Improved prediction of DNA and RNA binding proteins with deep learning models.

Nucleic acid-binding proteins (NABPs), including DNA-binding proteins (DBPs) and RNA-binding proteins (RBPs), play important roles in essential biological processes. To facilitate functional annotation and accurate prediction of different types of NABPs, many machine learning-based computational approaches have been developed. However, the datasets used for training and testing as well as the prediction scopes in these studies have limited their applications. In this paper, we developed new strategies to overcome these limitations by generating more accurate and robust datasets and developing deep learning-based methods including both hierarchical and multi-class approaches to predict the types of NABPs for any given protein. The deep learning models employ two layers of convolutional neural network and one layer of long short-term memory. Our approaches outperform existing DBP and RBP predictors with a balanced prediction between DBPs and RBPs, and are more practically useful in identifying novel NABPs. The multi-class approach greatly improves the prediction accuracy of DBPs and RBPs, especially for the DBPs with ~12% improvement. Moreover, we explored the prediction accuracy of single-stranded DNA binding proteins and their effect on the overall prediction accuracy of NABP predictions.

Multi-view contrastive heterogeneous graph attention network for lncRNA-disease association prediction.

MOTIVATION: Exploring the potential long noncoding RNA (lncRNA)-disease associations (LDAs) plays a critical role for understanding disease etiology and pathogenesis. Given the high cost of biological experiments, developing a computational method is a practical necessity to effectively accelerate experimental screening process of candidate LDAs. However, under the high sparsity of LDA dataset, many computational models hardly exploit enough knowledge to learn comprehensive patterns of node representations. Moreover, although the metapath-based GNN has been recently introduced into LDA prediction, it discards intermediate nodes along the meta-path and results in information loss. RESULTS: This paper presents a new multi-view contrastive heterogeneous graph attention network (GAT) for lncRNA-disease association prediction, MCHNLDA for brevity. Specifically, MCHNLDA firstly leverages rich biological data sources of lncRNA, gene and disease to construct two-view graphs, feature structural graph of feature schema view and lncRNA-gene-disease heterogeneous graph of network topology view. Then, we design a cross-contrastive learning task to collaboratively guide graph embeddings of the two views without relying on any labels. In this way, we can pull closer the nodes of similar features and network topology, and push other nodes away. Furthermore, we propose a heterogeneous contextual GAT, where long short-term memory network is incorporated into attention mechanism to effectively capture sequential structure information along the meta-path. Extensive experimental comparisons against several state-of-the-art methods show the effectiveness of proposed framework.The code and data of proposed framework is freely available at https://github.com/zhaoxs686/MCHNLDA.

TLimmuno2: predicting MHC class II antigen immunogenicity through transfer learning.

Major histocompatibility complex (MHC) class II molecules play a pivotal role in antigen presentation and CD4+ T cell response. Accurate prediction of the immunogenicity of MHC class II-associated antigens is critical for vaccine design and cancer immunotherapies. However, current computational methods are limited by insufficient training data and algorithmic constraints, and the rules that govern which peptides are truly recognized by existing T cell receptors remain poorly understood. Here, we build a transfer learning-based, long short-term memory model named 'TLimmuno2' to predict whether epitope-MHC class II complex can elicit T cell response. Through leveraging binding affinity data, TLimmuno2 shows superior performance compared with existing models on independent validation datasets. TLimmuno2 can find real immunogenic neoantigen in real-world cancer immunotherapy data. The identification of significant MHC class II neoantigen-mediated immunoediting signal in the cancer genome atlas pan-cancer dataset further suggests the robustness of TLimmuno2 in identifying really immunogenic neoantigens that are undergoing negative selection during cancer evolution. Overall, TLimmuno2 is a powerful tool for the immunogenicity prediction of MHC class II presented epitopes and could promote the development of personalized immunotherapies.

HiC4D: forecasting spatiotemporal Hi-C data with residual ConvLSTM.

