Convolutional Bidirectional Long Short-term Memory Research Articles

Doppler Radar Sensor-Based Fall Detection Using a Convolutional Bidirectional Long Short-Term Memory Model.

Falls among the elderly are a common and serious health risk that can lead to physical injuries and other complications. To promptly detect and respond to fall events, radar-based fall detection systems have gained widespread attention. In this paper, a deep learning model is proposed based on the frequency spectrum of radar signals, called the convolutional bidirectional long short-term memory (CB-LSTM) model. The introduction of the CB-LSTM model enables the fall detection system to capture both temporal sequential and spatial features simultaneously, thereby enhancing the accuracy and reliability of the detection. Extensive comparison experiments demonstrate that our model achieves an accuracy of 98.83% in detecting falls, surpassing other relevant methods currently available. In summary, this study provides effective technical support using the frequency spectrum and deep learning methods to monitor falls among the elderly through the design and experimental validation of a radar-based fall detection system, which has great potential for improving quality of life for the elderly and providing timely rescue measures.

IRLF-SRNet: A super-resolution network based on local–global feature enhance-refine for camera-array based infrared light field images

Super resolution (SR) is essential for the camera-array based infrared light field (IRLF) images. However, the existing SR methods are mainly designed for visible LF images and are unsuitable for IRLF. This is because the sub-aperture images (SAIs) in IRLF hold blurred edges and pixel-level shifts. Artifacts and unbalanced SR performance may exist. In this paper, we propose a novel SR network, named IRLF-SRnet, to mitigate the above problems. It includes two designs: (1) local–global feature enhance-refine strategy, and (2) multi-branch cross-view correlation modeling block. The former uses global features from all SAIs to enhance the local feature from one SAI, which enhances the edges in each SAI implicitly. Then, it refines the global feature with the enhanced local feature, which further refines the edges. The latter first divides and sends the features of SAIs into multiple branches, and then models the cross-view correlation among features in each branch by bidirectional convolutional long-short term memory (BiConvLSTM), so that be aware of the pixel-level shifts. Qualitative and quantitative results show that our method outperforms state-of-the-art methods, with more balanced SR performance and fewer artifacts.

Multi-dimensional attention-aided transposed ConvBiLSTM network for hyperspectral image super-resolution

Hyperspectral (HS) image always suffers from the deficiency of low spatial resolution, compared with conventional optical image types, which has limited its further applications in remote sensing areas. Therefore, HS image super-resolution (SR) techniques are broadly employed in order to observe finer spatial structures while preserving the spectra of ground covers. In this paper, a novel multi-dimensional attention-aided transposed convolutional long-short term memory (LSTM) network is proposed for single HS image super-resolution task. The proposed network employs the convolutional bi-directional LSTM for the purpose of local and non-local spatial–spectral feature explorations, and transposed convolution for the purpose of image amplification and reconstruction. Moreover, a multi-dimensional attention module is proposed, aiming to capture the salient features on spectral, channel, and spatial dimensions, simultaneously, to further improve the learning abilities of network. Experiments on four commonly-used HS images demonstrate the effectiveness of this approach, compared with several state-of-the-art deep learning-based SR methods.

Research on a Deep Ensemble Learning Model for the Ultra-Short-Term Probabilistic Prediction of Wind Power

An accurate method for predicting wind power is crucial in effectively mitigating wind energy fluctuations and ensuring a stable power supply. Nevertheless, the inadequacy of the stability of wind energy severely hampers the consistent functioning of the power grid and the reliable provision of electricity. To enhance the accuracy of wind power forecasting, this paper proposes an ensemble model named the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and convolutional bidirectional long short-term memory (CNN-BiLSTM), which incorporates a data preprocessing technique, feature selection method, deep ensemble model, and adaptive control. Initially, CEEMDAN is utilized to decompose wind speed and power sequences and hence obtain decomposed subsequences for further analysis. Subsequently, the CNN is used to extract features from each subsequence, whereas each subsequence is processed by BiLSTM to obtain an ultra-short-term deterministic prediction model. Additionally, the adaptive kernel density estimation (AKDE) method is employed to estimate the probabilistic distribution of prediction error, enabling ultra-short-term probabilistic wind power prediction. Finally, based on real datasets, the reliability of the model in probabilistic prediction is verified through the evaluation metrics of multi-step prediction intervals (PIs).

