Extract High-level Features Research Articles

FeDN2: Fuzzy-Enhanced Deep Neural Networks for Improvement of Sentence-Level Sentiment Analysis

Sentence-level sentiment analysis is a natural language processing model growing rapidly and strongly due to its role in artificial intelligence systems. There are many approaches to developing and improving the performance of sentence-level sentiment analysis with satisfactory performance, among which deep neural network methods are notable. However, sentence-level sentiment analysis methods based on deep neural networks often have two limitations: (i) The system architecture is not deep enough; (ii) Sentences containing unclear sentiments cannot be processed. To solve the above two challenges, in this paper, we propose a new sentence-level sentiment analysis method called Fuzzy-enhanced Deep Neural Networks (FeDN2) by deepening deep neural networks by adding fuzzy and defuzzy classes. FeDN2 includes the following main layers: (i) BERT layer to convert sentences into vectors. (ii) Fuzzification layer to blur sentence vectors. (iii) Deep convolutional layers to extract high-level features. (iv) Defuzzification layer to convert high-level feature vectors into clear values. (v) Fully connected layer to learn non-linear combinations of these high-level features. (vi) Classification layer to identify the sentiment polarity of sentences. FeDN2 was tested on two benchmark datasets. The results demonstrated that it can improve the performance of previous sentence-level sentiment analysis methods based on deep neural networks.

Deep Learning for Integrated Speckle Reduction and Super-Resolution in Multi-Temporal SAR

In the domain of synthetic aperture radar (SAR) image processing, a prevalent issue persists wherein research predominantly focuses on single-task learning, often neglecting the concurrent impact of speckle noise and low resolution on SAR images. Currently, there are two main processing strategies. The first strategy involves conducting speckle reduction and super-resolution processing step by step. The second strategy involves performing speckle reduction as an auxiliary step, with a focus on enhancing the primary task of super-resolution processing. However, both of these strategies exhibit clear deficiencies. Nevertheless, both tasks jointly focus on two key aspects, enhancing SAR quality and restoring details. The fusion of these tasks can effectively leverage their task correlation, leading to a significant improvement in processing effectiveness. Additionally, multi-temporal SAR images covering imaging information from different time periods exhibit high correlation, providing deep learning models with a more diverse feature expression space, greatly enhancing the model’s ability to address complex issues. Therefore, this study proposes a deep learning network for integrated speckle reduction and super-resolution in multi-temporal SAR (ISSMSAR). The network aims to reduce speckle in multi-temporal SAR while significantly improving the image resolution. Specifically, it consists of two subnetworks, each taking the SAR image at time 1 and the SAR image at time 2 as inputs. Each subnetwork includes a primary feature extraction block (PFE), a high-level feature extraction block (HFE), a multi-temporal feature fusion block (FFB), and an image reconstruction block (REC). Following experiments on diverse data sources, the results demonstrate that ISSMSAR surpasses speckle reduction and super-resolution methods based on a single task in terms of both subjective perception and objective evaluation metrics regarding the quality of image restoration.

Stance-Based Fake News Identification on Social Media with Hybrid CNN and RNN-LSTM Models

Today, fake news can be readily generated and disseminated via social media platforms. Misinformation and hoaxes propagated via online social media or traditional news media are commonly referred to as fake news. Stance-based fake news is based on the opinions of an audience rather than providing correct facts. This study presents a hybrid model focusing on the CNN model and RNN-LSTM model to identify fake news. A balanced dataset of 216k news items called ‘SherLock-FakeNewsNet’ is explored throughout the study resulting in the proposed hybrid model. The NLTK toolkit is utilized to perform some noise reduction. After that, the Keras tokenizer and pre-processor are used for the tokenization and pre-processing steps. Next, the text data is fitted and represented using pre-trained GloVe word embeddings. CNN model is applied with Conv1D layers and MaxPooling layers to extract higher-level features of the text. Following this, to detect the longer context of the given text and to capture interdependencies among word sequences LSTM units are employed in the RNN model. Dropout layers are carefully chosen to reduce overfitting in the final hybrid model. The proposed hybrid model achieves the highest accuracy rate of 92% by outperforming most of the conventional models today with an average Precision of 91%, Recall of 91%, and F1-Score of 91% using an Adam optimizer and a Binary Cross-Entropy loss function. Based on the five experiments performed in the study, we have presented the results by comparing our proposed hybrid model with five related datasets.

