Search

Strip steel serves as a crucial raw material in numerous industries, including aircraft and automobile manufacturing. Surface defects in strip steel can degrade the performance, quality, and appearance of industrial steel products. Detecting surface defects in steel strip products is challenging due to the low contrast between defects and background, small defect targets, as well as significant variations in defect sizes. To address these challenges, a two-stage attention-based feature-enhancement network (TAFENet) is proposed, wherein the first-stage feature-enhancement procedure utilizes an attentional convolutional fusion module with convolution to combine all four-level features and then strengthens the features of different levels via a residual spatial-channel attention connection module (RSC). The second-stage feature-enhancement procedure combines three-level features using an attentional self-attention fusion module and then strengthens the features using a RSC attention module. Experiments on the NEU-DET and GC10-DET datasets demonstrated that the proposed method significantly improved detection accuracy, thereby confirming the effectiveness and generalization capability of the proposed method. [ABSTRACT FROM AUTHOR]

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Low‐light image enhancement (LLIE) aims to recover high‐ quality images from low‐quality images acquired in dimly illuminated scenes. However, deep learning algorithms often struggle with uneven exposure and obscured texture features. To address these obstacles, we propose a simple but novel Transformer structure for LLIE, called Double Collapse Transformer (DCTFormer), which has the advantage of modeling non‐local self‐attention and capturing long‐range dependencies easily. The core of DCTFormer is multiple CT blocks composed of pixel‐level spaces and channel self‐attention, which can effectively aggregate features in both the space and channel dimensions. Furthermore, we design the Local Processing Unit (LPU) and an Inverted Residual Feed‐Forward Module (IRFFN) to further enhance the model's ability to learn effective features from current local information. DCTFormer adopts a high‐resolution preservation mechanism overall and gradually integrates deep features to achieve intra‐block feature aggregation. Experimental results on existing benchmark datasets demonstrate the superiority of the proposed DCTFormer. [ABSTRACT FROM AUTHOR]

Stress has been identified as one of major causes of health issues. To detect the stress levels with higher accuracy, fusion of multimodal physiological signals is a promising technique. However, there is an asynchrony between physiological signals observed from different perspectives. Exploring the temporal alignment relationship between modalities is helpful to improve the quality of multimodal fusion. This paper proposes an end-to-end multimodal stress detection model based on Bidirectional Cross- and Self-modal Attention (BCSA) mechanism. Specifically, we first construct different feature extractors based on the characteristics of Blood Volume Pulse (BVP) and Electrodermal Activity (EDA) to complete automated temporal feature extraction. Second, cross-modal attention is used to seek the alignment relationship between the two modalities and fully fuse cross-modal information. The self-modal attention is used to attenuate noise and redundant information, highlight important information and obtain salient stress representations. Finally, the stress representations of the two modalities are processed separately, and the mean square error (MSE) is used to narrow the gap between them. Experimental results on the UBFC-Phys dataset and WESAD dataset show that the proposed model can effectively improve the accuracy of stress recognition, and outperforms several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Registration of deformable objects is a fundamental prerequisite for many modern virtual reality and computer vision applications. However, due to the difficulties of acquiring labeled datasets and the inherent irregular deformation, non-rigid registration for 3D scanner-captured data remains challenging. This paper proposes an unsupervised non-rigid 3D point cloud registration network based on the self-attention mechanism. Specifically, considering the registration as the result of point drifts between the source and target shapes, a Transformer-based encoder-decoder module is utilized to estimate the point displacements. Additionally, a symmetric registration procedure is adopted with regularization loss to manage the regular deformation of points, ultimately producing reasonable registration results for real-world deformable objects. Experiments are conducted on public and synthesized datasets which simulate diversiform non-rigid 2D or 3D deformations. Numerical and qualitative experimental results demonstrate that the proposed network achieves outstanding performance and is robust in scenes with multiple interferences. [ABSTRACT FROM AUTHOR]

