检索结果-内蒙古大学图书馆

21st International computer Conference on Wavelet Active Media technology and Information Processing, ICCWAMTIP 2024

作者： Simin, Wang Yilin, Wang Zihan, Xie Qiang, Dong School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China University of Electronic Science and Technology of China Laboratory of Intelligent Collaborative Computing Chengdu611731 China

ISBN: (纸本)9798331519254

Natural connectivity serves as a pivotal metric for evaluating network robustness, reflecting the redundancy of alternative pathways between any two nodes and being mathematically expressed as the average eigenvalue of the adjacency matrix. Despite extensive research on the natural connectivity of numerous typical networks, there has been limited exploration into strategies for enhancing this metric. This paper introduces a link addition strategy aimed at maximizing natural connectivity, specifically targeting the addition of links between high-degree nodes with long-range distances. Experimental results, conducted on both synthetic and real-world networks, demonstrate that our proposed strategy attains near-optimal natural connectivity with remarkable computational efficiency, thereby proving its viability for large-scale network applications. © 2024 IEEE.

关键词： Link addition strategy Natural connectivity Network robustness

来源：评论

学校读者我要写书评

暂无评论

CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns 38

CycleNet: Enhancing Time Series Forecasting through Modeling...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Lin, Shengsheng Lin, Weiwei Hu, Xinyi Wu, Wentai Mo, Ruichao Zhong, Haocheng School of Computer Science and Engineering South China University of Technology China Pengcheng Laboratory China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong College of Information Science and Technology Jinan University China

The stable periodic patterns present in time series data serve as the foundation for conducting long-horizon forecasts. In this paper, we pioneer the exploration of explicitly modeling this periodicity to enhance the performance of models in long-term time series forecasting (LTSF) tasks. Specifically, we introduce the Residual Cycle Forecasting (RCF) technique, which utilizes learnable recurrent cycles to model the inherent periodic patterns within sequences, and then performs predictions on the residual components of the modeled cycles. Combining RCF with a Linear layer or a shallow MLP forms the simple yet powerful method proposed in this paper, called CycleNet. CycleNet achieves state-of-the-art prediction accuracy in multiple domains including electricity, weather, and energy, while offering significant efficiency advantages by reducing over 90% of the required parameter quantity. Furthermore, as a novel plug-and-play technique, the RCF can also significantly improve the prediction accuracy of existing models, including PatchTST and iTransformer. The source code is available at: https://***/ACAT-SCUT/CycleNet. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NotifyMiner: rule based user behavioral machine learning approach for context wise personalized notification services

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第10期14卷 13301-13317页

作者： Khan, Muhammad Faizan Lu, Lu Toseef, Muhammad Musyafa, Ahmed Amin, Ahmad School of Computer Science and Engineering South China University of Technology University Town Guangzhou China Department of Computer Science City University of Hong Kong 83 Tat Road Kowloon Tong Hong Kong

This paper devises the issue of machine learning rule-based methodology for uncovering the behavior-based rules of respective smart-phone users for purpose of providing context wise individualized notification services. Nowadays, the number of notifications arrived at an inappropriate moment of time or carried unrelated material, which can cause disruption. Previously Rule-based Classifier and Association Rule Mining (ARM) Techniques have been used to solve those problems. However, the classifier approach processes accuracy and reliability problems because of small data instances. ARM creates a vast number of redundant rules, which are pointless for creating context-aware decisions. Redundant rules can make the approach non-efficient and also make the dataset unnecessarily large, making decision-based problems more complicated. For those problems solution in this article, we propose a new Behavioral Adversarial Traversal Tree approach for extracting user behavioral rules with respect to different contexts. A real-world dataset is collected to make this approach more relevant. The Proposed approach effectively identifies and removes the redundant rules with individual behavior-oriented time slots, which are used in the proposed approach to make it more exact and efficient. Our experiments and comparisons on each individual contextual dataset exhibit that the following rule discovery approach is more adequate and more exact for context-aware notification services. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

An end-to-end instance segmentation method based on improved ConvNeXt V2

引用

International Journal of Wireless and Mobile Computing 2024年第4期26卷 384-392页

作者： Wang, Wenlu Sun, Ying Xu, Manman Bai, Dongxu Huang, Li Zou, Chunlong Chen, Baojia Tang, Dalai Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Hubei Wuhan China Research Centre for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Hubei Wuhan China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Hubei Wuhan China College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan China College of Mechanical Engineering Hubei University of Automotive Technology Hubei Shiyan China Hubei Key Laboratory of Hydroelectric Machinery Design and Maintenance China Three Gorges University Hubei Yichang China School of Computer Information Management Inner Mongolia University of Finance and Economics Hohhot China

In order to improve the efficiency of indoor mobile robots in locating and segmenting environmental instances, an instance segmentation method based on RTMDet is proposed. Firstly, the more powerful ConvNeXt V2 is used as the backbone network of the model, which improves the performance of the existing RTMDet model. Subsequently, NAS-FPN is used as a converged network to detect the network at any given time. Finally, AdamW is used as the model optimiser, which effectively solves the problem of excessive memory occupation when updating parameters and improves the performance of the model. The proposed method obtains the highest evaluation index in all cases. After training and testing on the Cityscapes data set, the recognition accuracy reaches 65.0%. © 2024 Inderscience Enterprises Ltd.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Design of SIW Filtering Power Dividers Based on Fractal Metamaterial Slotted Resonators

Design of SIW Filtering Power Dividers Based on Fractal Meta...