Adaptive learning point cloud and image diversity feature fusion network for 3D object detection

3D object detection is a critical task in the fields of virtual reality and autonomous driving. Given that each sensor has its own strengths and limitations, multi-sensor-based 3D object detection has gained popularity. However, most existing methods extract high-level image semantic features and fuse them with point cloud features, focusing solely on consistent information from both sensors while ignoring their complementary information. In this paper, we present a novel two-stage multi-sensor deep neural network, called the adaptive learning point cloud and image diversity feature fusion network (APIDFF-Net), for 3D object detection. Our approach employs the fine-grained image information to complement the point cloud information by combining low-level image features with high-level point cloud features. Specifically, we design a shallow image feature extraction module to learn fine-grained information from images, instead of relying on deep layer features with coarse-grained information. Furthermore, we design a diversity feature fusion (DFF) module that transforms low-level image features into point-wise image features and explores their complementary features through an attention mechanism, ensuring an effective combination of fine-grained image features and point cloud features. Experiments on the KITTI benchmark show that the proposed method outperforms state-of-the-art methods.

Ethnicity Classification: Discriminating Between Iranian and Asian Populations Using Hybrid Deep Learning Algorithm

The rapid advancement of deep learning techniques has opened new avenues for solving complex classification problems in various domains. This research explores the application of Convolutional Neural Networks (CNN), specifically the VGG16 architecture, in conjunction with Support Vector Machines (SVM) for the classification of ethnicity using Iranian and Asian facial images. The classification of ethnicity based on facial features is a challenging task due to the subtle and complex variations within and between different ethnic groups. The proposed methodology involves a two-step process. First, the VGG16 CNN model is utilized to extract high-level features from the facial images. The pre-trained VGG16 model, known for its depth and representational power, is fine-tuned on the dataset to capture relevant ethnic features. The extracted features are then fed into an SVM classifier, which is trained to distinguish between Iranian and Asian facial characteristics. A comprehensive dataset consisting of labeled Iranian and Asian facial images is compiled and preprocessed for training and evaluation. The model's performance is assessed using metrics such as accuracy. Various experiments are conducted to optimize hyperparameters and validate the generalization capability of the proposed model. Additionally, visualization techniques are employed to provide insights into the features learned by the CNN and the decision boundaries established by the SVM. The results indicate that the combined approach of CNN-VGG16 and SVM yields promising accuracy in the classification of ethnicity based on facial images.

Back-Guard: Wireless Backscattering Based User Sensing With Parallel Attention Model

With the rapid advance of wireless sensing techniques, it becomes possible to provide a fine-grained user activity tracking service at home and office. Such a technique is of broad applications in various domains such as personal activity diary, elderly care, and customized services. For example, several radio frequency (RF) based sensing systems were recently proposed for human activity recognition. However, most of them focused on specific scenarios and suffered from interference caused by other users and wireless devices. In this work, we propose Back-Guard, a backscattering-based sensing system that achieves accurate and non-intrusive user activity recognition and further user identification/authentication. Back-Guard carefully examines the backscatter spectrogram data and extracts high-level features from both spatial and temporal domains. Leveraging the parallel attention based deep learning model, our system can discriminate different motions and users accurately and robustly in various situations. We implemented a prototype system and collected data from 25 users for more than 2 months. Extensive experiments demonstrate that Back-Guard achieves 93.4 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> activity recognition accuracy and 91.5 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> user identification accuracy, respectively. In particular, Back-Guard can also tackle multiple user scenarios, which has little accuracy reduction when the users are separated, e.g., by around 2 meters.

3D-ResNet-BiLSTM Model: A Deep Learning Model for County-Level Soybean Yield Prediction with Time-Series Sentinel-1, Sentinel-2 Imagery, and Daymet Data

