Large-Scale Location-Aware Services in Access: Hierarchical Building/Floor Classification and Location Estimation Using Wi-Fi Fingerprinting Based on Deep Neural Networks

We report the results of our investigation on the use of deep neural networks (DNNs) for building/floor classification and floor-level location estimation based on Wi-Fi fingerprinting. We propose a new DNN architecture based on a stacked autoencoder for feature space dimension reduction and a feed-forward classifier for multi-label classification with arg max functions to convert multi-label classification results into multi-class classification ones. We also demonstrate a prototype system for floor-level location estimation using received signal strengths measured on XJTLU campus. Our results show the strengths of DNN-based approaches, providing near state-of-the-art performance with less parameter tuning and higher scalability.     

Deep-learning-based prediction of living cells mitosis via quantitative phase microscopy

We present a deep learning approach for living cells mitosis classification based on label-free quantitative phase imaging with transport of intensity equation methods. In the approach, we applied a pretrained deep convolutional neural network using transfer learning for binary classification of mitosis and non-mitosis. As a validation, we demonstrated the performances of the network trained by phase images and intensity images, respectively. The convolutional neural network trained by phase images achieved an average accuracy of 98.9% on the validation data, which outperforms the average accuracy 89.6% obtained by the network trained by intensity images. We believe that the quantitative phase microscopy in combination with deep learning enables researchers to predict the mitotic status of living cells noninvasively and efficiently.     

堆叠监督自动编码器的近红外光谱建模

近红外光谱中包含了物质中有机分子含氢基团的特征信息,具有维度高、冗余大等特点.传统的基于浅层校正模型,比如主成分回归、偏最小二乘回归、人工神经网络、支持向量回归等,无法提取近红外光谱数据深层的信息.提出一种基于堆叠监督自动编码器的近红外光谱建模方法,不仅可以拟合光谱数据与理化值之间复杂的非线性关系,还可以提取数据深层的...     

基于密集卷积和域自适应的高光谱图像分类

针对常规的高光谱图像分类算法不能很好地解决不同图像中的频谱偏移的问题,提出了一种基于密集卷积和域自适应的高光谱图像分类算法,首先在源域中使用密集卷积进行深度特征学习,然后应用域自适应技术转移到目标域。目前的域自适应高光谱图像分类框架中常用卷积神经网络进行特征学习,但是当深度增加时会出现因梯度消失而导致分类精度下降的情况,因此本文通过引入密集卷积进行深度特征学习,提高域自适应高光谱图像分类的精度。在Indiana高光谱数据集和Pavia高光谱数据集上验证所提算法的有效性,整体分类精度分别为61.06%和89.63%,与其他域自适应高光谱图像分类方法对比,所提方法具有更好的分类精度。     

An Interpretation Architecture for Deep Learning Models with the Application of COVID-19 Diagnosis

The Coronavirus disease 2019 (COVID-19) has become one of the threats to the world. Computed tomography (CT) is an informative tool for the diagnosis of COVID-19 patients. Many deep learning approaches on CT images have been proposed and brought promising performance. However, due to the high complexity and non-transparency of deep models, the explanation of the diagnosis process is challenging, making it hard to evaluate whether such approaches are reliable. In this paper, we propose a visual interpretation architecture for the explanation of the deep learning models and apply the architecture in COVID-19 diagnosis. Our architecture designs a comprehensive interpretation about the deep model from different perspectives, including the training trends, diagnostic performance, learned features, feature extractors, the hidden layers, the support regions for diagnostic decision, and etc. With the interpretation architecture, researchers can make a comparison and explanation about the classification performance, gain insight into what the deep model learned from images, and obtain the supports for diagnostic decisions. Our deep model achieves the diagnostic result of 94.75%, 93.22%, 96.69%, 97.27%, and 91.88% in the criteria of accuracy, sensitivity, specificity, positive predictive value, and negative predictive value, which are 8.30%, 4.32%, 13.33%, 10.25%, and 6.19% higher than that of the compared traditional methods. The visualized features in 2-D and 3-D spaces provide the reasons for the superiority of our deep model. Our interpretation architecture would allow researchers to understand more about how and why deep models work, and can be used as interpretation solutions for any deep learning models based on convolutional neural network. It can also help deep learning methods to take a step forward in the clinical COVID-19 diagnosis field.     

