检索结果-内蒙古大学图书馆

Analyzing topics in social media for improving digital twinning based product development

Digital Communications and Networks 2024年第2期10卷 273-281页

作者： Wenyi Tang Ling Tian Xu Zheng Ke Yan School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China

Digital twinning enables manufacturers to create digital representations of physical entities,thus implementing virtual simulations for product *** efforts of digital twinning neglect the decisive consumer feedback in product development stages,failing to cover the gap between physical and digital *** work mines real-world consumer feedbacks through social media topics,which is significant to product *** specifically analyze the prevalent time of a product topic,giving an insight into both consumer attention and the widely-discussed time of a *** primary body of current studies regards the prevalent time prediction as an accompanying task or assumes the existence of a preset ***,these proposed solutions are either biased in focused objectives and underlying patterns or weak in the capability of generalization towards diverse *** this end,this work combines deep learning and survival analysis to predict the prevalent time of *** propose a specialized deep survival model which consists of two *** first module enriches input covariates by incorporating latent features of the time-varying text,and the second module fully captures the temporal pattern of a rumor by a recurrent network ***,a specific loss function different from regular survival models is proposed to achieve a more reasonable *** experiments on real-world datasets demonstrate that our model significantly outperforms the state-of-the-art methods.

关键词： Digital twinning Product development Topic analysis Social media

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Visual Semantic Embedding Network for Image-Text Retrieval

引用

Journal of computer science & technology 2024年第4期39卷 811-826页

作者： Xue-Yang Qin Li-Shuang Li Jing-Yao Tang Fei Hao Mei-Ling Ge Guang-Yao Pang School of Computer Science and Technology Dalian University of TechnologyDalian 116024China School of Computer Science Shaanxi Normal UniversityXi’an 710119China School of Computer Engineering Weifang UniversityWeifang 261061China Guangxi Colleges and Universities Key Laboratory of Intelligent Industry Software Wuzhou UniversityWuzhou 543002 China

Image-text retrieval aims to capture the semantic correspondence between images and texts,which serves as a foundation and crucial component in multi-modal recommendations,search systems,and online *** mainstream methods primarily focus on modeling the association of image-text pairs while neglecting the advantageous impact of multi-task learning on image-text *** this end,a multi-task visual semantic embedding network(MVSEN)is proposed for image-text ***,we design two auxiliary tasks,including text-text matching and multi-label classification,for semantic constraints to improve the generalization and robustness of visual semantic embedding from a training ***,we present an intra-and inter-modality interaction scheme to learn discriminative visual and textual feature representations by facilitating information flow within and between ***,we utilize multi-layer graph convolutional networks in a cascading manner to infer the correlation of image-text *** results show that MVSEN outperforms state-of-the-art methods on two publicly available datasets,Flickr30K and MSCOCO,with rSum improvements of 8.2%and 3.0%,respectively.

关键词： image-text retrieval cross-modal retrieval multi-task learning graph convolutional network

来源：评论

学校读者我要写书评

暂无评论

Robust video question answering via contrastive cross-modality representation learning

引用

science China(Information sciences) 2024年第10期67卷 211-226页

作者： Xun YANG Jianming ZENG Dan GUO Shanshan WANG Jianfeng DONG Meng WANG School of Information Science and Technology University of Science and Technology of China Institute of Artificial Intelligence Hefei Comprehensive National Science Center School of Computer Science and Information Engineering Hefei University of Technology Institutes of Physical Science and Information Technology Anhui University School of Computer Science and Technology Zhejiang Gongshang University

