RNN-based Classifiers Research Articles

Hyperspectral Image Classification Using Attention-Based Bidirectional Long Short-Term Memory Network

Deep neural networks have been widely applied to hyperspectral image (HSI) classification areas, in which recurrent neural network (RNN) is one of the most typical networks. Most of the existing RNN-based classifiers treat the spectral signature of pixels as an ordered sequence, in which only unidirectional correlation along the wavelength direction of adjacent bands is considered. However, each band image is related to not only its preceding band images but also its successive band images. In order to fully explore such bidirectional spectral correlation within an HSI, in this article, a bidirectional long short-term memory (Bi-LSTM)-based network is designed for HSI classification. Moreover, a spatial&#x2013;spectral attention mechanism is designed and implemented in the proposed Bi-LSTM network to emphasize the effective information and reduce the redundant information among spatial&#x2013;spectral context of pixels, by which the performance of classification can be greatly improved. Experimental results over three benchmark HSIs, i.e., Salinas Valley, Pavia Centre, and Pavia University, demonstrate that our proposed Bi-LSTM obviously outperforms several state-of-the-art unidirectional RNN-based classification algorithms. Moreover, the proposed spatial&#x2013;spectral attention mechanism can further improve the classification accuracy of our proposed Bi-LSTM algorithm by effectively weighting spatial and spectral context of pixels. The source code of the proposed Bi-LSTM algorithm is available at <uri>https://github.com/MeiShaohui/Attention-based-Bidirectional-LSTM-Network</uri>.

Recognition of Multifunction Radars Via Hierarchically Mining and Exploiting Pulse Group Patterns

Recognition of multifunction radar (MFR) is an open problem in the field of electronic intelligence. Parameters of MFR pulses are generally agile and difficult to distinguish statistically. A prospective way to realize credible MFR recognition is mining and exploiting more distinguishable high-dimensional patterns buried in pulse groups, which may be designed for implementing infrequently used radar modes such as target tracking. A high-dimensional pattern is defined according to the agile range and switching law of sequential pulse repetitive intervals within a pulse group. This article establishes deep recurrent neural networks (RNN) to discriminate and coarsely cluster different pulse groups hierarchically with respect to their sequential structures. Afterwards, RNN-based classifiers are trained to extract and exploit features within different pulse group clusters. Distinct degrees of confidence are then attached to these classifiers to indicate the discriminabilities of the corresponding pulse group clusters. The pulse group clustering and classifying models are finally cascaded to form an integrated classification model, which mines distinguishable patterns from sequentially arriving pulse groups of the same radar and accumulate them to realize MFR recognition. Simulation results demonstrate the much improved performance of the proposed method over existing counterparts in different scenarios.

Deep Neural Network for Robust Modulation Classification Under Uncertain Noise Conditions

Recently, classifying the modulation schemes of signals using deep neural network has received much attention. In this paper, we introduce a general model of deep neural network (DNN)-based modulation classifiers for single-input single-output (SISO) systems. Its feasibility is analyzed using maximum a posteriori probability (MAP) criterion and its robustness to uncertain noise conditions is compared to that of the conventional maximum likelihood (ML)-based classifiers. To reduce the design and training cost of DNN classifiers, a simple but effective pre-processing method is introduced and adopted. Furthermore, featuring multiple recurrent neural network (RNN) layers, the DNN modulation classifier is realized. Simulation results show that the proposed RNN-based classifier is robust to the uncertain noise conditions, and the performance of it approaches to that of the ideal ML classifier with perfect channel and noise information. Moreover, with a much lower complexity, it outperforms the existing ML-based classifiers, specifically, expectation maximization (EM) and expectation conditional maximization (ECM) classifiers which iteratively estimate channel and noise parameters. In addition, the proposed classifier is shown to be invariant to the signal distortion such as frequency offset. Furthermore, the adopted pre-processing method is shown to accelerate the training process of our proposed classifier, thus reducing the training cost. Lastly, the computational complexity of our proposed classifier is analyzed and compared to other traditional ones, which further demonstrates its overall advantage.

Supervised methods to extract clinical events from cardiology reports in Italian.

