The prediction of peak power load is a critical factor directly impacting the stability of power supply, characterized significantly by its time series nature and intricate ties to the seasonal patterns in electricity usage. Despite its crucial importance, the current landscape of power peak load forecasting remains a multifaceted challenge in the field. This study aims to contribute to this domain by proposing a method that leverages a combination of three primary models - the GRU model, self-attention mechanism, and Transformer mechanism - to forecast peak power load. To contextualize this research within the ongoing discourse, it’s essential to consider the evolving methodologies and advancements in power peak load forecasting. By delving into additional references addressing the complexities and current state of the power peak load forecasting problem, this study aims to build upon the existing knowledge base and offer insights into contemporary challenges and strategies adopted within the field. Data preprocessing in this study involves comprehensive cleaning, standardization, and the design of relevant functions to ensure robustness in the predictive modeling process. Additionally, recognizing the necessity to capture temporal changes effectively, this research incorporates features such as “Weekly Moving Average” and “Monthly Moving Average” into the dataset. To evaluate the proposed methodologies comprehensively, this study conducts comparative analyses with established models such as LSTM, Self-attention network, Transformer, ARIMA, and SVR. The outcomes reveal that the models proposed in this study exhibit superior predictive performance compared to these established models, showcasing their effectiveness in accurately forecasting electricity consumption. The significance of this research lies in two primary contributions. Firstly, it introduces an innovative prediction method combining the GRU model, self-attention mechanism, and Transformer mechanism, aligning with the contemporary evolution of predictive modeling techniques in the field. Secondly, it introduces and emphasizes the utility of “Weekly Moving Average” and “Monthly Moving Average” methodologies, crucial in effectively capturing and interpreting seasonal variations within the dataset. By incorporating these features, this study enhances the model’s ability to account for seasonal influencing factors, thereby significantly improving the accuracy of peak power load forecasting. This contribution aligns with the ongoing efforts to refine forecasting methodologies and addresses the pertinent challenges within power peak load forecasting.

Real-time matting is a challenging research in deep learning. Conventional CNN (Convolutional Neural Networks) approaches are easy to misjudge the foreground and background semantic and have blurry matting edges, which result from CNN’s limited concentration on global context due to receptive field. We propose a real-time matting approach called RMViT (Real-time matting with Vision Transformer) with Transformer structure, attention and content-aware guidance to solve issues above. The semantic accuracy improves a lot due to the establishment of global context and long-range pixel information. The experiments show our approach exceeds a 30% reduction in error metrics compared with existing real-time matting approaches.

In the software testing phase, software reliability growth models (SRGMs) are commonly used to evaluate the reliability of software systems. Traditional SRGMs are restricted by their assumption of a continuous growth pattern for the failure detection rate (FDR) throughout the testing phase. However, the assumption is compromised by Change-Point phenomena, where FDR fluctuations stem from variations in testing personnel or procedural modifications, leading to reduced prediction accuracy and compromised software reliability assessments. Therefore, the objective of this study is to improve software reliability prediction using a novel approach that combines genetic algorithm (GA) and deep learning-based SRGMs to account for the Change-point phenomenon. The proposed approach uses a GA to dynamically combine activation functions from various deep learning-based SRGMs into a new mutated SRGM called MuSRGM. The MuSRGM captures the advantages of both concave and S-shaped SRGMs and is better suited to capture the change-point phenomenon during testing and more accurately reflect actual testing situations. Additionally, failure data is treated as a time series and analyzed using a combination of Long Short-Term Memory (LSTM) and Attention mechanisms. To assess the performance of MuSRGM, we conducted experiments on three distinct failure datasets. The results indicate that MuSRGM outperformed the baseline method, exhibiting low prediction error (MSE) on all three datasets. Furthermore, MuSRGM demonstrated remarkable generalization ability on these datasets, remaining unaffected by uneven data distribution. Therefore, MuSRGM represents a highly promising advanced solution that can provide increased accuracy and applicability for software reliability assessment during the testing phase.

