53 Hits in 4.8 sec

SPCBIG-EC: A Robust Serial Hybrid Model for Smart Contract Vulnerability Detection

Lejun Zhang, Yuan Li, Tianxing Jin, Weizheng Wang, Zilong Jin, Chunhui Zhao, Zhennao Cai, Huiling Chen
2022 Sensors  
We propose a flexible and systematic hybrid model, which we call the Serial-Parallel Convolutional Bidirectional Gated Recurrent Network Model incorporating Ensemble Classifiers (SPCBIG-EC).  ...  Numerous experiments showed that SPCBIG-EC is better than most existing methods.  ...  This paper proposed an ensemble learning (EL)-based contract vulnerability prediction method, which is based on seven different neural networks using contract vulnerability data for contract-level vulnerability  ... 
doi:10.3390/s22124621 pmid:35746403 pmcid:PMC9231163 fatcat:4fcgncb5xzcpjhey5tl6q72vly

CBGRU: A Detection Method of Smart Contract Vulnerability Based on a Hybrid Model

Lejun Zhang, Weijie Chen, Weizheng Wang, Zilong Jin, Chunhui Zhao, Zhennao Cai, Huiling Chen
2022 Sensors  
, BiLSTM, CNN, BiGRU).  ...  There has been an explosion in the number of smart contracts, and at the same time, the security of smart contracts has received widespread attention because of the financial losses caused by smart contract  ...  Duan J et al. proposed a hybrid neural network model (MLCN and BiGRU-ATT) that combines the multilayer convolutional neural network (MLCNN) and the bidirectional gated recurrent unit (BiGRU) with the attention  ... 
doi:10.3390/s22093577 pmid:35591263 pmcid:PMC9104336 fatcat:c64cpqpvszh73if6grco2mnyrq

Deep Convolutional Neural Network with RNNs for Complex Activity Recognition Using Wrist-Worn Wearable Sensor Data

Sakorn Mekruksavanich, Anuchit Jitpattanakul
2021 Electronics  
S-HAR has shown that deep learning (DL), a type of machine learning based on complicated artificial neural networks, has a significant degree of recognition efficiency.  ...  Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are two different types of DL methods that have been successfully applied to the S-HAR challenge in recent years.  ...  the proposed CNN-BiGRU for sensor-based HAR in this section.  ... 
doi:10.3390/electronics10141685 fatcat:zvruy7iqkfbvvll4eml7cw2lca

A Threat Intelligence Analysis Method Based on Feature Weighting and BERT-BiGRU for Industrial Internet of Things

Jingchen Yan, Zhe Du, Jifang Li, Shiduo Yang, Jinghao Li, Jianbin Li, Xun Yi
2022 Security and Communication Networks  
Therefore, this study proposes an IIoT threat intelligence analysis method based on feature weighting and BERT-BiGRU.  ...  In this method, BERT-BiGRU is used to classify attack behavior and attack strategy.  ...  Facing the increasingly severe security situation, a new network security defense mechanism driven by threat intelligence has emerged.  ... 
doi:10.1155/2022/7729456 fatcat:d2rdwzpe2jdopdrfba57z43pzi

HCovBi-Caps: Hate Speech Detection using Convolutional and Bi-Directional Gated Recurrent Unit with Capsule Network

Shakir Khan, Ashraf Kamal, Mohd Fazil, Mohammed Ali Alshara, Vineet Kumar Sejwal, Reemiah Muneer Alotaibi, Abdulrauf Baig, Salihah Alqahtani
2022 IEEE Access  
This study presents a novel Convolutional, BiGRU, and Capsule network-based deep learning model, HCovBi-Caps, to classify the hate speech.  ...  The hate speech problem on online social networks (OSNs) is also widespread. The existing literature has machine learning approaches for hate speech detection on OSNs.  ...  [42] : In this paper, authors uses a stack of BiGRU and capsule network layers to detect HS on tweets. • Roy et al. [31] : Authors use deep CNN for detecting HS or NHS on tweets.  ... 
doi:10.1109/access.2022.3143799 fatcat:n7vhnxineveddnlghpjdvh22iy

