针对步态周期检测直接影响到步态识别的计算量和精度的问题,本文基于深卷积神经网络实现步态周期检测,分别通过将步态序列根据周期性进行分类,和将步态序列拟合为正弦函数进行步态周期性检测的方法,对步态周期进行建模.其关键思想是根据步态周期的规律性,将步态起伏作为分类问题或一个正弦函数来建模,步态视频中的每个帧对应一个可以表示其周期特征的类别或函数值.而卷积神经网络被用于提取步态帧的周期性特征,以定位该帧在周期中的位置,得到分类或回归结果,最终实现步态周期检测.在CASIA-B数据集的不同视角下采用了多种网络结构进行了周期检测效果的验证.实验结果表明:该方法对步态周期性检测具有良好的精度和鲁棒性.

Gait recognition has significant potential for remote human identification, but it is easily influenced by identityunrelated factors such as clothing, carrying conditions, and view angles. Many gait templates have been presented that can effectively represent gait features. Each gait template has its advantages and can represent different prominent information. In this paper, gait template fusion is proposed to improve the classical representative gait template (such as a gait energy image) which represents incomplete information that is sensitive to changes in contour. We also present a partition method to reflect the different gait habits of different body parts of each pedestrian. The fused template is cropped into three parts (head, trunk, and leg regions) depending on the human body, and the three parts are then sent into the convolutional neural network to learn merged features. We present an extensive empirical evaluation of the CASIA-B dataset and compare the proposed method with existing ones. The results show good accuracy and robustness of the proposed method for gait recognition.

Facing the complex marine environment, it is extremely challenging to conduct underwater acoustic target feature extraction and recognition using ship-radiated noise. In this paper, firstly, taking the one-dimensional time-domain raw signal of the ship as the input of the model, a new deep neural network model for underwater target recognition is proposed. Depthwise separable convolution and time-dilated convolution are used for passive underwater acoustic target recognition for the first time. The proposed model realizes automatic feature extraction from the raw data of ship radiated noise and temporal attention in the process of underwater target recognition. Secondly, the measured data are used to evaluate the model, and cluster analysis and visualization analysis are performed based on the features extracted from the model. The results show that the features extracted from the model have good characteristics of intra-class aggregation and inter-class separation. Furthermore, the cross-folding model is used to verify that there is no overfitting in the model, which improves the generalization ability of the model. Finally, the model is compared with traditional underwater acoustic target recognition, and its accuracy is significantly improved by 6.8%.

This paper proposes a new detection model of a weak signal based on a third-order chaotic system. Using a dynamic analysis tool, such as the Lyapunov exponent and the bifurcation diagram, variations of dynamic behavior can be observed, and the weak signal underwater can be picked up. In order to improve the observability of detection signals in the time domain and frequency domain, the spectral entropy complexity algorithm (SE) and C-0 complexity algorithms are used to analyze and extract the weak signal. The experimental results show that the spectrum extraction based on the complexity algorithm can accurately reflect the dynamic characteristics of the detected signal. It provides the theoretical direction and experimental data support for the application of the chaotic system in the field of acoustic detection.

As a unique and promising biometric, video-based gait recognition has broad applications. The key step of this methodology is to learn the walking pattern of individuals, which, however, often suffers challenges to extract the behavioral feature from a sequence directly. Most existing methods just focus on either the appearance or the motion pattern. To overcome these limitations, we propose a sequential convolutional network (SCN) from a novel perspective, where spatiotemporal features can be learned by a basic convolutional backbone. In SCN, behavioral information extractors (BIE) are constructed to comprehend intermediate feature maps in time series through motion templates where the relation between frames can be analyzed, thereby distilling the information of the walking pattern. Furthermore, a multi-frame aggregator in SCN performs feature integration on a sequence whose length is uncertain, via a mobile 3D convolutional layer. To demonstrate the effectiveness, experiments have been conducted on two popular public benchmarks, CASIA-B and OU-MVLP, and our approach is demonstrated excellent performance, comparing with the state-of-art methods.

Facing the complex marine environment, it is extremely challenging to conduct underwater acoustic target recognition (UATR) using ship-radiated noise. Inspired by neural mechanism of auditory perception, this paper provides a new deep neural network trained by original underwater acoustic signals with depthwise separable convolution (DWS) and time-dilated convolution neural network, named auditory perception inspired time-dilated convolution neural network (ATCNN), and then implements detection and classification for underwater acoustic signals. The proposed ATCNN model consists of learnable features extractor and integration layer inspired by auditory perception, and time-dilated convolution inspired by language model. This paper decomposes original time-domain ship-radiated noise signals into different frequency components with depthwise separable convolution filter, and then extracts signal features based on auditory perception. The deep features are integrated on integration layer. The time-dilated convolution is used for long-term contextual modeling. As a result, like language model, intra-class and inter-class information can be fully used for UATR. For UATR task, the classification accuracy reaches 90.9%, which is the highest in contrast experiment. Experimental results show that ATCNN has great potential to improve the performance of UATR classification.

