Gating Unit Research Articles

Network Traffic Classification Model Based on Spatio-Temporal Feature Extraction

The demand for encrypted communication is increasing with the continuous development of secure and trustworthy networks. In edge computing scenarios, the requirement for data processing security is becoming increasingly high. Therefore, the accurate identification of encrypted traffic has become a prerequisite to ensure edge intelligent device security. Currently, encrypted network traffic classification relies on single-feature extraction methods. These methods have simple feature extraction, making distinguishing encrypted network data flows and designing compelling manual features challenging. This leads to low accuracy in multi-classification tasks involving encrypted network traffic. This paper proposes a hybrid deep learning model for multi-classification tasks to address this issue based on the synergy of dilated convolution and gating unit mechanisms. The model comprises a Gated Dilated Convolution (GDC) module and a CA-LSTM module. The GDC module completes the spatial feature extraction of encrypted network traffic through dilated convolution and gating unit mechanisms. In contrast, the CA-LSTM module focuses on extracting temporal network traffic features. By employing a collaborative approach to extract spatio-temporal features, the model ensures feature extraction diversity, guarantees robustness, and effectively enhances the feature extraction rate. We evaluate our multi-classification model using the ISCX VPN-nonVPN public dataset. Experimental results show that the proposed method achieves an accuracy rate of over 95% and a recall rate of over 90%, significantly outperforming existing methods.

Cached Transformers: Improving Transformers with Differentiable Memory Cachde

This work introduces a new Transformer model called Cached Transformer, which uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiable memory cache of tokens. GRC attention enables attending to both past and current tokens, increasing the receptive field of attention and allowing for exploring long-range dependencies. By utilizing a recurrent gating unit to continuously update the cache, our model achieves significant advancements in \textbf{six} language and vision tasks, including language modeling, machine translation, ListOPs, image classification, object detection, and instance segmentation. Furthermore, our approach surpasses previous memory-based techniques in tasks such as language modeling and displays the ability to be applied to a broader range of situations.

Narrative Thinking Oriented Content and Diagram

Abstract The development of contemporary mobile Internet and new media has ushered in a new paradigm of narrative and communication forms. This paper takes the performance of narrative thinking as an entry point and establishes a framework for narrative thinking design by combining the narrative design process and digital technology. Narrative theme analysis is carried out in text narrative and image narrative. The text narrative is characterized by the LDA theme model for extracting narrative theme features. Then the LSTM model is used to classify the emotion of the extracted narrative theme. The visual features of an image narrative are extracted by a self-attention mechanism, combined with a Net VLAD algorithm for feature aggregation, and a compression excitation context gating unit and classifier are introduced to achieve sentiment classification. For the application of narrative thinking design, the news event of MH370 and the elementary school students of A elementary school in S city are taken as the research objects to explore the content and illustration of narrative thinking. The study shows that narrative thinking design can clarify the news event’s specific emotional expression and visualization illustration. The coefficient of the dream narrative theme is 0.317 in the elementary school students’ narrative theme change. The score of the positive emotion is 0.349±0.205, which is 0.024 points lower than the negative emotion. Using narrative thinking to analyze the content and illustrations can identify specific changes, thus improving the corresponding narrative design.

GT-HAD: Gated Transformer for Hyperspectral Anomaly Detection.

Hyperspectral anomaly detection (HAD) aims to distinguish between the background and anomalies in a scene, which has been widely adopted in various applications. Deep neural network (DNN)-based methods have emerged as the predominant solution, wherein the standard paradigm is to discern the background and anomalies based on the error of self-supervised hyperspectral image (HSI) reconstruction. However, current DNN-based methods cannot guarantee correspondence between the background, anomalies, and reconstruction error, which limits the performance of HAD. In this article, we propose a novel gated transformer network for HAD (GT-HAD). Our key observation is that the spatial-spectral similarity in HSI can effectively distinguish between the background and anomalies, which aligns with the fundamental definition of HAD. Consequently, we develop GT-HAD to exploit the spatial-spectral similarity during HSI reconstruction. GT-HAD consists of two distinct branches that model the features of the background and anomalies, respectively, with content similarity as constraints. Furthermore, we introduce an adaptive gating unit to regulate the activation states of these two branches based on a content-matching method (CMM). Extensive experimental results demonstrate the superior performance of GT-HAD. The original code is publicly available at https://github.com/jeline0110/ GT-HAD, along with a comprehensive benchmark of state-of-the-art HAD methods.

