Violent crowd flow detection from surveillance cameras using deep transfer learning–gated recurrent unit

Due to the continuous growth and advancement of technology, an enormous volume of text data is generated daily across various sources including social media platforms, websites, search engines, healthcare records, and news articles. Extracting meaningful patterns from text data, such as viewpoints, related theories, journal distribution, facts, and the development of online news text, is a challenging task due to the varying lengths of the texts. One issue arises from the length of the text data itself, and another challenge lies in extracting valuable features, especially in news articles. In the deep learning models, the convolutional neural networks (CNNs) are capable of capturing local features in text data, but unable to capture the structural information or semantic relationships between words. Consequently, a sole CNN network often yields poor performance in text classification tasks, whereas the Gated Recurrent Unit (GRU) is adept at effectively extracting semantic information and understanding the global structural relationships present in textual data. This paper presents a solution to the problem by introducing a new text classification that integrates the strengths of CNN and GRU. The proposed hybrid models incorporate word vectorization and word dispersion in parallel. Initially, the model trains word vectors using the Word2vec model and then leverages the GRU model to capture semantic information from text sentences. Subsequently, the CNN method is employed to capture crucial semantic features, leading to classification using the SoftMax layer. Experimental findings demonstrated that the proposed hybrid GRU_CNN model outperformed and achieved accuracy 97.73% as compared to individual CNN, LSTM, and GRU models in terms of classification effectiveness and accuracy.

Spectral-spatial classification for hyperspectral image based on a single GRU

At present, the amount of network equipment, servers, and network traffic is increasing exponentially, and the way in which operators allocate and efficiently utilize network resources has attracted considerable attention from traffic forecasting researchers. However, with the advent of the 5G era, network traffic has also shown explosive growth, and network complexity has increased dramatically. Accurately predicting network traffic has become a pressing issue that must be addressed. In this paper, a multilayer perceptron ensemble learning method based on convolutional neural networks (CNN) and gated recurrent units (GRU) spatiotemporal feature extraction (MECG) is proposed for network traffic prediction. First, we extract spatial and temporal features of the data by convolutional neural networks (CNN) and recurrent neural networks (RNN). Then, the extracted temporal features and spatial features are fused into new spatiotemporal features through integrated learning of a multilayer perceptron, and a spatiotemporal prediction model is built in the sequence-to-sequence framework. At the same time, the teacher forcing mechanism and attention mechanism are added to improve the accuracy and convergence speed of the model. Finally, the proposed method is compared with other deep learning models for experiments. The experimental results show that the proposed method not only has apparent advantages in accuracy but also shows some superiority in time training cost.

With the world’s interaction moving more and more toward using online social media platforms, the advent of cyberbullying has also raised its head. Multiple forms of cyberbullying exist from the more common text based to images or even videos, and this paper will explore the context of textual comments. Even in the niche area of considering only text-based data, several approaches have already been worked upon such as n-grams, recurrent units, convolutional neural networks (CNNs), gated recurrent unit (GRU) and even a combination of the mentioned architectures. While all of these produce workable results, the main point of contention is that true contextual understanding is quite a complex concept. These methods fail due to two simple reasons: (i) lack of large datasets to properly utilize these architectures and (ii) the fact that understanding context requires some mechanism of remembering history that is only present in the recurrent units. This paper explores some of the recent approaches to the difficulties of contextual understanding and proposes an ALBERT-based fine-tuned model that achieves state-of-the-art results. ALBERT is a transformer-based architecture and thus even at its untrained form provides better contextual understanding than other recurrent units. This coupled with the fact that ALBERT is pre-trained on a large corpus allowing the flexibility to use a smaller dataset for fine-tuning as the pre-trained model already has deep understanding of the complexities of the human language. ALBERT showcases high scores in multiple benchmarks such as the GLUE and SQuAD showing that high levels of contextual understanding are inherently present and thus fine-tuning for the specific case of cyberbullying allows to use this to our advantage. With this approach, we have achieved an F1 score of 95% which surpasses current approaches such as the CNN + wordVec, CNN + GRU and BERT implementations.

