检索结果-内蒙古大学图书馆

6th IEEE International Conference on Electronic information and Communication technology, ICEICT 2023

作者： Li, Senlin Guo, Jinhong Li, Juan He, Wenbin Zhao, Kun School of Information and Control Engineering Qingdao University of Technology Qingdao China

ISBN: (纸本)9798350399059

Remote sensing image classification is gradually growing into an attractive research topic and is widely used in various tasks. But unlike natural general images, remote sensing images are usually high-resolution, which are consist of complex backgrounds and various randomly arranged targets. Remote sensing images usually have the characteristics of large intra-class differences and huge inter-class similarity, which make it difficult for the network to focus on the main objects in the scene, resulting in unsatisfactory classification performance. In this paper, we propose the Triple Attention Vision Transformers (TaViT) network to solve this problem. The backbone of TaViT is mainly composed of two branches, namely Dual Attention Vision Transformers (DaViT) and Branch Attention Module (BA Module). DAViT uses the self-attention mechanism of 'spatial tokens' and 'channel tokens' to capture the features of the global context. The BA Module aggregates the features of each channel along the horizontal and vertical directions, respectively, and continuously provides rich local details for the network. Experimental results on three publicly available remote sensing datasets demonstrate that our TaViT achieves state-of-the-art performance. © 2023 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Path Planning for Wheeled Robots Based on the Fusion of Improved A∗ and TEB Algorithms

Path Planning for Wheeled Robots Based on the Fusion of Impr...

引用

2023 China Automation Congress, CAC 2023

作者： Zai, Weiqiang Lin, Qihang Wang, Shiyuan Lin, Xumei School of Information and Control Engineering Qingdao University of Technology Qingdao China

ISBN: (纸本)9798350303759

In this paper, we propose a hierarchical path planning method to address the issues of unsmooth path curves in autonomous navigation for wheeled robots using the original A ∗ algorithm, and the adverse impact on robots caused by jumping changes in output commands of the original TEB algorithm. Firstly, we evaluate the curvature using the curvature smoothing function in the A ∗ algorithm, followed by introducing interpolation to replace some of the unsmoothed path nodes to enhance path smoothness. Secondly, we add jerk constraints on multiple nodes in the TEB algorithm to reduce the impact of acceleration jumps in the output on the mechanical structure of the robot body, thereby improving the operation efficiency of the local path planning algorithm. Finally, we integrate the improved A ∗ algorithm with the TEB algorithm to enable the robot to follow global path points better while bypassing obstacles on time. Simulation experiments demonstrate that the proposed method significantly improves global path smoothing, output speed changes more smoothly, and the wheeled robot's motion smoothness is enhanced. © 2023 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Efficient Air Quality Imputation with Transformer 23

Efficient Air Quality Imputation with Transformer

引用

2023 ACM Turing Award Celebration Conference, CHINA 2023

作者： Hu, Keyong Liu, Guoxiao Yang, Xin School of Information and Control Engineering Qingdao University of Technology Qingdao China

ISBN: (纸本)9798400702334

Air quality is a crucial environmental issue worldwide. The missing values in air quality datasets often impede further forecasting. To address this challenge, a transformer based model with spatio-temporal masked attention is proposed for simultaneous imputations of air quality values from multiple stations. Extensive experiments are conducted on a real dataset from Beijing city, demonstrating the effectiveness and superiority of the proposed model. © 2023 Owner/Author.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Research on Porosity Prediction Based on Wavelet Transform and BGRU 6

Research on Porosity Prediction Based on Wavelet Transform a...

引用

6th IEEE International Conference on Electronic information and Communication technology, ICEICT 2023

作者： Sun, Yiping Wang, Lijun Kong, Yifan Huang, Yan Chen, Yaqi Zhou, Lijian School of Information and Control Engineering Qingdao University of Technology Qingdao China