Leukemia is a common and highly dangerous blood disease that requires early detection and treatment. Currently, the diagnosis of leukemia types mainly relies on the pathologist’s morphological examination of blood cell images, which is a tedious and time-consuming process, and the diagnosis results are highly subjective and prone to misdiagnosis and missed diagnosis. This research suggests a blood cell image recognition technique based on an enhanced Vision Transformer to address these problems. Firstly, this paper incorporate convolutions with token embedding to replace the positional encoding which represent coarse spatial information. Then based on the Transformer’s self-attention mechanism, this paper proposes a sparse attention module that can select identifying regions in the image, further enhancing the model’s fine-grained feature expression capability. Finally, this paper uses a contrastive loss function to further increase the intra-class consistency and inter-class difference of classification features. According to experimental results, The model in this study has an identification accuracy of 92.49% on the Munich single-cell morphological dataset, which is an improvement of 1.41% over the baseline. And comparing with sota Swin transformer, this method still get greater performance. So our method has the potential to provide reference for clinical diagnosis by physicians.

The automatic defect detection for fabric images is an essential mission in textile industry. However, there are some inherent difficulties in the detection of fabric images, such as complexity of the background and the highly uneven scales of defects. Moreover, the trade-off between accuracy and speed should be considered in real applications. To address these problems, we propose a novel model based on YOLOv4 to detect defects in fabric images, called Feature Augmentation YOLO (FA-YOLO). In terms of network structure, FA-YOLO adds an additional detection head to improve the detection ability of small defects and builds a powerful Neck structure to enhance feature fusion. First, to reduce information loss during feature fusion, we perform the residual feature augmentation (RFA) on the features after dimensionality reduction by using 1×1 convolution. Afterward, the attention module (SimAM) is embedded into the locations with rich features to improve the adaptation ability to complex backgrounds. Adaptive spatial feature fusion (ASFF) is also applied to output of the Neck to filter inconsistencies across layers. Finally, the cross-stage partial (CSP) structure is introduced for optimization. Experimental results based on three real industrial datasets, including Tianchi fabric dataset (72.5% mAP), ZJU-Leaper fabric dataset (0.714 of average F1-score) and NEU-DET steel dataset (77.2% mAP), demonstrate the proposed FA-YOLO achieves competitive results compared to other state-of-the-art (SoTA) methods.

Software Defined Networking (SDN), a new network architecture, allows for centralized network management by separating the control plane from the forwarding plane. Because forwarding and control is separated, distributed denial of service (DDoS) assaults provide a greater threat to SDN networks. To address the problem, this paper uses a joint high-precision attack detection combining self-attentive mechanism and support vector machine: a trigger mechanism deployed at both control and data layers is proposed to trigger the initial detection of DDoS attacks; the data in the network under attack is screened in detail using a combination of self-attentive mechanism and support vector machine; the control plane is proposed to initiate attack defense using the OpenFlow protocol features to issue flow tables for accurate classification results. The experimental results show that the trigger mechanism can react to the attack in time with less than 20% load, and the accurate detection mechanism is better than the existing inspection and testing methods, with a precision rate of 98.95% and a false alarm rate of only 1.04%. At the same time, the defense strategy can achieve timely recovery of network characteristics.

A user wearing a Head-Mounted Display (HMD) is likely to feel isolated when sharing virtual reality (VR) experiences with Non-HMD users in the same physical space due to not being able to see the real space outside the virtual world. This research proposes a method for an HMD user to recognize the Non-HMD users' gaze and attention via a projector attached to the HMD. In the proposed approach, the projected HMD user's view is filtered darker than default, and when Non-HMD users point controllers towards the projected view, the filter is removed from a circular area for both HMD and Non-HMD users indicating which region the Non-HMD users are viewing. We conducted two user studies showing that the Non-HMD users' gaze can be recognized with the proposed method, and investigated the preferred range for the alpha value and the size of the area for removing the filter for the HMD user.