Rolling bearing is an essential part of various rotating machines, and its signal is the typical nonlinear signal. Traditional fault diagnosis usually relies on manual experience to extract the features of signals first. Deep convolutional neural networks (DCNN) can make fuller use of time series than traditional convolutional neural networks (CNN). Because of the low accuracy rate, fault diagnosis using gated recurrent unit (GRU) alone is not unsatisfactory. In order to improve the temporality of one-dimensional convolutional neural networks (1D-CNN) and enhance the accuracy of GRU, a novel fault diagnosis method called deep convolutional neural networks - gated recurrent unit (DCNN-GRU) is first put forward, which combines DCNN with GRU. The original signals without preprocessing are input into the DCNN, and the outputs of DCNN are input into the GRU consequently. Then the faults of rolling bearing can be diagnosed effectively. As the post-processing method, the t-distributed stochastic neighbor embedding (t-SNE) method is applied to visualize the fault diagnosis results. Six different network models, including the DCNN-GRU, are used to train the same fault dataset for comparison. The simulation results show that the proposed method can reach more than 99.9% accuracy stably for the given dataset, which can verify the feasibility and effectiveness of proposed method. And the DCNN-GRU can also be verified with good generalization ability using different dataset.

In this paper the new model is proposed to automatically detect and predict absence seizure using hybrid deep learning algorithm [convolutional recurrent neural network (CRNN)] with single channel electroencephalography (EEG) only as input. This model comprises of four steps: 1) single channel segmentation process; 2) extraction of relevant features using convolution network; 3) recurrent network for detection and early detection; 4) SVM have been used as last layer to obtain a result with respect to time. This model enhances the feature extraction by feeding the raw input into convolutional layer, improves the detection with gated recurrent unit (GRU) and reduces the early detection rate with support vector machine (SVM). Our proposed model achieves 100% overall accuracy on seizure detection as normal and absence seizure and detect within three seconds of the overall seizure duration. Also this model can be act as a generic model for classification task with detection and early detection of bio-signal (EEG, ECG and EMG).

In recent years, channel state information (CSI) in WiFi 802.11n has been increasingly used to collect data pertaining to human activity. Such raw data are then used to enhance human activity recognition. Activities such as lying down, falling, walking, running, sitting down, and standing up can now be detected with the use of information collected through CSI. Human activity recognition has a multitude of applications, such as home monitoring of patients. Four deep learning models are presented in this paper, namely: a convolution neural network (CNN) with a Gated Recurrent Unit (GRU); a CNN with a GRU and attention; a CNN with a GRU and a second CNN, and a CNN with Long Short-Term Memory (LSTM) and a second CNN. Those models were trained to perform Human Activity Recognition (HAR) using CSI amplitude data collected by a CSI tool. Experiments conducted to test the efficacy of these models showed superior results compared with other recent approaches. This enhanced performance of our models may be attributable the ability of our models to make full use of available data and to extract all data features, including high dimensionality and time sequence. The highest average recognition accuracy reached by the proposed models was achieved by the CNN-GRU, and the CNN-GRU with attention models, standing at 99.31% and 99.16%, respectively. In addition, the performance of the models was evaluated for unseen CSI data by training our models using a random split-of-dataset method (70% training and 30% testing). Our models achieved impressive results with accuracies reaching 100% for nearly all activities. For the lying down activity, accuracy obtained from the CNN-GRU model stood at 99.46%; slightly higher than the 99.05% achieved by the CNN-GRU with attention model. This confirmed the robustness of our models against environmental changes.

Messenger RNA (mRNA) has emerged as a critical global technology that requires global joint efforts from different entities to develop a COVID-19 vaccine. However, the chemical properties of RNA pose a challenge in utilizing mRNA as a vaccine candidate. For instance, the molecules are prone to degradation, which has a negative impact on the distribution of mRNA among patients. In addition, little is known of the degradation properties of individual RNA bases in a molecule. Therefore, this study aims to investigate whether a hybrid deep learning can predict RNA degradation from RNA sequences. Two deep hybrid neural network models were proposed, namely GCN_GRU and GCN_CNN. The first model is based on graph convolutional neural networks (GCNs) and gated recurrent unit (GRU). The second model is based on GCN and convolutional neural networks (CNNs). Both models were computed over the structural graph of the mRNA molecule. The experimental results showed that GCN_GRU hybrid model outperform GCN_CNN model by a large margin during the test time. Validation of proposed hybrid models is performed by well-known evaluation measures. Among different deep neural networks, GCN_GRU based model achieved best scores on both public and private MCRMSE test scores with 0.22614 and 0.34152, respectively. Finally, GCN_GRU pre-trained model has achieved the highest AuC score of 0.938. Such proven outperformance of GCNs indicates that modeling RNA molecules using graphs is critical in understanding molecule degradation mechanisms, which helps in minimizing the aforementioned issues. To show the importance of the proposed GCN_GRU hybrid model, in silico experiments has been contacted. The in-silico results showed that our model pays local attention when predicting a given position’s reactivity and exhibits interesting behavior on neighboring bases in the sequence.