Aiming at the problems of overfitting and low classification accuracy due to the scarcity of ore samples in industrial applications of deep learning models for online ore classification, a method combining X ray transmission imaging technology for ore data augmentation and classification is proposed. The method is based on an improved auxiliary classifier generative adversarial network (Enhance based Classification ACGAN gp, EC ACGAN gp), which uses convolutional and continuous residual blocks to construct the network structures of the discriminator and generator. An attention mechanism is introduced to capture detailed ore features and generate high quality samples to expand the original dataset. Simultaneously, the Wasserstein distance function with gradient penalty is used to reconstruct the classification loss function, achieving improved stability of adversarial training and avoiding mode collapse. Finally, an auxiliary classifier is utilized to reconstruct label information for ore sample category prediction. The research results show that the proposed method can accurately predict the ore grade classification, with an accuracy of up to 89. 62%, which is 3. 98% higher than traditional methods. The model generated ore samples demonstrate good generalization performance, significantly improving the generalization of small sample datasets* When tested on SVM, LeNet5, VGGNet, and ResNet, the accuracy is increased by 2. 83%, 2. 36%89%, and 3. 74%, respectively. This method can further be used to enhance the performance of other classification models in ore grade prediction* [ABSTRACT FROM AUTHOR]

Many diverse phenomena in nature often inherently encode both short- and long-term temporal dependencies, which especially result from the direction of the flow of time. In this respect, we discovered experimental evidence suggesting that interrelations of these events are higher for closer time stamps. However, to be able for attention-based models to learn these regularities in short-term dependencies, it requires large amounts of data, which are often infeasible. This is because, while they are good at learning piece-wise temporal dependencies, attention-based models lack structures that encode biases in time series. As a resolution, we propose a simple and efficient method that enables attention layers to better encode the short-term temporal bias of these data sets by applying learnable, adaptive kernels directly to the attention matrices. We chose various prediction tasks for the experiments using Electronic Health Records (EHR) data sets since they are great examples with underlying long- and short-term temporal dependencies. Our experiments show exceptional classification results compared to best-performing models on most tasks and data sets.

With the continuous evolution of novel network attacks, traditional Intrusion Detection Systems (IDSs) have commonly employed Deep Neural Networks (DNNs) for intrusion detection. However, the effectiveness of a DNN in this respect is closely related to the quality of the training data set, and large-scale network traffic data are difficult to label accurately. Therefore, some challenges still need to be addressed to detect network attacks. In this paper, we introduce a Time-Space Separable Attention Network (TSSAN) for intrusion detection. TSSAN utilizes depth wise separable convolution and a time-space self-attention mechanism to effectively extract temporal and spatial features. By extracting the common features from the unlabeled data, TSSAN significantly enhanced the detection performance for rare attack types. Experimental evaluations were conducted using UNSW-NB15 and CICIDS-2017 datasets. Meticulous experiments for evaluating the individual components of the model were rigorously carried out using the CICIDS-2017 dataset. In the unsupervised learning experiment, our method achieved 0.86 and 0.92 f1score in the two datasets. In semi-supervised learning, the experiment showed that our method performed significantly better than the traditional deep learning method when the labelled data were gradually reduced.

As global population growth and the use of household appliances increase, residential electricity consumption has surged, leading to challenges in maintaining a balanced electrical load. This surge often results in localized and intermittent power outages, adversely affecting residential electricity reliability and the profitability of power supply companies. Addressing this, we propose a novel CNN-BiLSTM-SA model, combining Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Self-Attention (SA) mechanisms, to accurately predict residential electricity consumption. The model integrates temporal feature extraction through the CNN module, correlation capture via BiLSTM, and intrinsic feature analysis using SA mechanisms, enhancing predictive accuracy. Our experimental results demonstrate the model’s precision, outperforming existing methods in key performance metrics. Additionally, ablation studies affirm the synergistic design of CNN-BiLSTM-SA’s network components, contributing to its overall efficacy.

Active learning is a strategy that involves the deliberate selection of training samples with significant discriminative features, to formulate a more efficient learning paradigm. While active learning has seen success in image classification, its application in object detection remains complex due to the multiple candidate object instances in an image and the interference of background regions on these instances. To tackle the challenge of sample selection in active learning for large object recognition datasets, this paper introduces a active learning method based on local feature saliency and posterior probability. Initially, the method selects active learning samples with discriminative saliency by clustering the multi-scale feature maps of the processed samples by self-attention weights. Subsequently, it calculates the posterior entropy based on the posterior probability of the current model’s candidate instances. This is combined with the entropy encoding of feature points corresponding to instances in the cluster to further select uncertain samples in the object set. On the COCO dataset, our method demonstrates superior overall performance in the learning curve compared to existing object detection baselines. Moreover, under the same training configuration, the final detection accuracy shows a notable improvement of at least 2.36%, thus confirming the effectiveness of our method in enhancing learning and detection performance.