A hybrid online and offline teaching model of professional English based on empirical modal decomposition method empowered by digital technology

Abstract With the rapid development of artificial intelligence digital technology, its related techniques have penetrated and been applied to the education industry and field. In this paper, we address the limitations of CEEMD in processing student performance prediction data and combine the hybrid gray wolf optimization algorithm with the minimum gating unit recurrent neural network to establish an English performance prediction model by simulating the leadership, hunting, and ranking mechanisms of the gray wolf population, as a way to complete the optimization of EMD limitations. Then, using the empirical modal decomposition method and other auxiliary methods, we conducted an experimental study on the online and offline “hybrid” teaching model for two classes of English majors in the School of Foreign Languages of Huanghe Science and Technology University in 2021 and passed equal-group pre-test and t-test. The results showed that the significance level α of English performance in class B was 0.10, and since the probability value P was less than 0.10, it was considered that there was a significant difference between the two overall means, i.e., there was a significant difference between the overall means of the improvement in the performance of class B and class A. The overall performance of class B students was significantly higher than that of class A. This study combines online and offline teaching modes through digital technology to promote the use of online and offline “hybrid” teaching modes in higher education institutions, which is very important.

Research on Wind Power Prediction Based on A Gated Transformer

Wind power, as a type of renewable energy, has received widespread attention from domestic and foreign experts. Although it has the advantages of cleanliness and low pollution, its strong randomness and volatility can bring disadvantages to the stable operation of the power grid. Accurate power prediction can avoid the adverse effects of wind power, and is of great significance for power grid frequency regulation, peak shaving, and energy improvement. However, traditional wind power prediction methods can only achieve accurate predictions in the short term and perform poorly in medium- to long-term prediction tasks. To address this issue, a power prediction model based on a Gated Transformer is proposed in this paper. Firstly, it can extract features from different types of data sources, effectively capture their correlations, and achieve data fusion. Secondly, gating unit, dilated convolution unit, and multi-head attention mechanism are added to improve the Receptive field and generalization ability of the model. In addition, adding a decoder to guide data prediction further improves the accuracy of prediction. Finally, experiments are carried out with the data collected from typical wind farms. The results show that the proposed Gated Transformer achieves consistent state-of-the-art results in prediction tasks on different time scales.

Dense ultraweak fiber Bragg grating temperature detection method based on minimal gating unit demodulation

To solve the problems encountered by fiber Bragg grating temperature sensing technology, such as slow response speed and low detection accuracy in small heat source monitoring, a dense ultraweak fiber Bragg grating (UWFBG) temperature detection method based on minimal gating unit (MGU) demodulation is proposed and experimentally demonstrated. This method utilizes a dense UWFBG array with a spatial distance of 10 cm for linear temperature sensing, which is approximate in size to the heat source. Field programmable gate array/advanced RISC machine-embedded circuitry implements data transfer, analog-to-digital conversion, and 1 GSPS high-speed sampling. The MGU network is trained using a mixture of real and simulated data for the demodulation of the central wavelength. Parameters, such as batch size and hidden units, are explored to optimize the demodulation speed and accuracy of the overlapping spectra. Results show that the UWFBG detection temperature method based on the MGU network can demodulate 1000 sets of wavelength data in 2.7 s and obtains a root mean square error of less than 0.923 pm, thereby achieving a fast response to heat sources of 10 cm size and a detection temperature accuracy better than 0.34 °C.

