An Intelligent Network Traffic Prediction Scheme Based on Ensemble Learning of Multi-Layer Perceptron in Complex Networks

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

This work aims to optimize college football training using deep learning techniques, addressing the inefficiencies, difficulty in action recognition, and insufficient data analysis present in current training methods. An intelligent optimization system combining Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) is proposed to tackle these challenges. Compared to traditional single models, the Convolutional Neural Network-Recurrent Neural Network (CNN-RNN) architecture remarkably improves the efficiency and accuracy of processing training data by leveraging the strengths o spatial features and temporal sequence features. The experimental results show that CNN-RNN model is significantly superior to the traditional 3D CNN model and other advanced models, such as Transformer, Long Short-Term Memory (LSTM), Bidirectional LSTM and Gated Recurrent Unit (GRU), in key indicators such as accuracy, precision, recall and F1 score. Specifically, CNN-RNN model achieves 92.5% accuracy, 91.2% precision, 93.1% recall and 92.1% F1 score. The lowest training loss rate is 0.24, which is significantly better than other models. In addition, the introduced data balance strategy effectively improves the prediction performance of a few categories (such as foul and yellow card events) through oversampling, undersampling and weighted loss function, and further enhances the generalization ability and practicability of the model. Future research focuses on expanding the dataset, further improving the model?s generalization ability, and exploring its application in real training scenarios.

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.

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

In this paper, alternative direction finding methods have been proposed using deep learning techniques. Firstly, Regeression and Classification models have created by using Convolutional Neural Networks (CNNs). In the second Convolutional Neural Networks and Recurrent Neural Networks (RNNs) have been utilized in the proposed methods. Despite having vast amount of direction finding studies, utilization of neural networks is scarce in literature and past works mostly only includes usage of CNNs. In this study, direction finding is performed by learning signals reaching multiple antenna arrays by networks. Created neural networks have been fed with different data formats and their performances against noisy and no-noise data have been shown. In addition, comparative analysis of the developed models were made in the similar Signal-to-Noise Ratio (SNR) range with the subspace based MUSIC algorithm, which is frequently used in direction finding.

The study presents the results of the development and testing of deep learning neural network architectures, which demonstrate high accuracy rates in classifying neurophysiological data, in particular hemodynamic brain activation patterns obtained by functional near-infrared spectroscopy, during solving mathematical problems on spatial-numerical associations. The analyzed signal represents a multidimensional time series of oxyhemoglobin and deoxyhemoglobin dynamics. Taking the specificity of the fNIRS signal into account, a comparative analysis of 2 types of neural network architectures was carried out: (1) architectures based on recurrent neural networks: recurrent neural network with long short-term memory, recurrent neural network with long short-term memory with fully connected layers, bidirectional recurrent neural network with long short-term memory, convolutional recurrent neural network with long short-term memory; (2) architectures based on convolutional neural networks with 1D convolutions: convolutional neural network, fully convolutional neural network, residual neural network. Trained long short-term memory recurrent neural network architectures showed worse results in accuracy in comparison with 1D convolutional neural network architectures. Residual neural network (model_Resnet) demonstrated the highest accuracy rates in three experimental conditions more than 88% in detecting age-related differences in brain activation during spatial-numerical association tasks considering the individual characteristics of the respondents’ signal.

In recent years, there were many attempts to classify human emotions based on corporeal signals including ECG, EEG, EMG. EEG based emotion classification is more accurate because it cannot be tainted by subjects' will. The recent development in CNNs has made it easier to systematically extract features from EEG easily. But again, the traditional CNNs fail to comprehend the multi-channel aspect of EEG. In this work, a simple and efficient pre-processing method by considering baseline signals is proposed to enhance the accuracy of recognition and we proposed a hybrid neural network which combines Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) to identify human emotions by extracting spatial and temporal features from raw EEG stream effectively. In CNN, the 1D EEG sequence is then efficiently converted into a 2D frame structure. In order to extract the inter-channel connection between physically adjacent EEG signals, the CNN module is used, and to extract the contextual information, the LSTM module is used. Using this logic, we were able to create a deep learning model which predicts arousal and valence emotions with 86.98% and 85.82% accuracy respectively.

Radar-based target recognition plays a crucial role in a variety of applications, such as surveillance, defense, and autonomous systems. High-resolution radar imagery, when processed effectively, can provide detailed information about objects of interest. However, due to the complex nature of radar signals and the limitations of traditional processing methods, extracting accurate and reliable target information remains challenging. Recent advancements in deep learning, particularly in the domain of image and video processing, have opened new avenues for improving radar-based target recognition. The primary challenge in radar target recognition is the effective use of high-resolution radar imagery, which often contains noise, motion blur, and other distortions. Traditional signal processing techniques struggle to handle these complexities, leading to reduced accuracy in real-world applications. Further, most existing methods are not well-equipped to handle the temporal dynamics and motion information inherent in radar-based video data, which is vital for identifying and tracking moving targets. This paper proposes a novel deep video processing technique designed for radar-based target recognition using high-resolution images. The approach leverages convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to extract spatial and temporal features from radar video sequences. By integrating image enhancement algorithms and advanced feature fusion techniques, the system is capable of processing high-resolution radar frames in real-time. The method involves a two-stage process: first, extracting high-level spatial features from individual radar images using CNNs; second, capturing temporal relationships between frames with RNNs for robust target identification and tracking. Experimental results on a radar video dataset show significant improvements in target recognition accuracy. The proposed technique achieves a recognition rate of 94.3% in identifying static and dynamic targets, outperforming traditional methods by 15-20%. In terms of processing speed, the method demonstrates real-time performance with an average frame processing time of 32 ms, ensuring its suitability for operational environments. The system also demonstrates robustness against noise, with a decrease in false positive rates by 12%.