Detection of violence incitation expressions in Urdu tweets using convolutional neural network

The popularity and widespread use of social media are constantly generating unmonitored data, spreading unwanted content such as hate speech and expressions that incite violence. Automatic detection of violence incitation is a challenging task and to the best of our knowledge, Urdu language has been completely neglected. Therefore, a robust framework is proposed for identifying expressions exhibiting violence incitation in Urdu tweets. The potentials of the semantic, word embeddings, and language models are explored to learn contextualized representations of the violence incitation in Urdu tweets. In addition, the strength of the 1-Dimensional Convolutional Neural Network (1D-CNN) is exploited by tunning its parameters on the newly proposed annotated Urdu corpus. The annotated dataset consists of 4808 tweets manually collected from Pakistani Twitter accounts. The performance of 1D-CNN with word uni-gram, Urdu Bidirectional Encoder Representations from Transformer (Urdu-BERT), and Urdu- Robustly Optimized BERT Approach (Urdu-RoBERTa) models is compared to fine-tuned Urdu-RoBERTa, Bidirectional Long short-term memory (BiLSTM), Convolutional BiLSTM (CBi-LSTM), and six state-of-the-art Machine Learning (ML) models. The results reveal that the 1D-CNN with word uni-gram model shows benchmark performance by demonstrating 89.84% accuracy and 89.80% macro f1-score. Furthermore, it outperforms all comparable models and achieves 89.76% f1-score for the violence class, and 89.84% f1-score for not-violence class identification. The uniqueness of the proposed model is evaluated using MARS shine-through and MARS occlusion metrics and the CNN model outperformed the others. The MARS metrics facilitate evaluation and visualization of the classifier performance in terms of capturing unique true positive samples that are not predicted by other models. The findings of the proposed framework are very supportive for further investigation in this domain.

Mass segmentation in automated breast ultrasound using an enhanced attentive UNet

Breast cancer is the most diagnosed cancer among women. Early detection of breast cancer through screening high risk population significantly reduces the mortality rate. To this end, 3-D Automated Breast Ultrasound (ABUS) is a favorable modality due to its complementary information in comparison with other modalities. Different characteristics of breast masses and the large number of ABUS slices result in time consuming and exhaustive evaluations by radiologists. This study aims to develop a fully-automatic segmentation system that acts as a second interpreter to facilitate the interpretation process. Specifically, a bidirectional convolutional long short-term memory (Bi-ConvLSTM) network is adopted for tumor detection. Afterwards, a 2-D attentive UNet takes an ABUS slice and its approximate saliency map to precisely segment breast masses. The attention blocks of the proposed network use this map to direct the network’s attention to regions with high saliency values. We proposed two enhanced versions of the base attention module with superior performance and less complexity. To increase the robustness against the mass size variations, we stacked several side outputs from different stages of the network and control their contribution to final results by a Convolutional Block Attention Module (CBAM). The effectiveness of the proposed modifications is verified with step-by-step evaluations, and our optimal model achieves a Dice similarity index of 85.82% on a dataset of 60 volumes.