In this study, different kinds of hybrid Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) algorithms with forecasting models including Random Forest (RF), Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM) neural networks, are developed to estimate the mean daily wind speed at the height of 2 m in Ağrı city (WS st12 ), Turkey. In these hybrid models, different layer networks of single and integrated LSTM and GRU models include general single LSTM, general single GRU, simple coupled LSTM-GRU, and novel coupled LSTM with GRU through Addition layer (i.e., LSTM + GRU model) structures are applied. The most effective parameters on the WS st12 , from a list of on-site potential meteorological parameters and wind speed values in its adjacent cities of Ağrı province from Jan 2015–Dec 2019 through the Pearson correlation coefficient method, are determined. In the hybrid CEEMDAN and DNNs-based models, State activation functions (SAF), numbers of hidden neurons (NHN), dropout rates (P-rate), and network structural architect (NSA) as the meta-parameters are tuned for lessening the impact of overfitting/underfitting dilemmas and improving modeling performance. According to the comparison plots, performance evaluation measures, and total learnable parameter (TLP), the novel developed hybrid CEEMDAN-RF-(LSTM + GRU) model is confirmed as the best approach with an R 2 of 0.86 while, in the optimal scenario using the RF model, R 2 was 0.47. Graphical Abstract Based on the graphical snapshot, this study focuses on estimating daily mean wind speed at a 2-meter height in Ağrı, Turkey, using hybrid data-driven models. The research integrates the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) algorithm with advanced forecasting techniques, including Random Forest (RF), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) neural networks. The modeling framework explores various configurations, such as standalone LSTM and GRU, coupled LSTM-GRU structures, and a novel LSTM + GRU model using an Addition layer to enhance predictive accuracy.

This article investigates whether higher classification accuracy can always be achieved by utilizing a pre-trained deep learning model as the feature extractor in the Bag-of-Deep-Visual-Words (BoDVW) classification model, as opposed to directly using the new classification layer of the pre-trained model for classification. Considering the multiple factors related to the feature extractor -such as model architecture, fine-tuning strategy, number of training samples, feature extraction method, and feature encoding method—we investigate these factors through experiments and then provide detailed answers to the question. In our experiments, we use five feature encoding methods: hard-voting, soft-voting, locally constrained linear coding, super vector coding, and fisher vector (FV). We also employ two popular feature extraction methods: one (denoted as Ext-DFs(CP)) uses a convolutional or non-global pooling layer, and another (denoted as Ext-DFs(FC)) uses a fully-connected or global pooling layer. Three pre-trained models—VGGNet-16, ResNext-50(32×4d), and Swin-B—are utilized as feature extractors. Experimental results on six datasets (15-Scenes, TF-Flowers, MIT Indoor-67, COVID-19 CXR, NWPU-RESISC45, and Caltech-101) reveal that compared to using the pre-trained model with only the new classification layer re-trained for classification, employing it as the feature extractor in the BoDVW model improves the accuracy in 35 out of 36 experiments when using FV. With Ext-DFs(CP), the accuracy increases by 0.13% to 8.43% (averaged at 3.11%), and with Ext-DFs(FC), it increases by 1.06% to 14.63% (averaged at 5.66%). Furthermore, when all layers of the pre-trained model are fine-tuned and used as the feature extractor, the results vary depending on the methods used. If FV and Ext-DFs(FC) are used, the accuracy increases by 0.21% to 5.65% (averaged at 1.58%) in 14 out of 18 experiments. Our results suggest that while using a pre-trained deep learning model as the feature extractor does not always improve classification accuracy, it holds great potential as an accuracy improvement technique.

Recently, Brain-Computer Interface (BCI) technology has been applied more and more in the field of clinical rehabilitation, which provides an effective way of communication for patients with brain disability and stroke. Because electroencephalogram (EEG) signals are extremely complex and contain many redundant signals, the recognition effect of BCI system based on EEG is not very well. The purpose of this paper is to solve the problem of brain intention classification in brain-computer interface system, which combines Deep Separation Convolutional Neural Network (DSCNN) and Gate Recurrent Unit (GRU) network to classify the motor imagination task of EEG. Firstly, one-dimensional timing EEG signals are transformed into two-dimensional array, and the temporal and spatial features of EEG signals are extracted by separate convolution. Then, these EEG signals containing spatio-temporal features are convolved once to extract spatial features, and the temporal features is extracted by GRU. Finally, the experiments shows that the final intention recognition accuracy reach 97.76% via the open physiological motor imagery data set EEGMMIDB, which is superior to some advanced research methods for motor imagery task recognition at present and helpful to restore the rehabilitation ability of patients with brain injury.

