种使用卷积神经网络(CNN)的方法。鱼类运动轨迹是当前所有文献使用的多种水质分类特征的综合性表现,是生物式水质分类的重要依据。使用Mask-RCNN的图像分割方法,求取鱼体的质心坐标,并绘制出一定时间段内鱼体的运动轨迹图像,制作正常与异常水质下两种轨迹图像数据集。融合Inception-v3网络作为数据集的特征预处理部分,重新建立卷积神经网络对Inception-v3网络提取的特征进行分类。通过设置多组平行实验,在不同的水质环境中对正常水质与异常水质进行分类。结果表明,卷积神经网络模型的水质识别率为99.38%,完全达到水质识别的要求。     

一种用细胞神经网络提取干涉条纹中心的新方法

提取干涉条纹的中心是干涉测量的关键环节,文中提出了一种基于细胞神经网络（CNN）提取干涉条纹中心的新方法.CNN是一种实时处理信号的大规模非线性模拟电路,同时它的局部联接特点使其适用于超大规模集成电路的实现.CNN具有并行运算的能力,可消除传统串行算法复杂性高、不能实时处理的缺点.对该方法进行了分析,给出了实例的仿真结果,证明该方法能快速准确地提取干涉条纹的中心,提高了干涉条纹的判别精度,从而增加了实验中干涉条纹处理的直观性和实时性.     

Centralized embedding hypersphere feature learning for person re-identification

ABSTRACT

Deep metric learning has become a general method for person re-identification (ReID) recently. Existing methods train ReID model with various loss functions to learn feature representation and identify pedestrian. However, the interaction between person features and classification vectors in the training process is rarely concerned. Distribution of pedestrian features will greatly affect convergence of the model and the pedestrian similarity computing in the test phase. In this paper, we formulate improved softmax function to learn pedestrian features and classification vectors. Our method applies pedestrian feature representation to be scattered across the coordinate space and embedding hypersphere to solve the classification problem. Then, we propose an end-to-end convolutional neural network (CNN) framework with improved softmax function to improve the performance of pedestrian features. Finally, experiments are performed on four challenging datasets. The results demonstrate that our work is competitive compared to the state-of-the-art.     

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。     

基于自身注意力时空特征的语音情感识别算法

针对语音情感识别中无法对关键的时空依赖关系进行建模,导致识别率低的问题,提出一种基于自身注意力(self-attention)时空特征的语音情感识别算法,利用双线性卷积神经网络、长短期记忆网络和多组注意力(multi-head attention)机制去自动学习语音信号的最佳时空表征.首先提取语音信号的对数梅尔(log...     

Deep convolutional neural networks for eigenvalue problems in mechanics

We show that deep convolutional neural networks (CNNs) can massively outperform traditional densely connected neural networks (NNs) (both deep or shallow) in predicting eigenvalue problems in mechanics. In this sense, we strike out in a new direction in mechanics computations with strongly predictive NNs whose success depends not only on architectures being deep but also being fundamentally different from the widely used to date. We consider a model problem: predicting the eigenvalues of one-dimensional (1D) and two-dimensional (2D) phononic crystals. For the 1D case, the optimal CNN architecture reaches 98% accuracy level on unseen data when trained with just 20 000 samples, compared to 85% accuracy even with 100 000 samples for the typical network of choice in mechanics research. We show that, with relatively high data efficiency, CNNs have the capability to generalize well and automatically learn deep symmetry operations, easily extending to higher dimensions and our 2D case. Most importantly, we show how CNNs can naturally represent mechanical material tensors, with its convolution kernels serving as local receptive fields, which is a natural representation of mechanical response. Strategies proposed are applicable to other mechanics' problems and may, in the future, be used to sidestep cumbersome algorithms with purely data-driven approaches based upon modern deep architectures.     

Deep Feature Fusion Model for Sentence Semantic Matching

Sentence semantic matching (SSM) is a fundamental research in solving natural language processing tasks such as question answering and machine translation. The latest SSM research benefits from deep learning techniques by incorporating attention mechanism to semantically match given sentences. However, how to fully capture the semantic context without losing significant features for sentence encoding is still a challenge. To address this challenge, we propose a deep feature fusion model and integrate it into the most popular deep learning architecture for sentence matching task. The integrated architecture mainly consists of embedding layer, deep feature fusion layer, matching layer and prediction layer. In addition, we also compare the commonly used loss function, and propose a novel hybrid loss function integrating MSE and cross entropy together, considering confidence interval and threshold setting to preserve the indistinguishable instances in training process. To evaluate our model performance, we experiment on two real world public data sets: LCQMC and Quora. The experiment results demonstrate that our model outperforms the most existing advanced deep learning models for sentence matching, benefited from our enhanced loss function and deep feature fusion model for capturing semantic context.     

