检索结果-内蒙古大学图书馆

2022 International Conference on Signal Processing, Computer Networks, and Communications, SPCNC 2022

作者： Dang, Lanxue Zhang, Miaoxin Xie, Yi Zuo, Xianyu Zhang, Lei Fan, Minghu Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer and Information Engineering Henan University Kaifeng China

ISBN: (纸本)9781510664616

Due to the terrain, the frequent floods of the Yellow River have posed a great threat to the cities along the Yellow River. At present, although the danger alarm system and video surveillance system are widely installed along the Yellow River Basin, there is a lack of linkage between the two, which wastes monitoring resources. In addition, the push rules of different types of alarm signals are relatively complex, and the coupling between rules and system implementation is high, which is not conducive to rule modification and expansion;moreover, there are many cities along the Yellow River, if each city customizes its own system, it will lead to more overhead. Therefore, this problem can be solved by improving the hierarchical scalability of the system. So, based on the Drools framework, this paper uses the rule engine to realize the unified processing of different rules and the linkage integration of sensors and cameras, and designs a recursive model to simplify the development process, so as to realize the accurate positioning of alarm information at all levels of provinces, cities and counties, and the hierarchical processing of various alarm information. © 2023 SPIE.

关键词： Alarm systems

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-guided Mutual Consistency Training for Semi-supervised Biomedical Relation Extraction

Uncertainty-guided Mutual Consistency Training for Semi-supe...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Mao, Bing Jia, Chang Huang, Yucheng He, Kai Wu, Jialun Gong, Tieliang Li, Chen Xi'an Jiaotong University School of Computer Science and Technology Xi'an China Xi'an Jiaotong University Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi'an China

ISBN: (纸本)9781665468190

Biomedical relation extraction seeks to automatically extract biomedical relations from biomedical text, which plays an important role in biomedical studies. However, constructing high-quality biomedical annotation data is not only time-consuming but also requires a high level of knowledge in the biomedical field. To alleviate this problem, Semi-supervised Biomedical Relation Extraction aims to extract relation facts from the limited labeled data and the more readily available unlabeled samples. Existing works can be roughly categorized as self-training methods and self-ensembling methods. The former aims to generate pseudo labels, which may lead to the gradual drift problem. The latter aims to encourage the output of one model to be consistent with the other model, where the acquisition of the model is tedious. To alleviate these issues, we propose a novel Uncertainty-Guided Mutual Consistency Training framework(UG-MCT) for semi-supervised Biomedical relation extraction. Specifically, our framework consists of two models with the same structure, which differ only when updating their weights, and then an intersecting pseudo-label mechanism is designed to convert the prediction discrepancies of the two models into mutual consistency training loss, thus promoting the consistency of model predictions. In addition, we utilize uncertainty as guided information to assist the model in focusing on the confident pseudo labels and mitigate the noise of inaccurate pseudo labeling during training. Thus, our model is very simple and efficient while mitigating the noise introduced by pseudo-labels. UG-MCT is evaluated on multiple datasets in different settings and the experimental results demonstrate that our method is highly effective in semi-supervised biomedical relation extraction compared to the state-of-the-art. © 2022 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Kubernetes-based Scripted Remote Sensing Process Service Platform 6

Kubernetes-based Scripted Remote Sensing Process Service Pla...

引用

6th IEEE Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2023

作者： Zhou, Liming Liu, Mengyu Yang, Wencheng Liu, Zhehao Zhao, Hang Han, Hongyu Henan University Henan Key Laboratory of Big Data Analysis and Processing Kaifeng China Henan University School of Computer and Information Engineering Kaifeng China

ISBN: (纸本)9781665460033

With the formation of the high-resolution satellite system, the information carried in remote sensing data is becoming more and more abundant, and the types of data are also increasing. In order to realize the efficient processing of remote sensing data, the construction of remote sensing process is very important. At the same time, higher requirements are put forward for the remote sensing system in terms of dynamic resource scheduling, easy maintenance, elastic expansion, controllable complexity, and flexible deployment. In response to the above problems, this paper first designs a scripted process construction technology, which realizes the efficient construction of various complex processes. And introduce Docker container technology and Kubernetes container cluster management technology, split the remote sensing system into different micro-service modules, run independently in mutually isolated containers, so that the system has the characteristics of flexible load scheduling and elastic scaling. © 2023 IEEE.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of highly scalable IoT platform based on Netty

Design and implementation of highly scalable IoT platform ba...