引用

2024 Photonics and Electromagnetics Research Symposium, PIERS 2024

作者： He, Zhilin Cao, Xin Cai, Qiangming Zhou, Longjian Li, Haoran Zhu, Yuyu Southwest University of Science and Technology School of Information Engineering Mianyang621010 China South China University of Technology School of Electronic and Information Engineering Guangzhou510640 China

ISBN: (纸本)9798350375909

With the development of new generation wireless communication technology, microwave devices are developing towards miniaturization and integration. Power dividers are important components of the transmitter, their size and performance can influence the quality of communication systems greatly. Therefore, in order to decrease the size of the power dividers and to reduce component size, this paper proposes several substrate integrated waveguide (SIW) power dividers based on fractal metamaterial slotted resonators. First, planar geometrical fractals such as the Minkowski fractals, Hilbert fractals and von Koch fractals have been applied in the SIW structure as slots. Due to the slow wave effects, the size of the proposed SIW can be reduced compared with conventional SIWs. Then by loading slotted resonators, the filtering characteristics can also be achieved. To verify the performance of the proposed structure, three SIW power division filters have been designed based on these proposed fractal metamaterial slotted resonators. The input and output of the power division filters are connected with tapered microstrip lines with the port characteristic impedance of 50 ohms. As the full-wave simulated results show that the proposed power division filters can achieve a filter band from 9 GHz to 11.9 GHz with the in-band S11 better than -10 dB. Based on the electric field distribution, it can also be observed that the size has been reduced. Further improvements have been achieved. Our proposed structures are easy to manufacture and can be applied in the modern wireless communication circuits and systems. © 2024 IEEE.

关键词： Substrate integrated waveguides

来源：评论

学校读者我要写书评

暂无评论

Multiscale Wavelet-Driven Transformer for Blade Icing Detection MWT 3

Multiscale Wavelet-Driven Transformer for Blade Icing Detect...

引用

2024 3rd International Conference on Frontiers of Artificial Intelligence and Machine Learning, FAIML 2024

作者： Xiang, Dong Cheng, Xu Chen, Sizhuo Liu, Mengna Shi, Fan Liu, Xiufeng School of Computer Science and Engineering Tianjin University of Technology China Department of Technology Management and Economics Technical University of Denmark Denmark

ISBN: (纸本)9798400709777

Currently, the global demand for green wind power generation is increasing day by day. However, the icing of fan blades can significantly reduce the efficiency of fan power generation, highlighting the increasing importance of efficiently detecting whether the wind turbine is icing. In the traditional approach, the operation status of wind turbines is manually collected. However, with technological advancements, the SCADA system now automatically collects the continuous operational status of wind turbines. Nevertheless, However, the monitored operational data suffers from data imbalance. In this study, we introduce a multi-level neural network built upon the Trans- former architecture. Specifically, to extract multi-level features from the time and frequency domains, we utilize discrete wavelet decomposition. By leveraging the self-attention mechanism of the Transformer, we enhance the feature extraction capabilities for predictive tasks. We investigate data resampling methods to address the data imbalance problem. Comprehensive studies demonstrate that our proposed algorithm improves F1 scores to 90.08%, 81.70%, and 76.21% on datasets processed using data resampling algorithms. The obtained icing detection results validate the applicability of our approach and demonstrate that adopting this algorithm can enhance the accuracy. © 2024 Copyright held by the owner/author(s).

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

Waveform Design for Integrated Sensing and Communication in the Presence of DRFM Forwarding Interference

Waveform Design for Integrated Sensing and Communication in ...

引用

IET International Radar Conference 2023, IRC 2023

作者： Zhou, Yu Shi, Qiao Zhou, Zhengchun Yang, Yang The School of Mathematics Southwest Jiaotong University Chengdu China The School of Information Science and Technology Southwest Jiaotong University Chengdu China

ISBN: (纸本)9781839539954

This paper focuses on the joint design of the integrated sensing and communication (ISAC) waveform and the receive filter in the presence of digital radio frequency memory (DRFM) forwarding interference. We first construct an optimization model by minimizing the integrated sidelobe level (ISL) of the ISAC waveform and the integrated level (IL) of the interference signal, under the constraints of the energy budget, peak loss, and peak-to-average power ratio (PAPR). Moreover, the phase similarity constraint, which minimizes the difference between the ISAC waveform and the communication symbol, is introduced to assure the communication performance. Then, a new decoupled majorization minimization (DMM) algorithm is developed to solve the above formulated non-convex multi-constrained problem. Finally, numerical and simulation results show that the proposed scheme can effectively suppress interference, and also display superior sensing and communication performance. © The Institution of Engineering & technology 2023.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

ON CYCLIC FREQUENCY SIDELOBE AND RANGE SIDELOBE REDUCTION FOR LPI RADAR WAVEFORM

ON CYCLIC FREQUENCY SIDELOBE AND RANGE SIDELOBE REDUCTION FO...