Video question answering(VideoQA) is a challenging yet important task that requires a joint understanding of low-level video content and high-level textual semantics. Despite the promising progress of existing efforts, recent studies revealed that current VideoQA models mostly tend to over-rely on the superficial correlations rooted in the dataset bias while overlooking the key video content, thus leading to unreliable results. Effectively understanding and modeling the temporal and semantic characteristics of a given video for robust VideoQA is crucial but, to our knowledge, has not been well investigated. To fill the research gap, we propose a robust VideoQA framework that can effectively model the cross-modality fusion and enforce the model to focus on the temporal and global content of videos when making a QA decision instead of exploiting the shortcuts in datasets. Specifically, we design a self-supervised contrastive learning objective to contrast the positive and negative pairs of multimodal input, where the fused representation of the original multimodal input is enforced to be closer to that of the intervened input based on video perturbation. We expect the fused representation to focus more on the global context of videos rather than some static keyframes. Moreover, we introduce an effective temporal order regularization to enforce the inherent sequential structure of videos for video representation. We also design a Kullback-Leibler divergence-based perturbation invariance regularization of the predicted answer distribution to improve the robustness of the model against temporal content perturbation of videos. Our method is model-agnostic and can be easily compatible with various VideoQA backbones. Extensive experimental results and analyses on several public datasets show the advantage of our method over the state-of-the-art methods in terms of both accuracy and robustness.

关键词： video question answering cross-modality fusion contrastive learning cross-media reasoning

来源：评论

学校读者我要写书评

暂无评论

Multi-Branch Fusion Module for Siamese Object Tracking 2

Multi-Branch Fusion Module for Siamese Object Tracking

引用

2nd International Conference on Informatics, Networking, and Computing, ICINC 2023

作者： Li, Gaoxiang Lu, xiaofeng Wang, Chongke Xu, Jingbo School of Computer Science and Engineering Xi`an University of Technology Xi’an China

ISBN: (纸本)9781510674745

Various mainstream target tracking algorithms based on siamese networks are gradually becoming a trend in the field of deep learning tracking due to their concurrent advantages of accuracy and speed. Most siamese network-based trackers describe the tracking of a target object as a similar matching problem, and these trackers have achieved more advanced performance in several public tests. Most trackers often suffer from tracking drift or performance degradation owing to the non-updating of the template in the first frame and the target appearance encounters disturbing environments such as occlusion and drastic deformation. To address the current problem, this paper proposes an algorithm for fusion of multi-branch modules based on siamese network to achieve the fusion of target templates for updating, which improves the tracker's anti-jamming ability and the network structure is anchor-free. Meanwhile, this paper designs a new fusion module that fuses templates by inserting weight tensor method for multi-template fusion and optimises the results by complementary weight tensors. This method is practiced in SiamFC++ algorithm, where the target dataset is input and features are extracted, and then classification and regression operations are performed by fusion of multi-branch modules to get the predicted position of the target. © 2024 SPIE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

SSA-LSTM High-Speed Railway Track Irregularity Prediction Model Based on Dual-Stage Decomposition 2

SSA-LSTM High-Speed Railway Track Irregularity Prediction Mo...

引用

2nd International Conference on Informatics, Networking, and Computing, ICINC 2023

作者： Wang, Chongke Lu, xiaofeng Li, Gaoxiang Wu, Chen School of Computer Science and Engineering Xi’an University of Technology Xi'an China

ISBN: (纸本)9781510674745

The smoothness of high-speed railway tracks is an important indicator for judging the quality of railway tracks. Accurately predicting the uneven trend of the track and dealing with it in advance is of great significance to the safe operation of high-speed railways. According to the data characteristics of specific road sections, this paper proposes a SSA-LSTM model based on dual-stage decomposition to predict track irregularity of high-speed railways. First, in order to eliminate the influence of noise in the original data, Singular Spectrum Analysis (SSA) is used to decompose, denoise, and reconstruct the original data. Secondly, in view of the existence of multiple modal mixing effects in the denoised data, the data is decomposed through the ensemble empirical mode decomposition (EEMD) method. Then, to solve the problem that the long short-term memory network (LSTM) hyper-parameters are difficult to effectively determine, the Sparrow Search Algorithm (SSA) is used to search and optimize. Finally, the optimized LSTM model is used to predict and reintegrate the decomposed multiple sequences. Experimental results show that the SSA-LSTM prediction model based on dual-stage decomposition proposed in this article can obtain more accurate prediction results. © 2024 SPIE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Flexibility evaluation and optimal scheduling of flexible energy loads considering association characteristics in residential buildings

