Bidirectional Long Short-term Memory Network Research Articles

Beat-to-beat continuous blood pressure estimation with optimal feature set of PPG and ECG signals using deep recurrent neural networks

Aim: Continuous blood pressure (BP) monitoring can provide invaluable information for cardiovascular disease (CVD) diagnosis. The purpose of this study is to develop a deep recurrent neural network (RNN) model with an optimal feature set of photoplethysmogram (PPG) and electrocardiogram (ECG) signals for continuous BP estimation. Methods: This paper presents a novel deep recurrent neural network (RNN), which consists of 2-layered bidirectional Long Short-term Memory (Bi-LSTM) and 6-layered LSTM networks. It is used to estimate BP based on the optimal feature set of PPG and ECG signals. In this work, the optimal feature set is determined using five different feature selection methods. Results: The proposed method is evaluated based on 660 subjects from the University of California Irvine (UCI) machine learning repository. The RNN model with optimal feature set achieved root mean square error (RMSE) of 3.223 and 1.781 mmHg for systolic BP (SBP) and diastolic BP (DBP), respectively. It also showed mean absolute error (MAE) of 2.514 and 1.383 mmHg for SBP and DBP, respectively. Regarding the British Hypertension Society (BHS) standard, the results attained grade A for the estimation of SBP and DBP. Conclusion: The experimental results suggest that the proposed deep RNN model with an optimal feature set can improve the performance of BP prediction. Thus, it is possible to further apply our proposed method to develop a wearable device for real-time BP monitoring.

Improving flight delays prediction by developing attention-based bidirectional LSTM network

Recently, the significance of accurate aircraft delay forecasting has grown in the aviation sector, which caused multi-billion-dollar losses faced by airlines and airports and passenger loyalty losses. Due to the importance of accurate flight delay prediction for all stakeholders involved, the aviation sector seeks to develop techniques for more robust flight delay prediction. Is quickly becoming an important research issue to improve airport and airline service performance and offer customers dependable travel itineraries. Machine learning techniques have been used in a number of studies to evaluate and resolve issues with flight delay prediction. This paper proposes a framework integrated network called ‘Attention-based Bidirectional long short-term memory’ (ATT-BI-LSTM) for flight delay prediction. The Bidirectional LSTM model extracts the spatial and temporal of the flight network with weather features. The ‘Attention mechanism’ has been proposed to enable the model to discover significant and discriminating features that contribute to categorization. The first stage of the proposed framework is the ‘preprocessing of dataset’ which is performed through two steps. The first step is data transformation using MinMax scaler to reduce the variation in the data. The second step is ‘balancing the dataset’ using SMOTE technique for balancing data. The second stage is the establishment of the ATT-BI-LSTM network through the deep tuning experiments of network structure to identify the best combination of parameters and network architecture. To validate the performance of the proposed framework, a wide network of US domestic flights tested in two scenarios. In Scenario 1, the objective is to predict the delay of flight arrival and departure, by using basic flight features with the weather. In Scenario 2, the objective is to predict the delay of flight arrival, by using basic flight features with departure delays. Simulation results show that in scenario 1, the training accuracy of flights’ delay is 88% in both flight delay arrivals and departure, and the testing accuracies of flights’ delay 83% and 82% in departure and arrival respectively. On the other hand, in scenario 2, testing accuracies are 94.30% and 93.71% in the two datasets respectively. The simulation results show that the ATT-BI-LSTM model outperforms other models found in the literature. Therefore, the developed ATT-BI-LSTM framework can contribute strongly to mitigating flight delays by providing a high accuracy prediction system in real-time monitoring to airport and aviation authorities.

Passenger flow prediction and management method of urban public transport based on SDAE model and improved Bi-LSTM neural network

In the era of big data, the exponentially increasing data volume and emerging technical tools have put forward new requirements for enterprise information management. Therefore, it is of great significance to enhance the core competitiveness of enterprises to explore how big data can empower the innovation of enterprise information management. Intelligent transportation system combines a variety of technologies and applies them to a large-scale transportation management system, so as to make a reasonable dispatch of traffic conditions. Aiming at the problem of the relatively low accuracy of bus passenger flow forecasting with the existing models, a short-term passenger flow prediction model combining Stacked Denoising Auto Encoder (SDAE) and improved bidirectional Long-short Term Memory network (Bi-LSTM) is proposed. First, the SDAE model is used to fill in the missing bus passenger flow data, the characteristics of the bus passenger flow data are effectively utilized, and the data with rich information is used to predict the missing values with high accuracy. Second, Bi-LSTM model combined with attention mechanism is used for short-term bus passenger flow prediction. Considering that the data sequence of bus passenger flow is relatively long and there is a two-way information flow, the BiLSTM neural network is used for prediction tasks, and the influence of key factors is highlighted through attention weights to mine the internal laws of passenger flow data. The experimental results show that the proposed method achieves the lowest prediction error among all the comparison methods in the task of short-term bus passenger flow prediction on the public transportation dataset, with MAE, MRE, and RMSE values of 6.014, 0.052, and 9.874, respectively. These findings confirmed the effectiveness of the new model in the passenger flow prediction field.