A tweet sentiment classification approach using an ensemble classifier

Social media users are more receptive to products or events and share their thoughts through raw textual data, which is classified as semi-structured data. This data, which is presented using a variety of terminologies, is noisy by nature but yet contains important information and superfluous details, giving analysts a way to identify patterns and knowledge. This hidden information must be extracted from language data in order to make informed decisions and create strategic plans for entering new markets. Among the most prominent fields of study are natural language processing (NLP) and data mining techniques, especially when it comes to sentiment analysis—the process of identifying the feelings and insights concealed in the data. Twitter is one of the significant microblogging platform with millions of users. These users use Twitter to share sentiments using hash tags on different topics and to make status updates known as tweets. Twitter is therefore regarded as a significant real-time source and as one of the most active opinion indicators. The volume of information is produced by Twitter is enormous and manually scanning the entire data set is difficult process. The paper proposed an ensemble classifier to categorize emotion of the tweets on the basis of polarities such as positive and negative.In our study, we ensemble classifiers which is a combination of Random Forest (RF), Support Vector Machine (SVM) and Decision Tree (DT). The data is collected from Twitter API and the Twitter data is analysed autonomously to define public view on particular topic. The features obtained after the process of dimensionality reduction using LDA undergoes the stage of feature selection using Wrapper based technique. The iterative Wrapper based technique predict score for the features, the features with low score are ignored and high score is proceeded for classification. The ensemble classifier used Adaptive Boosting (AdaBoost) technique where the output from the Machine Learning (ML) classifiers are combined to produce a single output. Adaboost combines the poor classifiers and extracts the prediction value to make a better classifier. The experimental results show that the proposed ensemble classifier provides better accuracy of 93.42 % that is comparatively better than existing Convolutional Bidirectional - Long Short-Term Memory (ConvBiLSTM) classifier and Hybrid Lexicon- Naïve Bayes Classifier (HL-NBC) which produce classification accuracy of 91.53 % and 89.61 % respectively.

Hybrid deep learning model for heart disease detection on 12-lead electrocardiograms

This research possesses the producing and taking the assessment of a new deep learning structure, namely, Deep Convolutional BiLSTM Hybrid Network, specialized for arrhythmia recognition before ECG records. Through PhysioNet Challenge 2021 dataset, which has collected different styles of the ECG recordings from nine different arrhythmia types, this study is trying to respond to the critical need that non-attendant and accurate arrhythmia detection is required in the medical field. By utilizing both convolutional neural networks (CNNs) and bidirectional long short-term memory (BiLSTM) units that allow our model to carry out spatial and temporal operations, which is essential to the native dynamics existing ECG signal, we are able to get in view a more fine-grained analysis surpassing other traditional approaches. The suggested algorithm which has achieved accuracy, precision, recall, and F-score of 98.5%, 98.2%, 98.2%, and 98.4% percent respectively has proven to be a novel and more accurate solution compared to the existing state-of-the-art model when similar kinds of tasks are performed. These results not only reveal the effectiveness of CNNs and BiLSTM toginger in understanding complicated biomedical signs but also shed a light on the prospect of deep learning in raising the standards of dairgocis and health care practices. The research outcome of arrhythmia diagnosis by arranging new standard carpatients would bring a lot of changes to the existing medical informatics that provide a scalable solution that would be implemented to every healthcare institution globally for timely and accurate diagnosis.

A new hybrid model for photovoltaic output power prediction.

Recently, with the development of renewable energy technologies, photovoltaic (PV) power generation is widely used in the grid. However, as PV power generation is influenced by external factors, such as solar radiation fluctuation, PV output power is intermittent and volatile, and thus the accurate PV output power prediction is imperative for the grid stability. To address this issue, based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), improved artificial rabbits optimization (IARO) and convolutional bidirectional long short-term memory (CBiLSTM), a new hybrid model denoted by CEEMDAN-IARO-CBiLSTM is proposed. In addition, inputs of the proposed model are optimized by analyzing influential factors of PV output power with Pearson correlation coefficient method. In order to verify the prediction accuracy, CEEMDAN-IARO-CBiLSTM is compared with other well-known methods under different weather conditions and different seasons. Specifically, for different weather conditions, MAE and RMSE of the proposed model decrease by at least 0.329 and 0.411, 0.086 and 0.021, and 0.140 and 0.220, respectively. With respect to different seasons, MAE and RMSE of the proposed model decrease by at least 0.270 and 0.378, 0.158 and 0.209, 0.210 and 0.292, and 1.096 and 1.148, respectively. Moreover, two statistical tests are conducted, and the corresponding results show that the prediction performance of CEEMDAN-IARO-CBiLSTM is superior to other well-known methods.

