Device-Free Through-the-Wall Activity Recognition Using Bi-Directional Long Short-Term Memory and WiFi Channel State Information

Activity recognition plays a key role in health management and security.Traditional approaches are based on vision or wearables,which only work under the line of sight(LOS)or require the targets to carry dedicated devices.As human bodies and their movements have influences on WiFi propagation,this paper proposes the recognition of human activities by analyzing the channel state information(CSI)from the WiFi physical layer.The method requires only the commodity:WiFi transmitters and receivers that can operate through a wall,under LOS and non-line of sight(NLOS),while the targets are not required to carry dedicated devices.After collecting CSI,the discrete wavelet transform is applied to reduce the noise,followed by outlier detection based on the local outlier factor to extract the activity segment.Activity recognition is fulfilled by using the bi-directional long short-term memory that takes the sequential features into consideration.Experiments in through-the-wall environments achieve recognition accuracy>95%for six common activities,such as standing up,squatting down,walking,running,jumping,and falling,outperforming existing work in this field.

Real-Time Speech Enhancement Based on Convolutional Recurrent Neural Network

Speech enhancement is the task of taking a noisy speech input and pro-ducing an enhanced speech output.In recent years,the need for speech enhance-ment has been increased due to challenges that occurred in various applications such as hearing aids,Automatic Speech Recognition(ASR),and mobile speech communication systems.Most of the Speech Enhancement research work has been carried out for English,Chinese,and other European languages.Only a few research works involve speech enhancement in Indian regional Languages.In this paper,we propose a two-fold architecture to perform speech enhancement for Tamil speech signal based on convolutional recurrent neural network(CRN)that addresses the speech enhancement in a real-time single channel or track of sound created by the speaker.In thefirst stage mask based long short-term mem-ory(LSTM)is used for noise suppression along with loss function and in the sec-ond stage,Convolutional Encoder-Decoder(CED)is used for speech restoration.The proposed model is evaluated on various speaker and noisy environments like Babble noise,car noise,and white Gaussian noise.The proposed CRN model improves speech quality by 0.1 points when compared with the LSTM base model and also CRN requires fewer parameters for training.The performance of the pro-posed model is outstanding even in low Signal to Noise Ratio(SNR).

Short-term train arrival delay prediction:a data-driven approach

Purpose-To optimize train operations,dispatchers currently rely on experience for quick adjustments when delays occur.However,delay predictions often involve imprecise shifts based on known delay times.Real-time and accurate train delay predictions,facilitated by data-driven neural network models,can significantly reduce dispatcher stress and improve adjustment plans.Leveraging current train operation data,these models enable swift and precise predictions,addressing challenges posed by train delays in high-speed rail networks during unforeseen events.Design/methodology/approach-This paper proposes CBLA-net,a neural network architecture for predicting late arrival times.It combines CNN,Bi-LSTM,and attention mechanisms to extract features,handle time series data,and enhance information utilization.Trained on operational data from the Beijing-Tianjin line,it predicts the late arrival time of a target train at the next station using multidimensional input data from the target and preceding trains.Findings-This study evaluates our model’s predictive performance using two data approaches:one considering full data and another focusing only on late arrivals.Results show precise and rapid predictions.Training with full data achieves aMAEof approximately 0.54 minutes and a RMSEof 0.65 minutes,surpassing the model trained solely on delay data(MAE:is about 1.02 min,RMSE:is about 1.52 min).Despite superior overall performance with full data,the model excels at predicting delays exceeding 15 minutes when trained exclusively on late arrivals.For enhanced adaptability to real-world train operations,training with full data is recommended.Originality/value-This paper introduces a novel neural network model,CBLA-net,for predicting train delay times.It innovatively compares and analyzes the model’s performance using both full data and delay data formats.Additionally,the evaluation of the network’s predictive capabilities considers different scenarios,providing a comprehensive demonstration of the model’s predictive performance.

