scholarly journals Text Sentiment Classification Based on Feature Fusion

2020 ◽  
Vol 34 (4) ◽  
pp. 515-520
Author(s):  
Chen Zhang ◽  
Qingxu Li ◽  
Xue Cheng
Keyword(s):  
Hybrid Model ◽  
Short Term Memory ◽  
Feature Fusion ◽  
Contextual Information ◽  
Sentiment Classification ◽  
Global Features ◽  
Softmax Classifier ◽  
Parallel Hybrid ◽  
Local And Global Features ◽  
Lstm Network

The convolutional neural network (CNN) and long short-term memory (LSTM) network are adept at extracting local and global features, respectively. Both can achieve excellent classification effects. However, the CNN performs poorly in extracting the global contextual information of the text, while LSTM often overlooks the features hidden between words. For text sentiment classification, this paper combines the CNN with bidirectional LSTM (BiLSTM) into a parallel hybrid model called CNN_BiLSTM. Firstly, the CNN was adopted to extract the local features of the text quickly. Next, the BiLSTM was employed to obtain the global text features containing contextual semantics. After that, the features extracted by the two neural networks (NNs) were fused, and processed by Softmax classifier for text sentiment classification. To verify its performance, the CNN_BiLSTM was compared with single NNs like CNN and LSTM, as well as other deep learning (DL) NNs through experiments. The experimental results show that the proposed parallel hybrid model outperformed the contrastive methods in F1-score and accuracy. Therefore, our model can solve text sentiment classification tasks effectively, and boast better practical value than other NNs.

scholarly journals Extraction of local and global features by a convolutional neural network–long short-term memory network for diagnosing bearing faults

2021 ◽  
pp. 095440622110165
Author(s):  
Zhang Chao ◽  
Wang Wei-zhi ◽  
Zhang Chen ◽  
Fan Bin ◽  
Wang Jian-guo ◽  
...  
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Condition Monitoring ◽  
Short Term Memory ◽  
Vibration Signal ◽  
Short Term ◽  
Global Features ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Lstm Network

Accurate and reliable fault diagnosis is one of the key and difficult issues in mechanical condition monitoring. In recent years, Convolutional Neural Network (CNN) has been widely used in mechanical condition monitoring, which is also a great breakthrough in the field of bearing fault diagnosis. However, CNN can only extract local features of signals. The model accuracy and generalization of the original vibration signals are very low in the process of vibration signal processing only by CNN. Based on the above problems, this paper improves the traditional convolution layer of CNN, and builds the learning module (local feature learning block, LFLB) of the local characteristics. At the same time, the Long Short-Term Memory (LSTM) is introduced into the network, which is used to extract the global features. This paper proposes the new neural network—improved CNN-LSTM network. The extracted deep feature is used for fault classification. The improved CNN-LSTM network is applied to the processing of the vibration signal of the faulty bearing collected by the bearing failure laboratory of Inner Mongolia University of science and technology. The results show that the accuracy of the improved CNN-LSTM network on the same batch test set is 98.75%, which is about 24% higher than that of the traditional CNN. The proposed network is applied to the bearing data collection of Western Reserve University under the condition that the network parameters remain unchanged. The experiment shows that the improved CNN-LSTM network has better generalization than the traditional CNN.

scholarly journals A Context-Aware Location Recommendation System for Tourists Using Hierarchical LSTM Model

2020 ◽  
Vol 12 (10) ◽  
pp. 4107
Author(s):  
Wafa Shafqat ◽  
Yung-Cheol Byun
Keyword(s):  
Recommendation System ◽  
Short Term Memory ◽  
Contextual Information ◽  
Optimal Size ◽  
Effective Parameters ◽  
Travel History ◽  
Proposed Model ◽  
Processing Information ◽  
Lstm Network ◽  
Gated Recurrent Unit