Pest identification is a challenging task in the agricultural sector, as accurate and timely detection of pests is essential for effective pest control and crop protection. Conventional approaches to pest detection, such as entomological knowledge and manual examination, take a lot of time and are prone to human mistakes. The advent of Deep Learning (DL) techniques has revolutionized the field of computer vision, enabling automated and efficient pest recognition systems.In this research, we compared the effectiveness of many deep learning models and suggested an enhanced approach for more effective feature extraction. In the proposed approach, we have incorporated two parallel attention mechanisms in ResNet architectures and it has a significant improvement in performance. Experimental result shows that the performance accuracy obtained in ResNet50-SA, ResNet101-SA, and ResNet152-SA is 99.80%, 88.48% and 96.68%, respectively. The performance of ResNet50-SA outperforms the other state of art deep learning by a large margin. The result shows that ResNet with self-attention (SA) has a better ability to extract features and focus on the important features which increases the performance.

Single-cell omics sequencing has rapidly advanced, enabling the quantification of diverse omics profiles at a single-cell resolution. To facilitate comprehensive biological insights, such as cellular differentiation trajectories, precise annotation of cell subtypes is essential. Conventional methods involve clustering cells and manually assigning subtypes based on canonical markers, a labor-intensive and expert-dependent process. Hence, an automated computational prediction framework is crucial. While several classification frameworks for predicting cell subtypes from single-cell RNA sequencing datasets exist, these methods solely rely on single-omics data, offering insights at a single molecular level. They often miss inter-omic correlations and a holistic understanding of cellular processes. To address this, the integration of multi-omics datasets from individual cells is essential for accurate subtype annotation. This article introduces moSCminer, a novel framework for classifying cell subtypes that harnesses the power of single-cell multi-omics sequencing datasets through an attention-based neural network operating at the omics level. By integrating three distinct omics datasets--gene expression, DNA methylation, and DNA accessibility--while accounting for their biological relationships, moSCminer excels at learning the relative significance of each omics feature. It then transforms this knowledge into a novel representation for cell subtype classification. Comparative evaluations against standard machine learning-based classifiers demonstrate moSCminer's superior performance, consistently achieving the highest average performance on real datasets. The efficacy of multi-omics integration is further corroborated through an in-depth analysis of the omics-level attention module, which identifies potential markers for cell subtype annotation. To enhance accessibility and scalability, moSCminer is accessible as a user-friendly web-based platform seamlessly connected to a cloud system, publicly accessible at http://203.252.206.118:5568. Notably, this study marks the pioneering integration of three single-cell multi-omics datasets for cell subtype identification. [ABSTRACT FROM AUTHOR]

The field of energy disaggregation deals with the approximation of appliance electric consumption using only the aggregate consumption measurement of a mains meter. Recent research developments have used deep neural networks and outperformed previous methods based on Hidden Markov Models. On the other hand, deep learning models are computationally heavy and require huge amounts of data. The main objective of the current paper is to incorporate the attention mechanism into neural networks in order to reduce their computational complexity. For the attention mechanism two different versions are utilized, named Additive and Dot Attention. The experiments show that they perform on par, while the Dot mechanism is slightly faster. The two versions of self-attentive neural networks are compared against two state-of-the-art energy disaggregation deep learning models. The experimental results show that the proposed architecture achieves faster or equal training and inference time and with minor performance drop depending on the device or the dataset. [ABSTRACT FROM AUTHOR]

