检索结果-内蒙古大学图书馆

4th International Conference on Mechanical, Electronics, and Electrical and Automation Control, METMS 2024

作者： Li, Wei Li, Ming Meng, Xiangjiao Tianjin Key Laboratory of Intelligent Information Processing in Remote Sensing Tianjin Zhong Wei Aerospace Data System Technology Co. Ltd. Tianjin China

ISBN: (数字)9781510679887

ISBN: (纸本)9781510679870

A high-performance unmanned helicopter based transmission line inspection system is proposed to address the issues of low single operation efficiency, low degree of autonomy, and single operation mode in the current multi rotor unmanned aerial vehicle inspection system. This system is based on an unmanned helicopter platform, with customized research and development of load quick replacement and mounting structural components, airborne load control units, optoelectronic pods, autonomous inspection software systems, and other parts. The number of towers that can be inspected in a single fine inspection operation is not less than 20 (visibility, distance between towers is 0.3 km), and the photographic data can meet the requirements of identifying pin level targets (10mm) 50 meters away. Through flight verification testing, it has been shown that the various working modes of the system are operating normally, and autonomous inspections do not require human intervention, greatly improving the efficiency of transmission line inspections. © 2024 SPIE.

关键词： Electric lines

来源：评论

学校读者我要写书评

暂无评论

CFinDEE: A Chinese Fine-Grained Financial Dataset for Document-Level Event Extraction 24

CFinDEE: A Chinese Fine-Grained Financial Dataset for Docume...

引用

33rd Companion of the ACM World Wide Web Conference, WWW 2023

作者： Zhang, Tian Liu, Maofu Zhou, Bingying School of Computer Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9798400701726

Document-level event extraction faces numerous challenges in accurately modeling real-world financial scenarios, particularly due to the inadequacies in existing datasets regarding data scale and fine-grained annotations. The development of datasets is a crucial factor in driving research progress;therefore, we present a high-quality Chinese document-level event extraction dataset, CFinDEE. This dataset, grounded in real-world financial news, defines 22 event types and 116 argument roles, annotating 26,483 events and 107,096 event arguments. CFinDEE aims to address these shortcomings by providing more comprehensive annotations and data augmentation, offering richer resources for document-level event extraction in the financial domain. CFinDEE extends data both horizontally and vertically, where horizontal expansion enriches the types of financial events, enhancing the diversity of the dataset;vertical expansion, by increasing the scale of the data, effectively boosts the practical value of the dataset. Experiments conducted on multiple advanced models have validated the high applicability and effectiveness of the CFinDEE dataset for document-level event extraction tasks in the financial field. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Expansion

来源：评论

学校读者我要写书评

暂无评论

The Methodology of Mask Detection Employing the YOLOv7 Framework 4

The Methodology of Mask Detection Employing the YOLOv7 Frame...

引用

4th International Conference on Neural Networks, information and Communication Engineering, NNICE 2024

作者： Zhang, Fucheng Tian, Pinfang Wuhan University of Science and Technology School of Computer Science and Technology Wuhan China Hubei Key Laboratory of Intelligent Information Processing and Real-TimeIndustrial Systems Wuhan China

ISBN: (纸本)9798350394375

In the current field of object detection, the YOLOv7 model demonstrates significant advantages in terms of both detection speed and accuracy. However, the model shows deficiencies in focussing on key information, and its loss function's sensitivity to bounding boxes results in suboptimal performance in densely populated environments and small target detection scenarios. To address these issues, this study proposes a mask target detection method based on YOLOv7. By integrating a channel attention mechanism into the YOLOv7 model, this method enhances the model's focus on important information in images, effectively reducing interference from background factors. Additionally, the method incorporates Normalized Wasserstein Distance (NWD) into the loss function to optimize the model's evaluation of small target detection. Experimental verification shows that the improved model maintains its original detection speed while increasing the overall accuracy to 92.1%, a 2.9% improvement over the original YOLOv7 model. It achieves a 3.3% increase in the mAP.5 metric. This indicates that the optimised YOLOv7 model has superior detection capabilities, allowing it to perform mask-wearing detection tasks more rapidly and accurately in natural environments. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