The significance of contextual data has been recognized by analysts and specialists in numerous disciplines such as customization, data recovery, ubiquitous and versatile processing, information mining, and management. While a generous research has just been performed in the zone of recommender frameworks, by far most of the existing approaches center on prescribing the most relevant items to customers. It usually neglects extra-contextual information, for example time, area, climate or the popularity of different locations. Therefore, we proposed a deep long-short term memory (LSTM) based context-enriched hierarchical model. This proposed model had two levels of hierarchy and each level comprised of a deep LSTM network. In each level, the task of the LSTM was different. At the first level, LSTM learned from user travel history and predicted the next location probabilities. A contextual learning unit was active between these two levels. This unit extracted maximum possible contexts related to a location, the user and its environment such as weather, climate and risks. This unit also estimated other effective parameters such as the popularity of a location. To avoid feature congestion, XGBoost was used to rank feature importance. The features with no importance were discarded. At the second level, another LSTM framework was used to learn these contextual features embedded with location probabilities and resulted into top ranked places. The performance of the proposed approach was elevated with an accuracy of 97.2%, followed by gated recurrent unit (GRU) (96.4%) and then Bidirectional LSTM (94.2%). We also performed experiments to find the optimal size of travel history for effective recommendations.

Fine reconstruction of underwater images for environmental feature fusion

2021 ◽  
Vol 18 (5) ◽  
pp. 172988142110396
Author(s):  
Tao Xu ◽  
Jiyong Zhou ◽  
Wentao Guo ◽  
Lei Cai ◽  
Yukun Ma
Keyword(s):  
Image Reconstruction ◽  
Feature Fusion ◽  
Image Data ◽  
Target Feature ◽  
Global Features ◽  
Data Set ◽  
Underwater Image ◽  
Reconstruction Methods ◽  
Local And Global Features ◽  
Underwater Target

Complicated underwater environments, such as occlusion by foreign objects and dim light, causes serious loss of underwater targets feature. Furthermore, underwater ripples cause target deformation, which greatly increases the difficulty of feature extraction. Then, existing image reconstruction models cannot effectively achieve target reconstruction due to insufficient underwater target features, and there is a blurred texture in the reconstructed area. To solve the above problems, a fine reconstruction of underwater images with the target feature missing from the environment feature was proposed. Firstly, the salient features of underwater images are obtained in terms of positive and negative sample learning. Secondly, a layered environmental attention mechanism is proposed to retrieve the relevant local and global features in the context. Finally, a coarse-to-fine image reconstruction model, with gradient penalty constraints, is constructed to obtain the fine restoration results. Contrast experiment between the proposed algorithm and the existing image reconstruction methods has been done in stereo quantitative underwater image data set, real-world underwater image enhancement data set, and underwater image data set, clearly proving that the proposed one is more effective and superior.

scholarly journals Intrusion Detection System in the Advanced Metering Infrastructure: A Cross-Layer Feature-Fusion CNN-LSTM-Based Approach

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 626
Author(s):  
Ruizhe Yao ◽  
Ning Wang ◽  
Zhihui Liu ◽  
Peng Chen ◽  
Xianjun Sheng
Keyword(s):  
Intrusion Detection ◽  
Short Term Memory ◽  
Feature Fusion ◽  
Detection System ◽  
Memory Function ◽  
Cross Layer ◽  
Advanced Metering Infrastructure ◽  
Global Features ◽  
Network Intrusion ◽  
Advanced Metering

Among the key components of a smart grid, advanced metering infrastructure (AMI) has become the preferred target for network intrusion due to its bidirectional communication and Internet connection. Intrusion detection systems (IDSs) can monitor abnormal information in the AMI network, so they are an important means by which to solve network intrusion. However, the existing methods exhibit a poor ability to detect intrusions in AMI, because they cannot comprehensively consider the temporal and global characteristics of intrusion information. To solve these problems, an AMI intrusion detection model based on the cross-layer feature fusion of a convolutional neural networks (CNN) and long short-term memory (LSTM) networks is proposed in the present work. The model is composed of CNN and LSTM components connected in the form of a cross-layer; the CNN component recognizes regional features to obtain global features, while the LSTM component obtain periodic features by memory function. The two types of features are aggregated to obtain comprehensive features with multi-domain characteristics, which can more accurately identify intrusion information in AMI. Experiments based on the KDD Cup 99 and NSL-KDD datasets demonstrate that the proposed cross-layer feature-fusion CNN-LSTM model is superior to other existing methods.

scholarly journals Short-Term Forecasting of Photovoltaic Power Generation Based on Feature Selection and Bias Compensation–LSTM Network