ISBN: (纸本)9798350399059

The traditional rock porosity measurement methods based on laboratory are costly and time consuming. The porosity prediction using logging data has been a research hotspot. A porosity prediction method based on wavelet transform and Bidirectional Gate Recurrent Unit network(BGRU) is proposed in this paper. First, to mine both the longitudinal depth deposition relationship among the adjacent samples and the transverse features relationship among different logging parameter in one data sample, the features with different scales are extracted and denoised using the wavelet decomposition at the same time. And then, to extract and process feature detail information with depth of the feature sample sequences, a Bidirectional Gated Recurrent Unit (BGRU) neural network is constructed to extract the detail feature with longitudinal and transverse information and predict the porosity. The experimental results show that the proposed method improves the accuracy of porosity prediction. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Ontology-Aware Network for Zero-Shot Sketch-Based Image Retrieval 48

Ontology-Aware Network for Zero-Shot Sketch-Based Image Retr...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Zhang, Haoxiang Jiang, He Wang, Ziqiang Cheng, Deqiang China University of Mining and Technology School of Information and Control Engineering China

ISBN: (纸本)9781728163277

Zero-Shot Sketch-Based Image Retrieval (ZSSBIR) is an emerging task. The pioneering work focused on the modal gap but ignored inter-class information. Although recent work has begun to consider the triplet-based or contrast-based loss to mine inter-class information, positive and negative samples need to be carefully selected, or the model is prone to lose modality-specific information. To respond to these issues, an Ontology-Aware Network (OAN) is proposed. Specifically, the smooth inter-class independence learning mechanism is put forward to maintain inter-class peculiarity. Meanwhile, distillation-based consistency preservation is utilized to keep modality-specific information. Extensive experiments have demonstrated the superior performance of our algorithm on two challenging Sketchy and Tu-Berlin datasets. © 2023 IEEE.

关键词： Inter-class peculiarity Modality-specific Ontology-aware Sketch-based image retrieval Zero-shot

来源：评论

学校读者我要写书评

暂无评论

An Interval Multiobjective Evolutionary Generation Algorithm for Product Design Change Plans in Uncertain Environments

引用

IEEE Transactions on Evolutionary Computation 2025年第3期29卷 836-850页

作者： Zheng, Rui-Zhao Zhang, Yong Sun, Xiao-Yan Gong, Dun-Wei Gao, Xiao-Zhi China University of Mining and Technology School of Information and Control Engineering Xuzhou221000 China Qingdao University of Science and Technology College of Automation and Electronic Engineering Shandong Qingdao266061 China University of Eastern Finland School of Computing Kuopio70210 Finland

Design change is an important issue in complex product development projects. In a complex product with numerous parts (also known as components), the change of one key part may spread to other parts associated with it, generating a chain reaction throughout the entire project. Therefore, it is necessary to select a suitable change plan involving only fewer crucial parts in order to enhance the product’s performance, minimize change cost, and reduce change duration/time. Focusing on the case where the correlation strength between parts cannot be accurately obtained, in this article we study an interval multiobjective evolutionary algorithm for finding excellent design change plans. First, on the basis of the established multilayer product network with interval correlation weights, an interval multiobjective optimization model of the product design change planning problem is established, where three new objective functions regarding product performance, carbon trading cost and supply risk are defined. Then, a constraint multiobjective evolutionary algorithm based on interval Pareto dominance is proposed to search for optimal change plans. Several novel operators, including the problem characteristic-guided population update strategy, the probability-based interval Pareto dominance, and the interval constraint handling strategy, are developed to enhance the algorithm’s performance. Finally, the proposed algorithm is compared with eight existing algorithms on the two design change cases, experimental results revealed its effectiveness. © 1997-2012 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Relay Selection Methods for the Uplink NOMA System 6

Relay Selection Methods for the Uplink NOMA System

引用

6th IEEE International Conference on Electronic information and Communication technology, ICEICT 2023

作者： Wang, Ye Li, Enyu Liang, Zanyang Zheng, Meijuan School of Information and Control Engineering Qingdao University of Technology Qingdao China

ISBN: (纸本)9798350399059

To further improve the transmission reliability of the uplink non-orthogonal multiple access (NOMA) system, based on decode-and-forward (DF) protocol, we propose two relay selection (RS) schemes: React RS (RRS) and successive interference cancellation (SIC) RS (SRS). Firstly, fully considering the decoding situation at the relay, we analyze the closed-form results of the two RS schemes in terms of exact outage performance under the perfect and imperfect SIC technologies, which can be derived that both schemes have the same outage performance. Then, asymptotic results are given in the high signal-to-noise ratio (SNR) region and the best power allocation coefficient is analyzed. Finally, the correctness of the theoretical derivation is verified by simulation. The results show that the proposed schemes are superior and have the best interrupt performance when compared to other RS schemes. © 2023 IEEE.