The method for synthesizing Gait Energy Image (GEI) is to use the silhouettes overlay of a pedestrian gait cycle, whereas, it is difficult to obtain the silhouettes of a pedestrian gait cycle in practical applications, due to many factors such as pedestrian occlusion and pedestrian direction change, etc. In addition, the existing gait cycle detection methods suffer from limitations. Therefore, a Nonstandard Periodic Gait Energy Image (NP-GEI) is proposed in this paper, which is synthesized without gait cycle detection. And it is verified that the CNN trained by NP-GEI can achieve the same recognition accuracy as that by CP-GEI in most cases. Moreover, we also verify that the CNN, trained by various NP-GEIs which is synthesized by different frame-number silhouettes, can recognize the GEI with robustness in single-view and multi-view scenarios. Finally, a data augmentation method is developed based on NP-GEI, and an experiment is provided to verify the effectiveness of this proposed method.

[This corrects the article DOI: 10.1371/journal.pone.0203824.].

This paper presents a regression approach to gait periodicity detection via fitting gait sequence to a sine function by deep convolutional neural networks. The key idea is to model the gait fluctuation as a sinusoidal function because of similar periodic regularity. Each frame of the gait video corresponds to a function value that can represent its periodic features. Convolutional network serves to learn and locate a frame in a gait cycle. To the best of our knowledge, it is the first work based on deep neural networks for gait period detection in the literature. An extensive empirical evaluation is provided on the CASIA-B dataset in terms of different views and network architectures with comparison to the existing works. The results show the good accuracy and robustness of the proposed method for gait periodicity detection.

It is becoming increasingly clear that major malignancies such as breast, colorectal and gastric cancers are not single disease entities, but comprising multiple cancer subtypes of distinct molecular properties. Molecular subtyping has been widely used to dissect inter-tumor biological heterogeneity, in relation to clinical outcomes. A key step of this methodology is to perform unsupervised classification of gene expression profiles, which, however, often suffers challenges of high-dimensionality, feature redundancy as well as noise and irrelevant information. To overcome these limitations, we propose ELM-CC, which employs hidden observation features obtained from extreme learning machines (ELMs) for cancer classification. To demonstrate the effectiveness and usefulness, we applied ELM-CC for gastric and ovarian cancer subtyping. Comparing with the widely-used consensus clustering method, our approach demonstrated much better clustering performance and identified molecular subtypes that are much more clinically relevant.

The fault detection (FD) reduced-order filtering problem is investigated for a family of polytopic uncertain discrete-time Markovian jump linear systems (MJLSs) with time-varying delays. Under meeting the control precision requirements of the complex systems, the reduced-order fault detection filter can improve the efficiency of the fault detection. Then, by the aid of the Markovian Lyapunov function and convex polyhedron techniques, some novel time-varying delays and polytopic uncertain sufficient conditions in terms of linear matrix inequality (LMI) are proposed to insure the existence of the FD reduced-order filter. Finally, an illustrative example is provided to verify the usefulness of the given method.

The classification and recognition technology of underwater acoustic signal were always an important research content in the field of underwater acoustic signal processing. Currently, wavelet transform, Hilbert-Huang transform, and Mel frequency cepstral coefficients are used as a method of underwater acoustic signal feature extraction. In this paper, a method for feature extraction and identification of underwater noise data based on CNN and ELM is proposed. An automatic feature extraction method of underwater acoustic signals is proposed using depth convolution network. An underwater target recognition classifier is based on extreme learning machine. Although convolution neural networks can execute both feature extraction and classification, their function mainly relies on a full connection layer, which is trained by gradient descent-based; the generalization ability is limited and suboptimal, so an extreme learning machine (ELM) was used in classification stage. Firstly, CNN learns deep and robust features, followed by the removing of the fully connected layers. Then ELM fed with the CNN features is used as the classifier to conduct an excellent classification. Experiments on the actual data set of civil ships obtained 93.04% recognition rate; compared to the traditional Mel frequency cepstral coefficients and Hilbert-Huang feature, recognition rate greatly improved.