New data about library service quality and convolution prediction

Library service quality, one of the key performance indicators of service qualities in universities, has been considered deeply in management strategies as part of the Fourth Industrial Revolution, especially, after the Covid-19 pandemic. We undertook a survey around Universities in Ho Chi Minh City and Tien Giang University, Vietnam focused on freshmen and sophomores to assess library service quality for improving the learning service quality. Machine learning has been deployed for predicting the library service, quality, and has been adopted successfully in depicting the assessment results. To perform the effectiveness of data, the Convolution Bidirectional Long-Short Term Memory (Conv-BiLSTM), and Convolution Bidirectional Gated Recurrent Unit (ConvBiGRU) were used. The models have illustrated appropriate performances when providing sufficient accuracy and extracting the prediction of the output.

Comparison of machine learning and deep learning techniques for the prediction of air pollution: a case study from China

The adverse effect of air pollution has always been a problem for human health. The presence of a high level of air pollutants can cause severe illnesses such as emphysema, chronic obstructive pulmonary disease (COPD), or asthma. Air quality prediction helps us to undertake practical action plans for controlling air pollution. The Air Quality Index (AQI) reflects the degree of concentration of pollutants in a locality. The average AQI was calculated for the various cities in China to understand the annual trends. Furthermore, the air quality index has been predicted for ten major cities across China using five different deep learning techniques, namely, Recurrent Neural Network (RNN), Bidirectional Gated Recurrent unit (Bi-GRU), Bidirectional Long Short-Term Memory (BiLSTM), Convolutional Neural Network BiLSTM (CNN-BiLSTM), and Convolutional BiLSTM (Conv1D-BiLSTM). The performance of these models has been compared with a machine learning model, eXtreme Gradient Boosting (XGBoost) to discover the most efficient deep learning model. The results suggest that the machine learning model, XGBoost, outperforms the deep learning models. While Conv1D-BiLSTM and CNN-BiLSTM perform well among the deep learning models in the estimation of the air quality index (AQI), RNN and Bi-GRU are the least performing ones. Thus, both XGBoost and neural network models are capable of capturing the non-linearity present in the dataset with reliable accuracy.

Chaotic Time Series Prediction of Multi‐Dimensional Nonlinear System Based on Bidirectional LSTM Model

AbstractThe current work proposes a hybrid data‐driven model—Convolutional bidirectional long–short term memory (CNN‐BLSTM) for predicting chaotic behavior of three‐coupled Duffing oscillator nonlinear system, in which the CNN is for efficiently extracting the more robust and informative representations of chaotic sequences while the BLSTM is for holding the long‐term dependencies combining the past and future contexts. Different from traditional analytical and numerical approaches, the proposed prediction model features the benefit of focusing on the measured data solely without extensive professional domain knowledge. Additionally, three more recurrent neural network (RNN) models, including simple RNNs, stack LSTMs, and BLSTM, are built and comparisons of generalization performances to the CNN‐BLSTM are conducted. From the findings so far, the CNN‐BLSTM is able to learn the pattern of chaotic time sequence data with less training time and apply the acquired knowledge to the unseen dataset with lower errors. Moreover, the current work decently demonstrates that the proposed model outperforms other three models in terms of stability at different noise levels from two evaluation criteria. The CNN‐BLSTM provides useful guidance for the consideration of predicting multi‐dimensional nonlinear chaotic behavior.

An End-to-End Multi-Channel Convolutional Bi-LSTM Network for Automatic Sleep Stage Detection.

