Earthquake Magnitude Prediction using Spatia-temporal Features Learning Based on Hybrid CNN- BiLSTM Model

Kavianpour, Parisa; Kavianpour, Mohammadreza; Jahani, Ehsan; Ramazani, Amin

doi:10.1109/icspis54653.2021.9729358

Cited by 8 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CNN-BiLSTM model leverages the CNN layers for local feature extraction from the input sequence, which are then passed to the BiLSTM layer for capturing long-term dependencies [31].…”

Section: Cnn-bilstmmentioning

confidence: 99%

Detecting Unknown Vulnerabilities in Smart Contracts with the CNN-BiLSTM Model

Gu,

Wang,

et al. 2024

Preprint

View full text Add to dashboard Cite

Smart contracts, fundamental to blockchain technology, are extensively utilized in diverse fields such as finance, supply chain management, and beyond. Nevertheless, their capability to handle significant transactions and their unchangeable nature, once deployed, bring about substantial risks, potentially leading to severe security breaches and financial losses. Unfortunately, existing research primarily focuses on known vulnerabilities, leaving the realm of unknown vulnerabilities largely unexplored. This article aims to address this gap by introducing an innovative approach that capitalizes on the similarities between known and unknown vulnerabilities. We propose a groundbreaking CNN-BiLSTM model meticulously designed to identify features of known vulnerabilities and employ them to detect unknown vulnerabilities. Our innovative methodology intricately gathers opcode sequences generated during smart contract execution using Geth instrumentation and meticulously analyzes them. Rigorous experiments validate the effectiveness of the model in detecting unknown vulnerabilities. This innovative approach represents a significant advancement in blockchain security by providing proactive measures to strengthen smart contract security against potential threats.

show abstract

“…The CNN-BiLSTM model leverages the CNN layers for local feature extraction from the input sequence, which are then passed to the BiLSTM layer for capturing long-term dependencies [31].…”

Section: Cnn-bilstmmentioning

confidence: 99%

Detecting Unknown Vulnerabilities in Smart Contracts with the CNN-BiLSTM Model

Gu,

Wang,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The optimal values of µ = 1 and γ = 0.05 are determined through experimental investigations. In the training phase, the network's parameters are initialized using the Xavier initializer [52], and the Adam optimizer [53] is employed for the training process. The datasets are partitioned into training, validation, and test sets, with proportions of 80%, 10%, and 10%, respectively.…”

Section: Implementation Detailsmentioning

confidence: 99%

A class alignment method based on graph convolution neural network for bearing fault diagnosis in presence of missing data and changing working conditions

Kavianpour

Ramezani²,

Beheshti³

2022

Measurement

View full text Add to dashboard Cite

“…Machine learning approach has better in handling nonstationary data especially earthquake dataset. However, the model produced by machine learning techniques have limitations, particularly the shallow recognition of earthquakes features and the needs of applying complex feature engineering or model optimization to produce adequate predictive results [8]. Furthermore, most of the studies related to earthquake or disaster mitigation tend to predict the probability of the occurrence time or the number of events in the future.…”

Section: Introductionmentioning

confidence: 99%

LUTanh Activation Function to Optimize BI-LSTM in Earthquake Forecasting

2024

IJIES

View full text Add to dashboard Cite

Earthquakes, as unpredictable and potentially catastrophic events, have long captured the attention of geophysicists due to their profound impact on communities. The devastating consequences of these events underscore the critical need for early earthquake prediction systems capable of forecasting location, magnitude, and depth. With the rapid advancements in technology, particularly in the fields of data science, earthquake prediction methods have undergone significant evolution. This study introduces a proposed method that modified ReLU (Rectified Linear Unit) called LUTanh (Linear Unit Hyperbolic Tangent) which combine both benefits of ReLU and Tanh activation functions. This study applied and compared the proposed method performance in long short-term memory (LSTM) and Bidirectional LSTM (Bi-LSTM) algorithms for predicting earthquake disaster. Furthermore, this proposed method was tested in architecture of multiple input multiple output (MIMO) principle in predicting the occurrence of earthquake disaster. The evaluation results decisively reveal that the LUTanh applied in Bi-LSTM model, particularly when optimized with the Adam optimizer, consistently outperforms the LSTM counterpart. Error assessments of LUTanh in Bi-LSTM consistently demonstrate lower average error scores compared to the origin ReLU activation function up to 4% of mean absolute error (MAE) and 3% of mean square error (MSE).

show abstract

Earthquake Magnitude Prediction using Spatia-temporal Features Learning Based on Hybrid CNN- BiLSTM Model

Cited by 8 publications

References 17 publications

Detecting Unknown Vulnerabilities in Smart Contracts with the CNN-BiLSTM Model

Detecting Unknown Vulnerabilities in Smart Contracts with the CNN-BiLSTM Model

A class alignment method based on graph convolution neural network for bearing fault diagnosis in presence of missing data and changing working conditions

LUTanh Activation Function to Optimize BI-LSTM in Earthquake Forecasting

Contact Info

Product

Resources

About