引用

Building Simulation 2025年第2期18卷 423-447页

作者： xi Luo Tingting Li Hui Wu Yupan Wang School of Building Services Science and Engineering Xi’an University of Architecture and TechnologyXi’an710055China State Key Laboratory of Green Building Xi’an710055China

The existing researches on the flexibility evaluation and optimal scheduling of flexible loads in residential buildings do not fully consider the association characteristics of different loads,resulting in a large deviation between the calculated results and experimental results of optimization scheduling.A flexibility evaluation methodology and an optimization model considering load associations characteristics are proposed for flexible loads in residential *** flexibility ratio,which is the ratio of temporal flexibility considering association characteristics to that without considering association characteristics,is defined in this *** optimization model is solved using the CPLEX solver under three different scenarios,namely,a scenario only considering the temporal overlapping load associations,a scenario only considering the temporal non-overlapping load associations,and a scenario considering both types of load *** was shown that in the residential building case in this study,the cooking loads with association characteristics exhibit less temporal flexibility but higher temporal flexibility ratio of up to 71.21%,while laundry loads exhibit higher temporal flexibility,but their temporal flexibility ratio is only around 36.84%.Additionally,when the users adopted the time of use(TOU)price,their electricity costs under the three considered scenarios increased by 0.00%,7.57%,and 7.57%relative to the scenario without considering load associations,*** installing a 3-kW household photovoltaic system,the electricity costs under the three scenarios increased by 0.00%,1.28%,and 1.28%,*** highlighted in the results,temporal non-overlapping association characteristics greatly affect the optimal scheduling of flexible energy loads,especially under TOU,while temporal overlapping association characteristics have little effect on that.

关键词： renewable energy flexible energy loads loads association characteristics optimal scheduling energy flexibility

来源：评论

学校读者我要写书评

暂无评论

Visual SLAM System Integrating Feature Extraction Based on Vision Transformer and Cloud-Edge technology

Visual SLAM System Integrating Feature Extraction Based on V...

引用

2024 International Conference on Intelligent Computing and Robotics, ICICR 2024

作者： Fu, Bo Yao, Xulin School of Computer Science and Engineering Xi'An University of Technology Xi'an China

ISBN: (纸本)9798350372274

Deep learning-based visual SLAM (Simultaneous Localization and Mapping) has become one of the highly researched areas in recent years. Deep learning can be integrated with various modules of visual SLAM systems, including VO (Visual Odometry), mapping, feature extraction, localization, BA (Bundle Adjustment) optimization, loop closure, dataset handling, etc. In visual SLAM, traditional feature point extraction using deep learning networks is based on Convolutional Neural Network (CNN) architectures. This paper proposes a method that combines feature extraction based on the vision Transformer network with edge-cloud technology to improve the performance of visual SLAM systems. This method addresses scenarios where neural network-based SLAM systems encounter limited computing resources, frequent environmental changes, or require realtime response. Experimental results demonstrate that the fusion of feature extraction based on vision Transformer and edge-cloud technology significantly improves the localization, mapping, and real-time performance of visual SLAM systems. It exhibits excellent robustness and accuracy in various indoor and outdoor environments, indicating promising application prospects and dissemination value. ©2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Robust Object Tracking with Gradient Activation Siamese Network 16

Robust Object Tracking with Gradient Activation Siamese Netw...

