检索结果-内蒙古大学图书馆

A novel protocol of RFID tag identification using a single mobile reader

International Journal of information and Communication technology 2021年第4期19卷 423-431页

作者： Li, Xiaowu Li, Runxin Jia, Lianyin Ding, Jiaman You, Jinguo Fan, Hongbo Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650504 China

Classic RFID tag anti-collision protocols mainly aim at the identification of tags in small area. That is, all unidentified tags are located in the reader’s read-write region. When there is one or more tag outside the reader coverage area, multi-reader RFID system is an effective method of identifying all tags. However, the cost of multi-reader RFID system is much higher than that of a single reader system. There are many other tag identification scenes where tag distribution area is only slightly larger than a reader coverage area. For the scene, in the paper, we let the all tags, including outside the reader coverage area, have an opportunity to enter the reader coverage area by moving reader and be identified. The scene is called single mobile reader systems (SMRS) at the paper. However, SMRS cause the tag reappearance phenomenon (TRP), which leads to the multiple identification problem of tag (MIPT). TRP and MIPT make low the effective tag identification efficiency happen. In the paper, we propose an improved EPC C1G2 protocol, which can decrease MIPT effectively and increase tag identification efficiency. Copyright © 2021 Inderscience Enterprises Ltd.

关键词： Radio frequency identification (RFID)

来源：评论

学校读者我要写书评

暂无评论

Review of research applications of wavelet transform in the field of image processing 6

Review of research applications of wavelet transform in the ...

引用

6th International Conference on Mechatronics and Intelligent Robotics, ICMIR 2022

作者： Feng, Yuhang Shao, Jianfei Shao, Jianlong Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Kunming650500 China

ISBN: (纸本)9781510656635

With the arrival of the information age, we can see images in every corner of our life, and images convey a lot of information to us. But not all images are clearly visible. And the image obtained after image transmission is often more blurred than the original image or the lack of information in the image. Therefore, the image we see may have been more or less disturbed, resulting in some damage to the image. This interference is mostly composed of noise, Such as AWGN and Poisson noise and so on. Aiming at the influence of noise on the image and preserving the integrity of image information to the greatest extent after eliminating noise, wavelet threshold denoising is one of the most important methods of image denoising. It is a relatively simple and less computational wavelet denoising algorithm [5]. This paper summarizes the related research of wavelet transform in the field of image denoising. Firstly, the general principle of wavelet threshold denoising is explained. Furthermore, three different wavelet threshold image denoising methods are described. The characteristics and problems of three kinds of wavelet threshold denoising are summarized. Finally, the prospect of wavelet transform is also given. © 2022 SPIE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Simulation analysis of erosion characteristics of slurry pipelines based on CFD-DDPM pipeline parameters 43

Simulation analysis of erosion characteristics of slurry pip...

引用

43rd Chinese Control Conference, CCC 2024

作者： Yuan, Haoran Wu, Jiande Xiong, Xin Yunnan University Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan Kunming650500 China Kunming University of Science and Technology Faculty of Information Engineering and Automation Yunnan Kunming650500 China Kunming University of Science and Technology Yunnan Key Laboratory of Intelligent Control and Application Yunnan Kunming650500 China

ISBN: (纸本)9789887581581

In order to explore the impact of pipe diameter, bend-diameter ratio and bend angle on the erosion of slurry pipe, a numerical simulation method approach grounded in Computational Fluid Dynamics - Dense Discrete Phase Model (CFD-DDPM) is proposed. Firstly, the geometric models of bends with different pipe diameters, bend-diameter ratios, and bend angles are constructed;secondly, the slurry pipe erosion model based on Dense Discrete Phase Model (DDPM) is constructed;then, model validation is conducted on the slurry pipe erosion model to affirm the accuracy of the model;finally, the computational fluid dynamics method is employed to simulate the erosion and wear behavior of the pipeline, to investigate the impact of pipe diameter, bend-diameter ratio and bend angle on the erosion and wear of the slurry pipeline. At the same time, gray correlation analysis was also used to analyze the significant relationship between the three pipeline factors and erosion and wear. The results show that the main erosion area is not determined, with the change of the pipeline parameters, the most serious erosion area will move;the effect of different pipeline parameter variations on the erosion rate is different, in which the pipe diameter of the largest impact, the second largest bend-diameter ratio, the smallest impact of the bend angle. Therefore, in the design of slurry pipeline, should first consider the influence of pipe diameter factors. © 2024 Technical Committee on Control Theory, Chinese Association of automation.

关键词： Slurry pipelines

来源：评论

学校读者我要写书评

暂无评论

Review of deep learning based target detection algorithm research 6

Review of deep learning based target detection algorithm res...