Recurrent Convolutional Neural Network MSER-Based Approach for Payable Document Processing

A tremendous amount of vendor invoices is generated in the corporate sector.To automate the manual data entry in payable documents,highly accurate Optical Character Recognition(OCR)is required.This paper proposes an end-to-end OCR system that does both localization and recognition and serves as a single unit to automate payable document processing such as cheques and cash disbursement.For text localization,the maximally stable extremal region is used,which extracts a word or digit chunk from an invoice.This chunk is later passed to the deep learning model,which performs text recognition.The deep learning model utilizes both convolution neural networks and long short-term memory(LSTM).The convolution layer is used for extracting features,which are fed to the LSTM.The model integrates feature extraction,modeling sequence,and transcription into a unified network.It handles the sequences of unconstrained lengths,independent of the character segmentation or horizontal scale normalization.Furthermore,it applies to both the lexicon-free and lexicon-based text recognition,and finally,it produces a comparatively smaller model,which can be implemented in practical applications.The overall superior performance in the experimental evaluation demonstrates the usefulness of the proposed model.The model is thus generic and can be used for other similar recognition scenarios.

Classification of Arrhythmia Based on Convolutional Neural Networks and Encoder-Decoder Model

As a common and high-risk type of disease,heart disease seriously threatens people’s health.At the same time,in the era of the Internet of Thing(IoT),smart medical device has strong practical significance for medical workers and patients because of its ability to assist in the diagnosis of diseases.Therefore,the research of real-time diagnosis and classification algorithms for arrhythmia can help to improve the diagnostic efficiency of diseases.In this paper,we design an automatic arrhythmia classification algorithm model based on Convolutional Neural Network(CNN)and Encoder-Decoder model.The model uses Long Short-Term Memory(LSTM)to consider the influence of time series features on classification results.Simultaneously,it is trained and tested by the MIT-BIH arrhythmia database.Besides,Generative Adversarial Networks(GAN)is adopted as a method of data equalization for solving data imbalance problem.The simulation results show that for the inter-patient arrhythmia classification,the hybrid model combining CNN and Encoder-Decoder model has the best classification accuracy,of which the accuracy can reach 94.05%.Especially,it has a better advantage for the classification effect of supraventricular ectopic beats(class S)and fusion beats(class F).

Use of Local Region Maps on Convolutional LSTM for Single-Image HDR Reconstruction

Low dynamic range(LDR)images captured by consumer cameras have a limited luminance range.As the conventional method for generating high dynamic range(HDR)images involves merging multiple-exposure LDR images of the same scene(assuming a stationary scene),we introduce a learning-based model for single-image HDR reconstruction.An input LDR image is sequentially segmented into the local region maps based on the cumulative histogram of the input brightness distribution.Using the local region maps,SParam-Net estimates the parameters of an inverse tone mapping function to generate a pseudo-HDR image.We process the segmented region maps as the input sequences on long short-term memory.Finally,a fast super-resolution convolutional neural network is used for HDR image reconstruction.The proposed method was trained and tested on datasets including HDR-Real,LDR-HDR-pair,and HDR-Eye.The experimental results revealed that HDR images can be generated more reliably than using contemporary end-to-end approaches.

Hybrid Model for Short-Term Passenger Flow Prediction in Rail Transit

A precise and timely forecast of short-term rail transit passenger flow provides data support for traffic management and operation,assisting rail operators in efficiently allocating resources and timely relieving pressure on passenger safety and operation.First,the passenger flow sequence models in the study are broken down using VMD for noise reduction.The objective environment features are then added to the characteristic factors that affect the passenger flow.The target station serves as an additional spatial feature and is mined concurrently using the KNN algorithm.It is shown that the hybrid model VMD-CLSMT has a higher prediction accuracy,by setting BP,CNN,and LSTM reference experiments.All models’second order prediction effects are superior to their first order effects,showing that the residual network can significantly raise model prediction accuracy.Additionally,it confirms the efficacy of supplementary and objective environmental features.