Prediction of Lost Circulation in Southwest Chinese Oil Fields Applying Improved WOA-BiLSTM

Drilling hazards can be significantly decreased by anticipating potential mud loss and then putting the right well control measures in place. Therefore, it is critical to provide early estimates of mud loss. To solve this problem, an enhanced WOA (Whale Optimization Algorithm) and a BiLSTM (Bidirectional Long Short Term Memory) optimization based prediction model of lost circulation prior to drilling has been created. In order to minimize the noise in the historical comprehensive logging data, a wavelet filtering technique was first used. Then, according to the nonlinear Spearman rank correlation coefficient between mud loss and logging parameter values from large to small, seven characteristic parameters were preferred, and the sliding window was used to extract the relevant data. Secondly, the number of neurons in the first and second hidden layers, the maximum training time, and the initial learning rate of the BiLSTM model were optimized using the enhanced WOA method. The BiLSTM network was given the acquired superparameters in order to improve the model’s ability to predict occurrences. Finally, the model was trained and tested using the processed data. In comparison to the LSTM model, BiLSTM model, and WOA-BiLSTM model, respectively, the improved WOA-BiLSTM early mud loss prediction in southwest Chinese oil fields suggested in this study beat the others, receiving 22.3%, 18.7%, and 4.9% higher prediction accuracy, respectively.

A bidirectional long short-term memory network for electron density diagnostic with double probe

The double probe method is a plasma in situ diagnostic technology. Compared with Langmuir single probe, it has less influence on the background plasma and can obtain relatively accurate results. However, it can only collect some high-energy electrons in the plasma, and cannot directly measure the electron density (N e). In this paper, a double probe N e diagnosis approach based on Bidirectional Long Short-Term Memory (BLSTM) is proposed. After the training is completed, the accurate prediction of N e can be realized by using the double probe data, which solves the problem that the double probe cannot directly measure N e. In the plasma simulation environment of the laboratory, the plasma source is controlled to generate plasma with different densities, the current–voltage (I–V) characteristic data of the double probe at the same position are used as features, and the N e calculated by the triple probe is used as the label to train the BLSTM model. The mean square error is used as the loss function, the root mean square error (RMSE) and the prediction accuracy (Acc) are used as the evaluation indicators. The BLSTM network is evaluated according to the evaluation indicators and the hyperparameters are adjusted. After about 100 iterations, the RMSE of the BLSTM network to N e can be reduced to about 0.03. The final network is evaluated on a separate test set. The results show that in the range of 2 × 1013m−3–3 × 1014 m−3, the model can predict N e more than 95% accurately. This approach extends the application of the double probe method and is of great significance for improving the accuracy of plasma diagnostic methods. If it is applied to ionospheric plasma diagnosis, it can reduce the amount of data collected by the probe and improve the spatial resolution of ionospheric detection.

Deep Learning-Based Detection Technology for SQL Injection Research and Implementation

Amid the incessant evolution of the Internet, an array of cybersecurity threats has surged at an unprecedented rate. A notable antagonist within this plethora of attacks is the SQL injection assault, a prevalent form of Internet attack that poses a significant threat to web applications. These attacks are characterized by their extensive variety, rapid mutation, covert nature, and the substantial damage they can inflict. Existing SQL injection detection methods, such as static and dynamic detection and command randomization, are principally rule-based and suffer from low accuracy, high false positive (FP) rates, and false negative (FN) rates. Contemporary machine learning research on SQL injection attack (SQLIA) detection primarily focuses on feature extraction. The effectiveness of detection is heavily reliant on the precision of feature extraction, leading to a deficiency in tackling more intricate SQLIA. To address these challenges, we propose a novel SQLIA detection approach harnessing the power of an enhanced TextCNN and LSTM. This method begins by vectorizing the samples in the corpus and then leverages an improved TextCNN to extract local features. It then employs a Bidirectional LSTM (Bi-LSTM) network to decipher the sequence information inherent in the samples. Given LSTM’s modest effectiveness for relatively long sequences, we further integrate an attention mechanism, reducing the distance between any two words in the sequence to one, thereby enhancing the model’s effectiveness. Moreover, pre-trained word vector features acquired via BERT for transfer learning are incorporated into the feature section. Comparative experimental results affirm the superiority of our deep learning-based SQLIA detection approach, as it effectively elevates the SQLIA recognition rate while reducing both FP and FN rates.