引用

IET International Radar Conference 2023, IRC 2023

作者： Wang, Yujie Shi, Qiao Yu, Tao Zhou, Yu Zhou, Zhengchun The School of Mathematics Southwest Jiaotong University Chengdu China The School of Information Science and Technology Southwest Jiaotong University Chengdu China

ISBN: (纸本)9781839539954

Design of radar waveform with low probability of intercept (LPI) performance has been a topic that has attracted much attention in recent years. In this paper, a new LPI radar waveform design scheme is proposed, which not only considers the LPI performance but also takes the integrated sidelobe level (ISL) into account to assure the radar detection performance. Based on the analysis of the cyclic spectrum, we develop a trade-off optimization model by minimizing the weighted summation of the cyclic frequency sidelobe level (CFSL) and ISL under energy constraint. Since the constructed problem is a non-convex quartic optimization problem, a majorization-minimization (MM) based low double sidelobes (MM-LDS) algorithm is proposed to transform it into a convex optimization problem for solving. Numerical simulation results verify LPI and low ISL performance of the designed waveform. © The Institution of Engineering & technology 2023.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Leveraging hierarchical semantic‐emotional memory in emotional conversation generation

引用

CAAI Transactions on Intelligence technology 2023年第3期8卷 824-835页

作者： Min Yang Zhenwei Wang Qiancheng Xu Chengming Li Ruifeng Xu Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhenChina School of Electrical and Computer Engineering Georgia Institute of TechnologyAtlantaUSA School of Intelligent Systems Engineering Sun Yat‐Sen UniversityGuangzhouChina School of Computer Science Harbin Institute of Technology(Shenzhen)ShenzhenChina

Handling emotions in human‐computer dialogues has emerged as a challenging task which requires artificial intelligence systems to generate emotional responses by jointly perceiving the emotion involved in the input posts and incorporating it into the gener-ation of semantically coherent and emotionally reasonable ***,most previous works generate emotional responses solely from input posts,which do not take full advantage of the training corpus and suffer from generating generic *** this study,we introduce a hierarchical semantic‐emotional memory module for emotional conversation generation(called HSEMEC),which can learn abstract semantic conver-sation patterns and emotional information from the large training *** learnt semantic and emotional knowledge helps to enrich the post representation and assist the emotional conversation *** experiments on a large real‐world conversation corpus show that HSEMEC can outperform the strong baselines on both automatic and manual *** reproducibility,we release the code and data publicly at:https://***/siat‐nlp/HSEMEC‐code‐data.

关键词： deep learning emotional conversation generation semantic‐emotional memory

来源：评论

学校读者我要写书评

暂无评论

MKGL: Mastery of a Three-Word Language 38

MKGL: Mastery of a Three-Word Language

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Guo, Lingbing Bo, Zhongpu Chen, Zhuo Zhang, Yichi Chen, Jiaoyan Lan, Yarong Sun, Mengshu Zhang, Zhiqiang Luo, Yangyifei Li, Qian Zhang, Qiang Zhang, Wen Chen, Huajun College of Computer Science and Technology Zhejiang University China ZJU-Ant Group Joint Lab of Knowledge Graph China Ant Group China Department of Computer Science The University of Manchester United Kingdom School of Computer Science and Engineering Beihang University China School of Computer Science Beijing University of Posts and Telecommunications China School of Software Technology Zhejiang University China

Large language models (LLMs) have significantly advanced performance across a spectrum of natural language processing (NLP) tasks. Yet, their application to knowledge graphs (KGs), which describe facts in the form of triplets and allow minimal hallucinations, remains an underexplored frontier. In this paper, we investigate the integration of LLMs with KGs by introducing a specialized KG Language (KGL), where a sentence precisely consists of an entity noun, a relation verb, and ends with another entity noun. Despite KGL's unfamiliar vocabulary to the LLM, we facilitate its learning through a tailored dictionary and illustrative sentences, and enhance context understanding via real-time KG context retrieval and KGL token embedding augmentation. Our results reveal that LLMs can achieve fluency in KGL, drastically reducing errors compared to conventional KG embedding methods on KG completion. Furthermore, our enhanced LLM shows exceptional competence in generating accurate three-word sentences from an initial entity and interpreting new unseen terms out of KGs. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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：