A spatiotemporal deep learning method for excavation-induced wall deflections

Data-driven approaches such as neural networks are increasingly used for deep excavations due to the growing amount of available monitoring data in practical projects.However,most neural network models only use the data from a single monitoring point and neglect the spatial relationships between multiple monitoring points.Besides,most models lack flexibility in providing predictions for multiple days after monitoring activity.This study proposes a sequence-to-sequence(seq2seq)two-dimensional(2D)convolutional long short-term memory neural network(S2SCL2D)for predicting the spatiotemporal wall deflections induced by deep excavations.The model utilizes the data from all monitoring points on the entire wall and extracts spatiotemporal features from data by combining the 2D convolutional layers and long short-term memory(LSTM)layers.The S2SCL2D model achieves a long-term prediction of wall deflections through a recursive seq2seq structure.The excavation depth,which has a significant impact on wall deflections,is also considered using a feature fusion method.An excavation project in Hangzhou,China,is used to illustrate the proposed model.The results demonstrate that the S2SCL2D model has superior prediction accuracy and robustness than that of the LSTM and S2SCL1D(one-dimensional)models.The prediction model demonstrates a strong generalizability when applied to an adjacent excavation.Based on the long-term prediction results,practitioners can plan and allocate resources in advance to address the potential engineering issues.

Visualization-based prediction of dendritic copper growth in electrochemical cells using convolutional long short-term memory

Electrodeposition in electrochemical cells is one of the leading causes of its performance deterioration. The prediction of electrodeposition growth demands a good understanding of the complex physics involved, which can lead to the fabrication of a probabilistic mathematical model. As an alternative, a convolutional Long shortterm memory architecture-based image analysis approach is presented herein. This technique can predict the electrodeposition growth of the electrolytes, without prior detailed knowledge of the system. The captured images of the electrodeposition from the experiments are used to train and test the model. A comparison between the expected output image and predicted image on a pixel level, percentage mean squared error, absolute percentage error, and pattern density of the electrodeposit are investigated to assess the model accuracy. The randomness of the electrodeposition growth is outlined by investigating the fractal dimension and the interfacial length of the electrodeposits. The trained model predictions show a significant promise between all the experimentally obtained relevant parameters with the predicted one. It is expected that this deep learning-based approach for predicting random electrodeposition growth will be of immense help for designing and optimizing the relevant experimental scheme in near future without performing multiple experiments.

Leucogranite mapping via convolutional recurrent neural networks and geochemical survey data in the Himalayan orogen

Geochemical survey data analysis is recognized as an implemented and feasible way for lithological mapping to assist mineral exploration.With respect to available approaches,recent methodological advances have focused on deep learning algorithms which provide access to learn and extract information directly from geochemical survey data through multi-level networks and outputting end-to-end classification.Accordingly,this study developed a lithological mapping framework with the joint application of a convolutional neural network(CNN)and a long short-term memory(LSTM).The CNN-LSTM model is dominant in correlation extraction from CNN layers and coupling interaction learning from LSTM layers.This hybrid approach was demonstrated by mapping leucogranites in the Himalayan orogen based on stream sediment geochemical survey data,where the targeted leucogranite was expected to be potential resources of rare metals such as Li,Be,and W mineralization.Three comparative case studies were carried out from both visual and quantitative perspectives to illustrate the superiority of the proposed model.A guided spatial distribution map of leucogranites in the Himalayan orogen,divided into high-,moderate-,and low-potential areas,was delineated by the success rate curve,which further improves the efficiency for identifying unmapped leucogranites through geological mapping.In light of these results,this study provides an alternative solution for lithologic mapping using geochemical survey data at a regional scale and reduces the risk for decision making associated with mineral exploration.