Multilevel Deep Feature Generation Framework for Automated Detection of Retinal Abnormalities Using OCT Images

Optical coherence tomography (OCT) images coupled with many learning techniques have been developed to diagnose retinal disorders. This work aims to develop a novel framework for extracting deep features from 18 pre-trained convolutional neural networks (CNN) and to attain high performance using OCT images. In this work, we have developed a new framework for automated detection of retinal disorders using transfer learning. This model consists of three phases: deep fused and multilevel feature extraction, using 18 pre-trained networks and tent maximal pooling, feature selection with ReliefF, and classification using the optimized classifier. The novelty of this proposed framework is the feature generation using widely used CNNs and to select the most suitable features for classification. The extracted features using our proposed intelligent feature extractor are fed to iterative ReliefF (IRF) to automatically select the best feature vector. The quadratic support vector machine (QSVM) is utilized as a classifier in this work. We have developed our model using two public OCT image datasets, and they are named database 1 (DB1) and database 2 (DB2). The proposed framework can attain 97.40% and 100% classification accuracies using the two OCT datasets, DB1 and DB2, respectively. These results illustrate the success of our model.     

A 3D densely connected convolution neural network with connection-wise attention mechanism for Alzheimer's disease classification

PurposeAlzheimer's disease (AD) is a progressive and irreversible neurodegenerative disease. In recent years, machine learning methods have been widely used on analysis of neuroimage for quantitative evaluation and computer-aided diagnosis of AD or prediction on the conversion from mild cognitive impairment (MCI) to AD. In this study, we aimed to develop a new deep learning method to detect or predict AD in an efficient way.Materials and methodsWe proposed a densely connected convolution neural network with connection-wise attention mechanism to learn the multi-level features of brain MR images for AD classification. We used the densely connected neural network to extract multi-scale features from pre-processed images, and connection-wise attention mechanism was applied to combine connections among features from different layers to hierarchically transform the MR images into more compact high-level features. Furthermore, we extended the convolution operation to 3D to capture the spatial information of MRI. The features extracted from each 3D convolution layer were integrated with features from all preceding layers with different attention, and were finally used for classification. Our method was evaluated on the baseline MRI of 968 subjects from ADNI database to discriminate (1) AD versus healthy subjects, (2) MCI converters versus healthy subjects, and (3) MCI converters versus non-converters.ResultsThe proposed method achieved 97.35% accuracy for distinguishing AD patients from healthy control, 87.82% for MCI converters against healthy control, and 78.79% for MCI converters against non-converters. Compared with some neural networks and methods reported in recent studies, the classification performance of our proposed algorithm was among the top ranks and improved in discriminating MCI subjects who were in high risks of conversion to AD.ConclusionsDeep learning techniques provide a powerful tool to explore minute but intricate characteristics in MR images which may facilitate early diagnosis and prediction of AD.     

ECG Signal Classification Using Deep Learning Techniques Based on the PTB-XL Dataset

The analysis and processing of ECG signals are a key approach in the diagnosis of cardiovascular diseases. The main field of work in this area is classification, which is increasingly supported by machine learning-based algorithms. In this work, a deep neural network was developed for the automatic classification of primary ECG signals. The research was carried out on the data contained in a PTB-XL database. Three neural network architectures were proposed: the first based on the convolutional network, the second on SincNet, and the third on the convolutional network, but with additional entropy-based features. The dataset was divided into training, validation, and test sets in proportions of 70%, 15%, and 15%, respectively. The studies were conducted for 2, 5, and 20 classes of disease entities. The convolutional network with entropy features obtained the best classification result. The convolutional network without entropy-based features obtained a slightly less successful result, but had the highest computational efficiency, due to the significantly lower number of neurons.     

Reliable Fault Diagnosis of Bearings Using an Optimized Stacked Variational Denoising Auto-Encoder

Variational auto-encoders (VAE) have recently been successfully applied in the intelligent fault diagnosis of rolling bearings due to its self-learning ability and robustness. However, the hyper-parameters of VAEs depend, to a significant extent, on artificial settings, which is regarded as a common and key problem in existing deep learning models. Additionally, its anti-noise capability may face a decline when VAE is used to analyze bearing vibration data under loud environmental noise. Therefore, in order to improve the anti-noise performance of the VAE model and adaptively select its parameters, this paper proposes an optimized stacked variational denoising autoencoder (OSVDAE) for the reliable fault diagnosis of bearings. Within the proposed method, a robust network, named variational denoising auto-encoder (VDAE), is, first, designed by integrating VAE and a denoising auto-encoder (DAE). Subsequently, a stacked variational denoising auto-encoder (SVDAE) architecture is constructed to extract the robust and discriminative latent fault features via stacking VDAE networks layer on layer, wherein the important parameters of the SVDAE model are automatically determined by employing a novel meta-heuristic intelligent optimizer known as the seagull optimization algorithm (SOA). Finally, the extracted latent features are imported into a softmax classifier to obtain the results of fault recognition in rolling bearings. Experiments are conducted to validate the effectiveness of the proposed method. The results of analysis indicate that the proposed method not only can achieve a high identification accuracy for different bearing health conditions, but also outperforms some representative deep learning methods.     