The main aim of this study is to introduce a new hybrid deep learning model for biomedical image classification. We propose a novel convolutional neural network (CNN), named HybridNeXt, for detecting pulmonary embolism (PE) from computed tomography (CT) images. To evaluate the HybridNeXt model, we created a new dataset consisting of two classes: (1) PE and (2) control. The HybridNeXt architecture combines different advanced CNN blocks, including MobileNet, ResNet, ConvNeXt, and Swin Transformer. We specifically designed this model to combine the strengths of these well-known CNNs. The architecture also includes stem, downsampling, and output stages. By adjusting the parameters, we developed a lightweight version of HybridNeXt, suitable for clinical use. To further improve the classification performance and demonstrate transfer learning capability, we proposed a deep feature engineering (DFE) method using a multilevel discrete wavelet transform (MDWT). This DFE model has three main phases: (i) feature extraction from raw images and wavelet bands, (ii) feature selection using iterative neighborhood component analysis (INCA), and (iii) classification using a k-nearest neighbors (kNN) classifier. We first trained HybridNeXt on the training images, creating a pretrained HybridNeXt model. Then, using this pretrained model, we extracted features and applied the proposed DFE method for classification. The HybridNeXt model achieved a test accuracy of 90.14%, while our DFE model improved accuracy to 96.35%. Overall, the results confirm that our HybridNeXt architecture is highly accurate and effective for biomedical image classification. The presented HybridNeXt and HybridNeXt-based DFE methods can potentially be applied to other image classification tasks.

Nowadays, video quality assessment (VQA) plays a vital role in video-related industries to predict human perceived video quality to maintain the quality of service. Although many deep neural network-based VQA methods have been proposed, the robustness and performance are limited by small scale of available human-label data. Recently, some transfer learning-based methods and pre-trained models in other domains have been adopted in VQA to compensate for the lack of enormous training samples. However, they result in a domain gap between the source and target domains, which provides sub-optimal feature representation for VQA tasks and deteriorates the accuracy. Therefore, in the paper, we propose quality feature learning via a multi-channel convolutional neural network (CNN) with a gated recurrent unit (GRU), taking into account both the motion-aware information and human visual perception (HVP) characteristics to solve the above issue for no-reference VQA. First, inspired by self-supervised learning (SSL), the multi-channel CNN is pre-trained on the image quality assessment (IQA) domain without using human annotation labels. Then, semi-supervised learning is applied on top of the pre-trained multi-channel CNN to fine-tune the model to transfer the domain from IQA to VQA while considering motion-aware information for better frame-level quality feature representation. After that, several HVP features are extracted with frame-level quality feature representation as the input of the GRU model to obtain the final precise predicted video quality. Finally, the experimental results demonstrate the robustness and validity of our model, which is superior to the state-of-the-art approaches and is closely related to human perception.

Artificial intelligence (AI) based computer-aided diagnostic (CAD) systems can effectively diagnose critical disease. AI-based detection of breast cancer (BC) through images data is more efficient and accurate than professional radiologists. However, the existing AI-based BC diagnosis methods have complexity in low prediction accuracy and high computation time. Due to these reasons, medical professionals are not employing the current proposed techniques in E-Healthcare to effectively diagnose the BC. To diagnose the breast cancer effectively need to incorporate advanced AI techniques based methods in diagnosis process. In this work, we proposed a deep learning based diagnosis method (StackBC) to detect breast cancer in the early stage for effective treatment and recovery. In particular, we have incorporated deep learning models including Convolutional neural network (CNN), Long short term memory (LSTM), and Gated recurrent unit (GRU) for the classification of Invasive Ductal Carcinoma (IDC). Additionally, data augmentation and transfer learning techniques have been incorporated for data set balancing and for effective training the model. To further improve the predictive performance of model we used stacking technique. Among the three base classifiers (CNN, LSTM, GRU) the predictive performance of GRU are better as compared to individual model. The GRU is selected as a meta classifier to distinguish between Non-IDC and IDC breast images. The method Hold-Out has been incorporated and the data set is split into 90% and 10% for training and testing of the model, respectively. Model evaluation metrics have been computed for model performance evaluation. To analyze the efficacy of the model, we have used breast histology images data set. Our experimental results demonstrated that the proposed StackBC method achieved improved performance by gaining 99.02% accuracy and 100% area under the receiver operating characteristics curve (AUC-ROC) compared to state-of-the-art methods. Due to the high performance of the proposed method, we recommend it for early recognition of breast cancer in E-Healthcare.

Graph convolutional network – Long short term memory neural network- multi layer perceptron- Gaussian progress regression model: A new deep learning model for predicting ozone concertation