Multi-scale semantic enhancement network for object detection

In the field of object detection, feature pyramid network (FPN) can effectively extract multi-scale information. However, the majority of FPN-based methods suffer from a semantic gap between features of various sizes before feature fusion, which can lead to feature maps with significant aliasing. In this paper, we present a novel multi-scale semantic enhancement feature pyramid network (MSE-FPN) which consists of three effective modules: semantic enhancement module, semantic injection module, and gated channel guidance module to alleviate these problems. Specifically, inspired by the strong ability of the self-attention mechanism to model context, we propose a semantic enhancement module to model global context to obtain the global semantic information before feature fusion. Then we propose the semantic injection module to divide and merge global semantic information into feature maps at various scales to narrow the semantic gap between features at different scales and efficiently utilize the semantic information of high-level features. Finally, to mitigate feature aliasing caused by feature fusion, the gated channel guidance module selectively outputs crucial features via a gating unit. By replacing FPN with MSE-FPN in Faster R-CNN, our models achieve 39.4 and 41.2 Average precision (AP) using ResNet50 and ResNet101 as the backbone network respectively. When using ResNet-101-64x4d as the backbone, MSE-FPN achieved up to 43.4 AP. Our results demonstrate that replacing FPN with MSE-FPN significantly enhances the detection performance of state-of-the-art FPN-based detectors.

Differential Reinforcement and Global Collaboration Network for RGBT Tracking

RGB-thermal (RGBT) tracking has received extensive attention as a research hotspot, benefiting from the complementarity of visible (RGB) and thermal (T) modalities, which can better handle tracking tasks in harsh environments. Existing studies typically deploy the same structure to extract features of heterogeneous modalities with different properties, which may be difficult to simultaneously search for mining strategies suitable for each modality, resulting in insufficient feature representation. With the success of transformer, how to jointly consider the heterogeneity and global mining to facilitate better integration of heterogeneous modalities is also a crucial issue worth exploring. To solve these problems, we propose a unique differential reinforcement and global collaboration network for RGBT tracking, which includes a parallel backbone, modal differential reinforcement (MDR), and global mining collaboration module (GMCM). Specifically, MDR introduces raw data to control adaptive differential reinforcement for both the modalities via a modality-sharing augmentation unit and a modality-aware gating unit. The data-driven design makes it easier for the two modalities to search for the respective appropriate mining strategies, further effectively enhancing the respective feature representations. GMCM first mines intra-modal and cross-modal global information separately, and then performs an adaptive ensemble operation to balance the two. This operation learns intra-modal and cross-modal global weights in RGB and T modalities to better integrate heterogeneous modalities based on heterogeneity and global cues. Extensive experiments on three datasets demonstrate that the performance of the proposed network is comparable to state-of-the-art RGBT trackers.

Design and Experimental Study of a Large Beam Waist Streak Tube in an ICF Experiment.

In order to realize in situ multi-frame framing, this paper designed and developed a large-waist framing converter tube. The size ratio between the waist and the object was about 1.16:1. The subsequent test results showed that the static spatial resolution of the tube could reach 10 lp/mm (@ 72.5%) under the premise of this adjustment, and the transverse magnification could reach 2.9. Once the MCP (Micro Channel Plate) traveling wave gating unit is equipped at the output end, it is expected to promote the further development of in situ multi-frame framing technology.

An Intelligent Channel Estimation Algorithm Based on Extended Model for 5G-V2X.

Car networking systems based on 5G-V2X (vehicle-to-everything) have high requirements for reliability and low-latency communication to further improve communication performance. In the V2X scenario, this article establishes an extended model (basic expansion model) suitable for high-speed mobile scenarios based on the sparsity of the channel impulse response. And propose a channel estimation algorithm based on deep learning, the method designed a multilayer convolutional neural network to complete frequency domain interpolation. A two-way control cycle gating unit (bidirectional gated recurrent unit) is designed to predict the state in the time domain. And introduce speed parameters and multipath parameters to accurately train channel data under different moving speed environments. System simulation shows that the proposed algorithm can accurately train the number of channels. Compared with the traditional car networking channel estimation algorithm, the proposed algorithm improves the accuracy of channel estimation and effectively reduces the bit error rate.