Compared with traditional methods, the action recognition model based on 3D convolutional deep neural network captures spatio-temporal features more accurately, resulting in higher accuracy. However, the large number of parameters and computational requirements of 3D models make it difficult to deploy on mobile devices with limited computing power. In order to achieve an efficient video action recognition model, we have analyzed and compared classic lightweight network principles and proposed the 3D-ShuffleViT network. By deeply integrating the self-attention mechanism with convolution, we have introduced an efficient ACISA module that further enhances the performance of our proposed model. This has resulted in exceptional performance in both context-sensitive and context-independent action recognition, while reducing deployment costs. It is worth noting that our 3D-ShuffleViT network, with a computational cost of only 6% of that of SlowFast-ResNet101, achieved 98% of the latter's Top1 accuracy on the EgoGesture dataset. Furthermore, on the same CPU (Intel i5-8300H), its speed was 2.5 times that of the latter. In addition, when we deployed our model on edge devices, our proposed network achieved the best balance between accuracy and speed among lightweight networks of the same order. [ABSTRACT FROM AUTHOR]

Survival analysis has become one of the paramount procedures in the modeling of time-to-event data. When we encounter complex survival problems, the traditional approach remains limited in accounting for the complex correlational structure between the covariates and the outcome due to the strong assumptions that limit the inference and prediction ability of the resulting models. Several studies exist on the deep learning approach to survival modeling; moreover, the application for the case of complex survival problems still needs to be improved. In addition, the existing models need to address the data structure's complexity fully and are subject to noise and redundant information. In this study, we design a deep learning technique (CmpXRnnSurv_AE) that obliterates the limitations imposed by traditional approaches and addresses the above issues to jointly predict the risk-specific probabilities and survival function for recurrent events with competing risks. We introduce the component termed Risks Information Weights (RIW) as an attention mechanism to compute the weighted cumulative incidence function (WCIF) and an external auto-encoder (ExternalAE) as a feature selector to extract complex characteristics among the set of covariates responsible for the cause-specific events. We train our model using synthetic and real data sets and employ the appropriate metrics for complex survival models for evaluation. As benchmarks, we selected both traditional, and machine learning models and our model demonstrates better performance across all datasets. [ABSTRACT FROM AUTHOR]

Auto coloring transforms grayscale images into reasonable colored versions of natural color images,allowing the restoration of color for old photographs,black-and-white films,videos,etc.Therefore,it is widely concerned in the realms of computer vision and graphics.Nevertheless,allocating colors to grayscale images is a highly challenging mission with a color overflow pro-blem.To address the problem,a technique for automatic coloring of images with polarized self-attention constrained color overflow is proposed.At first,separating instances in the foreground from the background minimizes the coloring effect of the background against the foreground,to mitigate the color overflow among the foreground and background.Second,the polarized self-attention block splits the features into color channels and spatial locations for more accurate and specific coloring,which reduces the color overflow within the global image,instance objects.At last,the fusion module is combined to integrate the global features and instance features through different weights to accomplish the ultimate coloring.Experiment results show that the main indexes FID and LPIPS are improved by 9.7% and 10.9% respectively,and the indexes SSIM and PSNR are optimal compared with ChromaGAN and MemoGAN.

Offline handwritten text recognition (HTR) typically relies on segmented text-line images for training and transcription. However, acquiring line-level position and transcript information can be challenging and time-consuming, while automatic line segmentation algorithms are prone to errors that impede the recognition phase. To address these issues, we introduce a state-of-the-art solution that integrates vision and language models using efficient split and multi-head attention neural networks, referred to as joint attention (ResneSt-Transformer), for end-to-end recognition of handwritten paragraphs. Our proposed novel one-stage, segmentation-free pipeline employs joint attention mechanisms to process paragraph images in an end-to-end trainable manner. This pipeline comprises three modules, with the output of one serving as the input for the next. Initially, a feature extraction module employing a CNN with a split attention mechanism (ResneSt50) is utilized. Subsequently, we develop an encoder module containing four transformer layers to generate robust representations of the entire paragraph image. Lastly, we designed a decoder module with six transformer layers to construct weighted masks. The encoder and decoder modules incorporate a multi-head self-attention mechanism and positional encoding, enabling the model to concentrate on specific feature maps at the current time step. By leveraging joint attention and a segmentation-free approach, our neural network calculates split attention weights on the visual representation, facilitating implicit line segmentation. This strategy signifies a substantial advancement toward achieving end-to-end transcription of entire paragraphs. Experiments conducted on paragraph-level benchmark datasets, including RIMES, IAM, and READ 2016 test datasets, demonstrate competitive results compared to recent paragraph-level models while maintaining reduced complexity. The code and pre-trained models are available on our GitHub repository here: HTTPS link.