引用

2022 International Conference on Signal Processing, Computer Networks, and Communications, SPCNC 2022

作者： Zuo, Xianyu Yuan, Bo Li, Shilong Dang, Lanxue Lin, Yinghao Han, Hongyu Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer and Information Engineering Henan University Kaifeng China

ISBN: (纸本)9781510664616

With the development of network technology and people's growing need for a better life, IoT technology has been integrated into more and more people's daily lives. At the same time, due to the different needs of individual users and the differences in the function of networking equipment spawned a variety of Internet of things products. Hence an IoT platform that is convenient, efficient and easy to expand is particularly important. This article designs and implements an integrated IoT platform for many types of persistent connected IoT devices on the market. The platform supports concurrent access of large-scale IoT devices with multiple sources and protocols, and supports remote management of devices through instructions. Monitor the health of the equipment in real time and alarm in real time in case of abnormalities. © 2023 SPIE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Fast Multivariate Time Series Anomaly Detection Based on Matrix Completion

Fast Multivariate Time Series Anomaly Detection Based on Mat...

引用

2023 International Conference on Frontiers of Robotics and Software engineering, FRSE 2023

作者： He, Shiming Yi, Tongzhijian Yang, Bo Guo, Chenxi Changsha University of Science & Technology School of Computer and Communication Engineering The Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha China

ISBN: (纸本)9798350301113

Increasingly complex systems contain large numbers of devices that generate great number of multivariate time series that are monitored and recorded. For anomaly detection of these complex time series, deep learning technology is often used to build a learning model for anomaly detection. The method based on deep learning usually takes a long time to train data in practice, and the online service system is deployed or changed very frequently, which makes the online service system need to frequently spend a lot of time updating the anomaly detection model. To overcome this challenge, this paper proposes a fast multivariate time series anomaly detection (FMAD) approach based on matrix completion. After sampling the primitive low-rank matrix, FMAD uses matrix completion to reconstruct the original low-rank matrix to detect anomalies in multivariate time series. We conducted related experimental analysis and discussion. The experimental results on three real data sets show that FMAD has improved the problem of too long model training time and improved the detection efficiency. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A Parallel Beamforming Algorithm for Sonar Signal Processing

A Parallel Beamforming Algorithm for Sonar Signal Processing

引用

2022 International Conference on Signal Processing, Computer Networks, and Communications, SPCNC 2022

作者： Dang, Lanxue Liu, Chongyang Yang, Kang Hou, Yan-E Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer and Information Engineering Henan University Kaifeng China

ISBN: (纸本)9781510664616

Sonar is a general term for various underwater acoustic devices, which are used to perform underwater target detection, positioning, identification, tracking and underwater communication, navigation, measurement and other tasks. All sonar devices including active sonar and passive sonar both require a signal processor to execute underwater acoustic signal processing. Beamforming is the main and core component of the sonar signal processor, and its processing speed affects the real-time performance of sonar. Thus, this paper first implements a parallel sonar beamforming algorithm to improve the processing speed of the beamforming algorithm. The proposed algorithm was carried out several experiments, and the experimental results demonstrate that the parallelism of multi-core CPU can bring better speedup ratio and efficiency than the traditional serial CPU algorithm. © 2023 SPIE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Research on Workflow Model and Verification Method of Remote Sensing data Processing 17th

Research on Workflow Model and Verification Method of Remote...

引用

17th International Conference on Computer Science and Education, ICCSE 2022

作者： Qiao, Baojun He, Siyuan Du, Ying Zuo, Xianyu Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer and Information Engineering Henan University Kaifeng China

ISBN: (纸本)9789819924424

To reduce the uncertainty factors in the remote sensing data processing process and the complexity of remote sensing data processing software, a remote sensing data processing workflow model is presented based on Petri net and UniNet theory. The model can not only describe the data, tasks and their logical relationships involved in remote sensing data processing workflow formally, but also analyze the logic of the process dynamically. Furthermore, the model can be effectively combined with workflow technology, which provide great help for solving remote sensing application needs. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