Ensuring food security in precision agriculture requires early prediction of soybean yield at various scales within the United States (U.S.), ranging from international to local levels. Accurate yield estimation is essential in preventing famine by providing insights into food availability during the growth season. Numerous deep learning (DL) algorithms have been developed to estimate soybean yield effectively using time-series remote sensing (RS) data to achieve this goal. However, the training data with short time spans can limit their ability to adapt to the dynamic and nuanced temporal changes in crop conditions. To address this challenge, we designed a 3D-ResNet-BiLSTM model to efficiently predict soybean yield at the county level across the U.S., even when using training data with shorter periods. We leveraged detailed Sentinel-2 imagery and Sentinel-1 SAR images to extract spectral bands, key vegetation indices (VIs), and VV and VH polarizations. Additionally, Daymet data was incorporated via Google Earth Engine (GEE) to enhance the model’s input features. To process these inputs effectively, a dedicated 3D-ResNet architecture was designed to extract high-level features. These enriched features were then fed into a BiLSTM layer, enabling accurate prediction of soybean yield. To evaluate the efficacy of our model, its performance was compared with that of well-known models, including the Linear Regression (LR), Random Forest (RF), and 1D/2D/3D-ResNet models, as well as a 2D-CNN-LSTM model. The data from a short period (2019 to 2020) were used to train all models, while their accuracy was assessed using data from the year 2021. The experimental results showed that the proposed 3D-Resnet-BiLSTM model had a superior performance compared to the other models, achieving remarkable metrics (R2 = 0.791, RMSE = 5.56 Bu Ac−1, MAE = 4.35 Bu Ac−1, MAPE = 9%, and RRMSE = 10.49%). Furthermore, the 3D-ResNet-BiLSTM model showed a 7% higher R2 than the ResNet and RF models and an enhancement of 27% and 17% against the LR and 2D-CNN-LSTM models, respectively. The results highlighted our model’s potential for accurate soybean yield predictions, supporting sustainable agriculture and food security.

Polarimetric Synthetic Aperture Radar Image Classification Based on Double-Channel Convolution Network and Edge-Preserving Markov Random Field

Deep learning methods have gained significant popularity in the field of polarimetric synthetic aperture radar (PolSAR) image classification. These methods aim to extract high-level semantic features from the original PolSAR data to learn the polarimetric information. However, using only original data, these methods cannot learn multiple scattering features and complex structures for extremely heterogeneous terrain objects. In addition, deep learning methods always cause edge confusion due to the high-level features. To overcome these limitations, we propose a novel approach that combines a new double-channel convolutional neural network (CNN) with an edge-preserving Markov random field (MRF) model for PolSAR image classification, abbreviated to “DCCNN-MRF”. Firstly, a double-channel convolution network (DCCNN) is developed to combine complex matrix data and multiple scattering features. The DCCNN consists of two subnetworks: a Wishart-based complex matrix network and a multi-feature network. The Wishart-based complex matrix network focuses on learning the statistical characteristics and channel correlation, and the multi-feature network is designed to learn high-level semantic features well. Then, a unified network framework is designed to fuse two kinds of weighted features in order to enhance advantageous features and reduce redundant ones. Finally, an edge-preserving MRF model is integrated with the DCCNN network. In the MRF model, a sketch map-based edge energy function is designed by defining an adaptive weighted neighborhood for edge pixels. Experiments were conducted on four real PolSAR datasets with different sensors and bands. The experimental results demonstrate the effectiveness of the proposed DCCNN-MRF method.

An Enhanced Detection Method of PCB Defect Based on D-DenseNet (PCBDD-DDNet)

Printed Circuit Boards (PCBs), as integral components of electronic products, play a crucial role in modern industrial production. However, due to the precision and complexity of PCBs, existing PCB defect detection methods exhibit some issues such as low detection accuracy and limited usability. In order to address these problems, a PCB defect detection method based on D-DenseNet (PCBDD-DDNet) has been proposed. This method capitalizes on the advantages of two deep learning networks, CDBN (Convolutional Deep Belief Networks) and DenseNet (Densely Connected Convolutional Networks), to construct the D-DenseNet (Combination of CDBN and DenseNet) network. Within this network, CDBN focuses on extracting low-level features, while DenseNet is responsible for high-level feature extraction. The outputs from both networks are integrated using a weighted averaging approach. Additionally, the D-DenseNet employs a multi-scale module to extract features from different levels. This is achieved by incorporating filters of sizes 3 × 3, 5 × 5, and 7 × 7 along the three paths of the CDBN network, multi-scale feature extraction network, and DenseNet network, effectively capturing information at various scales. To prevent overfitting and enhance network performance, the Adafactor optimization function and L2 regularization are introduced. Finally, online hard example mining mechanism (OHEM) is incorporated to improve the network’s handling of challenging samples and enhance the accuracy of the PCB defect detection network. The effectiveness of this PCBDD-DDNet method is demonstrated through experiments conducted on publicly available PCB datasets. And the method achieves a mAP (mean Average Precision) of 93.24%, with an accuracy higher than other classical networks. The results affirm the method’s efficacy in PCB defect detection.

