DIANet: Dense-and-Implicit Attention Network

Attention networks have successfully boosted the performance in various vision problems. Previous works lay emphasis on designing a new attention module and individually plug them into the networks. Our paper proposes a novel-and-simple framework that shares an attention module throughout different network layers to encourage the integration of layer-wise information and this parameter-sharing module is referred to as Dense-and-Implicit-Attention (DIA) unit. Many choices of modules can be used in the DIA unit. Since Long Short Term Memory (LSTM) has a capacity of capturing long-distance dependency, we focus on the case when the DIA unit is the modified LSTM (called DIA-LSTM). Experiments on benchmark datasets show that the DIA-LSTM unit is capable of emphasizing layer-wise feature interrelation and leads to significant improvement of image classification accuracy. We further empirically show that the DIA-LSTM has a strong regularization ability on stabilizing the training of deep networks by the experiments with the removal of skip connections (He et al. 2016a) or Batch Normalization (Ioffe and Szegedy 2015) in the whole residual network.

Download Full-text

Mobile sensor based human activity recognition: distinguishing of challenging activities by applying long short-term memory deep learning modified by residual network concept

Biomedical Engineering Letters ◽

10.1007/s13534-020-00160-x ◽

2020 ◽

Vol 10 (3) ◽

pp. 419-430

Author(s):

Seyed Vahab Shojaedini ◽

Mohamad Javad Beirami

Keyword(s):

Deep Learning ◽

Activity Recognition ◽

Human Activity ◽

Short Term Memory ◽

Mobile Sensor ◽

Residual Network ◽

Short Term ◽

Term Memory ◽

Network Concept ◽

Long Short Term Memory

Download Full-text

Using a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) to Classify Network Attacks

Information ◽

10.3390/info11050243 ◽

2020 ◽

Vol 11 (5) ◽

pp. 243 ◽

Cited By ~ 1

Author(s):

Pramita Sree Muhuri ◽

Prosenjit Chatterjee ◽

Xiaohong Yuan ◽

Kaushik Roy ◽

Albert Esterline

Keyword(s):

Neural Network ◽

Intrusion Detection ◽

Recurrent Neural Network ◽

Classification Accuracy ◽

Short Term Memory ◽

Short Term ◽

Term Memory ◽

Long Short Term Memory ◽

Multi Class Classification ◽

Optimal Feature

An intrusion detection system (IDS) identifies whether the network traffic behavior is normal or abnormal or identifies the attack types. Recently, deep learning has emerged as a successful approach in IDSs, having a high accuracy rate with its distinctive learning mechanism. In this research, we developed a new method for intrusion detection to classify the NSL-KDD dataset by combining a genetic algorithm (GA) for optimal feature selection and long short-term memory (LSTM) with a recurrent neural network (RNN). We found that using LSTM-RNN classifiers with the optimal feature set improves intrusion detection. The performance of the IDS was analyzed by calculating the accuracy, recall, precision, f-score, and confusion matrix. The NSL-KDD dataset was used to analyze the performances of the classifiers. An LSTM-RNN was used to classify the NSL-KDD datasets into binary (normal and abnormal) and multi-class (Normal, DoS, Probing, U2R, and R2L) sets. The results indicate that applying the GA increases the classification accuracy of LSTM-RNN in both binary and multi-class classification. The results of the LSTM-RNN classifier were also compared with the results using a support vector machine (SVM) and random forest (RF). For multi-class classification, the classification accuracy of LSTM-RNN with the GA model is much higher than SVM and RF. For binary classification, the classification accuracy of LSTM-RNN is similar to that of RF and higher than that of SVM.

Download Full-text

Collaborative Local-Global Learning for Temporal Action Proposal

ACM Transactions on Intelligent Systems and Technology ◽

10.1145/3466181 ◽

2021 ◽

Vol 12 (5) ◽

pp. 1-14

Author(s):

Yisheng Zhu ◽

Hu Han ◽

Guangcan Liu ◽

Qingshan Liu

Keyword(s):

Short Term Memory ◽

Background Suppression ◽

Global Learning ◽

Short Term ◽

Term Memory ◽

Temporal Intervals ◽

Benchmark Datasets ◽

Long Short Term Memory ◽

Temporal Action

Temporal action proposal generation is an essential and challenging task in video understanding, which aims to locate the temporal intervals that likely contain the actions of interest. Although great progress has been made, the problem is still far from being well solved. In particular, prevalent methods can handle well only the local dependencies (i.e., short-term dependencies) among adjacent frames but are generally powerless in dealing with the global dependencies (i.e., long-term dependencies) between distant frames. To tackle this issue, we propose CLGNet, a novel Collaborative Local-Global Learning Network for temporal action proposal. The majority of CLGNet is an integration of Temporal Convolution Network and Bidirectional Long Short-Term Memory, in which Temporal Convolution Network is responsible for local dependencies while Bidirectional Long Short-Term Memory takes charge of handling the global dependencies. Furthermore, an attention mechanism called the background suppression module is designed to guide our model to focus more on the actions. Extensive experiments on two benchmark datasets, THUMOS’14 and ActivityNet-1.3, show that the proposed method can outperform state-of-the-art methods, demonstrating the strong capability of modeling the actions with varying temporal durations.