基于密集连接时延神经网络的说话人识别算法*

说话人识别技术是一项重要的生物特征识别技术。近年来,使用深度神经网络提取发声特征的说话人识别算法取得了突出成果。时延神经网络作为其中的典型代表之一已被证明具有出色的特征提取能力。为进一步提升识别准确率并节约计算资源,通过对现有的说话人识别算法进行研究,提出一种带有注意力机制的密集连接时延神经网络用于说话人识别。密集连接的网络结构在增强不同网络层之间的信息复用的同时能有效控制模型体积。通道注意力机制和帧注意力机制帮助网络聚焦于更关键的细节特征,使得通过统计池化提取出的说话人特征更具有代表性。实验结果表明,在VoxCeleb1测试数据集上取得了1.40%的等错误率（EER）和0.15的最小检测代价标准（DCF）,证明了在说话人识别任务上的有效性。     

Fault Diagnosis of Permanent Magnet Synchronous Motor Based on Stacked Denoising Autoencoder

As a complex field-circuit coupling system comprised of electric, magnetic and thermal machines, the permanent magnet synchronous motor of the electric vehicle has various operating conditions and complicated condition environment. There are various forms of failure, and the signs of failure are crossed or overlapped. Randomness, secondary, concurrency and communication characteristics make it difficult to diagnose faults. Meanwhile, the common intelligent diagnosis methods have low accuracy, poor generalization ability and difficulty in processing high-dimensional data. This paper proposes a method of fault feature extraction for motor based on the principle of stacked denoising autoencoder (SDAE) combined with the support vector machine (SVM) classifier. First, the motor signals collected from the experiment were processed, and the input data were randomly damaged by adding noise. Furthermore, according to the experimental results, the network structure of stacked denoising autoencoder was constructed, the optimal learning rate, noise reduction coefficient and the other network parameters were set. Finally, the trained network was used to verify the test samples. Compared with the traditional fault extraction method and single autoencoder method, this method has the advantages of better accuracy, strong generalization ability and easy-to-deal-with high-dimensional data features.     

A neural-network method for the synthesis of informative features for the classification of signal sources in cognitive radio systems

This paper discusses possible methods for the synthesis of informative features for the classification of signal sources in cognitive radio systems using artificial neural networks. A synthesis method based on the use of autoassociative neural networks is proposed. From the point of view of the classification of the signals, informativeness of synthesized features is estimated using a modified artificial neural network based on radial basis functions that contains an additional self-organizing layer of neurons that provide the automatic selection of the variance of basis functions and a significant reduction of the network dimension. It is shown that the use of autoassociative networks in the problem of the classification of signal sources makes it possible to synthesize the feature space with a minimum dimension while maintaining separation properties.     

基于深度聚类的目标细粒度分类方法北大核心CSCD

为提高光电系统对弱小目标的识别和分类能力,降低算法对硬件平台和数据的依赖,提出一种无监督分类方法−基于目标深度特征聚类的细粒度分类方法。该方法通过轮廓、颜色、对比度等浅层特征提取提示目标,经超分辨处理后,利用卷积神经网络对目标的深层特征进行编码,进一步采用基于注意机制的主成分分析方法进行降维生成表征矩阵,最后利用聚类的方式实现目标细粒度分类。实验验证了基于不同神经网络的深度聚类方法在不同数据集上的分类性能,其中采用ResNet-34聚类方法在CIFAR-10测试集上细粒度分类性能达92.71%,结果表明,基于深度聚类的目标细粒度方法能够取得与强监督学习方法相当的目标分类效果。此外,还可以根据不同簇数和聚类等级的选择实现不同细粒度的分类效果。     