To investigate the recognition effect of flag motions based on 9 axis sensors, starting with deep learning methods, this paper proposes a framework for feature extraction and recognition of flag movements recognition by employing an improved Inception-ResNet dual-stream network. In traditional signal recognition studies, Support Vector Machine (SVM), Random Forest (RF) and One Dimensional Convolutional Neural Network (CNN) are usually used to extract signals' features. In the meanwhile, the time series data sets such as flag movements are usually the standard data set after processing. Therefore, there are usually some limitations in traditional systems. First, in actual environment, there exists a lack of effective segmentation detection method for the samples of long time series, resulting in the deviation of the data set in the recognition process. Second, the One-Dimensional CNN framework used and the machine learning frameworks used in previous studies are difficult to process large quantities of data with too high computational memory. Based on these problems, this study proposes a signal change point detection model based on the diversity factory function in the signal segmentation and detection stage, miniaturizes the convolution kernel in the original CNN by using the Inception-ResNet(I-R) dual-flow network separable convolution method, and proposes a CrossEntropy-Logistic(C-L) joint classification loss function. Through conducting comparative experiments, it is found that the average calculation parameter of the CNN framework based on the Inception-ResNet model is 2.7×10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">7</sup> , which is approximately 37% lower than the number of 3.7×10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">7</sup> in the original CNN model. Finally, the recognition rate between C-L joint loss function and other models such as Multi-Layer Perceptron and Ensemble Learning in recent years are compared. Compared with Ensemble Learning-CrossEntropy (ELC) model, the C-L joint loss function can improve the recognition rate by nearly 5% according to the results of flag movements identification measured by several classification models.

Investigation of crowdshipping delivery trip production with real-world data

The presented paper proposes a new speech command recognition model for novel engineering applications with limited resources. We built the proposed model with the help of a Convolutional Recurrent Neural Network (CRNN). The use of CRNN instead of Convolutional Neural Network (CNN) helps us to reduce the model parameters and memory requirement as per resource constraints. Furthermore, we insert transmute and curtailment layer between the layers of CRNN. By doing this we further reduce model parameters and float number of operations to half of the CRNN requirement. The proposed model is tested on Google’s speech command dataset. The obtained result shows that the proposed CRNN model requires 1/3 parameters as compared to the CNN model. The number of parameters of the CRNN model is further reduced by 45% and the float numbers of operations between 2% to 12 % in different recognition tasks. The recognition accuracy of the proposed model is 96% on Google’s speech command dataset, and on laboratory recording, its recognition accuracy is 89%.

Recognizing spontaneous micro-expression in video sequences is a challenging problem. In this paper, we propose a new method of small scale spatio-temporal feature learning. The proposed learning method consists of two parts. First, the spatial features of micro-expressions at different expression-states (i.e., onset, onset to apex transition, apex, apex to offset transition and offset) are encoded using convolutional neural networks (CNN). The expression-states are taken into account in the objective functions, to improve the expression class separability of the learned feature representation. Next, the learned spatial features with expression-state constraints are transferred to learn temporal features of micro-expression. The temporal feature learning encodes the temporal characteristics of the different states of the micro-expression using long short-term memory (LSTM) recurrent neural networks. Extensive and comprehensive experiments have been conducted on the publically available CASME II micro-expression dataset. The experimental results showed that the proposed method outperformed state-of-the-art micro-expression recognition methods in terms of recognition accuracy.

This paper proposes a novel deep learning architecture involving combinations of Convolutional Neural Networks (CNN) layers and Recurrent neural networks (RNN) layers that can be used to perform segmentation and classification of 5 cardiac rhythms based on ECG recordings. The algorithm is developed in a sequence to sequence setting where the input is a sequence of five second ECG signal sliding windows and the output is a sequence of cardiac rhythm labels. The novel architecture processes as input both the spectrograms of the ECG signal as well as the heartbeats' signal waveform. Additionally, we are able to train the model in the presence of label noise. The model's performance and generalizability is verified on an external database different from the one we used to train. Experimental result shows this approach can achieve an average F1 scores of 0.89 (averaged across 5 classes). The proposed model also achieves comparable classification performance to existing state-of-the-art approach with considerably less number of training parameters.

In recent years, deep-learning-based motor imagery (MI) electroencephalography (EEG) decoding methods have shown great potential in the field of the brain–computer interface (BCI). The existing literature is relatively mature in decoding methods for two classes of MI tasks. However, with the increase in MI task classes, decoding studies for four classes of MI tasks need to be further explored. In addition, it is difficult to obtain large-scale EEG datasets. When the training data are limited, deep-learning-based decoding models are prone to problems such as overfitting and poor robustness. In this study, we design a data augmentation method for MI-EEG. The original EEG is slid along the time axis and reconstructed to expand the size of the dataset. Second, we combine the gated recurrent unit (GRU) and convolutional neural network (CNN) to construct a parallel-structured feature fusion network to decode four classes of MI tasks. The parallel structure can avoid temporal, frequency and spatial features interfering with each other. Experimenting on the well-known four-class MI dataset BCI Competition IV 2a shows a global average classification accuracy of 80.7% and a kappa value of 0.74. The proposed method improves the robustness of deep learning to decode small-scale EEG datasets and alleviates the overfitting phenomenon caused by insufficient data. The method can be applied to BCI systems with a small amount of daily recorded data.

A hybrid model based on neural networks for biomedical relation extraction