关键词： Rayleigh fading

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of CR-NOMA Based on Untrusted Relay in IoT 6

Performance Analysis of CR-NOMA Based on Untrusted Relay in ...

引用

6th IEEE International Conference on Electronic information and Communication technology, ICEICT 2023

作者： Liang, Zanyang Li, Enyu Wang, Ye Zheng, Meijuan School of Information and Control Engineering Qingdao University of Technology Qingdao China

ISBN: (纸本)9798350399059

Cognitive radio (CR) technology can be used as a key technology for wireless communication to integrate heterogeneous networks, increasing channel capacity and improving spectrum efficiency because secondary users can access to the spectrum of the primary network for communication without authorization. It can, to some extent, pose communication security issues. To address this issue, a system model combining CR network with non-orthogonal multiple access (CR-NOMA) is proposed, in which secondary users are utilized to support the primary network communication while cognitive users are untrusted. To begin, the proposed system CR-NOMA model is constructed in the Internet of Things to guarantee that it is compatible with a wider range of scenarios. Secondly, physical layer security technologies such as redundant information and jamming signal are used to improve the secrecy performance. Finally, the closed-form results for the exact and asymptotic outage probabilities of the near-end user and the remote user are studied, taking information secrecy into account. The secrecy throughput performance of various users is examined. The simulation results demonstrate that using cognitive users as relays to forward information can significantly improve the performance of the proposed system. The performance of the remote user, in particular, demonstrates that the considered model may effectively improve the quality of service of the cellular-edge user and therefore expand the coverage of the base station. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Label Update Based Partial Label Learning for Remote Sensing Scene Classification 6

Label Update Based Partial Label Learning for Remote Sensing...

引用

6th IEEE International Conference on Electronic information and Communication technology, ICEICT 2023

作者： Zeng, Shiwen Zhang, Xianwei Zhang, Hongxing Meng, Fan Zhao, Kun School of Information and Control Engineering Qingdao University of Technology Qingdao China

ISBN: (纸本)9798350399059

A remote sensing scene image frequently contains various objects, hence it is described with multiple labels, all of which are equivalent in status. In fact, however, the importance of these labels to the description of the scene is different from a semantic point of view. In order to obtain the importance distribution of a set of multiple labels, partial label learning (PLL) is introduced into remote sensing scene classification task in this paper. Multiple labels used to describe a scene image are considered as candidate labels in the context of partial labeling learning. During the training process, 'partial label' are gradually strengthened, while other labels are gradually weakened, resulting in an indication of the importance of the labels. Specifically, in this paper, a 'label update based partial label learning' (LU-PLL) method is proposed to learn the relationship between a set of multiple labels in remote sensing scene images. The model will simultaneously learn the most significant labels and use them as the primary classification basis. Experiments on several classical remote sensing data sets demonstrate the superiority of the proposed method for label importance description. © 2023 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Improve the Security of Bandwidth Utilization of Legitimate Users 6

Improve the Security of Bandwidth Utilization of Legitimate ...

引用

6th IEEE International Conference on Electronic information and Communication technology, ICEICT 2023

作者： Zu, Zhengquan Li, Zixi Chen, Shuo Li, Yansheng School of Information and Control Engineering Qingdao University of Technology Qingdao China

ISBN: (纸本)9798350399059

In the field of wireless communication, the signals transmitted by mobile devices are vulnerable to illegal eavesdropping by illegal eavesdroppers and blocked by obstacles. By using wireless mobile devices combined with intelligent reflectors, the signals transmitted through the transmitter have certain stability and flexibility in the process of transmission. This process is to adjust the amplitude and phase of the signals between the transmitter and receiver. Therefore, this paper proposes a model to improve the security of MIMO mobile devices with intelligent reflector. By establishing the reflection model, and then using the mathematical equation to obtain the maximum channel utilization rate, the results are derived, and the advantages of the security of the intelligent reflector are compared through simulation. © 2023 IEEE.

关键词： Transmitters

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：