Joint Hierarchical Semantic Clipping and Sentence Extraction for Document Summarization

Wanying Yan, Junjun Guo
2020 Journal of Information Processing Systems  
Extractive document summarization aims to select a few sentences while preserving its main information on a given document, but the current extractive methods do not consider the sentence-information repeat  ...  Specifically, a hierarchical selective encoding network is constructed for both sentence-level and documentlevel document representations, and data containing important information is extracted on news  ...  ( 4 ) 4 SummaRunner: This model is a recurrent neural network model based on a sequence classifier.  ... 
doi:10.3745/jips.04.0181 dblp:journals/jips/YanG20 fatcat:4b755cvpvzemndotvbw5nxje3a

A Concurrent Fault Diagnosis Method of Transformer Based on Graph Convolutional Network and Knowledge Graph

Liqing Liu, Bo Wang, Fuqi Ma, Quan Zheng, Liangzhong Yao, Chi Zhang, Mohamed A. Mohamed
2022 Frontiers in Energy Research  
Therefore, in this paper, a concurrent fault diagnosis method is proposed for power equipment based on graph neural networks and knowledge graphs.  ...  First, an electrical equipment failure knowledge map is created based on operational and maintenance records to emphasize the relevance of the failed equipment or component.  ...  The structure of the BiGRU-Attention model is shown in Figure 4. Based on BiGRU, the attention mechanism is introduced in the BiGRU-Attention model to find words.  ... 
doi:10.3389/fenrg.2022.837553 fatcat:ji6j7cbhavdqpofppxy7d4c3me

A Deep-Learning Intelligent System Incorporating Data Augmentation for Short-Term Voltage Stability Assessment of Power Systems [article]

Yang Li, Meng Zhang, Chen Chen
2021 arXiv   pre-print
Facing the difficulty of expensive and trivial data collection and annotation, how to make a deep learning-based short-term voltage stability assessment (STVSA) model work well on a small training dataset  ...  Third, to extract temporal dependencies from the post-disturbance dynamic trajectories of a system, a bi-directional gated recurrent unit with attention mechanism based assessment model is established,  ...  In view of this situation, this paper puts forward a deep adversarial data augmentation technique based on LSGAN such that the BiGRU-Attention-based STVSA model is able to be applicable to small training  ... 
arXiv:2112.03265v1 fatcat:2ogg7kkmsrhmzkofwy4ledzbku

Flood Discharge Prediction Based on Remote-Sensed Spatiotemporal Features Fusion and Graph Attention

Chen Chen, Dingbin Luan, Song Zhao, Zhan Liao, Yang Zhou, Jiange Jiang, Qingqi Pei
2021 Remote Sensing  
Based on this situation, this paper abstracts the rainfall data into the graph structure data, uses remote sensing images to extract the elevation information, introduces the graph attention mechanism  ...  to extract the spatial characteristics of rainfall, and employs long-term and short-term memory (LSTM) network to fuse the spatial and temporal characteristics for flood prediction.  ...  Acknowledgments: These authors would like to thank the Xi'an Key Laboratory of Mobile Edge Computing and Security. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/rs13245023 fatcat:7qz5aeylhzgylfwnbcclkggwxq

A Bidirectional Context-Aware and Multi-Scale Fusion Hybrid Network for Short-Term Traffic Flow Prediction

Zhixing CHEN, Guizhou ZHENG
2022 Promet (Zagreb)  
Short-term traffic flow prediction is to automatically predict the traffic flow changes in a period of future time based on the extraction of the spatiotemporal features in the road network.  ...  However, previous methods based on deep learning are mainly limited to temporal features and have so far failed to predict the bidirectional con-textual spatiotemporal relationship correctly.  ...  A multi-scale short-term traffic flow prediction model based on wavelet transform is designed in [12] , while parametric model lacks the generalisation ability.  ... 
doi:10.7307/ptt.v34i3.3957 fatcat:txku2w4r4nc6ta6zrnnhryl7tq