Predicting peak deviatoric stress of gravels with a novel segmented feature transformation approach

The assessment of peak deviatoric stress (qpeak) in gravels is crucial for engineering stability and safety. Due to the various influencing factors and the limited available samples, present empirical methods and conventional machine learning algorithms have limitations in generalization capability and achieving high performance in this complex relationship. This paper proposes a novel deep learning-based model termed Seft-Net. The model utilizes a segmented feature transformation (Seft) approach to improve convergence and robustness by leveraging prior knowledge that grouping gravel properties into three categories: particle (e.g., shape, hardness), soil mass (e.g., gradation, void ratio), and external factors (e.g., confining pressure). Subsequently, it applies a feature transformation module using depthwise separable convolutions to learn and fuse hierarchical representations across multiple layers. This enables Seft-Net to automatically extract high-level features from gravel properties that capture intricate nonlinear relationships with qpeak. The model is trained and validated using a large-scale practical dataset from triaxial test results. Ablation studies confirmed the superiority of the proposed segmented feature transformation approach over the unsegmented approach, and the feature transformation module demonstrated optimal feature extraction capabilities. Comparative evaluations with three machine learning methods further validated the superior performance of Seft-Net.

SOC content of global Mollisols at a 30 m spatial resolution from 1984 to 2021 generated by the novel ML-CNN prediction model

Carbon cycle is influenced by agricultural soils, and accurately mapping the soil organic carbon (SOC) content of global Mollisols at a 30 m spatial resolution can contribute to clarifying the carbon sequestration capacity of each region, facilitate the quantification of agroecosystems and contribute to global food security. However, the high heterogeneity of environmental variables in global regions, coupled with the challenges posed by small-sample tasks, creates significant obstacles to producing reliable SOC content datasets. In this study, we collected 191,465 scenes of Landsat TM and OLI images and elevation model data to calculate spectral indices that can represent soil formation information based on a soil-pedogenic model. Second, a local strategy (LS) was proposed to reduce the influence of the high heterogeneity of SOC content and environmental variables on the prediction results. More importantly, the first meta-learning convolutional neural network (ML-CNN) model was proposed. It provides high prediction accuracy for small-sample tasks and was used to generate the first high-resolution global Mollisol region SOC content product (GMR-MCNN). Finally, we compared GMR-MCNN with the existing SoilGrids250m and Soil SubCenter products. The results showed that long-term, high-accuracy and high-resolution prediction of the SOC content in global Mollisol regions was achieved by the ML-CNN model (RMSE = 4.84 g kg−1, R2 = 0.75, RPIQ = 2.43). Compared with a CNN, ML-CNN can continuously optimize the meta-task, thus improving the performance of the model in small-sample tasks. Compared to the prediction model that combined the recursive feature elimination technique with the random forest model (RFE-RF), ML-CNN can efficiently extract high-level features from time-series data, thus improving the model performance. Compared with that of the global strategy, the RMSE of the LS decreased by 0.20 g kg−1, and R2 and RPIQ increased by 13.00% and 0.22, respectively. In addition, the GMR-MCNN results illustrated that the SOC content in the global Mollisol regions shows a decreasing trend, and the trend can be divided into significant decrease (1984–2000) and moderate decrease (2001−2021) phases. Different products were tested based on laboratory-measured SOC contents, and GMR-MCNN (RMSE = 6.13 g kg−1, R2 = 0.63) displayed better performance than SoilGrids250m (RMSE = 23.37 g kg−1, R2 = 0.28) and the Soil SubCenter map (RMSE = 8.59 g kg−1, R2 = 0.43). The developed methodology can provide a reference for the long-term observation of soil and crop properties at moderate and high resolutions globally.

Hierarchical features extraction and data reorganization for code search

According to a natural language query, code search aims to retrieve relevant code snippets from a codebase. Recent works mainly rely on transformer-based pretraining models to measure the matching degree of queries and codes. Compared with works that rely on earlier deep learning methods, such as LSTM and Attention, they can significantly improve the performance of code search tasks. However, the different layers of the transformer-based models have different features that are intuitive and efficient for understanding the semantics of codes and queries but are rarely considered. Moreover, existing methods do not consider further increasing the amount of training data during training to improve the model’s performance.Toward this end, we propose a novel method called HFEDR, which utilizes the hierarchical features of transformer-based models and reorganizes original training data during a training phase. Specifically, we first extract high-level and low-level features of queries and codes from the higher and lower layers of GraphCodeBERT, respectively, achieving multi-view and comprehensive semantic representation. After that, we organize the original training data into hierarchical-uncorrelated feature pairs and then reorganize them into hierarchical-correlated feature pairs, achieving training the model with more data. Finally, we update the model’s parameters using a contrastive training method. We conduct extensive experiments on CodeSearchNet, demonstrating the effectiveness and rationality of our proposed approach.