The Hi-C experiments have been extensively used for the studies of genomic structures. In the last few years, spatiotemporal Hi-C has largely contributed to the investigation of genome dynamic reorganization. However, computationally modeling and forecasting spatiotemporal Hi-C data still have not been seen in the literature. We present HiC4D for dealing with the problem of forecasting spatiotemporal Hi-C data. We designed and benchmarked a novel network and named it residual ConvLSTM (ResConvLSTM), which is a combination of residual network and convolutional long short-term memory (ConvLSTM). We evaluated our new ResConvLSTM networks and compared them with the other five methods, including a naïve network (NaiveNet) that we designed as a baseline method and four outstanding video-prediction methods from the literature: ConvLSTM, spatiotemporal LSTM (ST-LSTM), self-attention LSTM (SA-LSTM) and simple video prediction (SimVP). We used eight different spatiotemporal Hi-C datasets for the blind test, including two from mouse embryogenesis, one from somatic cell nuclear transfer (SCNT) embryos, three embryogenesis datasets from different species and two non-embryogenesis datasets. Our evaluation results indicate that our ResConvLSTM networks almost always outperform the other methods on the eight blind-test datasets in terms of accurately predicting the Hi-C contact matrices at future time-steps. Our benchmarks also indicate that all of the methods that we benchmarked can successfully recover the boundaries of topologically associating domains called on the experimental Hi-C contact matrices. Taken together, our benchmarks suggest that HiC4D is an effective tool for predicting spatiotemporal Hi-C data. HiC4D is publicly available at both http://dna.cs.miami.edu/HiC4D/ and https://github.com/zwang-bioinformatics/HiC4D/.

Incomplete time-series gene expression in integrative study for islet autoimmunity prediction.

Type 1 diabetes (T1D) outcome prediction plays a vital role in identifying novel risk factors, ensuring early patient care and designing cohort studies. TEDDY is a longitudinal cohort study that collects a vast amount of multi-omics and clinical data from its participants to explore the progression and markers of T1D. However, missing data in the omics profiles make the outcome prediction a difficult task. TEDDY collected time series gene expression for less than 6% of enrolled participants. Additionally, for the participants whose gene expressions are collected, 79% time steps are missing. This study introduces an advanced bioinformatics framework for gene expression imputation and islet autoimmunity (IA) prediction. The imputation model generates synthetic data for participants with partially or entirely missing gene expression. The prediction model integrates the synthetic gene expression with other risk factors to achieve better predictive performance. Comprehensive experiments on TEDDY datasets show that: (1) Our pipeline can effectively integrate synthetic gene expression with family history, HLA genotype and SNPs to better predict IA status at 2 years (sensitivity 0.622, AUC 0.715) compared with the individual datasets and state-of-the-art results in the literature (AUC 0.682). (2) The synthetic gene expression contains predictive signals as strong as the true gene expression, reducing reliance on expensive and long-term longitudinal data collection. (3) Time series gene expression is crucial to the proposed improvement and shows significantly better predictive ability than cross-sectional gene expression. (4) Our pipeline is robust to limited data availability. Availability: Code is available at https://github.com/compbiolabucf/TEDDY.

Grain protein function prediction based on self-attention mechanism and bidirectional LSTM.

With the development of genome sequencing technology, using computing technology to predict grain protein function has become one of the important tasks of bioinformatics. The protein data of four grains, soybean, maize, indica and japonica are selected in this experimental dataset. In this paper, a novel neural network algorithm Chemical-SA-BiLSTM is proposed for grain protein function prediction. The Chemical-SA-BiLSTM algorithm fuses the chemical properties of proteins on the basis of amino acid sequences, and combines the self-attention mechanism with the bidirectional Long Short-Term Memory network. The experimental results show that the Chemical-SA-BiLSTM algorithm is superior to other classical neural network algorithms, and can more accurately predict the protein function, which proves the effectiveness of the Chemical-SA-BiLSTM algorithm in the prediction of grain protein function. The source code of our method is available at https://github.com/HwaTong/Chemical-SA-BiLSTM.