Relation extraction in Chinese using attention-based bidirectional long short-term memory networks.

Relation extraction is an important topic in information extraction, as it is used to create large-scale knowledge graphs for a variety of downstream applications. Its goal is to find and extract semantic links between entity pairs in natural language sentences. Deep learning has substantially advanced neural relation extraction, allowing for the autonomous learning of semantic features. We offer an effective Chinese relation extraction model that uses bidirectional LSTM (Bi-LSTM) and an attention mechanism to extract crucial semantic information from phrases without relying on domain knowledge from lexical resources or language systems in this study. The attention mechanism included into the Bi-LSTM network allows for automatic focus on key words. Two benchmark datasets were used to create and test our models: Chinese SanWen and FinRE. The experimental results show that the SanWen dataset model outperforms the FinRE dataset model, with area under the receiver operating characteristic curve values of 0.70 and 0.50, respectively. The models trained on the SanWen and FinRE datasets achieve values of 0.44 and 0.19, respectively, for the area under the precision-recall curve. In addition, the results of repeated modeling experiments indicated that our proposed method was robust and reproducible.

Non-destructive detection method for wheat freshness degree based on delayed luminescence

Accurate identification to freshness degree is one of the preconditions for secure storage of wheat. Up to now, the detection on wheat freshness mainly depends on biochemical methods. However, biochemical methods are always involved in a series of problems, such as long pretreatment processes to wheat samples, poor repeatability, destructive detection and so on, which hardly meet the detection requirements of scientific and intelligent grain storage. Therefore, finding out a simple, accurate, and non-destructive detection method for wheat freshness degree is of necessity. For this reason, we propose a novel wheat freshness degree detection model based on the delayed luminescence (DL) signals of wheat samples in this paper. Furthermore, a bidirectional LSTM network based on Walsh coding (Walsh-Bi-LSTM) is introduced in order to make the detection model have the error-correcting performance by reasonably splitting the multi-classification target task into several binary classification targets. Shown by the experimental results, the classification accuracy rates of the detection model established in this paper achieve 90% and 94% on the test sets of storage wheat and artificial aging seed wheat samples, improving 9% and 12% compared with conventional Bi-LSTM network model respectively, which validates that the proposed model can accurately detect wheat freshness degree.

Modified gate activation functions of Bi-LSTM-based SC-FDMA channel equalization

Abstract In recent years, artificial neural networks (ANNs) have grown a lot and helped solve numerous problems in wireless communication systems. We have evaluated the performance of the Bidirectional-Long-Short-Term-Memory (Bi-LSTM) recurrent neural networks (RNNs) for joint blind channel equalization and symbol detection using a variety of activation functions (Afs) for the gate units (sigmoid) of Bi-LSTMs without requiring any prior knowledge of channel state information (CSI). The performance of Bi-LSTM networks with different AFs found in the literature is compared. This comparison was carried out with the assistance of three different learning algorithms, namely Adam, rmsprop, and SGdm. The research findings clearly show that performance, as measured by equalization accuracy, can be improved. Furthermore, demonstrate that the sigmoid gate activation function (GAF), which is commonly used in Bi-LSTMs, does not significantly contribute to optimal network behavior. In contrast, there are a great many less well-known AFs that are capable of outperforming the ones that are most frequently utilized.

A Daily Air Pollutant Concentration Prediction Framework Combining Successive Variational Mode Decomposition and Bidirectional Long Short-Term Memory Network