Retracted: Software based sentiment analysis of clinical data for healthcare sector

AbstractRetraction: [Vimal Shanmuganathan, Victor Hugo C. de Albuquerque, Paulo C. S. Barbosa, Marcello Carvalho dos Reis, Gaurav Dhiman, Mohd Asif Shah, Software based sentiment analysis of clinical data for healthcare sector, IET Software 2023 (https://doi.org/10.1049/sfw2.12115)].The above article from IET Software, published online on 7 February 2023 in Wiley Online Library (wileyonlinelibrary.com), has been retracted by agreement between the Editor‐in‐Chief, Hana Chockler, the Institution of Engineering and Technology (the IET) and John Wiley and Sons Ltd. This article was published as part of a Guest Edited special issue. Following an investigation, the IET and the journal have determined that the article was not reviewed in line with the journal’s peer review standards and there is evidence that the peer review process of the special issue underwent systematic manipulation. Accordingly, we cannot vouch for the integrity or reliability of the content. As such we have taken the decision to retract the article. The authors have been informed of the decision to retract.

Design of Spectrum Processing Chiplet Based on FFT Algorithm

With the rapid development of electronic information and computer science, the fast Fourier transform (FFT) has played an increasingly important role in digital signal processing (DSP). This paper presented a spectrum processing chiplet design method to solve slow speed, low precision, and low resource utilization in spectrum processing of general-purpose spectrum chips and field programmable gate array (FPGA). To realize signal processing, the Radix-2 4096-point FFT algorithm with pipeline structure is used to process spectral signals extracted from the time domain. To reduce the harm caused by spectrum leakage, a windowing module is added to optimize the input data, and the clock gating unit (CGU) is used to perform low-power management on the entire clock reset. The result shows the chiplet takes 0.368 ms to complete a 4096-point frequency sweep under a clock frequency of 61.44 MHz. The chiplet significantly improves speed and accuracy in spectrum processing, which has great application potential in wireless communication.

RayMVSNet++: Learning Ray-Based 1D Implicit Fields for Accurate Multi-View Stereo.

Learning-based multi-view stereo (MVS) has by far centered around 3D convolution on cost volumes. Due to the high computation and memory consumption of 3D CNN, the resolution of output depth is often considerably limited. Different from most existing works dedicated to adaptive refinement of cost volumes, we opt to directly optimize the depth value along each camera ray, mimicking the range (depth) finding of a laser scanner. This reduces the MVS problem to ray-based depth optimization which is much more light-weight than full cost volume optimization. In particular, we propose RayMVSNet which learns sequential prediction of a 1D implicit field along each camera ray with the zero-crossing point indicating scene depth. This sequential modeling, conducted based on transformer features, essentially learns the epipolar line search in traditional multi-view stereo. We devise a multi-task learning for better optimization convergence and depth accuracy. We found the monotonicity property of the SDFs along each ray greatly benefits the depth estimation. Our method ranks top on both the DTU and the Tanks & Temples datasets over all previous learning-based methods, achieving an overall reconstruction score of 0.33 mm on DTU and an F-score of 59.48% on Tanks & Temples. It is able to produce high-quality depth estimation and point cloud reconstruction in challenging scenarios such as objects/scenes with non-textured surface, severe occlusion, and highly varying depth range. Further, we propose RayMVSNet++ to enhance contextual feature aggregation for each ray through designing an attentional gating unit to select semantically relevant neighboring rays within the local frustum around that ray. This improves the performance on datasets with more challenging examples (e.g., low-quality images caused by poor lighting conditions or motion blur). RayMVSNet++ achieves state-of-the-art performance on the ScanNet dataset. In particular, it attains an AbsRel of 0.058m and produces accurate results on the two subsets of textureless regions and large depth variation.