DeepSTF: predicting transcription factor binding sites by interpretable deep neural networks combining sequence and shape.

Precise targeting of transcription factor binding sites (TFBSs) is essential to comprehending transcriptional regulatory processes and investigating cellular function. Although several deep learning algorithms have been created to predict TFBSs, the models' intrinsic mechanisms and prediction results are difficult to explain. There is still room for improvement in prediction performance. We present DeepSTF, a unique deep-learning architecture for predicting TFBSs by integrating DNA sequence and shape profiles. We use the improved transformer encoder structure for the first time in the TFBSs prediction approach. DeepSTF extracts DNA higher-order sequence features using stacked convolutional neural networks (CNNs), whereas rich DNA shape profiles are extracted by combining improved transformer encoder structure and bidirectional long short-term memory (Bi-LSTM), and, finally, the derived higher-order sequence features and representative shape profiles are integrated into the channel dimension to achieve accurate TFBSs prediction. Experiments on 165 ENCODE chromatin immunoprecipitation sequencing (ChIP-seq) datasets show that DeepSTF considerably outperforms several state-of-the-art algorithms in predicting TFBSs, and we explain the usefulness of the transformer encoder structure and the combined strategy using sequence features and shape profiles in capturing multiple dependencies and learning essential features. In addition, this paper examines the significance of DNA shape features predicting TFBSs. The source code of DeepSTF is available at https://github.com/YuBinLab-QUST/DeepSTF/.

O-GlcNAcPRED-DL: Prediction of Protein O-GlcNAcylation Sites Based on an Ensemble Model of Deep Learning.

O-linked ß-N-acetylglucosamine (O-GlcNAc) is a post-translational modification (i.e., O-GlcNAcylation) on serine/threonine residues of proteins, regulating a plethora of physiological and pathological events. As a dynamic process, O-GlcNAc functions in a site-specific manner. However, the experimental identification of the O-GlcNAc sites remains challenging in many scenarios. Herein, by leveraging the recent progress in cataloguing experimentally identified O-GlcNAc sites and advanced deep learning approaches, we establish an ensemble model, O-GlcNAcPRED-DL, a deep learning-based tool, for the prediction of O-GlcNAc sites. In brief, to make a benchmark O-GlcNAc data set, we extracted the information on O-GlcNAc from the recently constructed database O-GlcNAcAtlas, which contains thousands of experimentally identified and curated O-GlcNAc sites on proteins from multiple species. To overcome the imbalance between positive and negative data sets, we selected five groups of negative data sets in humans and mice to construct an ensemble predictor based on connection of a convolutional neural network and bidirectional long short-term memory. By taking into account three types of sequence information, we constructed four network frameworks, with the systematically optimized parameters used for the models. The thorough comparison analysis on two independent data sets of humans and mice and six independent data sets from other species demonstrated remarkably increased sensitivity and accuracy of the O-GlcNAcPRED-DL models, outperforming other existing tools. Moreover, a user-friendly Web server for O-GlcNAcPRED-DL has been constructed, which is freely available at http://oglcnac.org/pred_dl.

iLoc-miRNA: extracellular/intracellular miRNA prediction using deep BiLSTM with attention mechanism.

The location of microRNAs (miRNAs) in cells determines their function in regulation activity. Studies have shown that miRNAs are stable in the extracellular environment that mediates cell-to-cell communication and are located in the intracellular region that responds to cellular stress and environmental stimuli. Though in situ detection techniques of miRNAs have made great contributions to the study of the localization and distribution of miRNAs, miRNA subcellular localization and their role are still in progress. Recently, some machine learning-based algorithms have been designed for miRNA subcellular location prediction, but their performance is still far from satisfactory. Here, we present a new data partitioning strategy that categorizes functionally similar locations for the precise and instructive prediction of miRNA subcellular location in Homo sapiens. To characterize the localization signals, we adopted one-hot encoding with post padding to represent the whole miRNA sequences, and proposed a deep bidirectional long short-term memory with the multi-head self-attention algorithm to model. The algorithm showed high selectivity in distinguishing extracellular miRNAs from intracellular miRNAs. Moreover, a series of motif analyses were performed to explore the mechanism of miRNA subcellular localization. To improve the convenience of the model, a user-friendly web server named iLoc-miRNA was established (http://iLoc-miRNA.lin-group.cn/).