Precise and efficient air quality prediction plays a vital role in safeguarding public health and informing policy-making. Fine particulate matter, specifically PM2.5 and PM10, serves as a crucial indicator for assessing and managing air pollution levels. In this paper, a daily pollution concentration prediction model combining successive variational mode decomposition (SVMD) and a bidirectional long short-term memory (BiLSTM) neural network is proposed. Firstly, SVMD is used as an unsupervised feature-learning method to divide data into intrinsic mode functions (IMFs) and to extract frequency features and improve short-term trend prediction. Secondly, the BiLSTM network is introduced for supervised learning to capture small changes in the air pollutant sequence and perform prediction of the decomposed sequence. Furthermore, the Bayesian optimization (BO) algorithm is employed to identify the optimal key parameters of the BiLSTM model. Lastly, the predicted values are reconstructed to generate the final prediction results for the daily PM2.5 and PM10 datasets. The prediction performance of the proposed model is validated using the daily PM2.5 and PM10 datasets collected from the China Environmental Monitoring Center in Tianshui, Gansu, and Wuhan, Hubei. The results show that SVMD can smooth the original series more effectively than other decomposition methods, and that the BO-BiLSTM method is better than other LSTM-based models, thereby proving that the proposed model has excellent feasibility and accuracy.

Effective Video Event Detection Using Optimized Bidirectional Long Short-Term Memory Network

In recent times, video event detection gained high attention in the researcher’s community, because of its widespread applications. In this paper, a new model is proposed for detecting different human actions in the video sequences. First, the videos are acquired from the University of Central Florida (UCF) 101, Human Motion Database (HMDB) 51 and Columbia Consumer Video (CCV) datasets. In addition, the DenseNet201 model is implemented for extracting deep feature values from the acquired datasets. Further, the Improved Gray Wolf Optimization (IGWO) algorithm is developed for selecting active/relevant feature values that effectively improve the computational time and system complexity. In the IGWO, leader enhancement and competitive strategies are employed to improve the convergence rate and to prevent the algorithm from falling into the local optima. Finally, the Bi-directional Long Short Term Memory (BiLSTM) network is used for event classification (101 action types in UCF101, 51 action types in HMDB51, and 20 action types in CCV). In the resulting phase, the IGWO-based BiLSTM network achieved 94.73%, 96.53%, and 93.91% accuracy on the UCF101, HMDB51, and CCV datasets.

The Social Media Big Data Analysis for Demand Forecasting in the Context of Globalization

This paper aims to analyze the predictive effect of artificial intelligence on user demand in big data social media and to provide suggestions for developing enterprise innovation frameworks and implementing marketing strategies. In response to the inconsistency between the supply of enterprise products and services and market demand, deep learning algorithms have been introduced using social media big data analysis. This algorithm has been improved to construct a user demand prediction model in social media big data based on bidirectional long short-term memory (BiLSTM) fused with Word2Vec. The model uses data acquisition and pre-processing, Word2Vec algorithm to vectorization the data information, and BiLSTM network to model and train the sequence. Finally, the model is evaluated as an example.

An efficient attention-driven deep neural network approach for continuous estimation of knee joint kinematics via sEMG signals during running

The smooth interaction and coordination between lower-limb amputees and their prosthetics is crucial when performing complex tasks such as running. To address this, simultaneous and proportional control (SPC) based on continuous estimation of joint angles through surface electromyogram (sEMG) signals offers a more seamless interaction between users and their prosthetic limbs than conventional pattern recognition-based control, which relies on recognizing pre-defined movement classes from specific sEMG patterns using classification algorithms. This study proposes a deep learning-based model (AM-BiLSTM) that integrates the attention mechanism (AM) and bidirectional long short-term memory (BiLSTM) network to provide an accurate and robust SPC for estimating knee joint angle during running from a minimal number of sEMG sensors. The sEMG signals of four muscles recorded from 14 subjects during treadmill running at various speeds were utilized by the AM-BiLSTM model to decode knee joint kinematics. To comprehensively investigate the generalizability of the proposed model, it was tested in intra-subject and speed, intra-subject and inter-speed, and inter-subject and speed scenarios and compared with BiLSTM, standard LSTM, and multi-layer perceptron (MLP) approaches. Normalized root-mean-square error and correlation coefficient were used as performance metrics. According to nonparametric statistical tests, the proposed AM-BiLSTM model significantly outperformed the BiLSTM network as well as classical techniques including LSTM and MLP networks in all three experiments (p-value < 0.05) and achieved state-of-the-art performance. Based on our findings, the AM-BiLSTM model may facilitate the deployment of intuitive user-driven deep learning-based control schemes for a wide variety of miniaturized robotic lower-limb devices, including myoelectric prostheses.