A Two-Stage Method for Ultra-Short-Term PV Power Forecasting Based on Data-Driven

To promote the real-time dispatching of a power grid and balanced decision-making of power producers, accuracy and real-time forecasting are two main problems that need to be solved in ultra-short-term photovoltaic (PV) forecasting. Focusing on the problems of slow model training speed and low forecasting accuracy due to the redundancy of training data samples and insufficient long periodic capture of data in complex weather, this paper proposes a two-stage method for ultra-short-term PV power forecasting based on data-driven. In the meteorological analysis stage, the generation power samples similar to the forecast day were extracted by inputting daily meteorological features and using maximal information coefficient (MIC) weighted grey correlation degree to form the corresponding forecast data set. In the power forecasting stage, the temporal convolutional used network (TCN) extracts local features to maintain the sequence of extracted features. Then the bidirectional gating unit (BiGRU) combined with the Skip connection strategy was used to fully learn the long and the short time sequence of photovoltaic sequences, and the attention mechanism was used to pay adaptive attention to the more important historical states. This study experimented on the measured data from a photovoltaic power station in Southeastern China. The experimental results show that this method is effective in photovoltaic power short-term forecasts. In addition, compared with some traditional forecasting models, this method has smaller forecasting errors and higher robustness in the time scales of 15 minutes, 30 minutes, 45 minutes, and 60 minutes.

SHNN: A single-channel EEG sleep staging model based on semi-supervised learning

Sleep staging is an essential step in the diagnosis and treatment of sleep-related diseases. Currently, most supervised learning models face the problem of insufficient labeled data. In addition, most sleep staging models are based on multi-channel EEG, and the models are too complex to be suitable for home sleep monitoring scenarios. To tackle these problems, this study proposes a sleep staging method based on pseudo-label optimization and a single-channel sleep hybrid neural network called SHNN. In the SHNN model, we design a multi-scale convolutional neural network (CNN) to extract the features from the single-channel EEG and use a Bi-directional recurrent gating unit (Bi-GRU) to obtain temporal context information of sleep data sequences. Extensive experiments based on the single-channel EEG (FPz-Cz, Pz-Oz, and Cz-A1) of the Sleep-EDFx and the DREAMS-SUB datasets validate the effectiveness of the SHNN model and the pseudo-label optimization algorithm therein outperforming current single-channel methods regarding the accuracy, kappa, and MF1 Score. Moreover, the pseudo-label optimization algorithm can achieve good results on other sleep staging methods. The SHNN code is available at https://github.com/Caowenpeng/SHNN.

Semi-supervised Remote Sensing Image Scene Classification Based on Generative Adversarial Networks

With the availability of numerous high-resolution remote sensing images, remote sensing image scene classification has been widely used in various fields. Compared with the field of natural images, the insufficient number of labeled remote sensing images limits the performance of supervised scene classification, while unsupervised methods are difficult to meet the practical applications. Therefore, this paper proposes a semi-supervised remote sensing image scene classification method using generative adversarial networks. The proposed method introduces dense residual block, pre-trained Inception V3 networks, gating unit, pyramidal convolution, and spectral normalization into GANs to promote the semi-supervised classification performance. To be specific, the pre-trained Inception V3 network is introduced to extract semantic features to enhance the feature discriminant capability. The gating unit is utilized to capture the relationships among features. The pyramidal convolution is integrated into dense residual block to capture different levels of details to strengthen the feature representation capability. The spectral normalization is introduced to stabilize the GANs training to improve semi-supervised classification accuracy. Extensive experimental results on publicly available EuroSAT and UC Merced datasets show that the proposed method gains the highest overall accuracy, especially when only a few labeled samples are available.