Facial Beauty Prediction (FBP) is a significant pattern recognition task that aims to achieve consistent facial attractiveness assessment with human perception. Currently, Convolutional Neural Networks (CNNs) have become the mainstream method for FBP. The training objective of most conventional CNNs is usually to learn static convolution kernels, which, however, makes the network quite difficult to capture global attentive information, and thus usually ignores the key facial regions, e.g., eyes, and nose. To tackle this problem, we devise a new convolution manner, Dynamic Attentive Convolution (DyAttenConv), which integrates the dynamic and attention mechanism into convolution in kernel-level, with the aim of enforcing the convolution kernels adapted to each face dynamically. DyAttenConv is a plug-and-play module that can be flexibly combined with existing CNN architectures, making the acquisition of the beauty-related features more globally and attentively. Extensive ablation studies show that our method is superior to other fusion and attention mechanisms, and the comparison with other state-of-the-arts also demonstrates the effectiveness of DyAttenConv on facial beauty prediction task.

Text classification is a fundamental task in natural language processing, which finds extensive applications in various domains, such as spam detection and sentiment analysis. Syntactic information can be effectively utilized to improve the performance of neural network models in understanding the semantics of text. The Chinese text exhibits a high degree of syntactic complexity, with individual words often possessing multiple parts of speech. In this paper, we propose BRsyn-caps, a capsule network-based Chinese text classification model that leverages both Bert and dependency syntax. Our proposed approach integrates semantic information through Bert pre-training model for obtaining word representations, extracts contextual information through Long Short-term memory neural network (LSTM), encodes syntactic dependency trees through graph attention neural network, and utilizes capsule network to effectively integrate features for text classification. Additionally, we propose a character-level syntactic dependency tree adjacency matrix construction algorithm, which can introduce syntactic information into character-level representation. Experiments on five datasets demonstrate that BRsyn-caps can effectively integrate semantic, sequential, and syntactic information in text, proving the effectiveness of our proposed method for Chinese text classification.

Despite Siamese trackers attracting much attention due to their scalability and efficiency in recent years, researchers have ignored the background appearance, which leads to their inapplicability in recognizing arbitrary target objects with various variations, especially in complex scenarios with background clutter and distractors. In this paper, we present a simple yet effective Siamese tracker, where the shifted windows multi-head self-attention is produced to learn the characteristics of a specific given target object for visual tracking. To validate the effectiveness of our proposed tracker, we use the Swin Transformer as the backbone network and introduced an auxiliary feature enhancement network. Extensive experimental results on two evaluation datasets demonstrate that the proposed tracker outperforms other baselines.

Song-level feature summarization is fundamental for the browsing, retrieval, and indexing of digital music archives. This study proposes a deep neural network model, CQTXNet, for extracting song-level feature summary for cover song identification. CQTXNet incorporates depth-wise separable convolution, residual network connections, and attention models to extend previous approaches. An experimental evaluation of the proposed CQTXNet was performed on two publicly available cover song datasets by varying the number of network layers and the type of attention modules.

In this paper, we present a novel photometric compensation network named CASEformer, which is built upon the Swin module. For the first time, we combine coordinate attention and channel attention mechanisms to extract rich features from input images. Employing a multi-level encoder-decoder architecture with skip connections, we establish multiscale interactions between projection surfaces and projection images, achieving precise inference and compensation. Furthermore, through an attention fusion module, which simultaneously leverages both coordinate and channel information, we enhance the global context of feature maps while preserving enhanced texture coordinate details. The experimental results demonstrate the superior compensation effectiveness of our approach compared to the current state-of-the-art methods. Additionally, we propose a method for multi-surface projection compensation, further enriching our contributions.

Driver fatigue detection has become crucial in vehicle safety technology. Achieving high accuracy and real-time performance in detecting driver fatigue is paramount. In this paper, we propose a novel driver fatigue detection algorithm based on dynamic tracking of Facial Eyes and Yawning using YOLOv7, named FEY-YOLOv7. The Coordinate Attention module is inserted into YOLOv7 to enhance its dynamic tracking accuracy by focusing on coordinate information. Additionally, a small target detection head is incorporated into the network architecture to promote the feature extraction ability of small facial targets such as eyes and mouth. In terms of compution, the YOLOv7 network architecture is significantly simplified to achieve high detection speed. Using the proposed PERYAWN algorithm, driver status is labeled and detected by four classes: open_eye, closed_eye, open_mouth, and closed_mouth. Furthermore, the Guided Image Filtering algorithm is employed to enhance image details. The proposed FEY-YOLOv7 is trained and validated on RGB-infrared datasets. The results show that FEY-YOLOv7 has achieved mAP of 0.983 and FPS of 101. This indicates that FEY-YOLOv7 is superior to state-of-the-art methods in accuracy and speed, providing an effective and practical solution for image-based driver fatigue detection.