Load Forecasting Based on LVMD-DBFCM Load Curve Clustering and the CNN-IVIA-BLSTM Model

Power load forecasting plays an important role in power systems, and the accuracy of load forecasting is of vital importance to power system planning as well as economic efficiency. Power load data are nonsmooth, nonlinear time-series and “noisy” data. Traditional load forecasting has low accuracy and curves not fitting the load variation. It is not well predicted by a single forecasting model. In this paper, we propose a novel model based on the combination of data mining and deep learning to improve the prediction accuracy. First, data preprocessing is performed. Second, identification and correction of anomalous data, normalization of continuous sequences, and one-hot encoding of discrete sequences are performed. The load data are decomposed and denoised using the double decomposition modal (LVMD) strategy, the load curves are clustered using the double weighted fuzzy C-means (DBFCM) algorithm, and the typical curves obtained are used as load patterns. In addition, data feature analysis is performed. A convolutional neural network (CNN) is used to extract data features. A bidirectional long short-term memory (BLSTM) network is used for prediction, in which the number of hidden layer neurons, the number of training epochs, the learning rate, the regularization coefficient, and other relevant parameters in the BLSTM network are optimized using the influenza virus immunity optimization algorithm (IVIA). Finally, the historical data of City H from 1 January 2016 to 31 December 2018, are used for load forecasting. The experimental results show that the novel model based on LVMD-DBFCM load c1urve clustering combined with CNN-IVIA-BLSTM proposed in this paper has an error of only 2% for electric load forecasting.

Part-of-Speech Tagging of Odia Language Using Statistical and Deep Learning Based Approaches

Automatic part-of-speech (POS) tagging is a preprocessing step of many natural language processing tasks, such as named entity recognition, speech processing, information extraction, word sense disambiguation, and machine translation. It has already gained promising results in English and European languages. However, in Indian languages, particularly in the Odia language, it is not yet well explored because of the lack of supporting tools, resources, and morphological richness of the language. Unfortunately, we were unable to locate an open source POS tagger for the Odia language, and only a handful of attempts have been made to develop POS taggers for the Odia language. The main contribution of this research work is to present statistical approaches such as the maximum entropy Markov model and conditional random field (CRF), as well as deep learning based approaches, including the convolutional neural network (CNN) and bidirectional long short-term memory (Bi-LSTM) to develop the Odia POS tagger. A publicly accessible corpus annotated with the Bureau of Indian Standards (BIS) tagset is used in our work. However, most of the languages around the globe have used the dataset annotated with the Universal Dependencies (UD) tagset. Hence, to maintain uniformity, the Odia dataset should use the same tagset. Thus, following the BIS and UD guidelines, we constructed a mapping from the BIS tagset to the UD tagset. The maximum entropy Markov model, CRF, Bi-LSTM, and CNN models are trained using the Indian Languages Corpora Initiative corpus with the BIS and UD tagsets. We have experimented with various feature sets as input to the statistical models to prepare a baseline system and observed the impact of constructed feature sets. The deep learning based model includes the Bi-LSTM network, the CNN network, the CRF layer, character sequence information, and a pre-trained word vector. Seven different combinations of neural sequence labeling models are implemented, and their performance measures are investigated. It has been observed that the Bi-LSTM model with the character sequence feature and pre-trained word vector achieved a result with 94.58% accuracy.

Automatic defect detection and three-dimensional reconstruction from pulsed thermography images based on a bidirectional long-short term memory network

Machine learning techniques have become increasingly applied to non-destructive testing based on pulsed thermography. However, existing methods need to extract characteristic data manually. The present work addresses this issue by applying a bidirectional long-short term memory (Bi-LSTM) network to identify defects, predict defect depths, and reconstruct defective materials in three dimensions automatically based on raw cooling data sequences. The network is trained and tested based on data collected for stainless-steel specimens with multiple flat-bottom holes introduced at various specimen depths. A dual-task method and a single-task method were proposed based on Bi-LSTM network. A classification model and a regression model are constructed in the dual-task method for identifying defects and predicting defect depths. Only the regression network is implemented in a single-task method to more quickly obtain the same results based on a depth threshold. Both methods are demonstrated to achieve satisfactory accuracy in the 3D reconstruction of the defects in the testing specimen. In addition, higher pulse energy and faster acquisition frequency can promote the prediction accuracy. Then the results of Bi-LSTM were compared with the results of 1D CNN and MLP. To verify the generalization of the proposed method, CFRP specimen is employed for 3D reconstruction, which also performed with good results.

ABLNCPP: Attention Mechanism-Based Bidirectional Long Short-Term Memory for Noncoding RNA Coding Potential Prediction.