Sleep stage detection from polysomnography (PSG) recordings is a widely used method of monitoring sleep quality. Despite significant progress in the development of machine-learning (ML)-based and deep-learning (DL)-based automatic sleep stage detection schemes focusing on single-channel PSG data, such as single-channel electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG), developing a standard model is still an active subject of research. Often, the use of a single source of information suffers from data inefficiency and data-skewed problems. Instead, a multi-channel input-based classifier can mitigate the aforementioned challenges and achieve better performance. However, it requires extensive computational resources to train the model, and, hence, a tradeoff between performance and computational resources cannot be ignored. In this article, we aim to introduce a multi-channel, more specifically a four-channel, convolutional bidirectional long short-term memory (Bi-LSTM) network that can effectively exploit spatiotemporal features of data collected from multiple channels of the PSG recording (e.g., EEG Fpz-Cz, EEG Pz-Oz, EOG, and EMG) for automatic sleep stage detection. First, a dual-channel convolutional Bi-LSTM network module has been designed and pre-trained utilizing data from every two distinct channels of the PSG recording. Subsequently, we have leveraged the concept of transfer learning circuitously and have fused two dual-channel convolutional Bi-LSTM network modules to detect sleep stages. In the dual-channel convolutional Bi-LSTM module, a two-layer convolutional neural network has been utilized to extract spatial features from two channels of the PSG recordings. These extracted spatial features are subsequently coupled and given as input at every level of the Bi-LSTM network to extract and learn rich temporal correlated features. Both Sleep EDF-20 and Sleep EDF-78 (expanded version of Sleep EDF-20) datasets are used in this study to evaluate the result. The model that includes an EEG Fpz-Cz + EOG module and an EEG Fpz-Cz + EMG module can classify sleep stage with the highest value of accuracy (ACC), Kappa (Kp), and F1 score (e.g., 91.44%, 0.89, and 88.69%, respectively) on the Sleep EDF-20 dataset. On the other hand, the model consisting of an EEG Fpz-Cz + EMG module and an EEG Pz-Oz + EOG module shows the best performance (e.g., the value of ACC, Kp, and F1 score are 90.21%, 0.86, and 87.02%, respectively) compared to other combinations for the Sleep EDF-78 dataset. In addition, a comparative study with respect to other existing literature has been provided and discussed in order to exhibit the efficacy of our proposed model.

Accelerating magnetotelluric forward modeling with deep learning: Conv-BiLSTM and D-LinkNet

Magnetotelluric forward modeling is important for exploring underground electromagnetic anomalies. Although directly solving the electromagnetic wave equation has high accuracy, its computational cost is usually unaffordable for large-scale models. A neural network (NN) can increase the computation of the magnetotelluric forward modeling; however, its numerical accuracy is limited owing to the use of a simple network structure and small-scale training data sets. We have increased the computational efficiency of the magnetotelluric forward modeling by deep learning based on cyclic NN and full convolution NN models. First, we have extracted the basic characteristics of the 2D-magnetotelluric forward modeling, which were important for selecting and optimizing the network. Then, we have developed two forward network models: convolutional bidirectional long short-term memory (Conv-BiLSTM) and LinkNet with pretrained encoder and dilated convolution (D-LinkNet). Next, we have constructed data sets of large-scale multiple anomalies. Finally, we have tested our models using various examples. Existing methods only consider a single anomaly and have low accuracy; in contrast, our methods can handle multianomaly models because they have strong generalization, even though the training is based on models with two or three anomalies. Numerical experiments find that the average accuracy of the Conv-BiLSTM and D-LinkNet forward network models was 87.5% and 95.3%, respectively. Compared with D-LinkNet, the Conv-BiLSTM network model has lower accuracy but higher computational efficiency. Our deep-learning schemes can significantly reduce the computational burdens of the magnetotelluric forward modeling, and thus allow us to perform swift inversions of multianomaly models.

Deep-Learning-Driven Proactive Maintenance Management of IoT-Empowered Smart Toilet