Do deep learning models make a difference in the identification of antimicrobial peptides?

In the last few decades, antimicrobial peptides (AMPs) have been explored as an alternative to classical antibiotics, which in turn motivated the development of machine learning models to predict antimicrobial activities in peptides. The first generation of these predictors was filled with what is now known as shallow learning-based models. These models require the computation and selection of molecular descriptors to characterize each peptide sequence and train the models. The second generation, known as deep learning-based models, which no longer requires the explicit computation and selection of those descriptors, started to be used in the prediction task of AMPs just four years ago. The superior performance claimed by deep models regarding shallow models has created a prevalent inertia to using deep learning to identify AMPs. However, methodological flaws and/or modeling biases in the building of deep models do not support such superiority. Here, we analyze the main pitfalls that led to establish biased conclusions on the leading performance of deep models. Also, we analyze whether deep models truly contribute to achieve better predictions than shallow models by performing fair studies on different state-of-the-art benchmarking datasets. The experiments reveal that deep models do not outperform shallow models in the classification of AMPs, and that both types of models codify similar chemical information since their predictions are highly similar. Thus, according to the currently available datasets, we conclude that the use of deep learning could not be the most suitable approach to develop models to identify AMPs, mainly because shallow models achieve comparable-to-superior performances and are simpler (Ockham's razor principle). Even so, we suggest the use of deep learning only when its capabilities lead to obtaining significantly better performance gains worth the additional computational cost.

Deep hybrid modeling of a HEK293 process: Combining long short-term memory networks with first principles equations.

The combination of physical equations with deep learning is becoming a promising methodology for bioprocess digitalization. In this paper, we investigate for the first time the combination of long short-term memory (LSTM) networks with first principles equations in a hybrid workflow to describe human embryonic kidney 293 (HEK293) culture dynamics. Experimental data of 27 extracellular state variables in 20 fed-batch HEK293 cultures were collected in a parallel high throughput 250 mL cultivation system in an industrial process development setting. The adaptive moment estimation method with stochastic regularization and cross-validation were employed for deep learning. A total of 784 hybrid models with varying deep neural network architectures, depths, layers sizes and node activation functions were compared. In most scenarios, hybrid LSTM models outperformed classical hybrid Feedforward Neural Network (FFNN) models in terms of training and testing error. Hybrid LSTM models revealed to be less sensitive to data resampling than FFNN hybrid models. As disadvantages, Hybrid LSTM models are in general more complex (higher number of parameters) and have a higher computation cost than FFNN hybrid models. The hybrid model with the highest prediction accuracy consisted in a LSTM network with seven internal states connected in series with dynamic material balance equations. This hybrid model correctly predicted the dynamics of the 27 state variables (R2 = 0.93 in the test data set), including biomass, key substrates, amino acids and metabolic by-products for around 10 cultivation days.

Developing a deep learning model for sleep stage prediction in obstructive sleep apnea cohort using 60 GHz frequency-modulated continuous-wave radar.