UNRAVELING THE ENIGMA OF DOUBLE DESCENT: AN IN-DEPTH ANALYSIS THROUGH THE LENS OF LEARNED FEATURE SPACE 12

UNRAVELING THE ENIGMA OF DOUBLE DESCENT: AN IN-DEPTH ANALYSI...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Gu, Yufei Zheng, Xiaoqing Aste, Tomaso School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing China Department of Computer Science University College London United Kingdom

Double descent presents a counter-intuitive aspect within the machine learning domain, and researchers have observed its manifestation in various models and tasks. While some theoretical explanations have been proposed for this phenomenon in specific contexts, an accepted theory for its occurring mechanism in deep learning remains yet to be established. In this study, we revisit the phenomenon of double descent and demonstrate that the presence of noisy data strongly influences its occurrence. By comprehensively analysing the feature space of learned representations, we unveil that double descent arises in imperfect models trained with noisy data. We argue that while small and intermediate models before the interpolation threshold follow the traditional bias-variance trade-off, over-parameterized models interpolate noisy samples among robust data thus acquiring the capability to separate the information from the noise. The source code is available at https://***/Yufei-Gu-451/double_descent_***. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

VANet: A New Network for Multi-modal Self-supervised Learning from Video and Audio

VANet: A New Network for Multi-modal Self-supervised Learnin...

引用

International Conference on Image, Vision and intelligent Systems, ICIVIS 2023

作者： Liu, Xingrui Zhang, Chen Feng, Zeming Dong, Jiwen Niu, Sijie Gao, Xizhan School of Information Science and Engineering University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network-Based Intelligent Computing Jinan250022 China

ISBN: (纸本)9789819708543

A new Network for Multi-modal Self-Supervised Learning from Video and Audio (VANet) is proposed for video action recognition. To overcome the input issues of different modalities, we establish auxiliary tasks by exploiting the natural synchronization and correlation between video and audio, and align them at both the segment-level representation and the video/audio-level representation. In this work, we introduce a contrastive loss for joint embedding learning of the two input modalities, which is improved to enhance the proximity of semantically relevant samples and meet the special needs of multi-modal learning. In addition, we identify and remove false negative samples from the negative set. Our method achieves competitive results in video action recognition tasks and demonstrates that joint multi-modal learning is superior to single modality. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

L2GC: Lorentzian Linear Graph Convolutional Networks For Node Classification 30

L2GC: Lorentzian Linear Graph Convolutional Networks For Nod...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Liang, Qiuyu Wang, Weihua Bao, Feilong Gao, Guanglai College of Computer Science Inner Mongolia University Hohhot China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Hohhot China

ISBN: (纸本)9782493814104

Linear Graph Convolutional Networks (GCNs) are used to classify the node in the graph data. However, we note that most existing linear GCN models perform neural network operations in Euclidean space, which do not explicitly capture the tree-like hierarchical structure exhibited in real-world datasets that modeled as graphs. In this paper, we attempt to introduce hyperbolic space into linear GCN and propose a novel framework for Lorentzian linear GCN. Specifically, we map the learned features of graph nodes into hyperbolic space, and then perform a Lorentzian linear feature transformation to capture the underlying tree-like structure of data. Experimental results on standard citation networks datasets with semi-supervised learning show that our approach yields new state-of-the-art results of accuracy 74.7% on Citeseer and 81.3% on PubMed datasets. Furthermore, we observe that our approach can be trained up to two orders of magnitude faster than other nonlinear GCN models on PubMed dataset. Our code is publicly available at https://***/llqy123/LLGC-master. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Fully Distributed Approach to Optimal Energy Scheduling of Users and Generators Considering a Novel Combined Neurodynamic Algorithm in Smart Grid

引用

IEEE/CAA Journal of Automatica Sinica 2021年第7期8卷 1325-1335页

作者： Chentao Xu Xing He the Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information EngineeringSouthwest UniversityChongqing 400715China

A fully distributed microgrid system model is presented in this *** the user side,two types of load and plug-in electric vehicles are considered to schedule energy for more *** charging and discharging states of the electric vehicles are represented by the zero-one variables with more *** solve the nonconvex optimization problem of the users,a novel neurodynamic algorithm which combines the neural network algorithm with the differential evolution algorithm is designed and its convergence speed is faster.A distributed algorithm with a new approach to deal with the inequality constraints is used to solve the convex optimization problem of the generators which can protect their *** results and comparative experiments show that the model and algorithms are effective.