Clinical narratives are a valuable source of information for both patient care and biomedical research. Given the unstructured nature of medical reports, specific automatic techniques are required to extract relevant entities from such texts. In the natural language processing (NLP) community, this task is often addressed by using supervised methods. To develop such methods, both reliably-annotated corpora and elaborately designed features are needed. Despite the recent advances on corpora collection and annotation, research on multiple domains and languages is still limited. In addition, to compute the features required for supervised classification, suitable language- and domain-specific tools are needed. In this work, we propose a novel application of recurrent neural networks (RNNs) for event extraction from medical reports written in Italian. To train and evaluate the proposed approach, we annotated a corpus of 75 cardiology reports for a total of 4365 mentions of relevant events and their attributes (e.g., the polarity). For the annotation task, we developed specific annotation guidelines, which are provided together with this paper. The RNN-based classifier was trained on a training set including 3335 events (60 documents). The resulting model was integrated into an NLP pipeline that uses a dictionary lookup approach to search for relevant concepts inside the text. A test set of 1030 events (15 documents) was used to evaluate and compare different pipeline configurations. As a main result, using the RNN-based classifier instead of the dictionary lookup approach allowed increasing recall from 52.4% to 88.9%, and precision from 81.1% to 88.2%. Further, using the two methods in combination, we obtained final recall, precision, and F1 score of 91.7%, 88.6%, and 90.1%, respectively. These experiments indicate that integrating a well-performing RNN-based classifier with a standard knowledge-based approach can be a good strategy to extract information from clinical text in non-English languages.

Classification of snoring sound based on a recurrent neural network

Snoring is a sleep disorder that may have adverse effects on an individual's health and social activities. Polysomnography is the most common way to diagnose snoring but involves considerable time and cost. Many recent studies have attempted to classify snoring and non-snoring. However, since the length, frequency, and period of snoring episodes (SE) differ according to the individual being measured, it is very difficult to develop a general reference point to classify snoring. Therefore, in order to classify different snoring patterns and noise for different individuals, a learning-based snoring classification algorithm is essential. To this end, this study proposes a classification method based on a recurrent neural network (RNN) that can classify SEs and non-snoring episodes (NSEs) by learning the features of an individual's SEs and NSEs, measured in daily life based on the subjects’ sleep recordings using smartphone. The method proposed in this study can be largely divided into segmentation, feature extraction, and classification. The performance of this study was evaluated through statistical parameters. Despite the fact that the proposed RNN-based classifiers were trained using a relative small dataset, they exhibited an extremely high accuracy of 98.9%.

Deep Recurrent Neural Network for Agricultural Classification using multitemporal SAR Sentinel-1 for Camargue, France

The development and improvement of methods to map agricultural land cover are currently major challenges, especially for radar images. This is due to the speckle noise nature of radar, leading to a less intensive use of radar rather than optical images. The European Space Agency Sentinel-1 constellation, which recently became operational, is a satellite system providing global coverage of Synthetic Aperture Radar (SAR) with a 6-days revisit period at a high spatial resolution of about 20 m. These data are valuable, as they provide spatial information on agricultural crops. The aim of this paper is to provide a better understanding of the capabilities of Sentinel-1 radar images for agricultural land cover mapping through the use of deep learning techniques. The analysis is carried out on multitemporal Sentinel-1 data over an area in Camargue, France. The data set was processed in order to produce an intensity radar data stack from May 2017 to September 2017. We improved this radar time series dataset by exploiting temporal filtering to reduce noise, while retaining as much as possible the fine structures present in the images. We revealed that even with classical machine learning approaches (K nearest neighbors, random forest, and support vector machines), good performance classification could be achieved with F-measure/Accuracy greater than 86% and Kappa coefficient better than 0.82. We found that the results of the two deep recurrent neural network (RNN)-based classifiers clearly outperformed the classical approaches. Finally, our analyses of the Camargue area results show that the same performance was obtained with two different RNN-based classifiers on the Rice class, which is the most dominant crop of this region, with a F-measure metric of 96%. These results thus highlight that in the near future these RNN-based techniques will play an important role in the analysis of remote sensing time series.