The recent proliferation of Internet of Things (IoT) sensors has driven a myriad of industrial and urban applications. Through analyzing massive data collected by these sensors, the proactive maintenance management can be achieved such that the maintenance schedule of the installed equipment can be optimized. Despite recent progress in proactive maintenance management in industrial scenarios, there are few studies on proactive maintenance management in urban informatics. In this article, we present an integrated framework of IoT and cloud computing platform for the proactive maintenance management in smart city. Our framework consists of: 1) an IoT monitoring system for collecting time-series data of operating and ambient conditions of the equipment and 2) a hybrid deep learning model, namely, convolutional bidirectional long short-term memory (CBLM) model for forecasting the operating and ambient conditions based on the collected time-series data. In addition, we also develop a naïve Bayes classifier to detect abnormal operating and ambient conditions and assist management personnel in scheduling maintenance tasks. To evaluate our framework, we deployed the IoT system in a Hong Kong public toilet, which is the first application of proactive maintenance management for a public hygiene and sanitary facility to the best of our knowledge. We collected the sensed data more than 33 days (808 h) in this real system. Extensive experiments on the collected data demonstrated that our proposed CBLM outperformed six traditional machine learning algorithms.

Short term power load forecasting based on BES-VMD and CNN-Bi-LSTM method with error correction

Aiming at the strong non-linear and non-stationary characteristics of power load, a short-term power load forecasting method based on bald eagle search (BES) optimization variational mode decomposition (VMD), convolutional bi-directional long short-term memory (CNN-Bi-LSTM) network and considering error correction is studied to improve the accuracy of load forecasting. Firstly, a decomposition loss evaluation criterion is established, and the VMD optimal decomposition parameters under the evaluation criterion are determined based on BES to improve the decomposition quality of the signal. Then, the original load sequence is decomposed into different modal components, and the corresponding CNN-Bi-LSTM network prediction models are established for each modal component. In addition, considering the influence of various modal components, holiday and meteorological factors on the error, an error correction model considering short-term factors is established to mine the hidden information contained in the error to reduce the inherent error of the model. Finally, the proposed method is applied to a public dataset provided by a public utility in the United States. The results show that this method can better track the changes of load and effectively improve the accuracy of short-term power load forecasting.

Differential diagnosis of prostate cancer and benign prostatic hyperplasia based on DCE-MRI using bi-directional CLSTM deep learning and radiomics.

Dynamic contrast-enhanced MRI (DCE-MRI) is routinely included in the prostate MRI protocol for a long time; its role has been questioned. It provides rich spatial and temporal information. However, the contained information cannot be fully extracted in radiologists' visual evaluation. More sophisticated computer algorithms are needed to extract the higher-order information. The purpose of this study was to apply a new deep learning algorithm, the bi-directional convolutional long short-term memory (CLSTM) network, and the radiomics analysis for differential diagnosis of PCa and benign prostatic hyperplasia (BPH). To systematically investigate the optimal amount of peritumoral tissue for improving diagnosis, a total of 9 ROIs were delineated by using 3 different methods. The results showed that bi-directional CLSTM with ± 20% region growing peritumoral ROI achieved the mean AUC of 0.89, better than the mean AUC of 0.84 by using the tumor alone without any peritumoral tissue (p = 0.25, not significant). For all 9 ROIs, deep learning had higher AUC than radiomics, but only reaching the significant difference for ± 20% region growing peritumoral ROI (0.89 vs. 0.79, p = 0.04). In conclusion, the kinetic information extracted from DCE-MRI using bi-directional CLSTM may provide helpful supplementary information for diagnosis of PCa.

A Fusion Deep Learning Model via Sequence-to-Sequence Structure for Multiple-Road-Segment Spot Speed Prediction

Forecasting the future average speed fluctuation is conducive to timely perceiving the degree of urban road congestion. Nevertheless, a new challenge has arisen in accurately predicting the spot speed on an urban road network area composed by multiple road segments. To surmount this, an intelligent method for spot speed estimation, namely, the fusion deep learning model with sequence-to-sequence structure (Seq2Seq-FDL), is proposed. It is a sequence-to-sequence learning structure that covers the encoding context vector. The unidirectional convolutional long short-term memory (ConvLSTM) and bidirectional ConvLSTM networks are used to capture traffic short-term and periodic spatiotemporal synchronization characteristics, respectively. Finally, the prediction results are computed by linear feature fusion. Furthermore, the black-box effect of the proposed model is explained by the least absolute shrinkage and selection operator regression model based on Granger causality, and the rationality of the model is verified with an example of spot speed in a road network of Guangzhou. The experimental results were shown to indicate that the traffic spatiotemporal characteristics significantly contributed to the prediction effect of the Seq2Seq-FDL model. The prediction accuracy was superior to a convolutional neural network-connected LSTM network and a ConvLSTM network with or without a bidirectional LSTM; the proposed model presented good applicability in the multiple-time-step prediction of spot speed for multiple road segments.