Deep Learning for Financial Time Series Prediction:A State-of-the-Art Review of Standalone and HybridModels

Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep learning has largely contributed to the elevation of the prediction performance.Currently,the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking,making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better,what techniques and components are involved,and how themodel can be designed and implemented.This review article provides an overview of techniques,components and frameworks for financial time series prediction,with an emphasis on state-of-the-art deep learning models in the literature from2015 to 2023,including standalonemodels like convolutional neural networks(CNN)that are capable of extracting spatial dependencies within data,and long short-term memory(LSTM)that is designed for handling temporal dependencies;and hybrid models integrating CNN,LSTM,attention mechanism(AM)and other techniques.For illustration and comparison purposes,models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input,output,feature extraction,prediction,and related processes.Among the state-of-the-artmodels,hybrid models like CNNLSTMand CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only model.Some remaining challenges have been discussed,including non-friendliness for finance domain experts,delayed prediction,domain knowledge negligence,lack of standards,and inability of real-time and highfrequency predictions.The principal contributions of this paper are to provide a one-stop guide for both academia and industry to review,compare and summarize technologies and recent advances in this area,to facilitate smooth and informed implementation,and to highlight future research directions.

Credit Card Fraud Detection Using Improved Deep Learning Models

Fraud of credit cards is a major issue for financial organizations and individuals.As fraudulent actions become more complex,a demand for better fraud detection systems is rising.Deep learning approaches have shown promise in several fields,including detecting credit card fraud.However,the efficacy of these models is heavily dependent on the careful selection of appropriate hyperparameters.This paper introduces models that integrate deep learning models with hyperparameter tuning techniques to learn the patterns and relationships within credit card transaction data,thereby improving fraud detection.Three deep learning models:AutoEncoder(AE),Convolution Neural Network(CNN),and Long Short-Term Memory(LSTM)are proposed to investigate how hyperparameter adjustment impacts the efficacy of deep learning models used to identify credit card fraud.The experiments conducted on a European credit card fraud dataset using different hyperparameters and three deep learning models demonstrate that the proposed models achieve a tradeoff between detection rate and precision,leading these models to be effective in accurately predicting credit card fraud.The results demonstrate that LSTM significantly outperformed AE and CNN in terms of accuracy(99.2%),detection rate(93.3%),and area under the curve(96.3%).These proposed models have surpassed those of existing studies and are expected to make a significant contribution to the field of credit card fraud detection.

A multi-source information fusion layer counting method for penetration fuze based on TCN-LSTM

When employing penetration ammunition to strike multi-story buildings,the detection methods using acceleration sensors suffer from signal aliasing,while magnetic detection methods are susceptible to interference from ferromagnetic materials,thereby posing challenges in accurately determining the number of layers.To address this issue,this research proposes a layer counting method for penetration fuze that incorporates multi-source information fusion,utilizing both the temporal convolutional network(TCN)and the long short-term memory(LSTM)recurrent network.By leveraging the strengths of these two network structures,the method extracts temporal and high-dimensional features from the multi-source physical field during the penetration process,establishing a relationship between the multi-source physical field and the distance between the fuze and the target plate.A simulation model is developed to simulate the overload and magnetic field of a projectile penetrating multiple layers of target plates,capturing the multi-source physical field signals and their patterns during the penetration process.The analysis reveals that the proposed multi-source fusion layer counting method reduces errors by 60% and 50% compared to single overload layer counting and single magnetic anomaly signal layer counting,respectively.The model's predictive performance is evaluated under various operating conditions,including different ratios of added noise to random sample positions,penetration speeds,and spacing between target plates.The maximum errors in fuze penetration time predicted by the three modes are 0.08 ms,0.12 ms,and 0.16 ms,respectively,confirming the robustness of the proposed model.Moreover,the model's predictions indicate that the fitting degree for large interlayer spacings is superior to that for small interlayer spacings due to the influence of stress waves.

DPAL-BERT:A Faster and Lighter Question Answering Model

Recent advancements in natural language processing have given rise to numerous pre-training language models in question-answering systems.However,with the constant evolution of algorithms,data,and computing power,the increasing size and complexity of these models have led to increased training costs and reduced efficiency.This study aims to minimize the inference time of such models while maintaining computational performance.It also proposes a novel Distillation model for PAL-BERT(DPAL-BERT),specifically,employs knowledge distillation,using the PAL-BERT model as the teacher model to train two student models:DPAL-BERT-Bi and DPAL-BERTC.This research enhances the dataset through techniques such as masking,replacement,and n-gram sampling to optimize knowledge transfer.The experimental results showed that the distilled models greatly outperform models trained from scratch.In addition,although the distilled models exhibit a slight decrease in performance compared to PAL-BERT,they significantly reduce inference time to just 0.25%of the original.This demonstrates the effectiveness of the proposed approach in balancing model performance and efficiency.