引用

6th International Conference on Mechatronics and Intelligent Robotics, ICMIR 2022

作者： Ye, Rong Shao, Jianfei Shao, Jianlong Ji, Jianjie Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Kunming650500 China

ISBN: (纸本)9781510656635

With the rapid development of the times, big data has started to affect all aspects of our life, and more and more products in industries are becoming carriers of big data. For example, CNNs with more implicit layers are proposed to meet our needs, although they have a more complex network structure. Compared with traditional machine learning, it has more powerful feature learning and feature representation ability, which can better meet the needs in the era of big data. Since its introduction, deep learning has achieved remarkable results in several large-scale recognition tasks in the field of computer vision. This paper presents a review of target detection methods based on a survey of domestic and international literature on the subject. Firstly, the current state of research in the field of target detection is introduced. Next, the development and rise of deep learning and convolutional neural networks are briefly introduced, and the basic structure of convolutional neural networks, convolutional feature extraction, and pooling operations are outlined. The analysis and discussion of deep learning-based target detection algorithms are focused, and the current shortcomings are pointed out. Finally, the applications of deep learning-based target detection and the future development directions are summarized. © 2022 SPIE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

MILISS: Multi-instance Learning with Instance Selection Strategy for Gastric Cancer Classification 43

MILISS: Multi-instance Learning with Instance Selection Stra...

引用

43rd Chinese Control Conference, CCC 2024

作者： Qiu, Houshu Tao, Haibo Jin, Huaiping Li, Zhenhui Wang, Bin Kunming University of Science and Technology Faculty of Information Engineering and Automation Department of Automation Kunming650500 China Yunnan Key Laboratory of Artificial Intelligence Kunming650500 China Peking University Cancer Hospital Yunnan Yunnan Cancer Hospital The Third Affiliated Hospital of Kunming Medical University Kunming650118 China

ISBN: (纸本)9789887581581

Accurate distinction of histopathological subtypes of gastric cancer is essential for individualized treatment. However, accurate gastric cancer subtypes classification remains challenging due to the chaotic and disordered distribution of gastric cancer-positive tissues, and the fact that mixed type organizations resemble all other subtypes, as well as the lack of instance-level labeled medical image data. To this end, a multi-instance learning gastric cancer subtypes method incorporating instance selection strategy is proposed. The method begins by constructing a public anchor set through the collection of key instances, next selects appropriate instances as inputs to the backbone network using the public anchor set as a benchmark, then aggregates the obtained instance-level features into slide-level features through one-dimensional maximum pooling, and finally sends them to the multi-instance classifier to obtain slide-level prediction results. Experimental results on the Lauren subtypes dataset of gastric cancer show that the method has higher classification accuracy than existing classification methods. © 2024 Technical Committee on Control Theory, Chinese Association of automation.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Multi-behavior aware recommendation with joint contrastive learning and reinforced negative sampling

引用

Complex & Intelligent Systems 2025年第8期11卷 1-17页

作者： Du, Yujia Yu, Zhengtao Wang, Hongbin Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Key Laboratory of Artificial Intelligence in Yunnan Province Kunming University of Science and Technology Kunming China

Traditional recommendation systems usually rely on single user-item interaction information to capture the characteristics of users and items. However, in real-world applications, the interactions between users and items are far more diverse. Therefore, efficiently integrating multidimensional interaction data is crucial to improve the performance of recommendation systems. The existing methods still face challenges in terms of modeling behavioral dependencies, handling skewed data distributions, and optimizing the quality of negative samples. To address these obstacles, a joint contrastive learning and reinforced negative sampling model is proposed to multi-behavior aware recommendation. First, user interaction data concerning multiple behaviors are incorporated to automatically capture and encode behavioral context information and high-order dependencies, enabling a more comprehensive understanding of user behavior patterns. Second, contrastive learning is applied to the user data acquired under different behaviors to construct enhanced personalized user behavior representations. Additionally, a similarity-based strategy using the dot product operation is introduced to identify hard negative samples with high similarity to users, thereby strengthening the item-side representations. The model is optimized through multi-task learning. Extensive experiments conducted on three real datasets, i.e., IJCAI, Tmall, and Retail, demonstrate that the proposed method improves upon the performance of the existing multi-behavior baseline models by 14.5%, 6.0%, and 1.1% in terms of hit ratio and by 19.7%, 9.4%, and 2.3% in terms of the normalized discounted cumulative gain, respectively, verifying the effectiveness of the new approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Chinese Named Entity Recognition Based on Grid Tagging and Semantic Segmentation 9

Chinese Named Entity Recognition Based on Grid Tagging and S...

