Bendong Zhao

Convolutional neural networks for time series classification

Time series classification is an important task in time series data mining, and has attracted great interests and tremendous efforts during last decades. However, it remains a challenging problem due to the nature of time series data: high dimensionality, large in data size and updating continuously. The deep learning techniques are explored to improve the performance of traditional feature-based approaches. Specifically, a novel convolutional neural network (CNN) framework is proposed for time series classification. Different from other feature-based classification approaches, CNN can discover and extract the suitable internal structure to generate deep features of the input time series automatically by using convolution and pooling operations. Two groups of experiments are conducted on simulated data sets and eight groups of experiments are conducted on real-world data sets from different application domains. The final experimental results show that the proposed method outperforms state-of-the-art methods for time series classification in terms of the classification accuracy and noise tolerance.

Micromotion dynamics and geometrical shape parameters estimation of exoatmospheric infrared targets

Abstract. The micromotion dynamics and geometrical shape are considered to be essential characteristics for exoatmospheric targets discrimination. Many methods have been investigated to retrieve the micromotion features using radar signals returned from targets of a given shape. We explore a way of jointly estimating micromotion dynamics and geometrical shape parameters from the infrared (IR) signals of targets in remote detection distance. It is found that the micromotion dynamics of the target would induce a periodic fluctuating variation on the IR irradiance intensity signature. In addition to the micromotion characteristics, the fluctuation could also reflect target structure properties, which offer a possible clue in extracting the features of micromotion dynamics and geometrical shape. Thus, the data model of target IR irradiance intensity signatures induced by micromotion patterns including spinning, coning, and tumbling is developed, and a method of parameters estimation based on joint optimization analysis techniques is proposed. Experimental results demonstrated that the parameters of target micromotion dynamics and geometrical shape can be effectively estimated using the proposed method, if the input signature contains multiple dominant frequency components.

Ballistic targets micro-motion and geometrical shape parameters estimation from sparse decomposition representation of infrared signatures

Micro-motion dynamics and geometrical shape are considered to be essential evidence for infrared (IR) ballistic target recognition. However, it is usually hard or even impossible to describe the geometrical shape of an unknown target with a finite number of parameters, which results in a very difficult task to estimate target micro-motion parameters from the IR signals. Considering the shapes of ballistic targets are relatively simple, this paper explores a joint optimization technique to estimate micro-motion and dominant geometrical shape parameters from sparse decomposition representation of IR irradiance intensity signatures. By dividing an observed target surface into a number of segmented patches, an IR signature of the target can be approximately modeled as a linear combination of the observation IR signatures from the dominant segmented patches. Given this, a sparse decomposition representation of the IR signature is established with the dictionary elements defined as each segmented patchs IR signature. Then, an iterative optimization method, based on the batch second-order gradient descent algorithm, is proposed to jointly estimate target micro-motion and geometrical shape parameters. Experimental results demonstrate that the micro-motion and geometrical shape parameters can be effectively estimated using the proposed method, when the noise of the IR signature is in an acceptable level, for example, SNR>0  dB.

Nutation characteristics analysis and infrared signature simulation of ballistic targets

Nutation characteristics are the important evidence to classify ballistic targets in the missile defense. Current nutation researches are mainly on the targets of the rotational symmetric mass distribution. However, in fact a little bit of asymmetric tolerances of the mass distribution would induce a large difference in nutation characteristics and result in classification errors. This article does an extension study on the nutation dynamics taking asymmetric tolerances into account, analyzes the nutation characteristics and establishes the infrared (IR) irradiance signature simulation model of ballistic targets. It is found that the asymmetric spinning target would form an elliptic coning motion with a time-varying angular velocity due to the existence of cross-coupling effects; IR signatures of different nutation types can be described into a unified data generative model, which enhances the abilities to analyze nutation data and helps to improve the accuracy of target classification.

Heterogeneous area extraction based on background suppression and adaptive clustering

Infrared small target detection is an extremely challenging problem, especially under a complex background. Generally, targets can be easily detected by some simple and fast algorithms in the homogeneous area, but in the heterogeneous area, advanced and complicated algorithms are always needed. Therefore, heterogeneous area extraction is an important task for us to use different detection methods in different backgrounds to achieve simplifying computation while maintaining high detection performance. In this paper, a novel heterogeneous area extraction approach is proposed. Firstly, a traditional background suppression algorithm named mean filter is used to detect a group of interesting points. Then, a new adaptive clustering algorithm based on region growing is proposed to cluster the interesting points into several clusters. Finally, heterogeneous areas can be determined according to the size of cluster and the density of interesting points in the cluster. Experimental results show that our proposed method can extract heterogeneous areas of any size quickly and accurately.

Waveforms classification based on convolutional neural networks

A novel waveforms classification method based on convolutional neural networks (CNN) is proposed in this paper. Firstly, convolution and pooling operations are cross used for generating deep features, and then fully connected to the output layer for classification. Different from other traditional approaches which need human-designed features, CNN can discover and extract the suitable internal structure of the input waveform to obtain deep features for classification automatically. So that the generalization ability of this method is significantly improved comparing to other methods. Experimental results show that CNN can obtain state of the art performance for waveforms classification in terms of classification accuracy and noise tolerance.

Point Target Detection in Space-Based Infrared Imaging System Based on Multi-Direction Filtering Fusion

Point target detection in space-based infrared (IR) imaging system is an important task in many applications such as IR searching and tracking and remote sensing. Although it has attracted great interest and tremendous efforts during last decades, it remains a challenging problem due to the uncertain heterogeneous background and the limited processing resources on the planet. Aiming at this problem, a novel background suppression method based on multi-direction filtering fusion is proposed in this paper. The process of background prediction for each pixel by this method can be divided into two steps. Firstly, eight predicted values are obtained by using linear filtering methods along eight different directions respectively. Then, Gaussian weighted sum of the eight predicted values is computed to generate the final result. We conduct several groups of experiments on different categories scenes with simulated targets, and the final experimental results demonstrate that our methods can not only obtain state-of-the-art performance on background suppression (especially for heterogeneous backgrounds), but also detect targets accurately with low false alarm rate and high speed in IR point target detection tasks.

Micro-motion dynamic and geometric parameters estimation of exo-atmospheric infrared targets

The motion dynamics and geometric information are considered to be one of the most useful features for infrared (IR) targets recognition. Especially for the exo-atmospheric target, when a target undergoes micro-motion dynamics in the outer space, such as mechanical vibrations or rotations, it would induce amplitude modulations on signature of target projected area along the Line-of-Sight (LOS) of IR detection. The aim of this article is to estimate micro-motion dynamics and geometric parameters from the amplitude signature of target projected area. For that, we introduce a projection model of exo-atmospheric targets, derive formulas of signature induced by targets with spinning, tumbling and coning motion, and estimate related target parameters with heuristic optimization techniques. By analyzing the estimated results, we confirmed the effective-ness of our estimation procedures.