Given the significant impact of sleep on overall health, radar technology offers a promising, non-invasive, and cost-effective avenue for the early detection of sleep disorders, even prior to relying on polysomnography (PSG)-based classification. In this study, we employed an attention-based bidirectional long short-term memory (Attention Bi-LSTM) model to accurately predict sleep stages using 60 GHz frequency-modulated continuous-wave (FMCW) radar. Our dataset comprised 78 participants from an ongoing obstructive sleep apnea (OSA) cohort, recruited between July 2021 and November 2022, who underwent overnight polysomnography alongside radar sensor monitoring. The dataset encompasses comprehensive polysomnography recordings, spanning both sleep and wakefulness states. The predictions achieved a Cohen's kappa coefficient of 0.746 and an overall accuracy of 85.2% in classifying wakefulness, rapid-eye-movement (REM) sleep, and non-REM (NREM) sleep (N1 + N2 + N3). The results demonstrated that the models incorporating both Radar 1 and Radar 2 data consistently outperformed those using only Radar 1 data, indicating the potential benefits of utilising multiple radars for sleep stage classification. Although the performance of the models tended to decline with increasing OSA severity, the addition of Radar 2 data notably improved the classification accuracy. These findings demonstrate the potential of radar technology as a valuable screening tool for sleep stage classification.

Identification of Methamphetamine Abusers Can Be Supported by EEG-Based Wavelet Transform and BiLSTM Networks.

Methamphetamine (MA) is a neurological drug, which is harmful to the overall brain cognitive function when abused. Based on this property of MA, people can be divided into those with MA abuse and healthy people. However, few studies to date have investigated automatic detection of MA abusers based on the neural activity. For this reason, the purpose of this research was to investigate the difference in the neural activity between MA abusers and healthy persons and accordingly discriminate MA abusers. First, we performed event-related potential (ERP) analysis to determine the time range of P300. Then, the wavelet coefficients of the P300 component were extracted as the main features, along with the time and frequency domain features within the selected P300 range to classify. To optimize the feature set, F_score was used to remove features below the average score. Finally, a Bidirectional Long Short-term Memory (BiLSTM) network was performed for classification. The experimental result showed that the detection accuracy of BiLSTM could reach 83.85%. In conclusion, the P300 component of EEG signals of MA abusers is different from that in normal persons. Based on this difference, this study proposes a novel way for the prevention and diagnosis of MA abuse.

Forecasting acute kidney injury and resource utilization in ICU patients using longitudinal, multimodal models.

BACKGROUND: Advances in artificial intelligence (AI) have realized the potential of revolutionizing healthcare, such as predicting disease progression via longitudinal inspection of Electronic Health Records (EHRs) and lab tests from patients admitted to Intensive Care Units (ICU). Although substantial literature exists addressing broad subjects, including the prediction of mortality, length-of-stay, and readmission, studies focusing on forecasting Acute Kidney Injury (AKI), specifically dialysis anticipation like Continuous Renal Replacement Therapy (CRRT) are scarce. The technicality of how to implement AI remains elusive. OBJECTIVE: This study aims to elucidate the important factors and methods that are required to develop effective predictive models of AKI and CRRT for patients admitted to ICU, using EHRs in the Medical Information Mart for Intensive Care (MIMIC) database. METHODS: We conducted a comprehensive comparative analysis of established predictive models, considering both time-series measurements and clinical notes from MIMIC-IV databases. Subsequently, we proposed a novel multi-modal model which integrates embeddings of top-performing unimodal models, including Long Short-Term Memory (LSTM) and BioMedBERT, and leverages both unstructured clinical notes and structured time series measurements derived from EHRs to enable the early prediction of AKI and CRRT. RESULTS: Our multimodal model achieved a lead time of at least 12 h ahead of clinical manifestation, with an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.888 for AKI and 0.997 for CRRT, as well as an Area Under the Precision Recall Curve (AUPRC) of 0.727 for AKI and 0.840 for CRRT, respectively, which significantly outperformed the baseline models. Additionally, we performed a SHapley Additive exPlanation (SHAP) analysis using the expected gradients algorithm, which highlighted important, previously underappreciated predictive features for AKI and CRRT. CONCLUSION: Our study revealed the importance and the technicality of applying longitudinal, multimodal modeling to improve early prediction of AKI and CRRT, offering insights for timely interventions. The performance and interpretability of our model indicate its potential for further assessment towards clinical applications, to ultimately optimize AKI management and enhance patient outcomes.