Automatic vessel segmentation in the fundus images plays an important role in the screening, diagnosis, treatment, and evaluation of various cardiovascular and ophthalmologic diseases. However, due to the limited well-annotated data, varying size of vessels, and intricate vessel structures, retinal vessel segmentation has become a long-standing challenge. Therefore, it proposes a self-attention fusion network which combines spatial attention and channel attention in parallel to handle the retinal vessels segmentation problem. It focuses on high-frequency information extraction by combining the channel and spatial mechanism. It sums the outputs of the two attention modules to further improve feature representation which contributes to more precise segmentation results. It validates the algorithm on public datasets DRIVE, CHASE_DB1 and STARE. The results show that compared with the retinal vessel segmentation algorithm in recent years, the self attention fusion network proposed in this paper has great advantages over other algorithms. [ABSTRACT FROM AUTHOR]

A sequence of radar echo maps can visually show the motion and variation trends of the echo area, making it a common tool for precipitation forecasting. The spatiotemporal context reveals the correlations of variation trends among different parts within the echo area. This paper proposes a novel precipitation forecasting model, ISTC-SA-MIM (Interactive Spatiotemporal Context Learning with Self-Attention and Memory in Memory), based on the MIM. Leveraging the spatiotemporal interactions and self-attention mechanism of the ISTC-SA structure, the proposed model effectively captures both long-term and short-term spatiotemporal contexts. By memorizing the spatiotemporal context and non-stationary information, ISTC-SA-MIM can accurately predict the motion and variation trends of the echo area. Radar echo data from the Qingdao station are collected as the dataset to evaluate the commonly used spatiotemporal models and ISTC-SA-MIM. The experiments demonstrate that ISTC-SA-MIM can predict the variation trends of the echo area more accurately by learning the spatiotemporal context. [ABSTRACT FROM AUTHOR]

Thangka murals hold significant cultural value in Tibet, but unfortunately, many of these precious murals have sustained damage over time. Therefore, the restoration of Thangka murals is crucial in preserving Tibet’s cultural heritage. The potential of Gated Convolution for Thangka mural restoration is significant due to its impressive performance. However, existing Gated Convolution-based approaches for Thangka restoration face two challenges: 1) restoration results using Gated Convolution still show blurring at the pixel level, and 2) Gated Convolution remains dependent on the perceptual field of the convolution during image inpainting. To address two challenges, we propose a novel Thangka mural inpainting method that incorporates two key components: 1) an Edge-assisted Feature Fusion (EFF) method that leverages edge information to assist in inpainting the texture details of the image and enhance the consistency of textures and edges; and 2) a Self Attention based Local Refine (SALR) network that effectively enhances the perceptual field of the convolution and captures long-distance dependencies. The experimental results demonstrate that our proposed method is effective in repairing broken areas of Thangka murals, even on a small dataset (N = 5605). To validate the effectiveness of our proposed architecture and its components, we conduct a series of ablation experiments. The results demonstrate the necessity of our approach and highlight the contributions of each component. Moreover, the proposed end-to-end approach exhibits broad applicability and can be extended to other profiling tasks based on small datasets.

In recent years, the wide use of deep learning based methods has greatly improved the classification performance of hyperspectral image (HSI). As an effective method to improve the performance of deep convolution networks, attention mechanism is also widely used for HSI classification tasks. However, the majority of the existing attention mechanisms for HSI classification are based on the convolution layer, and the classification accuracy still has margins for improvement. Motivated by the latest self attention mechanism in natural language processing, a deep transformer is proposed for HSI classification in this paper. Specifically, deep transformer along the spectral dimension and the spatial dimension are explored respectively. Then, a deep spatial-spectral transformer (DSS-TRM) is proposed to improve the classification performance of HSI. The contribution of this paper is to make full use of self attention mechanism, that is to use transformer layer instead of convolution layer. More importantly, a DSS-TRM is proposed to realize end-to-end HSI classification. Extensive experiments are conducted on three HSI data sets. The experimental results demonstrates that the proposed DSS-TRM could outperform the traditional convolutional neural networks and attention based methods.