As a typical surface defect of tunnel lining structures, cracking disease affects the durability of tunnel structures and poses hidden dangers to tunnel driving safety. Factors such as interference from the complex service environment of the tunnel and the low signal-to-noise ratio of the crack targets themselves, have led to existing crack recognition methods based on semantic segmentation being unable to meet actual engineering needs. Based on this, this paper uses the Unet network as the basic framework for crack identification and proposes to construct a multi-kernel convolution cascade enhancement (MKCE) model to achieve accurate detection and identification of crack diseases. First of all, to ensure the performance of crack feature extraction, the model modified the main feature extraction network in the basic framework to ResNet-50 residual network. Compared with the VGG-16 network, this modification can extract richer crack detail features while reducing model parameters. Secondly, considering that the Unet network cannot effectively perceive multi-scale crack features in the skip connection stage, a multi-kernel convolution cascade enhancement module is proposed by combining a cascaded connection of multi-kernel convolution groups and multi-expansion rate dilated convolution groups. This module achieves a comprehensive perception of local details and the global content of tunnel lining cracks. In addition, to better weaken the effect of tunnel background clutter interference, a convolutional block attention calculation module is further introduced after the multi-kernel convolution cascade enhancement module, which effectively reduces the false alarm rate of crack recognition. The algorithm is tested on a large number of subway tunnel crack image datasets. The experimental results show that, compared with other crack recognition algorithms based on deep learning, the method in this paper has achieved the best results in terms of accuracy and intersection over union (IoU) indicators, which verifies the method in this paper has better applicability.

High-performance deep learning-based object detection models can reduce traffic accidents using dashcam images during nighttime driving. Deep learning requires a large-scale dataset to obtain a high-performance model. However, existing object detection datasets are mostly daytime scenes and a few nighttime scenes. Increasing the nighttime dataset is laborious and time-consuming. In such a case, it is possible to convert daytime images to nighttime images by image-to-image translation model to augment the nighttime dataset with less effort so that the translated dataset can utilize the annotations of the daytime dataset. Therefore, in this study, a GAN-based image-to-image translation model is proposed by incorporating self-attention with cycle consistency and content/style separation for nighttime data augmentation that shows high fidelity to annotations of the daytime dataset. Experimental results highlight the effectiveness of the proposed model compared with other models in terms of translated images and FID scores. Moreover, the high fidelity of translated images to the annotations is verified by a small object detection model according to detection results and mAP. Ablation studies confirm the effectiveness of self-attention in the proposed model. As a contribution to GAN-based data augmentation, the source code of the proposed image translation model is publicly available at https://github.com/subecky/Image-Translation-With-Self-Attention

The thermal imaging pedestrian segmentation system has excellent performance in different illumination conditions, but it has some drawbacks(e.g., weak pedestrian texture information, blurred object boundaries). Meanwhile, high-performance large models have higher latency on edge devices with limited computing performance. To solve the above problems, in this paper, we propose a real-time thermal infrared pedestrian segmentation method. The feature extraction layers of our method consist of two paths. Firstly, we utilize the lossless spatial downsampling to obtain boundary texture details on the spatial path. On the context path, we use atrous convolutions to improve the receptive field and obtain more contextual semantic information. Then, the parameter-free attention mechanism is introduced at the end of the two paths for effective feature selection, respectively. The Feature Fusion Module (FFM) is added to fuse the semantic information of the two paths after selection. Finally, we accelerate method inference through multi-threading techniques on the edge computing device. Besides, we create a high-quality infrared pedestrian segmentation dataset to facilitate research. The comparative experiments on the self-built dataset and two public datasets with other methods show that our method also has certain effectiveness. Our code is available at https://github.com/mcjcs001/LEIPNet.