The Influence of Air Pollution Concentrations on Solar Irradiance Forecasting Using CNN-LSTM-mRMR Feature Extraction

Maintaining a steady power supply requires accurate forecasting of solar irradiance,since clean energy resources do not provide steady power.The existing forecasting studies have examined the limited effects of weather conditions on solar radiation such as temperature and precipitation utilizing convolutional neural network(CNN),but no comprehensive study has been conducted on concentrations of air pollutants along with weather conditions.This paper proposes a hybrid approach based on deep learning,expanding the feature set by adding new air pollution concentrations,and ranking these features to select and reduce their size to improve efficiency.In order to improve the accuracy of feature selection,a maximum-dependency and minimum-redundancy(mRMR)criterion is applied to the constructed feature space to identify and rank the features.The combination of air pollution data with weather conditions data has enabled the prediction of solar irradiance with a higher accuracy.An evaluation of the proposed approach is conducted in Istanbul over 12 months for 43791 discrete times,with the main purpose of analyzing air data,including particular matter(PM10 and PM25),carbon monoxide(CO),nitric oxide(NOX),nitrogen dioxide(NO_(2)),ozone(O₃),sulfur dioxide(SO_(2))using a CNN,a long short-term memory network(LSTM),and MRMR feature extraction.Compared with the benchmark models with root mean square error(RMSE)results of 76.2,60.3,41.3,32.4,there is a significant improvement with the RMSE result of 5.536.This hybrid model presented here offers high prediction accuracy,a wider feature set,and a novel approach based on air concentrations combined with weather conditions for solar irradiance prediction.

A Time Series Intrusion Detection Method Based on SSAE,TCN and Bi-LSTM

In the fast-evolving landscape of digital networks,the incidence of network intrusions has escalated alarmingly.Simultaneously,the crucial role of time series data in intrusion detection remains largely underappreciated,with most systems failing to capture the time-bound nuances of network traffic.This leads to compromised detection accuracy and overlooked temporal patterns.Addressing this gap,we introduce a novel SSAE-TCN-BiLSTM(STL)model that integrates time series analysis,significantly enhancing detection capabilities.Our approach reduces feature dimensionalitywith a Stacked Sparse Autoencoder(SSAE)and extracts temporally relevant features through a Temporal Convolutional Network(TCN)and Bidirectional Long Short-term Memory Network(Bi-LSTM).By meticulously adjusting time steps,we underscore the significance of temporal data in bolstering detection accuracy.On the UNSW-NB15 dataset,ourmodel achieved an F1-score of 99.49%,Accuracy of 99.43%,Precision of 99.38%,Recall of 99.60%,and an inference time of 4.24 s.For the CICDS2017 dataset,we recorded an F1-score of 99.53%,Accuracy of 99.62%,Precision of 99.27%,Recall of 99.79%,and an inference time of 5.72 s.These findings not only confirm the STL model’s superior performance but also its operational efficiency,underpinning its significance in real-world cybersecurity scenarios where rapid response is paramount.Our contribution represents a significant advance in cybersecurity,proposing a model that excels in accuracy and adaptability to the dynamic nature of network traffic,setting a new benchmark for intrusion detection systems.