We investigate two neuro-developmental disorders in children– Autism Spectrum Disorder (ASD) and Attention-deficit/hyperactivity disorder (ADHD). Most works in literature have examined these disorders separately, e.g., ASD or ADHD subjects vs healthy subjects. We base our framework on the approach adopted by a paediatrician. We propose a one-class model for characterizing healthy subjects. Any subject with ASD/ADHD is considered an outlier by this one-class model. We adopt a Dense GAN architecture with self-attention modules as our one-class model. Our system uses T1-weighted longitudinal structural magnetic resonance images (sMRI) as input modalities. Further, we train our framework using longitudinal data (two scans per subject over time) only, instead of the traditional approaches using cross-sectional data (one scan per subject). Our approach is similar to paediatricians diagnosing the subject over multiple sessions to confirm the disorder. Comprehensive experiments show that our proposed approach performs better than competing ASD and ADHD works.

Person re-identification (Re-ID) is a computer vision task that involves recognizing and tracking individuals across multiple non-overlapping cameras or over time within the same camera view. It is particularly important in surveillance systems, where it can help in identifying potential threats or tracking suspects. Convolutional neural networks (CNNs) have been used to extract invariant person representation for this challenging task. However, CNNs do not consider global dependencies in their initial layers, causing some vital information to be lost during the convolution process. The development of vision-based transformers has opened up new research avenues for person re-identification. This work proposes a purely transformer-based solution, called TansPose Re-ID, that learns pose-invariant person representations. The proposed system uses a vision transformer baseline and enhances its architecture by introducing multiple streams to learn global and local dependencies as well as pose invariance in person images. The architecture includes a Global Self-Attention Module (GSM) and a Local Self-Attention Module (LSM) that jointly learn global and local patch-based person embeddings. The LSM is further improved by stochastically grouping local patches and aligning them. Additionally, an attention feature learning module (AFLM) is introduced in the LSM to handle pose and viewpoint variations. The proposed method is evaluated on two public Re-ID benchmarks, Market1501 and DukeMTMC-ReID, and demonstrates superior performance compared to existing transformer baselines. [ABSTRACT FROM AUTHOR]

Both Nickel and Cobalt have been extensively used in cutting-edge technologies, such as electric vehicle battery manufacturing, stainless steel, and special alloys production. As governments focus on greener solutions for areas such as transportation and energy generation, both metals are increasingly used for energy storage purposes. However, their price uncertainty makes for an interesting case in the modern economy. This study focuses on the price volatility forecasting of Nickel and Cobalt using ANN (Artificial Neural Network) built on a special class of Transformer models used for multi-step ahead forecasts. Our results suggest that the given model is only slightly better in predictive accuracy compared to traditional sequential deep learning models such as BiLSTM (Bidirectional Long Short-Term Memory) and GRUs (gated recurrent units). Moreover, our findings also show that, like conventional approaches, in-sample behavior does not guarantee out-of-sample behavior. The given study could be utilized by industry participants for an inquiry into new and efficient ways to forecast and identify temporal-based structural patterns in commodity-based time series. [ABSTRACT FROM AUTHOR]

Generating dynamic node representation via limited samples at a time is a challenging task. Meanwhile, the human brain can quickly capture dynamic features without much information in a changing environment. Motivated by the idea of brain functions from the adaptive resonance theory (ART), in this paper, we designed and built a dynamic model for node representation generation. Based on the data flow of the ART model, we replaced the classic ART components with deep learnable modules. Our proposed method is suitable for capturing different graph evolution events even with very sparse changes. Experimental results on several synthetic and real-world dynamic graphs for many vital applications show the superiority of our proposed method. [ABSTRACT FROM AUTHOR]

There is dynamic complexity of preference among members in group recommendation, and the preferences of group members will affect each other. As for these questions, this paper proposes a group recommendation algorithm that combines the context information and self attention mechanism. Specifically, first of all, in order to better capture the dynamic relationship among group members, the author used self attention mechanism to automatically learn the context information of users in the group and the relationship weights among other members in the group; Secondly, according to the group matrix learned from the self attention mechanism, the author embedded the average value to obtain the group preference expression. Finally, according to group preference, the author applied the Bayesian personalized ranking method into the test for group recommendation. During the research, the author used the above mentioned method to test on two datasets, namely Movielens-1 M and CAMRa2011. As a result, compared with the benchmark algorithm, this method has improved the evaluation indexes HR and NDCG. And the experimental results show that this method has achieved better effect in group recommendation. [ABSTRACT FROM AUTHOR]