In human-computer interaction, acoustic scene classification (ASC) is one of the relevant research domains. In real life, the recorded audio may include a lot of noise and quiet clips, making it hard for earlier ASC-based research to isolate the crucial scene information in sound. Furthermore, scene information may be scattered across numerous audio frames; hence, selecting scene-related frames is crucial for ASC. In this context, an integrated convolutional neural network with a fusion attention mechanism (ICNN-FA) is proposed for ASC. Firstly, segmented mel-spectrograms as the input of ICNN can assist the model in learning the short-term time-frequency correlation information. Then, the designed ICNN model is employed to learn these segment-level features. In addition, the proposed global attention layer may gather global information by integrating these segment features. Finally, the developed fusion attention layer is utilized to fuse all segment-level features while the classifier classifies various situations. Experimental findings using ASC datasets from DCASE 2018 and 2019 indicate the efficacy of the suggested method.

Speech emotion recognition (SER) has been a complex and difficult task for a long time due to emotional complexity. In this paper, we propose a multitask deep learning approach based on cascaded attention network and self-adaption loss for SER. First, non-personalized features are extracted to represent the process of emotion change while reducing external variables' influence. Second, to highlight salient speech emotion features, a cascade attention network is proposed, where spatial temporal attention can effectively locate the regions of speech that express emotion, while self-attention reduces the dependence on external information. Finally, the influence brought by the differences in gender and human perception of external information is alleviated by using a multitask learning strategy, where a self-adaption loss is introduced to determine the weights of different tasks dynamically. Experimental results on IEMOCAP dataset demonstrate that our method gains an absolute improvement of 1.97% and 0.91% over state-of-the-art strategies in terms of weighted accuracy (WA) and unweighted accuracy (UA), respectively.

Visual Question Answering (VQA) usually uses deep attention mechanisms to learn fine-grained visual content of images and textual content of questions. However, the deep attention mechanism can only learn high-level semantic information while ignoring the impact of the low-level semantic information on answer prediction. For such, we design a High- and Low-Level Semantic Information Network (HLSIN), which employs two strategies to achieve the fusion of high-level semantic information and low-level semantic information. Adaptive weight learning is taken as the first strategy to allow different levels of semantic information to learn weights separately. The gate-sum mechanism is used as the second to suppress invalid information in various levels of information and fuse valid information. On the benchmark VQA-v2 dataset, we quantitatively and qualitatively evaluate HLSIN and conduct extensive ablation studies to explore the reasons behind HLSIN's effectiveness. Experimental results demonstrate that HLSIN significantly outperforms the previous state-of-the-art, with an overall accuracy of 70.93% on test-dev.

Fine-grained image classification is one of the key basic tasks of computer vision. The appearance of traditional deep convolutional neural network (DCNN) combined with attention mechanism can focus on partial and local features of fine-grained images, but it still lacks the consideration of the embedding mode of different attention modules in the network, leading to the unsatisfactory result of classification model. To solve the above problems, three different attention mechanisms are introduced into the DCNN network (like ResNet, VGGNet, etc.), including SE, CBAM and ECA modules, so that DCNN could better focus on the key local features of salient regions in the image. At the same time, we adopt three different embedding modes of attention modules, including serial, residual and parallel modes, to further improve the performance of the classification model. The experimental results show that the three attention modules combined with three different embedding modes can improve the performance of DCNN network effectively. Moreover, compared with SE and ECA, CBAM has stronger feature extraction capability. Among them, the parallelly embedded CBAM can make the local information paid attention to by DCNN richer and more accurate, and bring the optimal effect for DCNN, which is 1.98% and 1.57% higher than that of original VGG16 and Resnet34 in CUB-200-2011 dataset, respectively. The visualization analysis also indicates that the attention modules can be easily embedded into DCNN networks, especially in the parallel mode, with stronger generality and universality.