Energies ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 3086
Author(s):  
Cai Tao ◽  
Junjie Lu ◽  
Jianxun Lang ◽  
Xiaosheng Peng ◽  
Kai Cheng ◽  
...  
Keyword(s):  
Power Generation ◽  
Feature Selection ◽  
Hybrid Model ◽  
Prediction Error ◽  
Prediction Accuracy ◽  
Short Term Memory ◽  
Feature Selection Method ◽  
Short Term ◽  
Lstm Network ◽  
Bias Compensation

In this paper, a hybrid model that considers both accuracy and efficiency is proposed to predict photovoltaic (PV) power generation. To achieve this, improved forward feature selection is applied to obtain the optimal feature set, which aims to remove redundant information and obtain related features, resulting in a significant improvement in forecasting accuracy and efficiency. The prediction error is irregularly distributed. Thus, a bias compensation–long short-term memory (BC–LSTM) network is proposed to minimize the prediction error. The experimental results show that the new feature selection method can improve the prediction accuracy by 0.6% and the calculation efficiency by 20% compared to using feature importance identification based on LightGBM. The BC–LSTM network can improve accuracy by 0.3% using about twice the time compared with the LSTM network, and the hybrid model can further improve prediction accuracy and efficiency based on the BC–LSTM network.

scholarly journals Noisy Multipath Parallel Hybrid Model for Remaining Useful Life Estimation (NMPM)

2020 ◽  
Vol 12 (1) ◽  
pp. 10
Author(s):  
Ali AlDulaimi ◽  
Arash Mohammadi ◽  
Amir Asif
Keyword(s):  
Neural Networks ◽  
Hybrid Model ◽  
Short Term Memory ◽  
Sequence Data ◽  
Remaining Useful Life ◽  
Life Estimation ◽  
Parallel Path ◽  
Temporal Features ◽  
Parallel Hybrid ◽  
Useful Life

The parallel hybrid models of different deep neural networks architectures are the most promising approaches for remaining useful life (RUL) estimation. In light of that, this paper introduces for the first time in the literature a new parallel hybrid deep neural network (DNN) solution for RUL estimation, named as the Noisy Multipath Parallel Hybrid Model for Remaining Useful Life Estimation (NMPM). The proposed framework comprises of three parallel paths, the first one utilizes a noisy Bidirectional Long-short term memory (BLSTM) that used for extracting temporal features and learning the dependencies of sequence data in two directions, forward and backward, which can benefit completely from the input data. While the second parallel path employs noisy multilayer perceptron (MLP) that consists of three layers to extract different class of features. The third parallel path utilizes noisy convolutional neural networks (CNN) to extract another class of features. The concatenated output of the previous parallel paths is then fed into a noisy fusion center (NFC) to predict the RLU. The NMPM has been trained based on a noisy training to enhance the generalization behavior, as well as strengthen the model accuracy and robustness. The NMPM framework is tested and evaluated by using CMAPSS dataset provided by NASA.

scholarly journals A Multichannel Model for Microbial Key Event Extraction Based on Feature Fusion and Attention Mechanism

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Peng Li ◽  
Qian Wang
Keyword(s):  
Sentiment Analysis ◽  
Feature Fusion ◽  
Attention Mechanism ◽  
Event Extraction ◽  
Semantic Features ◽  
Analysis Model ◽  
Global Features ◽  
Public Health Emergencies ◽  
Multimodal Information ◽  
Local And Global Features

In order to further mine the deep semantic information of the microbial text of public health emergencies, this paper proposes a multichannel microbial sentiment analysis model MCMF-A. Firstly, we use word2vec and fastText to generate word vectors in the feature vector embedding layer and fuse them with lexical and location feature vectors; secondly, we build a multichannel layer based on CNN and BiLSTM to extract local and global features of the microbial text; then we build an attention mechanism layer to extract the important semantic features of the microbial text; thirdly, we merge the multichannel output in the fusion layer and use soft; finally, the results are merged in the fusion layer, and a surtax function is used in the output layer for sentiment classification. The results show that the F1 value of the MCMF-A sentiment analysis model reaches 90.21%, which is 9.71% and 9.14% higher than the benchmark CNN and BiLSTM models, respectively. The constructed dataset is small in size, and the multimodal information such as images and speech has not been considered.