Copyright of Bearing is the property of Bearing Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

As a pioneering work that directly applies deep learning methods to raw point cloud data, PointNet has the advantages of fast convergence speed and high computational efficiency. However, its feature learning in local areas has a certain defect, which limits the expressive ability of the model. In order to enhance the feature representation in the local area, this paper proposes a new point cloud processing model, which is called PointSwin. By applying the Self-Attention with Shifted-Window mechanism to learn the correlation between mixed features and points, PointSwin encourages features to enhance their interactions with each other to achieve the effect of feature enhancement. At the same time, PointSwin also achieves a better balance between higher accuracy results and less time overhead by adopting the Mask mechanism to reduce redundant computations. In addition, this paper also proposes an efficient model called PointSwin-E. It can maintain good performance while greatly reducing the computational overhead. The results of the comparative experiments on ModelNet40 dataset show that PointSwin and PointSwin-E are better than PointNet and PointNet++ in terms of accuracy, and the effectiveness verification experiments on the Self-Attention with Shifted-Window mechanism also prove the superiority of this model. [ABSTRACT FROM AUTHOR]

In recent years, the wide use of deep learning based methods has greatly improved the classification performance of hyperspectral image (HSI). As an effective method to improve the performance of deep convolution networks, attention mechanism is also widely used for HSI classification tasks. However, the majority of the existing attention mechanisms for HSI classification are based on the convolution layer, and the classification accuracy still has margins for improvement. Motivated by the latest self attention mechanism in natural language processing, a deep transformer is proposed for HSI classification in this paper. Specifically, deep transformer along the spectral dimension and the spatial dimension are explored respectively. Then, a deep spatial-spectral transformer (DSS-TRM) is proposed to improve the classification performance of HSI. The contribution of this paper is to make full use of self attention mechanism, that is to use transformer layer instead of convolution layer. More importantly, a DSS-TRM is proposed to realize end-to-end HSI classification. Extensive experiments are conducted on three HSI data sets. The experimental results demonstrates that the proposed DSS-TRM could outperform the traditional convolutional neural networks and attention based methods. [ABSTRACT FROM AUTHOR]

The evolution of technology has raised concerns regarding cybersecurity for intelligent connected vehicles (ICVs). In-vehicle network in ICVs lacks robust protection mechanisms, making it vulnerable to cyber threats. In response, intrusion detection systems (IDSs) for ICVs have been developed to protect vehicles from malicious cyber attacks. However, current IDS methods solely rely on independent features, limiting their learning capabilities and increasing the number of false detections. Moreover, many IDSs require the knowledge of mapping between network messages and contents, which restricts their application. To address these limitations, we propose the Multi-order Feature Interaction-aware Intrusion Detection (MIFI) scheme for ICVs. Feature attention cross network is designed to address higher-order feature interactions, while factorization machine is used for second-order interactions. Then a discriminator is utilized to detect the attacks. MIFI expands the feature space through features interaction, thereby enhancing its ability to detect attacks. Moreover, it perceives the relationships of vehicle messages, facilitating intrusion detection without knowing the corresponding rules of vehicle messages. The performance of the proposed method is evaluated on two real-vehicle datasets, affirming its effectiveness and robustness. MIFI achieves an accuracy of over 99% in detecting different attacks. The proposed method can improve the accuracy of traditional IDS to a maximum of 99.99%, and increase the highest F1-score to 97.18%, demonstrating the model's ability of achieving multi-order feature interactions. Ultimately, MIFI is suitable for intrusion detection in different types of ICV networks, significantly contributing to the cybersecurity of ICVs. • We reveal a robust similarity between different real-vehicle attacks data. • Feature attention cross network explores interactions between different features. • No need for prior knowledge of vehicle message rules for intrusion detection. • Proposed scheme detects intrusion with 99% accuracy in real vehicle data. [ABSTRACT FROM AUTHOR]