Hybrid Japanese Language Teaching Aid System with Multi-Source Information Fusion Mapping

Learning Japanese can enhance competitiveness in a globalized economy, and we address the problems of poor open-source Japanese language teaching, cumbersome teaching tasks, and a single teaching model. We propose a hybrid Japanese teaching aid system with multiple information fusion mapping, which can effectively improve the efficiency of Japanese teaching and reduce the tedious human teaching procedures. The system is divided into two branches of Japanese language recognition, namely, the Japanese text recognition branch and the Japanese voice sequence recognition branch. In the Japanese text recognition branch, we integrate attention mechanisms and long short-term memory networks as the basic network for Japanese character text recognition. In addition, we set up separate text feature recognition systems for Japanese computer writing and handwriting to prevent feature overlap problems. For Japanese voice sequence recognition, we used a combination of memory gating unit and encoder, based on the network still extending the structure of the deep neural network and using the residual structure connection in the gating unit to avoid the gradient disappearance problem. At the end of the system, we use a softmax layer to connect the text recognition and voice recognition networks to form a Japanese language teaching aid system. To verify the efficiency of our system, we selected the Japanese text recognition public dataset and voice recognition public dataset for experimental validation. To match the practical application of the system, we created our dataset based on the dataset standard and conducted experimental validation. To compare other Japanese recognition methods, we selected the six most representative Japanese recognition algorithms for experimental comparison. To ensure the balance of the experiments, each algorithm is trained in a separate experimental environment for modeling and tuning parameters. Experimental performance and the experimental results show that our method significantly outperforms the other methods and has better system stability.

Image Super-Resolution Reconstruction Method for Lung Cancer CT-Scanned Images Based on Neural Network.

The super-resolution (SR) reconstruction of a single image is an important image synthesis task especially for medical applications. This paper is studying the application of image segmentation for lung cancer images. This research work is utilizing the power of deep learning for resolution reconstruction for lung cancer-based images. At present, the neural networks utilized for image segmentation and classification are suffering from the loss of information where information passes through one layer to another deep layer. The commonly used loss functions include content-based reconstruction loss and generative confrontation network. The sparse coding single-image super-resolution reconstruction algorithm can easily lead to the phenomenon of incorrect geometric structure in the reconstructed image. In order to solve the problem of excessive smoothness and blurring of the reconstructed image edges caused by the introduction of this self-similarity constraint, a two-layer reconstruction framework based on a smooth layer and a texture layer is proposed for a medical application of lung cancer. This method uses a global nonzero gradient number constrained reconstruction model to reconstruct the smooth layer. The proposed sparse coding method is used to reconstruct high-resolution texture images. Finally, a global and local optimization models are used to further improve the quality of the reconstructed image. An adaptive multiscale remote sensing image super-division reconstruction network is designed. The selective core network and adaptive gating unit are integrated to extract and fuse features to obtain a preliminary reconstruction. Through the proposed dual-drive module, the feature prior drive loss and task drive loss are transmitted to the super-resolution network. The proposed work not only improves the subjective visual effect but the robustness has also been enhanced with more accurate construction of edges. The statistical evaluators are used to test the viability of the proposed scheme.

Traffic Prediction of Space-Integrated Ground Information Network Using the GTCN Algorithm

The traffic data of the intelligent network with the Space-Integrated Ground Information Network have the characteristics of robust traffic burst, large traffic data, and high volatility compared with the ground traffic. We propose a Gated Temporal Convolution Network (GTCN) algorithm to solve the above problems, the algorithm segments the traffic time series into equal length according to the autocorrelation of the network traffic, and creates the feature sequence by extracting the segmented features using Temporal Convolution Network (TCN), to learn the burst and fluctuation of the intelligent network traffic of the Space-Integrated Ground Information Intelligent Network and to improve the processing efficiency of the traffic time series. Then, the feature sequences of each subsection data are stored, screened, and retained through the gated unit. Finally, the network traffic data are accurately predicted using the characteristics of the sequences stored by the TCN and the gating unit. The simulation experiments showed that, compared with the comparison algorithms, the accuracy of the proposed algorithm is improved by at least 58.72%, the training speed of the algorithm is improved by 84.05%, and the algorithm execution speed is improved by 71.92%, which meet the requirements of the accuracy and timeliness of the traffic prediction model of the Space-Integrated Ground Information Intelligent Network.