融合注意力机制和语义关联性的多标签图像分类

卷积神经网络在单标签图像分类中表现出了良好的性能,但是,如何将其更好地应用到多标签图像分类仍然是一项重要的挑战。本文提出一种基于卷积神经网络并融合注意力机制和语义关联性的多标签图像分类方法。首先,利用卷积神经网络来提取特征;其次,利用注意力机制将数据集中的每个标签类别和输出特征图中的每个通道进行对应;最后,利用监督学习的方式学习通道之间的关联性,也就是学习标签之间的关联性。实验结果表明,本文方法可以有效地学习标签之间语义关联性,并提升多标签图像分类效果。     

Acoustic Emission Recognition Based on a Two-Streams Convolutional Neural Network

The Convolutional Neural Network (CNN) is a widely used deep neural network. Compared with the shallow neural network, the CNN network has better performance and faster computing in some image recognition tasks. It can effectively avoid the problem that network training falls into local extremes. At present, CNN has been applied in many different fields, including fault diagnosis, and it has improved the level and efficiency of fault diagnosis. In this paper, a two-streams convolutional neural network (TCNN) model is proposed. Based on the short-time Fourier transform (STFT) spectral and Mel Frequency Cepstrum Coefficient (MFCC) input characteristics of two-streams acoustic emission (AE) signals, an AE signal processing and classification system is constructed and compared with the traditional recognition methods of AE signals and traditional CNN networks. The experimental results illustrate the effectiveness of the proposed model. Compared with single-stream convolutional neural network and a simple Long Short-Term Memory (LSTM) network, the performance of TCNN which combines spatial and temporal features is greatly improved, and the accuracy rate can reach 100% on the current database, which is 12% higher than that of single-stream neural network.     

基于改进编辑距离的中文相似句子检索

中文相似句子检索的方法在基于实例的机器翻译等中文信息处理领域,具有非常广泛的应用背景。本文提出的基于改进编辑距离的中文相似句子检索方法,在使用信息检索技术提高检索效率的同时,以普通编辑距离算法为基础,加入了词汇的语义信息,使之更加符合中文句子相似度计算的要求。改进编辑距离与单纯基于语义辞典计算句子相似度的方法相比,具有便于扩展,准确率高等优点。在基于大规模双语句对检索的英文辅助写作系统中使用该算法进行中文句子检索,最后获得了81．33％的查准率和95．31％的查全率。     

Enhancement of Sentiment Analysis Using Clause and Discourse Connectives

The sentiment of a text depends on the clausal structure of the sentence and the connectives’ discourse arguments. In this work, the clause boundary, discourse argument, and syntactic and semantic information of the sentence are used to assign the text’s sentiment. The clause boundaries identify the span of the text, and the discourse connectives identify the arguments. Since the lexicon-based analysis of traditional sentiment analysis gives the wrong sentiment of the sentence, a deeper-level semantic analysis is required for the correct analysis of sentiments. Hence, in this study, explicit connectives in Malayalam are considered to identify the discourse arguments. A supervised method, conditional random fields, is used to identify the clause boundary and discourse arguments. For the study, 1,000 sentiment sentences from Malayalam documents were analyzed. Experimental results show that the discourse structure integration considerably improves sentiment analysis performance from the baseline system.     

Detecting Driver Distraction Using Deep-Learning Approach

Currently, distracted driving is among the most important causes of traffic accidents. Consequently, intelligent vehicle driving systems have become increasingly important. Recently, interest in driver-assistance systems that detect driver actions and help them drive safely has increased. In these studies, although some distinct data types, such as the physical conditions of the driver, audio and visual features, and vehicle information, are used, the primary data source is images of the driver that include the face, arms, and hands taken with a camera inside the car. In this study, an architecture based on a convolution neural network (CNN) is proposed to classify and detect driver distraction. An efficient CNN with high accuracy is implemented, and to implement intense convolutional networks for large-scale image recognition, a new architecture was proposed based on the available Visual Geometry Group (VGG-16) architecture. The proposed architecture was evaluated using the StateFarm dataset for driver-distraction detection. This dataset is publicly available on Kaggle and is frequently used for this type of research. The proposed architecture achieved 96.95% accuracy.     

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.     

基于一维卷积神经网络的房颤智能诊断方法研究

针对“大数据”时代如何利用数据对房颤进行智能、高效的诊断问题,提出了基于一维卷积神经网络的智能诊断方法,以避免传统算法依赖人工特征提取和先验知识的问题。首先,分别构建一维LeNet-5和AlexNet神经网络模型,合理设置网络结构参数;然后,在采集的实验数据基础上针对心电信号的特点进行一系列的数据处理,随机构建训练样本和测试样本;最后,将训练样本分别输入上述2个神经网络模型中训练学习,再将训练好的模型用于房颤的诊断。实验结果表明:一维LeNet-5网络模型存在“过拟合”现象,而一维AlexNet网络模型在避免了上述现象的同时,诊断精度达到了95.34%,较传统方法有了较大提升,为房颤诊断提供了有效的手段。     

ACLSTM: A Novel Method for CQA Answer Quality Prediction Based on Question-Answer Joint Learning

Given the limitations of the community question answering (CQA) answer quality prediction method in measuring the semantic information of the answer text, this paper proposes an answer quality prediction model based on the question-answer joint learning (ACLSTM). The attention mechanism is used to obtain the dependency relationship between the Question-and-Answer (Q&A) pairs. Convolutional Neural Network (CNN) and Long Short-term Memory Network (LSTM) are used to extract semantic features of Q&A pairs and calculate their matching degree. Besides, answer semantic representation is combined with other effective extended features as the input representation of the fully connected layer. Compared with other quality prediction models, the ACLSTM model can effectively improve the prediction effect of answer quality. In particular, the mediumquality answer prediction, and its prediction effect is improved after adding effective extended features. Experiments prove that after the ACLSTM model learning, the Q&A pairs can better measure the semantic match between each other, fully reflecting the model’s superior performance in the semantic information processing of the answer text.