Novel Spatiotemporal Feature Extraction Parallel Deep Neural Network for Forecasting Confirmed Cases of Coronavirus Disease 2019 [article]

Chiou-Jye Huang, Yamin Shen, Ping-Huan Kuo, Yung-Hsiang Chen
2020 medRxiv   pre-print
The prediction results acquired from COVID-19Net were compared to those obtained using a CNN, GRU, and CNN-GRU.  ...  This study proposed a novel deep neural network framework, COVID-19Net, which parallelly combines a convolutional neural network (CNN) and bidirectional gated recurrent units (GRUs).  ...  1D-CNN [32], a 2D-291 CNN [33] , and BiGRUs to form a mixed deep learning network.  ... 
doi:10.1101/2020.04.30.20086538 fatcat:hrz57ntmirh5fnd2jud2t52v7i

Multi-features based Semantic Augmentation Networks for Named Entity Recognition in Threat Intelligence [article]

Peipei Liu, Hong Li, Zuoguang Wang, Jie Liu, Yimo Ren, Hongsong Zhu
2022 arXiv   pre-print
contextual clues based on a large-scale general field corpus.  ...  Extracting cybersecurity entities such as attackers and vulnerabilities from unstructured network texts is an important part of security analysis.  ...  Accurate and speedy NER can be beneficial for researchers to carry out security analysis and assessment as well as enhance the real-time and precision of network security situation awareness.  ... 
arXiv:2207.00232v1 fatcat:vqmmkvdlsrf6pogijydxnhpdyq

A Review of Data-Driven Short-Term Voltage Stability Assessment of Power Systems: Concept, Principle, and Challenges

Jiting Cao, Meng Zhang, Yang Li, Jun Peng
2021 Mathematical Problems in Engineering  
With the rapid growth of power market reform and power demand, the power transmission capacity of a power grid is approaching its limit and the secure and stable operation of power systems becomes increasingly  ...  This article comprehensively sorts out the STVS problems of power systems from the perspective of data-driven methods and discusses existing challenges.  ...  Reference [35] proposed a pre-fault STVS prediction method based on support vector machines.  ... 
doi:10.1155/2021/5920244 fatcat:bqa2hfkej5bhhflyqoan2ake3m

Network Intrusion Detection Model Based on CNN and GRU

Bo Cao, Chenghai Li, Yafei Song, Yueyi Qin, Chen Chen
2022 Applied Sciences  
Then, the spatial features are extracted by using a convolutional neural network, and further extracted by fusing Averagepooling and Maxpooling, using attention mechanism to assign different weights to  ...  A network intrusion detection model that fuses a convolutional neural network and a gated recurrent unit is proposed to address the problems associated with the low accuracy of existing intrusion detection  ...  Network Intrusion Detection Model Based on CNN and GRU. Figure 1 . 1 Figure 1. Network Intrusion Detection Model Based on CNN and GRU.  ... 
doi:10.3390/app12094184 doaj:310e0902ff4c4bec802a56e9aa096ede fatcat:n2tairkcivgqpproqivlrvlesi

Multilayer Graph-Based Deep Learning Approach for Stock Price Prediction

Mohammed Ali Alshara
2022 Security and Communication Networks  
The experiment compares several distinct neural network algorithms. This approach is more accurate than the previous method when ideal parameters are used.  ...  Although a strategy for predicting stock prices using relational data has been described recently, no practical way for selecting aggregating various forms of relational data to forecast stock prices has  ...  References [19, 20] presented a novel Convolutional, BiGRU, and Capsule network-based deep learning model, HCovBi-Caps, to classify the hate speech, and multichannel CNN modeling is discussed in [21  ... 
doi:10.1155/2022/5200110 doaj:793cafef95974cf49b6ad74b4f94b69b fatcat:vv6pewz72zbkzav2k7th5lrpea
« Previous Showing results 1 — 15 out of 53 results