引用

16th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discover, CyberC 2024

作者： Yan, Zixuan Lu, xiaofeng Pang, Tiantian Xu, Jingbo Xi'an University of Technology School of Computer Science and Engineering Xi'an China

ISBN: (纸本)9798331506896

Deep learning technology has driven continuous advancements in the visual tracking field. In order to overcome various challenges, Siamese-based trackers and Attention-based trackers improve tracking performance by adding or deepening the network structure. However, they also increase training costs and model complexity. Lightweight trackers focus on achieving efficient and real-time tracking with limited computational resources, but these methods often face issues with lower accuracy and robustness in complex scenarios. Our approach - Gradient Activation Siamese Network(Grad-Siam), adds fully connected layers to the backbone of SiamFC to obtain gradient activation information. By using the gradient activation strategy, we dynamically update the feature extraction process of the template and search branches. We trained on GOT-10k and validated on multiple standard test datasets. Experiments show that Grad-Siam balances accuracy and efficiency well, while also enhancing robustness in complex scenarios. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Improved safety helmet target detection algorithm of YOLOv8n 24

Improved safety helmet target detection algorithm of YOLOv8n

引用

14th International Conference on Communication and Network Security, ICCNS 2024

作者： Li, Aiguo Li, Linru School of Computer Science and Technology Xi'an University of Science and Technology Shaanxi Xi'an China School of Computer Science Xi'an University Of Science And Technology Shanxi Xi'an China

ISBN: (纸本)9798400717994

In order to solve the shortcomings of the existing safety helmet detection algorithms in construction sites, tunnels, coal mines and other construction scenarios, it is difficult to detect occluded targets and small targets, and when the model faces too large or too small targets, the detection performance will decline. Tiny targets have fewer pixels, and it is easy to lose information in repeated downsampling, which increases the false detection rate and missed detection rate of helmet detection. In order to solve this problem, a safety helmet detection algorithm based on improved YOLOv8n is proposed. On this basis, the weighted bidirectional feature pyramid network (BiFPN) is introduced. The convolution module is introduced before the first detection head to extract features, and then fused with the P2 detection head and output, which can increase the feature map and increase the receptive field. Finally, the Tanh activation function is added to the GAM attention module to obtain more details and features. while improving the detection ability of small-scale targets, the accuracy and recall rate are improved, and the false detection rate and missed detection rate of the model are reduced. The experimental results on the self-made safety helmet data set show that the accuracy of the BPCG-YOLOv8n model reaches 96.5 percent. Compared with the YOLOv8n model, the average accuracy is improved by 1.1 percentage points, which is superior to other classical detection models in accuracy and has practical application value. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Coal mines

来源：评论

学校读者我要写书评

暂无评论

Literature overview of basic characteristics and flotation laws of flocs

引用

International Journal of Minerals,Metallurgy and Materials 2024年第5期31卷 943-958页

作者： Wanzhong Yin Yu xie Zhanglei Zhu School of Resources and Civil Engineering Northeastern UniversityShenyang 110819China College of Chemistry and Chemical Engineering Xi’an University of Science and TechnologyXi’an 710054China

Flocculation flotation is the most efficient method for recovering fine-grained minerals,and its essence lies in flotation and recovery of *** physical characteristics of flocs are mainly determined by their apparent particle size and structure(density and morphology).Substantial researches have been conducted regarding the effect of floc characteristics on particle settling and water ***,the influence of floc characteristics on flotation has not been widely *** on the floc formation and flocculation flotation,this study reviews the fundamental physical characteristics of flocs from the perspectives of floc particle size and structure,summarizing the interaction between floc particle size and ***,it thoroughly discusses the effect of floc particle size and structure on floc floatability,further revealing the influence of floc characteristics on bubble collision and adhesion and elucidating the mechanisms of interaction between flocs and ***,it is observed that floc particle size is not the only factor influencing flocculation *** the appropriate apparent particle size range,flocs with a compact structure exhibit higher efficiency in bubble collision and adhesion during flotation,thereby resulting in enhanced flotation *** study aims to provide a reference for flocculation flotation,targeting the development of more efficient and refined flocculation flotation processes in the future.

关键词： flocs basic characteristics particle size and structure flotation laws bubbles

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：