Capsule network-based deep ensemble transfer learning for multimodal sentiment analysis

Understanding the attitudes of users about different topics through their huge amount of comments and opinions on social networks is an emerging hot issue. Analyzing the sentiments of these posts and comments provides useful information utilized for many applications. Multimodal sentiments often contain more information than single-modal sentiments, including text, image, audio and video, which leads to better performance of multimodal sentiment analysis (MSA) compared to single-modal sentiment analysis (SSA). In this paper, a capsule network-based deep ensemble transfer learning approach, called DSY-ETL-MSA, is proposed for MSA on images and texts, the results of which are fused using Yager theory. Capsule networks and ensemble learning methods improve classification performance, and the deep transfer learning approach reduces the training time. A hybrid deep architecture is used for automatic feature extraction in the proposed method. For analyzing the sentiment of image modality, a pre-trained VGG16 model, fine-tuned on the datasets, is used to extract high-level features for image classification. A capsule convolutional neural network (CNN) is also separately used for extracting image features and classifying them. In the text modality, the pre-trained GloVe model is exploited to embed words and 2 separate classifiers are employed for text classifications. The Yager fusion rules are finally used for early and late fusions of the results of the classifiers. The results of the text and image classifiers are combined separately as the early fusion and the final results of them are fused at the decision level as the late fusion. The proposed model is empirically evaluated on the MVSA and T4SA datasets. The significant performance improvement compared to a variety of former methods is shown in the experimental results. The final accuracies obtained by the proposed method on the MVSA and T4SA datasets are 0.9866 and 0.9996, respectively.

Multi-scale Transformer Network with Edge-aware Pre-training for Cross-Modality MR Image Synthesis.

Cross-modality magnetic resonance (MR) image synthesis can be used to generate missing modalities from given ones. Existing (supervised learning) methods often require a large number of paired multi-modal data to train an effective synthesis model. However, it is often challenging to obtain sufficient paired data for supervised training. In reality, we often have a small number of paired data while a large number of unpaired data. To take advantage of both paired and unpaired data, in this paper, we propose a Multi-scale Transformer Network (MT-Net) with edge-aware pre-training for cross-modality MR image synthesis. Specifically, an Edge-preserving Masked AutoEncoder (Edge-MAE) is first pre-trained in a self-supervised manner to simultaneously perform 1) image imputation for randomly masked patches in each image and 2) whole edge map estimation, which effectively learns both contextual and structural information. Besides, a novel patch-wise loss is proposed to enhance the performance of Edge-MAE by treating different masked patches differently according to the difficulties of their respective imputations. Based on this proposed pre-training, in the subsequent fine-tuning stage, a Dual-scale Selective Fusion (DSF) module is designed (in our MT-Net) to synthesize missing-modality images by integrating multi-scale features extracted from the encoder of the pre-trained Edge-MAE. Furthermore, this pre-trained encoder is also employed to extract high-level features from the synthesized image and corresponding ground-truth image, which are required to be similar (consistent) in the training. Experimental results show that our MT-Net achieves comparable performance to the competing methods even using 70% of all available paired data. Our code will be released at https://github.com/lyhkevin/MT-Net.

Cross domain fault diagnosis method based on MLP-mixer network

The quality of rolling bearings determines the safety of mechanical equipment operation, and bearings with more precise structures are prone to damage due to excessive operation. Therefore, cross domain fault diagnosis of bearings has become a research hotspot. To better improve the accuracy of bearing cross domain fault diagnosis, this study proposes two models. One is a cross domain feature extraction model constructed using a mixed attention mechanism, which recognizes and extracts high-level features of bearing faults through channel attention and spatial attention mechanisms. The other is a bearing cross domain fault diagnosis model based on multi-layer perception mechanism. This model takes the feature signals collected by the attention mechanism model as input to identify and align the differences between the source and target domain features, facilitating cross domain transfer of features. The experimental results show that the mixed attention mechanism model has a maximum accuracy of 97.3 % for feature recognition of different faults, and can successfully recognize corresponding signal values. The multi-layer perception model can achieve the highest recognition accuracy of 99.5 % in bearing fault diagnosis, and it can reach a stable state when it iterates to 26, and the final stable loss value is 0.28. Therefore, the two models proposed in this study have good application value.