Artificial intelligence-based forecasting model for incinerator in sulfur recovery units to predict SO2 emissions.

Pollutant emissions from chemical plants are a major concern in the context of environmental safety. A reliable emission forecasting model can provide important information for optimizing the process and improving the environmental performance. In this work, forecasting models are developed for the prediction of SO2 emission from a Sulfur Recovery Unit (SRU). Since SRUs incorporate complex chemical reactions, first-principle models are not suitable to predict emission levels based on a given feed condition. Accordingly, artificial intelligence-based models such as standard machine learning (ML) algorithms, multi-layer perceptron (MLP), long short-term memory (LSTM), one-dimensional convolution (1D-CNN), and CNN-LSTM models were tested, and their performance was evaluated. The input features and hyperparameters of the models were optimized to achieve maximum performance. The performance was evaluated in terms of mean squared error (MSE) and mean absolute percentage Error (MAPE) for 1 h, 3 h and 5 h ahead of forecasting. The reported results show that the CNN-LSTM encoder-decoder model outperforms other tested models, with its superiority becoming more pronounced as the forecasting horizon increased from 1 h to 5 h. For the 5-h ahead forecasting, the proposed model showed a MAPE advantage of 17.23%, 4.41%, and 2.83%, respectively over the 1D-CNN, Deep LSTM, and single-layer LSTM models in the larger dataset.

Predicting concrete strength early age using a combination of machine learning and electromechanical impedance with nano-enhanced sensors.

To ensure the structural integrity of concrete and prevent unanticipated fracturing, real-time monitoring of early-age concrete's strength development is essential, mainly through advanced techniques such as nano-enhanced sensors. The piezoelectric-based electro-mechanical impedance (EMI) method with nano-enhanced sensors is emerging as a practical solution for such monitoring requirements. This study presents a strength estimation method based on Non-Destructive Testing (NDT) Techniques and Long Short-Term Memory (LSTM) and artificial neural networks (ANNs) as hybrid (NDT-LSTMs-ANN), including several types of concrete strength-related agents. Input data includes water-to-cement rate, temperature, curing time, and maturity based on interior temperature, allowing experimentally monitoring the development of concrete strength from the early steps of hydration and casting to the last stages of hardening 28 days after the casting. The study investigated the impact of various factors on concrete strength development, utilizing a cutting-edge approach that combines traditional models with nano-enhanced piezoelectric sensors and NDT-LSTMs-ANN enhanced with nanotechnology. The results demonstrate that the hybrid provides highly accurate concrete strength estimation for construction safety and efficiency. Adopting the piezoelectric-based EMI technique with these advanced sensors offers a viable and effective monitoring solution, presenting a significant leap forward for the construction industry's structural health monitoring practices.

Support vector machine-based stock market prediction using long short-term memory and convolutional neural network with aquila circle inspired optimization.

Predicting the stock market is one of the significant chores and has a successful prediction of stock rates, and it helps in making correct decisions. The prediction of the stock market is the main challenge due to blaring, chaotic data as well as non-stationary data. In this research, the support vector machine (SVM) is devised for performing an effective stock market prediction. At first, the input time series data is considered and the pre-processing of data is done by employing a standard scalar. Then, the time intrinsic features are extracted and the suitable features are selected in the feature selection stage by eliminating other features using recursive feature elimination. Afterwards, the Long Short-Term Memory (LSTM) based prediction is done, wherein LSTM is trained to employ Aquila circle-inspired optimization (ACIO) that is newly introduced by merging Aquila optimizer (AO) with circle-inspired optimization algorithm (CIOA). On the other hand, delay-based matrix formation is conducted by considering input time series data. After that, convolutional neural network (CNN)-based prediction is performed, where CNN is tuned by the same ACIO. Finally, stock market prediction is executed utilizing SVM by fusing the predicted outputs attained from LSTM-based prediction and CNN-based prediction. Furthermore, the SVM attains better outcomes of minimum mean absolute percentage error; (MAPE) and normalized root-mean-square error (RMSE) with values about 0.378 and 0.294.

