检索结果-内蒙古大学图书馆

Proceedings of the 2023 6th International Conference on Artificial Intelligence and Pattern Recognition

作者： Wei Guan Xiaoru Lian Li Ma Shaanxi provincial key laboratory of network data analysis and intelligent processing Xi'an University of Posts and Telecommunications China

ISBN: (纸本)9798400707674

The knowledge graph completion algorithm can make the knowledge graph more complete and is currently a research hotspot in the field of artificial intelligence. The knowledge graph completion model is mainly defined in three aspects, the way of negative example generation, the design of scoring function and the design of loss function. The previous knowledge graph completion models only rely on factual view data to predict the missing links between entities and ignore the valuable common sense knowledge, and there is invalid negative sampling in knowledge graph embedding techniques; on the other hand, the existing graph neural network-based knowledge graph embedding models mainly consider capturing the graph structure around entities, and the relational representation is only used to update the entity embedding, which may miss the potentially useful information about the relational structure of potentially useful information. To address the above challenges, this paper proposes a two-view graph neural network-based knowledge graph completion model combined with common sense awareness. Common knowledge is first automatically extracted from fact triples with entity concepts to facilitate high-quality negative sampling, and then positive and weighted negative triples are fed into the two-view graph neural network-based knowledge graph embedding model to capture entity- and relationship-centric graph structures and learn vector representations of entities and relationships, and then the learned entity and relationship representations are fed into a weighted score function to return the final the final score. Extensive experimental and ablation studies on four datasets, FB15K, FB15K237, NELL995, and DBpedia-242, show that the model achieves better performance compared to the state-of-the-art models.

关键词： Common Sense Awareness Graph Neural Network Knowledge Graph Completion Knowledge Graph Embedding Negative Sampling

来源：评论

学校读者我要写书评

暂无评论

Application study of oil pipe entity recognition combined with Deep Reinforcement Learning 23

Application study of oil pipe entity recognition combined wi...

引用

Proceedings of the 2023 6th International Conference on Artificial Intelligence and Pattern Recognition

作者： Wei Guan Shijie Liu Li Ma Shaanxi provincial key laboratory of network data analysis and intelligent processing Xi'an University of Posts and Telecommunications China

ISBN: (纸本)9798400707674

Aiming at the problems of inaccurate extraction of entity feature information and mislabeling of recognition results in the construction of knowledge graphs in the field of oil pipe failure using traditional methods, this paper proposes a research method of BERT-BiLSTM-CRF named entity recognition combined with deep reinforcement learning. The method firstly uses the BERT (Bidirectional encoder representations from transformers) pre-training model to obtain the word vectors of the input sequence semantics; secondly, the trained word vectors are fed into the bi-directional long short- term memory network (BiLSTM) to further obtain contextual features and output the maximum probability sequence annotation results according to the labeling rules of conditional random fields (CRF) and sequence decoding ability; finally, the BERT-BiLSTM-CRF model is supplemented with the deep reinforcement learning-based labeling Finally, the BERT-BiLSTM-CRF-DRL model is added to the BERT-BiLSTM-CRF model to form the framework of named entity recognition model in oil pipe failure domain. The model is compared with other 2 named entity recognition models on a self-built oil pipe data-set, and the experimental results show that the accuracy, recall and F1 values of the model reach 90.5%, 92.7% and 91.9%, respectively, and the entity recognition is better than the other 2 models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network with Attention Mechanism for image-Based Smoke Detection 4

Convolutional Neural Network with Attention Mechanism for Im...

引用

4th International Conference on Advances in Computer Technology, Information Science and Communications, CTISC 2022

作者： Chen, Hanyang Ji, Qingge Sun Yat-sen University Guangdong Key Laboratory of Big Data Analysis and Processing School of Computer Science and Engineering Guangzhou510006 China

ISBN: (数字)9781665458726

ISBN: (纸本)9781665458726

Smoke detection based on computer vision plays a key role in fire prevention. With the development of deep learning, convolutional neural network frameworks are increasingly used in this field. However, due to the large span of smoke's scale and the variety of its color as well as its texture, the features are even more complex. In addition, the sampling of features by the existing neural networks is limited to the size of the convolution kernel. It is difficult to extract the global features. So, detecting smoke from pictures is still a problem. In this work, we proposed a feature-fusion method based on local and global attention mechanisms. It is able to better fuse the low-level and high-level features. In order to solve the scale problem, we proposed a mechanism for selection and offset of the receptive field. In addition, we combine the transformer based on self-attention mechanism and convolution operation to make the model aware of global information. Finally, we optimize the sampling of feature maps by the detection head of the one-stage network based on the smoke color features. Experiments show that the proposed model outperforms state-of-the-art relevant competitors by 4.6% on AP.5:.95. © 2022 IEEE.