Internal Flow Prediction in Arbitrary Shaped Channel Using Stream-Wise Bidirectional LSTM

Deep learning (DL) methods have become the trend in predicting feasible solutions in a shorter time compared with traditional computational fluid dynamics (CFD) approaches. Recent studies have stacked numerous convolutional layers to extract high-level feature maps, which are then used for the analysis of various shapes under differing conditions. However, these applications only deal with predicting the flow around the objects located near the center of the domain, whereas most fluid-transport-related phenomena are associated with internal flows, such as pipe flows or air flows inside transportation vehicle engines. Hence, to broaden the scope of the DL approach in CFD, we introduced a stream-wise bidirectional (SB)-LSTM module that generates a better latent space from the internal fluid region by additionally extracting lateral connection features. To evaluate the effectiveness of the proposed method, we compared the results obtained using SB-LSTM to those of the encoder–decoder(ED) model and the U-Net model, as well as with the results when not using it. When SB-LSTM was applied, in the qualitative comparison, it effectively addressed the issue of erratic fluctuations in the predicted field values. Furthermore, in terms of quantitative evaluation, the mean relative error (MRE) for the x-component of velocity, y-component of velocity, and pressure was reduced by at least 2.7%, 4.7%, and 15%, respectively, compared to the absence of the SB-LSTM module. Furthermore, through a comparison of the calculation time, it was found that our approach did not undermine the superiority of the neural network’s computational acceleration effect.

A deep learning approach for inpatient length of stay and mortality prediction

PurposeAccurate prediction of the Length of Stay (LoS) and mortality in the Intensive Care Unit (ICU) is crucial for effective hospital management, and it can assist clinicians for real-time demand capacity (RTDC) administration, thereby improving healthcare quality and service levels. MethodsThis paper proposes a novel one-dimensional (1D) multi-scale convolutional neural network architecture, namely 1D-MSNet, to predict inpatients’ LoS and mortality in ICU. First, a 1D multi-scale convolution framework is proposed to enlarge the convolutional receptive fields and enhance the richness of the convolutional features. Following the convolutional layers, an atrous causal spatial pyramid pooling (SPP) module is incorporated into the networks to extract high-level features. The optimized Focal Loss (FL) function is combined with the synthetic minority over-sampling technique (SMOTE) to mitigate the imbalanced-class issue. ResultsOn the MIMIC-IV v1.0 benchmark dataset, the proposed approach achieves the optimum R-Square and RMSE values of 0.57 and 3.61 for the LoS prediction, and the highest test accuracy of 97.73% for the mortality prediction. ConclusionThe proposed approach presents a superior performance in comparison with other state-of-the-art, and it can effectively perform the LoS and mortality prediction tasks.

Forecasting Vertical Profiles of Ocean Currents from Surface Characteristics: A Multivariate Multi-Head Convolutional Neural Network–Long Short-Term Memory Approach

While study of ocean dynamics usually involves modeling deep ocean variables, monitoring and accurate forecasting of nearshore environments is also critical. However, sensor observations often contain artifacts like long stretches of missing data and noise, typically after an extreme event occurrence or some accidental damage to the sensors. Such data artifacts, if not handled diligently prior to modeling, can significantly impact the reliability of any further predictive analysis. Therefore, we present a framework that integrates data reconstruction of key sea state variables and multi-step-ahead forecasting of current speed from the reconstructed time series for 19 depth levels simultaneously. Using multivariate chained regressions, the reconstruction algorithm rigorously tests from an ensemble of tree-based models (fed only with surface characteristics) to impute gaps in the vertical profiles of the sea state variables down to 20 m deep. Subsequently, a deep encoder–decoder model, comprising multi-head convolutional networks, extracts high-level features from each depth level’s multivariate (reconstructed) input and feeds them to a deep long short-term memory network for 24 h ahead forecasts of current speed profiles. In this work, we utilized Viking buoy data, and demonstrated that with limited training data, we could explain an overall 80% variation in the current speed profiles across the forecast period and the depth levels.