Predicting Knee Joint Contact Forces During Normal Walking Using Kinematic Inputs With a Long-Short Term Neural Network.

Knee joint contact forces are commonly estimated via surrogate measures (i.e., external knee adduction moments or musculoskeletal modeling). Despite its capabilities, modeling is not optimal for clinicians or persons with limited experience. The purpose of this study was to design a novel prediction method for knee joint contact forces that is simplistic in terms of required inputs. This study included marker trajectories and instrumented knee forces during normal walking from the "Grand Challenge" (n = 6) and "CAMS" (n = 2) datasets. Inverse kinematics were used to derive stance phase hip (sagittal, frontal, transverse), knee (sagittal, frontal), ankle (sagittal), and trunk (frontal) kinematics. A long-short term memory network (LSTM) was created using matlab to predict medial and lateral knee force waveforms using combinations of the kinematics. The Grand Challenge and CAMS datasets trained and tested the network, respectively. Musculoskeletal modeling forces were derived using static optimization and joint reaction tools in OpenSim. Waveform accuracy was determined as the proportion of variance and root-mean-square error between network predictions and in vivo data. The LSTM network was highly accurate for medial forces (R2 = 0.77, RMSE = 0.27 BW) and required only frontal hip and knee and sagittal hip and ankle kinematics. Modeled medial force predictions were excellent (R2 = 0.77, RMSE = 0.33 BW). Lateral force predictions were poor for both methods (LSTM R2 = 0.18, RMSE = 0.08 BW; modeling R2 = 0.21, RMSE = 0.54 BW). The designed LSTM network outperformed most reports of musculoskeletal modeling, including those reached in this study, revealing knee joint forces can accurately be predicted by using only kinematic input variables.

Feasibility and validity of using deep learning to reconstruct 12-lead ECG from three­lead signals.

BACKGROUND: In the field of mobile health, portable dynamic electrocardiogram (ECG) monitoring devices often have a limited number of lead electrodes due to considerations, such as portability and battery life. This situation leads to a contradiction between the demand for standard 12­lead ECG information and the limited number of leads collected by portable devices. METHODS: This study introduces a composite ECG vector reconstruction network architecture based on convolutional neural network (CNN) combined with recurrent neural network by using leads I, II, and V2. This network is designed to reconstruct three­lead ECG signals into 12­lead ECG signals. A 1D CNN abstracts and extracts features from the spatial domain of the ECG signals, and a bidirectional long short-term memory network analyzes the temporal trends in the signals. Then, the ECG signals are inputted into the model in a multilead, single-channel manner. RESULTS: Under inter-patient conditions, the mean reconstructed Root mean squared error (RMSE) for precordial leads V1, V3, V4, V5, and V6 were 28.7, 17.3, 24.2, 36.5, and 25.5 µV, respectively. The mean overall RMSE and reconstructed Correlation coefficient (CC) were 26.44 µV and 0.9562, respectively. CONCLUSION: This paper presents a solution and innovative approach for recovering 12­lead ECG information when only three­lead information is available. After supplementing with comprehensive leads, we can analyze the cardiac health status more comprehensively across 12 dimensions.

Detecting DoS Attacks through Synthetic User Behavior with Long Short-Term Memory Network.

With the escalation in the size and complexity of modern Denial of Service attacks, there is a need for research in the context of Machine Learning (ML) used in attack execution and defense against such attacks. This paper investigates the potential use of ML in generating behavioral telemetry data using Long Short-Term Memory network and spoofing requests for the analyzed traffic to look legitimate. For this research, a custom testing environment was built that listens for mouse and keyboard events and analyzes them accordingly. While the economic feasibility of this attack currently limits its immediate threat, advancements in technology could make it more cost-effective for attackers in the future. Therefore, proactive development of countermeasures remains essential to mitigate potential risks and stay ahead of evolving attack methods.