引用

9th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2023

作者： Zhao, Xuedong Shi, Zhiliang Xiang, Yan Ren, Ying Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650500 China Kunming University of Science and Technology Yunnan Key Laboratory of Artificial Intelligence Kunming650500 China Kunming Enersun Technology Co. Ltd. Kunming650217 China

ISBN: (纸本)9798350304428

Chinese Named Entity Recognition (CNER) is one of the fundamental tasks in Chinese Natural Language Processing and has been extensively researched. However, previous studies have primarily focused on specific types of CNER subtasks, which hindered the overall progress and practical implementation of CNER. Recently, grid-tagging-based methods have emerged as having significant advantages in information extraction tasks due to the flexible annotation framework and model architecture they provide. Building on this, we unify the CNER task as a character pair relation classification problem and solve it by predicting the character pair relation matrix, which is similar to the semantic segmentation task in computer vision. To do this, we utilize the U-shaped segmentation module to capture low-level and high-level features in the feature map of image style, enabling us to extract more semantic information. We also effectively model the boundary information of the entity, which in turn enhances the overall accuracy of entity recognition. To test the effectiveness of our method, we conduct experiments on two NER datasets containing flat and nested entities in the Chinese medical domain (CMeEEV2, MMC). Our results demonstrate that our approach improves the F1 score by 0.73% and 1.07% respectively compared to current state-of-the-art models, further validating its effectiveness. © 2023 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A classification method for compound mass spectrum data based on the Flex-Bootstrap method and Resnet network

A classification method for compound mass spectrum data base...

引用

Chinese Control Conference (CCC)

作者： Jiayao Pan Li Ping Wu Yong Li Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Aiming at the low accuracy of mass spectrum data recognition due to the subjectivity of artificial feature extraction and the limitation of a single sample and unbalanced mass spectrum data in current research, a classification method based on the fusion of the Flex-Bootstrap and Residual Network models is proposed and compared with the DNN model and the fusion model of CNN and DNN. The Flex-Bootstrap method and Resnet fusion model used the Flex-Bootstrap method to expand the combined mass spectrum data perform sparse sequence representation and use the extracted feature vectors to construct the Resnet model. Compared with the traditional classification methods, the proposed method achieves better results in classifying small molecule compounds by mass spectrum data. The accuracy of the test set is increased to $98.894 \%$, and the loss function value is reduced to 0.0502. This model effectively solves the problem of underfitting when using the DNN and the fusion models of CNN and DNN for data classification and improves the prediction accuracy and search efficiency for the mass spectrum database.

关键词： Analytical models Accuracy Predictive models Mass spectroscopy Feature extraction Data models Vectors

来源：评论

学校读者我要写书评

暂无评论

A Meta-learning-based Online Adaptive Fine-tuning VAE for Industrial Process Data Streams 16

A Meta-learning-based Online Adaptive Fine-tuning VAE for In...

引用

16th International Conference on Signal Processing Systems, ICSPS 2024

作者： Gao, Yu Yu, Wangyang Jin, Huaiping Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Wuhan Maritime Communication Research Institute Wuhan430223 China Yunnan Kunshi Expressway Co. Ltd. Kunming650100 China

ISBN: (纸本)9781510689251

Data-driven deep learning soft sensor has been recognized as an efficient industrial modeling technique for addressing high-dimensional nonlinear problems. However, when confronted with industrial process data streams that simultaneously exhibit high nonlineality and strong time-varying characteristics, offline deep learning models with poor adaptability struggle to achieve accurate quality parameter predictions. To address these challenges, this paper proposes a meta-learning-based online adaptive VAE method for data streams. Specifically, this method introduces a variational autoencoder regression (VAER) model, which incorporates Gaussian distribution constraints into latent variable learning, thereby alleviating the adverse effects of complex variable distributions on predictions. Additionally, a meta-learning algorithm is incorporated into model pre-training to obtain the meta-parameters, thereby enhancing generalization capabilities. Finally, a just-in-time learning fine-tuning update process based on meta-parameters of VAER is completed in online test phase. The effectiveness and practicality of the proposed method are validated through a case study on substrate concentration prediction in the penicillin fermentation process. © 2025 SPIE.

关键词： Just in time production

来源：评论

学校读者我要写书评

暂无评论

Multi-feature fusion friend recommendation algorithm based on complex network

引用

International Journal of information and Communication technology 2023年第4期23卷 401-423页

作者： Pan, Kan Chen, Hailong Liu, Qian Wang, Jian Pu, Yingming Yin, Chunlin Yang, Zheng Zhao, Na Electric Power Research Institute Yunnan Power Grid Co. Ltd. Kunming650217 China School of Software Yunnan University Kunming650504 China College of Information Engineering and Automation Kunming University of Science and Technology Kunming650504 China

At present, one of the problems of friend recommendation algorithms used in most social networks is that these networks often rely on a single index for recommendation. To solve this problem, multi-feature fusion (MFF) algorithm, a social network friend recommendation algorithm based on complex network theory, is proposed. The recommendation algorithm works by firstly divides the existing social networks into different communities. The importance of nodes in a social network is then calculated through the fusion of nodes’ importance information. Lastly, by integrating node importance information, friend number information and the shortest path information features are comprehensively evaluated, so as to generate final friend recommendation list. Simulation shows that with the increase of network nodes, the MFF algorithm outperforms common friend (CF) algorithm and friend similarity (FS) algorithm over all evaluation indicators including P-value, R-value and F1-value. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Complex networks

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：