PromptGCN: Bridging Subgraph Gaps in Lightweight GCNs

arXiv

引用

arXiv 2024年

作者： Ji, Shengwei Tian, Yujie Liu, Fei Li, Xinlu Wu, Le The School of Artificial Intelligence and Big Data Hefei University Hefei China The School of Computer Science and Information Engineering Hefei University of Technology Hefei China The Key Laboratory of Knowledge Engineering with Big Data Ministry of Education China

Graph Convolutional Networks (GCNs) are widely used in graph-based applications, such as social networks and recommendation systems. Nevertheless, large-scale graphs or deep aggregation layers in full-batch GCNs consume significant GPU memory, causing out of memory (OOM) errors on mainstream GPUs (e.g., 29GB memory consumption on the Ogbn-products graph with 5 layers). The subgraph sampling methods reduce memory consumption to achieve lightweight GCNs by partitioning the graph into multiple subgraphs and sequentially training GCNs on each subgraph. However, these methods yield gaps among subgraphs, i.e., GCNs can only be trained based on subgraphs instead of global graph information, which reduces the accuracy of GCNs. In this paper, we propose PromptGCN, a novel prompt-based lightweight GCN model to bridge the gaps among subgraphs. First, the learnable prompt embeddings are designed to obtain global information. Then, the prompts are attached into each subgraph to transfer the global information among subgraphs. Extensive experimental results on seven large-scale graphs demonstrate that PromptGCN exhibits superior performance compared to baselines. Notably, PromptGCN improves the accuracy of subgraph sampling methods by up to 5.48% on the Flickr dataset. Overall, PromptGCN can be easily combined with any subgraph sampling method to obtain a lightweight GCN model with higher accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Anatomical Prior Guided Spatial Contrastive Learning for Few-Shot Medical Image Segmentation 24

Anatomical Prior Guided Spatial Contrastive Learning for Few...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Huang, Wendong Hu, Jinwu Bi, Xiuli Xiao, Bin Chongqing Key Laboratory of Image Cognition Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Post and Telecommunications Chongqing China Pazhou Lab School of Software Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798400706868

Few-shot semantic segmentation has considerable potential for low-data scenarios, especially for medical images that require expert-level dense annotations. Existing few-shot medical image segmentation methods strive to deal with the task by means of prototype learning. However, this scheme relies on support prototypes to guide the segmentation of query images, ignoring the rich anatomical prior knowledge in medical images, which hinders effective feature enhancement for medical images. In this paper, we propose an anatomical prior guided spatial contrastive learning, called APSCL, which exploits anatomical prior knowledge derived from medical images to construct contrastive learning from a spatial perspective for few-shot medical image segmentation. The new framework forces the model to learn the features in line with the embedded anatomical representations. Besides, to fully exploit the guidance information of the support samples, we design a mutual guidance decoder to predict the label of each pixel in the query image. Furthermore, our APSCL can be trained end-to-end in the form of episodic training. Comprehensive experiments on three challenging medical image datasets, i.e., CHAOS-T2, MS-CMRSeg, and Synapse, prove that our method significantly surpasses state-of-the-art few-shot medical segmentation methods, with a mean improvement of 3.61%, 2.30%, and 6.38% on the Dice score, respectively. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Multi-Label Classification Algorithm Based on Self-paced Learning and LDA 8

A Multi-Label Classification Algorithm Based on Self-paced L...

引用

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Wang, Qiangqiang Gu, Shenming Zhejiang Ocean University School of Information Engineering Zhoushan China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhoushan China

ISBN: (纸本)9798350302455

To address the problem that existing multi-label learning algorithms treat all samples equally during model training and ignore inter-sample variability, this paper proposes a multi-label classification algorithm based on self-paced learning and LDA (SPLDA for short). SPLDA first constructs an adaptive self-paced function based on the label prediction loss values in multi-label data, and introduces a self-paced learning framework. Secondly, the linear discriminant analysis regularization term in the low-dimensional space of the samples is constructed by combining the principles of minimizing the within-class distance and maximizing the between-class distance in this framework. Next, a multi-label classification model is trained using alternating optimization methods. Finally, the experimental results on 5 real datasets and 3 evaluation metrics show that SPLDA outperforms the existing multi-label classification algorithms. © 2023 IEEE.

关键词： Learning algorithms

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：