基于卷积神经网络与特征融合的天气识别方法

在太阳能热水器及太阳能电池等太阳能发电领域,下雨、下雪、阴天等气候因素将严重影响发电效果,而太阳能随动系统工作也必须消耗能量,所以迅速判断当前的天气状况,并设计自适应的开关随动系统极其重要。当天气状况为阴雨或者雪天时,系统应当关闭从而减少能耗。鉴于传统的天气识别方法效率低、准确度差、计算量大的问题,在公开的天气图像基础上创建了一个具有多种类别的天气分类集,并提供了一种基于卷积神经网络与特征融合的天气图像识别技术。通过采用传统方式获取图像的颜色、纹理、形状3种特征作为整个模型的底层特征,在原本的VGG16(visual geometry group-16)模型基础上进行了改进,从而提取图像的深层特征,最后将底层特征与深层特征融合起来在Softmax上进行输出,总识别率达到94%。     

Boosting COVID-19 Image Classification Using MobileNetV3 and Aquila Optimizer Algorithm

Currently, the world is still facing a COVID-19 (coronavirus disease 2019) classified as a highly infectious disease due to its rapid spreading. The shortage of X-ray machines may lead to critical situations and delay the diagnosis results, increasing the number of deaths. Therefore, the exploitation of deep learning (DL) and optimization algorithms can be advantageous in early diagnosis and COVID-19 detection. In this paper, we propose a framework for COVID-19 images classification using hybridization of DL and swarm-based algorithms. The MobileNetV3 is used as a backbone feature extraction to learn and extract relevant image representations as a DL model. As a swarm-based algorithm, the Aquila Optimizer (Aqu) is used as a feature selector to reduce the dimensionality of the image representations and improve the classification accuracy using only the most essential selected features. To validate the proposed framework, two datasets with X-ray and CT COVID-19 images are used. The obtained results from the experiments show a good performance of the proposed framework in terms of classification accuracy and dimensionality reduction during the feature extraction and selection phases. The Aqu feature selection algorithm achieves accuracy better than other methods in terms of performance metrics.     

基于磁共振图像和改进的UNet++模型区分阿尔茨海默症患者和健康人群

阿尔茨海默症（Alzheimer's Disease，AD）是一种神经退行性疾病，高效准确的早期诊断对其治疗至关重要．本文提出了一种融合多语义级别的深度卷积神经网络结构，基于磁共振图像，用于区分AD患者与正常受试者的方法．首先，在传统UNet++网络的基础上改进了深度监督整合算法；然后，构建了一种新的特征融合结构，进一步细化了不同语义级别的特征；最后，基于不同组织区域（白质、灰质和脑脊液）的磁共振图像，使用本文所提出的方法区分AD患者和正常受试者，并探究了从不同组织获得的信息对分类准确率的影响．实验结果表明，使用本文提出的方法区分两类人群的最高准确率为98.74%，平均准确率为98.47%，高于目前文献报道的其他方法．     

残差网络分层融合的高光谱地物分类

高光谱图像具有较高的空间分辨率,蕴含着丰富的空间光谱信息,近年来被广泛用于城市地物分类中。在高光谱图像分类过程中,空间光谱特征的提取直接影响着分类精度;传统的高光谱图像特征提取方法只利用了4或8邻域的像素进行简单卷积处理,因而丢失了大量的复杂、有效信息;卷积神经网络（CNN）虽然可以自动提取空间光谱特征,在保留图像空间信息的同时,简化网络模型,但是,随着网络深度增加,网络分类产生退化现象,而且网络间缺乏相关信息的互补性,从而影响分类精度。该工作引入CNN自动提取空间光谱特征,并且针对CNN深度增加所导致的退化问题,设计了面向地物分类的高光谱特征融合残差网络。首先,为了降低高光谱图像的光谱冗余度,利用PCA提取主要光谱波段;然后,为了逐级提取光谱图像的空间光谱特征,定义了卷积核为16,32,64的低、中、高3层残差网络模块,并利用64个1×1的卷积核对3层特征输出进行卷积,完成维度匹配与特征图融合;接着,对融合后的特征图进行全局平均池化(GAP)生成用于分类的特征向量;最后,引入具有可调节机制的Large-Margin Softmax损失函数,监督模型完成训练过程,实现高光谱图像分类。实验采用Indian Pines,University of Pavia和Salinas地区的高光谱图像来验证方法有效性,设置批次训练的样本集为100,网络训练的初始学习率为0.1,当损失函数稳定后学习率降低为0.001,动量为0.9,权重延迟为0.000 1,最大训练迭代次数为2×104,当3个数据集的样本块像素分别设置为25×25,23×23,27×27,网络深度分别为28,32和28时,3个数据集的分类准确率最高,其平均总体准确率（OA）为98.75%、平均准确率（AA）的评价值为98.1%,平均Kappa系数为0.98。实验结果表明,基于残差网络的分类方法能够自动学习更丰富的空间光谱特征,残差网络层数的增加和不同网络层融合可以提高高光谱分类精度;Large-Margin Softmax实现了类内紧凑和类间分离,可以进一步提高高光谱图像分类精度。     