关键词： Smoke

来源：评论

学校读者我要写书评

暂无评论

Using Rough Sets to Improve the High-dimensional data Anomaly Detection Method Based on Extended Isolation Forest 26

Using Rough Sets to Improve the High-dimensional Data Anomal...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Liu, Hanlin Zhou, Jiantao Li, Hua Inner Mongolia University College of Computer Science Hohhot China Natl. Loc. Jt. Eng. Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Ministry of Education Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (纸本)9798350331684

Anomaly detection refers to the identification of data objects that deviate from the general data distribution. One of the important challenges in anomaly detection is handling high-dimensional data, especially when it contains a large number of redundant attributes. Although traditional Isolation Forest (iForest) and Extended Isolation Forest (EIF) have performed well in anomaly detection, the detection accuracy is still extremely influenced by redundant attributes. In this paper, we propose a two-tier architecture named RS-EIF, to alleviate the negative impact of redundant attributes. Specifically, the RS-EIF combines the rough set theory and EIF algorithm and provides an effective basis for the EIF-based anomaly detection method by removing redundant attributes with rough set theory. Experimental results show that the RS-EIF algorithm performs better than the iForest and EIF algorithms in terms of anomaly detection rate, and the results of the combination of rough set theory and EIF are more prominent compared to the other combination methods. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of a Cesium-based 3D visualization platform for the Yellow River dam bank

Design and implementation of a Cesium-based 3D visualization...

引用

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

作者： Zuo, Xianyu Sun, Huaiyuan Zhang, Lei Dang, Lanxue Liu, Yang Xie, Yi Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Henan Universfiity Kaifeng475001 China Zhong Ke Langfang Institute of Spatial Information Applications Langfang065000 China

ISBN: (纸本)9781510664616

Flood control is one of the most important operations of Yellow River control. The dam bank danger in flood season every year has the characteristics of time-varying, multi-dimension and complex situation, which poses a certain threat to people's life and property safety. For timely, flood control engineering data quickly and implement management interface of information visualization, effectively reduce the labor intensity of artificial working risk, this paper puts forward a kind of based on three-dimensional library of Cesium Huang Heba shore the realization method of 3D visualization platform adopted the aerial drones to create dam shore entity 3D model, Combined with WebGIS technology and front-end technology, the system's 3D expression is realized. Through interface design and system function development, the system has three-dimensional model display,with the functions of dam bank cruise and measurement tools, the platform has strong sense of reality and good interaction effect, which realizes the three-dimensional visual display of the Madu control project in Zhengzhou, Henan Province. © 2023 SPIE.

关键词： Flood control

来源：评论

学校读者我要写书评

暂无评论

Opponent-aware Order Pricing towards Hub-oriented Mobility Services 39

Opponent-aware Order Pricing towards Hub-oriented Mobility S...

引用

39th IEEE International Conference on data Engineering, ICDE 2023

作者： Wu, Zuohan Zheng, Libin Zhang, Chen Jason Zhu, Huaijie Yin, Jian Jiang, Di Sun Yat-sen University Guangzhou China Hong Kong Polytechnic University Hong Kong WeBank Co. Ltd Shenzhen China The Guangdong Key Laboratory of Big Data Analysis and Processing China

ISBN: (纸本)9798350322279

Hub-oriented mobility services have gained great developments in recent years, enabling riders to simultaneously call vehicles from multiple mobility-supply companies (agents) on a single APP (which we call "hub"). Competing with others on such a hub, to obtain an order, an agent company first needs to get admitted by the requester, which is in turn affected by its quotation. The quotation needs to be attractively low compared to those of the opposing agents. Thus, an opponent-aware pricing strategy is needed for an agent to play well in the hub scenario, which is rarely discussed in existing works. To address the aforementioned issue, in this work, we first propose a quotation prediction model, which employs a neural network with a customized loss function to predict the opponents' quotations. Based on the predictions, we then propose multi-arm bandit based methods to decide a proper quotation for the agent, in order to obtain orders while retaining profits. We finally conduct extensive experiments on real data, where the quotation-determining method integrated with the prediction model has achieved a remarkable profit improvement up to 85.5% compared to baseline methods, demonstrating their effectiveness. © 2023 IEEE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method

arXiv

引用

arXiv 2024年

作者： Song, Xinshuai Chen, Weixing Liu, Yang Chen, Weikai Li, Guanbin Lin, Liang Sun Yat-sen University China Peng Cheng Laboratory China Guangdong Key Laboratory of Big Data Analysis and Processing China