With the continuous development of ribosome profiling, sequencing technology, and proteomics, evidence is mounting that noncoding RNA (ncRNA) may be a novel source of peptides or proteins. These peptides and proteins play crucial roles in inhibiting tumor progression and interfering with cancer metabolism and other essential physiological processes. Therefore, identifying ncRNAs with coding potential is vital to ncRNA functional research. However, existing studies perform well in classifying ncRNAs and mRNAs, and no research has been explicitly raised to distinguish whether ncRNA transcripts have coding potential. For this reason, we propose an attention mechanism-based bidirectional LSTM network called ABLNCPP to assess the coding possibility of ncRNA sequences. Considering the sequential information loss in previous methods, we introduce a novel nonoverlapping trinucleotide embedding (NOLTE) method for ncRNAs to obtain embeddings containing sequential features. The extensive evaluations show that ABLNCPP outperforms other state-of-the-art models. In general, ABLNCPP overcomes the bottleneck of ncRNA coding potential prediction and is expected to provide valuable contributions to cancer discovery and treatment in the future. The source code and data sets are freely available at https://github.com/YinggggJ/ABLNCPP.

Optimizing BiLSTM Network Attack Prediction Based on Improved Gray Wolf Algorithm

Aiming at the problems of low accuracy of network attack prediction and long response time of attack detection, bidirectional long short-term memory (BiLSTM) was used to predict network attacks. However, BiLSTM has the problems of difficulty in parameter setting and low accuracy of the prediction model. This paper first proposes the Improved Grey Wolf algorithm (IGWO) to optimize the BiLSTM (IGWO-BiLSTM). First, IGWO uses Dimension Learning Hunting (DLH) strategy to construct the wolf neighborhood. In the established wolf neighborhood, the BiLSTM parameters are iteratively optimized to obtain a prediction model with fast convergence speed and small reconstruction error. Secondly, the dataset is preprocessed, and the IP packet statistical signature (IPDCF) is defined according to the characteristics of denial of service (DOS) and distributed denial of service (DDOS) attacks. IPDCF was used to establish the time series model and network traffic time series data were input into IGWO-BiLSTM to get the prediction results. Finally, the DOS and DDOS network packets were input into the trained prediction model to obtain the prediction results of attack data. By comparing the predicted values of IGWO-BiLSTM normal network packets and attack packets, a reasonable threshold is set to provide the basis for the subsequent attack prediction. Experiments show that the IGWO-BiLSTM can reach 99.05% of the fitting degree and accurately distinguish network attacks from normal network demand increases.

Data‐driven modeling and prediction on hysteresis behavior of flexure RC columns using deep learning networks

SummaryHysteresis behavior of structural components has been one of the research focus for the structural engineering community for decades, comprehensively determines the structural performance and safety, and plays an important role in structural disaster mitigation. It is of great significance to continuously monitor structural responses and accurately characterize structural hysteresis. Currently, the nonlinear properties of real‐world structural components cannot be obtained before its failure. Thus, a historical database is collected firstly. Then, a data‐driven analysis method is proposed for predicting hysteresis behaviors of reinforced concrete (RC) columns. A bidirectional LSTM (BLSTM) network is developed to model and predict hysteresis curves. The data with unfixed lengths are specially processed to simultaneously guarantee a uniform size and avoid data loss, and the clipping layers are inserted in the model to clip off inferior predictions and improve the accuracy. This methodology is systematically studied and validated by employing a sythetic database generated by numerical simulation and the full‐scale experiment database named PEER database. Result shows that proposed BLSTM can predict the hysteresis curves of the RC components with acceptable accuracy and robustness. Moreover, the interpretability analysis is performed on identifying the learning and prediction principle of the BLSTM model on hysteresis prediction and its accuracy variation under different model architectures.

Phishing Detection in Blockchain Transaction Networks Using Ensemble Learning

The recent progress in blockchain and wireless communication infrastructures has paved the way for creating blockchain-based systems that protect data integrity and enable secure information sharing. Despite these advancements, concerns regarding security and privacy continue to impede the widespread adoption of blockchain technology, especially when sharing sensitive data. Specific security attacks against blockchains, such as data poisoning attacks, privacy leaks, and a single point of failure, must be addressed to develop efficient blockchain-supported IT infrastructures. This study proposes the use of deep learning methods, including Long Short-Term Memory (LSTM), Bi-directional LSTM (Bi-LSTM), and convolutional neural network LSTM (CNN-LSTM), to detect phishing attacks in a blockchain transaction network. These methods were evaluated on a dataset comprising malicious and benign addresses from the Ethereum blockchain dark list and whitelist dataset, and the results showed an accuracy of 99.72%.