A knowledge-driven feature learning and integration method for breast cancer diagnosis on multi-sequence MRI

BackgroundThe classification of benign versus malignant breast lesions on multi-sequence Magnetic Resonance Imaging (MRI) is a challenging task since breast lesions are heterogeneous and complex. Recently, deep learning methods have been used for breast lesion diagnosis with raw image input. However, without the guidance of domain knowledge, these data-driven methods cannot ensure that the features extracted from images are comprehensive for breast cancer diagnosis. Specifically, these features are difficult to relate to clinically relevant phenomena.PurposeInspired by the cognition process of radiologists, we propose a Knowledge-driven Feature Learning and Integration (KFLI) framework, to discriminate between benign and malignant breast lesions using Multi-sequences MRI.MethodsStarting from sequence division based on characteristics, we use domain knowledge to guide the feature learning process so that the feature vectors of sub-sequence are constrained to lie in characteristic-related semantic space. Then, different deep networks are designed to extract various sub-sequence features. Furthermore, a weighting module is employed for the integration of the features extracted from different sub-sequence images adaptively.ResultsThe KFLI is a domain knowledge and deep network ensemble, which can extract sufficient and effective features from each sub-sequence for a comprehensive diagnosis of breast cancer. Experiments on 100 MRI studies have demonstrated that the KFLI achieves sensitivity, specificity, and accuracy of 84.6%, 85.7% and 85.0%, respectively, which outperforms other state-of-the-art algorithms.     

可见-近红外光谱的古陶瓷断代分类识别

为客观、有效对古陶瓷进行无损断代,提出了一种基于可见-近红外光谱古陶瓷断代分类识别方法。耀州窑古陶瓷跨代较多,且不同朝代之间具有物理相似性,因此耀州窑的断代具有一定的挑战性。以耀州窑为研究对象,在采用紫外-可见-近红外光谱分析仪获取古陶瓷不同朝代的多光谱数据的基础上,提出基于分数阶微分对光谱数据进行预处理,避免微分预处理常用的一阶微分和二阶微分遗漏中间过渡信息,同时压制并消除光谱数据中的背景信息和噪声干扰。实验结果表明,未进行微分处理(0阶)时,耀州窑不同年代古陶瓷的分类准确率仅为84.8%,而基于不同分数阶微分的分类准确率均较0阶明显高,分数阶微分的最优阶数为0.7阶。另外,提出基于深度信念网络对不同朝代古陶瓷进行断代分类,首先采用层叠的受限玻尔兹曼机(RBM)对深度网络进行预训练,提取光谱数据高层特征以消除光谱数据中的冗余特征。实验结果表明,光谱数据经RBM降维之前特征间的相关系数为0.885 7,经第一层和第二层RBM降维后的相关系数分别为0.544 6和0.391 5,特征间的相关性明显下降,冗余度明显减少。然后将RBM预训练得到的权值参数对BP神经网络进行初始化,并对深度信念网络进行微调,在克服BP神经网络因随机初始化权值参数而陷入局部最优局限性的同时,提升网络训练主动性。实验可得,深度信念网络的最优RBM数量为2,RBM隐藏层最优节点数为100。最后,为避免小样本数据基于深度信念网络进行训练易出现过拟合,提出了一种Dropout随机丢弃策略,在深度信念网络训练阶段以一定概率随机让网络某些隐含层节点的权重不工作,以减少网络训练过程特征之间的相互依赖性,实验可得当Dropout丢弃比例为0.45时,分类性能最高。采用所提方法,耀州窑不同朝代古陶瓷分类的平均准确率为93.5%,而耀州窑五代时期的分类识别率最高为96.3%。通过与同类古陶瓷断代分析方法的客观定量对比,表明所提方法有效、可行,为古陶瓷的断代提供了新方法。