COVID-19 Detection using Hybrid CNN-RNN Architecture with Transfer Learning from X-Rays.

Millions of people have been infected with COVID-19, which has spread quickly worldwide since the start of 2020, resulting in numerous fatalities. Identification of infected individuals is essential to control the spread of the virus. In this study, we propose a hybrid architecture that combines Convolutional Neural Networks (CNNs) with Recurrent Neural Networks (RNNs) and leverages transfer learning to enhance the accuracy of COVID-19 detection from X-ray images. The proposed work utilizes 4 pre-trained CNN architectures, namely, InceptionnetV3, Densenet121, Inception-ResNet V2, and VGG19, to extract high-level features from the input X-ray images. These features are then fed into the second component, an RNN-based network, which captures the temporal dependencies within the extracted features. To evaluate the performance of the proposed architecture, a comprehensive dataset consisting of X-ray images from COVID-19 positive cases, non-COVID-19 pneumonia cases, and healthy individuals is used. Gradient class activation map (Grad-CAM) analysis has been applied to the obtained results to provide heat-map pictures specific to each class and coloured visualizations of the COVID-19-infected areas in CXR images. Experimental results demonstrate that the proposed hybrid CNN-RNN architecture achieves promising results in COVID-19 detection from X-ray images. The model exhibits high accuracy, precision, recall, area under the receiver operating characteristics (ROC) curve (AUC), and F1-score, outperforming other state-of-the-art methods. The combination of CNNs and RNNs enables the model to effectively capture spatial and temporal information, leading to improved performance in COVID-19 detection. The proposed hybrid architecture with transfer learning from X-ray images provides a robust and efficient solution for COVID-19 detection. The model can potentially assist healthcare professionals in making accurate and timely diagnoses, thereby contributing to the global efforts to combat the COVID-19 pandemic. In the present work, VGG19-RNN architecture outperformed all other networks in terms of accuracy. The most effective training and validation accuracy for the VGG19-RNN architecture is 99% & 97.70%, respectively, and the loss was 0.02 & 0.09 at epoch 100.

Big Data and Deep Learning Analytics

There has been an enormous growth of the Internet, mobile phone, medical facilities, and many more in the 21st century, which can also be known as the beginning of the knowledge era. Knowledge is defined not for what it is, but for what it can do. In this fast-moving technological era, as a result, a huge amount of data is generated in different regions of the world and it is growing day by day, this growing data is known as “Big Data”. To extract useful information (analyze) from large unstructured data (like Web, sales, customer contact center, social media, mobile data, and so on) is a complex task, as data being generated is a combination of structured, semi-structured and unstructured data. Traditional systems are not capable to handle semi-structured or unstructured data generated whose volume could range in petabytes or exabytes, as the major challenges are limited memory usage, computational hurdles and slower response time, data redundancy, etc. This problem can be overcome with big data analytics having technologies like Apache Hadoop, Apache Spark, Hive, Pig, etc. which can extract useful information from these large data. Authors are going to explore more on them in these chapters. Alongside authors will explore “Deep Learning” also known as “Deep Neural Learning” or “Deep Neural Network”, which is a class of Machine Learning that progressively extract higher-level features from raw data automatically. It performs 'end-to- end learning' and uses layers of algorithms to process data, understand human speech, and visually recognize objects, which is an important part of it. Feature extraction, self-driving cars, fraud detection, healthcare, neural language processing, etc. are some of the areas where it is applied in daily life. Algorithms like RNN, CNN, FNN, Backpropagation, etc, are some of the algorithms used in deep learning. The authors will explore how Machine learning is different from deep learning. Deep learning (DL) is also associated with data science in many ways as the DL algorithms work better than older learning algorithms for prediction or feature extraction etc. Which has brought it, more closer towards one of its main objectives i.e., artificial intelligence (AI)? Hence it is immensely advantageous to the data scientists who aim for making predictions and draw useful information to analyze and interpret it for helping the organization in its growth. The processing of Big Data and the evolution of Artificial Intelligence are both dependent on Deep Learning. Deep learning technology came up along with big data analytics. The concept of deep learning is supportive in the big data analytics due to its efficient use for processing huge and enormous data. This chapter explains about deep learning and big data analytics use in healthcare and alongside authors will study about algorithms used in deep learning and technologies used in big data analytics with its architecture. After reading this chapter, authors must be able to connect deep learning with big data analytics for building new products and contribute to society in a much better way