Download Full-text

Detecting Multiple Speech Disfluencies Using a Deep Residual Network with Bidirectional Long Short-Term Memory

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ◽

10.1109/icassp40776.2020.9053893 ◽

2020 ◽

Author(s):

Tedd Kourkounakis ◽

Amirhossein Hajavi ◽

Ali Etemad

Keyword(s):

Short Term Memory ◽

Residual Network ◽

Short Term ◽

Term Memory ◽

Long Short Term Memory

Download Full-text

Radar High-Resolution Range Profile Ship Recognition Using Two-Channel Convolutional Neural Networks Concatenated with Bidirectional Long Short-Term Memory

Remote Sensing ◽

10.3390/rs13071259 ◽

2021 ◽

Vol 13 (7) ◽

pp. 1259

Author(s):

Chih-Lung Lin ◽

Tsung-Pin Chen ◽

Kuo-Chin Fan ◽

Hsu-Yung Cheng ◽

Chi-Hung Chuang

Keyword(s):

Neural Network ◽

High Resolution ◽

Short Term Memory ◽

Target Recognition ◽

Short Term ◽

Long Distance ◽

Term Memory ◽

Adjacent Structures ◽

Long Short Term Memory ◽

Ship Recognition

Radar automatic target recognition is a critical research topic in radar signal processing. Radar high-resolution range profiles (HRRPs) describe the radar characteristics of a target, that is, the characteristics of the target that is reflected by the microwave emitted by the radar are implicit in it. In conventional radar HRRP target recognition methods, prior knowledge of the radar is necessary for target recognition. The application of deep-learning methods in HRRPs began in recent years, and most of them are convolutional neural network (CNN) and its variants, and recurrent neural network (RNN) and the combination of RNN and CNN are relatively rarely used. The continuous pulses emitted by the radar hit the ship target, and the received HRRPs of the reflected wave seem to provide the geometric characteristics of the ship target structure. When the radar pulses are transmitted to the ship, different positions on the ship have different structures, so each range cell of the echo reflected in the HRRP will be different, and adjacent structures should also have continuous relational characteristics. This inspired the authors to propose a model to concatenate the features extracted by the two-channel CNN with bidirectional long short-term memory (BiLSTM). Various filters are used in two-channel CNN to extract deep features and fed into the following BiLSTM. The BiLSTM model can effectively capture long-distance dependence, because BiLSTM can be trained to retain critical information and achieve two-way timing dependence. Therefore, the two-way spatial relationship between adjacent range cells can be used to obtain excellent recognition performance. The experimental results revealed that the proposed method is robust and effective for ship recognition.

Download Full-text

Open-Circuit Fault Detection and Classification of Modular Multilevel Converters in High Voltage Direct Current Systems (MMC-HVDC) with Long Short-Term Memory (LSTM) Method

Sensors ◽

10.3390/s21124159 ◽

2021 ◽

Vol 21 (12) ◽

pp. 4159

Author(s):

Qinghua Wang ◽

Yuexiao Yu ◽

Hosameldin O. A. Ahmed ◽

Mohamed Darwish ◽

Asoke K. Nandi

Keyword(s):

Neural Networks ◽

Classification Accuracy ◽

Short Term Memory ◽

Short Term ◽

Multilevel Converters ◽

Term Memory ◽

Training Time ◽

High Voltage Direct Current ◽

Modular Multilevel Converters ◽

Long Short Term Memory

Fault detection and classification are two of the challenging tasks in Modular Multilevel Converters in High Voltage Direct Current (MMC-HVDC) systems. To directly classify the raw sensor data without certain feature extraction and classifier design, a long short-term memory (LSTM) neural network is proposed and used for seven states of the MMC-HVDC transmission power system simulated by Power Systems Computer Aided Design/Electromagnetic Transients including DC (PSCAD/EMTDC). It is observed that the LSTM method can detect faults with 100% accuracy and classify different faults as well as provide promising fault classification performance. Compared with a bidirectional LSTM (BiLSTM), the LSTM can get similar classification accuracy, requiring less training time and testing time. Compared with Convolutional Neural Networks (CNN) and AutoEncoder-based deep neural networks (AE-based DNN), the LSTM method can get better classification accuracy around the middle of the testing data proportion, but it needs more training time.

Download Full-text

Semi-Supervised Convolutional Long Short-Term Memory Neural Networks for Time Series Land Cover Classification

Remote Sensing ◽

10.3390/rs13173504 ◽

2021 ◽

Vol 13 (17) ◽

pp. 3504

Author(s):

Jing Shen ◽

Chao Tao ◽

Ji Qi ◽

Hao Wang

Keyword(s):

Remote Sensing ◽

Neural Networks ◽

Time Series ◽

Land Cover ◽

Classification Accuracy ◽

Short Term Memory ◽

Remote Sensing Images ◽

Short Term ◽

Term Memory ◽

Long Short Term Memory

Time series images with temporal features are beneficial to improve the classification accuracy. For abstract temporal and spatial contextual information, deep neural networks have become an effective method. However, there is usually a lack of sufficient samples in network training: one is the loss of images or the discontinuous distribution of time series data because of the inevitable cloud cover, and the other is the lack of known labeled data. In this paper, we proposed a Semi-supervised convolutional Long Short-Term Memory neural network (SemiLSTM) for time series remote sensing images, which was validated on three data sets with different time distributions. It achieves an accurate and automated land cover classification via a small number of labeled samples and a large number of unlabeled samples. Besides, it is a robust classification algorithm for time series optical images with cloud coverage, which reduces the requirements for cloudless remote sensing images and can be widely used in areas that are often obscured by clouds, such as subtropical areas. In conclusion, this method makes full advantage of spectral-spatial-temporal characteristics under the condition of limited training samples, especially expanding time context information to enhance classification accuracy.

Download Full-text