Existing Vision-Language Navigation (VLN) methods primarily focus on single-stage navigation, limiting their effectiveness in multi-stage and long-horizon tasks within complex and dynamic environments. To address these limitations, we propose a novel VLN task, named Long-Horizon Vision-Language Navigation (LH-VLN), which emphasizes long-term planning and decision consistency across consecutive subtasks. Furthermore, to support LH-VLN, we develop an automated data generation platform NavGen, which constructs datasets with complex task structures and improves data utility through a bidirectional, multi-granularity generation approach. To accurately evaluate complex tasks, we construct the Long-Horizon Planning and Reasoning in VLN (LHPR-VLN) benchmark consisting of 3,260 tasks with an average of 150 task steps, serving as the first dataset specifically designed for the long-horizon vision-language navigation task. Furthermore, we propose Independent Success Rate (ISR), Conditional Success Rate (CSR), and CSR weight by Ground Truth (CGT) metrics, to provide fine-grained assessments of task completion. To improve model adaptability in complex tasks, we propose a novel Multi-Granularity Dynamic Memory (MGDM) module that integrates short-term memory blurring with long-term memory retrieval to enable flexible navigation in dynamic environments. Our platform, benchmark and method supply LH-VLN with a robust data generation pipeline, comprehensive model evaluation dataset, reasonable metrics, and a novel VLN model, establishing a foundational framework for advancing LH-VLN. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Grouped Graph Neural Networks for Anomaly Detection in Time Series

Grouped Graph Neural Networks for Anomaly Detection in Time ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ziyu Guo Weiyang Kong Yubao Liu Sun Yat-Sen University GuangZhou China Guangdong Key Laboratory of Big Data Analysis and Processing GuangZhou China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Anomaly detection in time series data (e.g., sensor data) is becoming a fundamental research problem that has various applications. Due to the complex inter-sensor relationships, it is challenging to detect anomalous events such as system faults and attacks hidden the high-dimensional time series. Recent advancements in deep learning approaches such as Graph Neural Networks (GNN) have greatly improved anomaly detection performance in time series data. However, existing methods do not learn the dependence relationships between sensors and groups of sensors and may not efficiently detect anomalous events in time series. In this paper, we propose a novel approach GGNN (short for Grouped Graph Neural Networks) that combines a structure learning approach with graph neural networks. In particular, GGNN learns the graph structure containing groups of sensors, which are represented by virtual nodes. In addition, we use the learned graph structure and attention weights to explain the detected anomalies. The experiments on three real world datasets show our superiority in detection accuracy, anomaly diagnosis, and model interpretation compared with state-of-the-art methods.

关键词： Training Deep learning Accuracy Soft sensors Time series analysis Graph neural networks Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Intelligent Service Cluster Construction Method Based on Remote Sensing Application 6

Intelligent Service Cluster Construction Method Based on Rem...

引用

6th IEEE Information Technology and Mechatronics Engineering Conference, ITOEC 2022

作者： Zhou, Liming Yang, Wencheng Du, Ying Liu, Cheng Li, Heng 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)9781665431859

The production of remote sensing products needs to go through various links of evaluation and deploy a variety of software and hardware resources. It is necessary to study how to improve the efficiency of service cluster deployment, simplify the evaluation process, and optimize its structure. This paper designs an intelligent service cluster construction method based on remote sensing applications, which realizes the accurate and efficient deployment of various complex network structures and equipment on the visual interface. The method is convenient and simple to operate. It can set various types of resource information according to the needs of users, can choose a more reasonable server cluster deployment plan, improve the efficiency of data storage and processing of remote sensing products, better serve users, and greatly promote The development of related industries. © 2022 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Blockchain Fragment Expansion Scheme Based on Community Detection and MSR Code 5

Blockchain Fragment Expansion Scheme Based on Community Dete...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Zhai, Sheping Tong, Tong Bai, Xifang Xi'an University of Posts and Telecommunications Shaanxi Provincial Key Laboratory of Network Data Analysis and Intelligent Processing China Xi'an University of Posts and Telecommunications China

ISBN: (纸本)9781450396899

Aiming at the current performance of blockchain system can not meet the actual needs of high-frequency data interaction in the era of information explosion, a blockchain fragment expansion scheme based on community detection and MSR code is proposed. Firstly, based on the random walk community detection algorithm and the blockchain node network, a node grouping method is proposed. Each group of nodes maintains a copy of the blockchain ledger to reduce the storage redundancy of blockchain. Secondly, the block data is divided by minimum storage regenerating codes (MSR), which further reduces the storage pressure of nodes, reduces the amount of data required for block requests, and reduces network pressure. Finally, a blockchain scalable fragment storage scheme is proposed. The simulation experiment and result analysis show that the blockchain fragment expansion scheme based on community detection and MSR has improved in terms of storage scalability, response efficiency and fault tolerance. © 2022 ACM.

关键词： Blockchain

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：