关键词： Differential evolution algorithm distributed algorithm electric vehicle neural network zero-one variable.

来源：评论

学校读者我要写书评

暂无评论

CNN channel pruning via gradient integration and knowledge distillation 17

CNN channel pruning via gradient integration and knowledge d...

引用

17th IEEE International Conference on Signal processing, ICSP 2024

作者： Lian, Suyun Zhao, Yang Cai, Jiajian Pei, Jihong Shenzhen University The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

ISBN: (纸本)9798350387384

With the advancement of artificial intelligence technology, intelligent applications have permeated all aspects of human life, including automatic driving, intelligent security, and face recognition. Convolutional neural networks (CNNs) are essential models for AI, but their complexity increases with more available data. The complex models are unsuitable for edge devices like wearables and smartphones due to high memory and computational requirements. In this paper, the compact model is achieved by pruning some redundant output channels. To effectively measure the validity of the output channels, this paper proposes a channel pruning algorithm based on gradient integration, which combines the gradient of the channel with the model output and the channel's values. This pruning could destroy model accuracy, so knowledge distillation is introduced during fine-tuning to leverage the original model's reasoning ability. Experiments show that our approach improves accuracy by 0.51% while reducing parameters by 30.1% and FLOPs by 26% in the VGG16 model. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

"study on the Grammatical Function of "la dhon"as Function Words in the Tibetan Language processing" 6

"study on the Grammatical Function of "la dhon"as Function W...

引用

6th International Conference on Machine Learning and Natural Language processing, MLNLP 2023

作者： Suonan, Cairang Gongque, Duojie Computer College of Qinghai Normal University Qinghai Xining810016 China Key Laboratory of Tibetan Information Processing Ministry of Education Qinghai Xining810008 China Tibetan Intelligent Information Processing and Machine Translation Key Laboratory Qinghai Xining810008 China

ISBN: (纸本)9798400709241

The study of Tibetan function words is an indispensable basic work in Tibetan natural language processing and has a wide range of practical application value. It is the core of Tibetan information processing and the basis of Tibetan natural language understanding, and has wide application prospects in Tibetan proofreading, information retrieval, bilingual translation, automatic classification and other technologies. On the basis of previous studies, this paper discusses the grammatical functions of Tibetan function words la dhon from the perspective of information processing, classification system and formal description of unfree function words, focuses on the grammatical functions of Tibetan function words la dhon, and puts forward the preliminary conception and processing methods of Tibetan function words. © 2023 ACM.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Design Technology of Multi-AGV Warehouse intelligent Scheduling Optimization Control System 15th

Design Technology of Multi-AGV Warehouse Intelligent Schedul...

引用

15th International Conference on Genetic and Evolutionary computing, ICGEC 2023

作者： Pan, YanPeng Zhang, XueTing Zhang, FuQuan Tan, LiLi Yang, LiJie Ma, Jun China Academy of Launch Vehicle Technology Beijing100076 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China

ISBN: (纸本)9789819700677

Different from the traditional warehousing system, in the multi-AGV warehouse scheduling control system, the constraints of poor connectivity of the conveying track have led to the emergence of urgent problems such as vehicle conflicts in the task, low efficiency of multitasking concurrency, difficulty of delineating the conditions for entering the transporting area and so on. This paper proposes a design of multi-AGV warehouse intelligent scheduling optimized control system, which takes multitask scheduling research as an entry point, designs the warehouse layout and vehicle operation rules assumptions and modeling, studies the scheduling solution of Monorail Vehicles in multiple tasks, designs a scheduling optimization method based on the algorithm of Time Window, solves conflicts between key process and operation task process and optimize the scheduling, so as to effectively enhance the efficient scheduling capability of multi-AGV warehouse intelligent scheduling optimized control system. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Warehouses

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：