A New Industrial Intrusion Detection Method Based on CNN-BiLSTM

Nowadays,with the rapid development of industrial Internet technology,on the one hand,advanced industrial control systems(ICS)have improved industrial production efficiency.However,there are more and more cyber-attacks targeting industrial control systems.To ensure the security of industrial networks,intrusion detection systems have been widely used in industrial control systems,and deep neural networks have always been an effective method for identifying cyber attacks.Current intrusion detection methods still suffer from low accuracy and a high false alarm rate.Therefore,it is important to build a more efficient intrusion detection model.This paper proposes a hybrid deep learning intrusion detection method based on convolutional neural networks and bidirectional long short-term memory neural networks(CNN-BiLSTM).To address the issue of imbalanced data within the dataset and improve the model’s detection capabilities,the Synthetic Minority Over-sampling Technique-Edited Nearest Neighbors(SMOTE-ENN)algorithm is applied in the preprocessing phase.This algorithm is employed to generate synthetic instances for the minority class,simultaneously mitigating the impact of noise in the majority class.This approach aims to create a more equitable distribution of classes,thereby enhancing the model’s ability to effectively identify patterns in both minority and majority classes.In the experimental phase,the detection performance of the method is verified using two data sets.Experimental results show that the accuracy rate on the CICIDS-2017 data set reaches 97.7%.On the natural gas pipeline dataset collected by Lan Turnipseed from Mississippi State University in the United States,the accuracy rate also reaches 85.5%.

Track correlation algorithm based on CNN-LSTM for swarm targets

The rapid development of unmanned aerial vehicle(UAV) swarm, a new type of aerial threat target, has brought great pressure to the air defense early warning system. At present, most of the track correlation algorithms only use part of the target location, speed, and other information for correlation.In this paper, the artificial neural network method is used to establish the corresponding intelligent track correlation model and method according to the characteristics of swarm targets.Precisely, a route correlation method based on convolutional neural networks (CNN) and long short-term memory (LSTM)Neural network is designed. In this model, the CNN is used to extract the formation characteristics of UAV swarm and the spatial position characteristics of single UAV track in the formation,while the LSTM is used to extract the time characteristics of UAV swarm. Experimental results show that compared with the traditional algorithms, the algorithm based on CNN-LSTM neural network can make full use of multiple feature information of the target, and has better robustness and accuracy for swarm targets.

Analysis and Modeling of Time Output Characteristics for Distributed Photovoltaic and Energy Storage

Due to the unpredictable output characteristics of distributed photovoltaics,their integration into the grid can lead to voltage fluctuations within the regional power grid.Therefore,the development of spatial-temporal coordination and optimization control methods for distributed photovoltaics and energy storage systems is of utmost importance in various scenarios.This paper approaches the issue from the perspective of spatiotemporal forecasting of distributed photovoltaic(PV)generation and proposes a Temporal Convolutional-Long Short-Term Memory prediction model that combines Temporal Convolutional Networks(TCN)and Long Short-Term Memory(LSTM).To begin with,an analysis of the spatiotemporal distribution patterns of PV generation is conducted,and outlier data is handled using the 3σ rule.Subsequently,a novel approach that combines temporal convolution and LSTM networks is introduced,with TCN extracting spatial features and LSTM capturing temporal features.Finally,a real spatiotemporal dataset from Gansu,China,is established to compare the performance of the proposed network against other models.The results demonstrate that the model presented in this paper exhibits the highest predictive accuracy,with a single-step Mean Absolute Error(MAE)of 1.782 and an average Root Mean Square Error(RMSE)of 3.72 for multi-step predictions.

Dynamic Hand Gesture Recognition Based on Short-Term Sampling Neural Networks

Hand gestures are a natural way for human-robot interaction.Vision based dynamic hand gesture recognition has become a hot research topic due to its various applications.This paper presents a novel deep learning network for hand gesture recognition.The network integrates several well-proved modules together to learn both short-term and long-term features from video inputs and meanwhile avoid intensive computation.To learn short-term features,each video input is segmented into a fixed number of frame groups.A frame is randomly selected from each group and represented as an RGB image as well as an optical flow snapshot.These two entities are fused and fed into a convolutional neural network(Conv Net)for feature extraction.The Conv Nets for all groups share parameters.To learn longterm features,outputs from all Conv Nets are fed into a long short-term memory(LSTM)network,by which a final classification result is predicted.The new model has been tested with two popular hand gesture datasets,namely the Jester dataset and Nvidia dataset.Comparing with other models,our model produced very competitive results.The robustness of the new model has also been proved with an augmented dataset with enhanced diversity of hand gestures.