DAE-ConvBiLSTM: End-to-end learning single-lead electrocardiogram signal for heart abnormalities detection.

The electrocardiogram (ECG) is a widely used diagnostic that observes the heart activities of patients to ascertain a heart abnormality diagnosis. The artifacts or noises are primarily associated with the problem of ECG signal processing. Conventional denoising techniques have been proposed in previous literature; however, some lacks, such as the determination of suitable wavelet basis function and threshold, can be a time-consuming process. This paper presents end-to-end learning using a denoising auto-encoder (DAE) for denoising algorithms and convolutional-bidirectional long short-term memory (ConvBiLSTM) for ECG delineation to classify ECG waveforms in terms of the PQRST-wave and isoelectric lines. The denoising reconstruction using unsupervised learning based on the encoder-decoder process can be proposed to improve the drawbacks. First, The ECG signals are reduced to a low-dimensional vector in the encoder. Second, the decoder reconstructed the signals. The last, the reconstructed signals of ECG can be processed to ConvBiLSTM. The proposed architecture of DAE-ConvBiLSTM is the end-to-end diagnosis of heart abnormality detection. As a result, the performance of DAE-ConvBiLSTM has obtained an average of above 98.59% accuracy, sensitivity, specificity, precision, and F1 score from the existing studies. The DAE-ConvBiLSTM has also experimented with detecting T-wave (due to ventricular repolarisation) morphology abnormalities. The development architecture for detecting heart abnormalities using an unsupervised learning DAE and supervised learning ConvBiLSTM can be proposed for an end-to-end learning algorithm. In the future, the precise accuracy of the ECG main waveform will affect heart abnormalities detection in clinical practice.

Abdominal Aortic Thrombus Segmentation in Postoperative Computed Tomography Angiography Images Using Bi-Directional Convolutional Long Short-Term Memory Architecture

Abdominal aortic aneurysm (AAA) is a fatal clinical condition with high mortality. Computed tomography angiography (CTA) imaging is the preferred minimally invasive modality for the long-term postoperative observation of AAA. Accurate segmentation of the thrombus region of interest (ROI) in a postoperative CTA image volume is essential for quantitative assessment and rapid clinical decision making by clinicians. Few investigators have proposed the adoption of convolutional neural networks (CNN). Although these methods demonstrated the potential of CNN architectures by automating the thrombus ROI segmentation, the segmentation performance can be further improved. The existing methods performed the segmentation process independently per 2D image and were incapable of using adjacent images, which could be useful for the robust segmentation of thrombus ROIs. In this work, we propose a thrombus ROI segmentation method to utilize not only the spatial features of a target image, but also the volumetric coherence available from adjacent images. We newly adopted a recurrent neural network, bi-directional convolutional long short-term memory (Bi-CLSTM) architecture, which can learn coherence between a sequence of data. This coherence learning capability can be useful for challenging situations, for example, when the target image exhibits inherent postoperative artifacts and noises, the inclusion of adjacent images would facilitate learning more robust features for thrombus ROI segmentation. We demonstrate the segmentation capability of our Bi-CLSTM-based method with a comparison of the existing 2D-based thrombus ROI segmentation counterpart as well as other established 2D- and 3D-based alternatives. Our comparison is based on a large-scale clinical dataset of 60 patient studies (i.e., 60 CTA image volumes). The results suggest the superior segmentation performance of our Bi-CLSTM-based method by achieving the highest scores of the evaluation metrics, e.g., our Bi-CLSTM results were 0.0331 higher on total overlap and 0.0331 lower on false negative when compared to 2D U-net++ as the second-best.