A Joint Approach to Detect Malicious URL Based on Attention Mechanism

2019 ◽  
Vol 18 (03) ◽  
pp. 1950021
Author(s):  
Yongfang Peng ◽  
Shengwei Tian ◽  
Long Yu ◽  
Yalong Lv ◽  
Ruijin Wang
Keyword(s):  
Short Term Memory ◽  
Local Features ◽  
Attention Mechanism ◽  
Global Features ◽  
Combined Model ◽  
Lexical Information ◽  
Softmax Classifier ◽  
Joint Approach ◽  
Deep Learning Model ◽  
Better Than

To improve the accuracy and automation of malware Uniform Resource Locator (URL) recognition, a joint approach of Convolutional neural network (CNN) and Long-short term memory (LSTM) based on the Attention mechanism (JCLA) is proposed to identify and detect malicious URL. Firstly, the URL features including texture information, lexical information and host information are extracted and filtered, and pre-processed with encode. Then, the feature matrix more relevant to the output are chose according to the weight of the attention mechanism and input to the constructed parallel processing model called CNN_LSTM, combinating CNN and LSTM to get local features. Next, the extracted local features are merged to calculate the global features of the URLs to be detected. Finally, the URLs are classified by the SoftMax classifier using global features, the accuracy of the model in malicious URL recgonition is 98.26%. The experimental results show that the JCLA model proposed in this paper is better than the traditional deep learning model or CNN_LSTM combined model for detecting malicious URLs.

scholarly journals Palmprint Authentication System Based on Local and Global Feature Fusion Using DOST

2014 ◽  
Vol 2014 ◽  
pp. 1-11 ◽  
Author(s):  
N. B. Mahesh Kumar ◽  
K. Premalatha
Keyword(s):  
Feature Fusion ◽  
Personal Identification ◽  
Identification System ◽  
Global Information ◽  
Global Feature ◽  
Global Features ◽  
Global Matching ◽  
Local And Global Features ◽  
Physical Stimuli ◽  
Stockwell Transform

Palmprint is the region between wrist and fingers. In this paper, a palmprint personal identification system is proposed based on the local and global information fusion. The local and global information is critical for the image observation based on the results of the relationship between physical stimuli and perceptions. The local features of the enhanced palmprint are extracted using discrete orthonormal Stockwell transform. The global feature is obtained by reducing the scale of discrete orthonormal Stockwell transform to infinity. The local and global matching distances of the two palmprint images are fused to get the final matching distance of the proposed scheme. The results show that the fusion of local and global features outperforms the existing works on the available three datasets.

scholarly journals Multidimensional CNN-LSTM Network for Automatic Modulation Classification

Electronics ◽  
2021 ◽  
Vol 10 (14) ◽  
pp. 1649
Author(s):  
Na Wang ◽  
Yunxia Liu ◽  
Liang Ma ◽  
Yang Yang ◽  
Hongjun Wang
Keyword(s):  
Short Term Memory ◽  
Modulation Classification ◽  
Short Term ◽  
One Dimensional ◽  
Softmax Classifier ◽  
Automatic Modulation Classification ◽  
Temporal Features ◽  
Long Short Term Memory ◽  
Lstm Network ◽  
Public Datasets

Automatic modulation classification (AMC) is the premise for signal detection and demodulation applications, especially in non-cooperative communication scenarios. It has been a popular topic for decades and has gained significant progress with the development of deep learning methods. To further improve classification accuracy, a hierarchical multifeature fusion (HMF) based on a multidimensional convolutional neural network (CNN)-long short-term memory (LSTM) network is proposed in this paper. First, a multidimensional CNN module (MD-CNN) is proposed for feature compensation between interactive features extracted by two-dimensional convolutional filters and respective features extracted by one-dimensional filters. Second, learnt features of the MD-CNN module are fed into an LSTM layer for further exploitation of temporal features. Finally, classification results are obtained by the Softmax classifier. The effectiveness of the proposed method is verified by abundant experimental results on two public datasets, RadioML.2016.10a and RadioML.2016.10b. Satisfying results are obtained as compared with state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document