检索结果-内蒙古大学图书馆

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Si, Jiasheng Zhu, Yingjie Lu, Wenpeng Zhou, Deyu China School of Computer Science and Engineering Southeast University China Ministry of Education China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing China

ISBN: (纸本)9798891761681

The success of deep learning models on multi-hop fact verification has prompted researchers to understand the behavior behind their veracity. One feasible way is erasure search: obtaining the rationale by entirely removing a subset of input without compromising verification accuracy. Despite extensive exploration, current rationalization methods struggle to discern nuanced composition within the correlated evidence, which inevitably leads to noise rationalization in multi-hop scenarios. To address this issue, this paper proposes the consistent multi-granular rationale extraction method, aiming to realize the denoising rationalization for multi-hop fact verification. Specifically, given a pretrained veracity prediction model, two independent external explainers are introduced and trained collaboratively to enhance the discriminating ability by imposing varied constraints. Meanwhile, three key properties (Fidelity, Consistency, Salience) are introduced to regularize the denoising and faithful rationalization process. Additionally, a new Noiselessness metric is proposed to measure the purity of the rationales. Experimental results on three multi-hop fact verification datasets show that the proposed approach outperforms 12 baselines. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Strong Co-Location Pattern Mining Incorporating Multi-Path and Distance Decay Effects 7

Strong Co-Location Pattern Mining Incorporating Multi-Path a...

引用

7th International Conference on Algorithms, computing and Artificial Intelligence, ACAI 2024

作者： He, Yonggui Yang, Peizhong Wang, Lizhen Chen, Hongmei Yunnan University School of Information Science and Engineering Kunming China Yunnan University Yunnan Key Laboratory of Intelligent Systems and Computing School of Information Science and Engineering Kunming China

ISBN: (纸本)9798331529314

Spatial co-location pattern mining (SCPM) is a sub-field of data mining, which aims to discover the subset of spatial features whose instances are frequently located in proximate areas. SCPM has broad prospects in many applications, such as ecology, public health, smart cities, etc. In recent years, improving and applying SCPM technology with the constraints of road networks has emerged as a prominent research focus. However, existing studies solely focus on the shortest path between instances when assessing the proximity relationships, neglecting other proximity paths, and thus may overlook co-location patterns with strong associations. To address this issue, this paper introduces a novel metric called Strong Proximity Score, which integrates both multi-path proximity and distance decay effects to measure the strength of proximity relationships. Additionally, the Minimum First Search (MFS) algorithm is presented, which utilizes the strategy of minimum instance pair search to accelerate the calculation of Strong Proximity Score. Extensive experiments conducted on real datasets of points of interest demonstrate the superiority of the method based on Strong Proximity Score over traditional SCPM methods and confirm the efficiency of MFS algorithm. © 2024 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

A Semi-supervised Protein Complex Identification Algorithm Based on Sparseness Constraint

A Semi-supervised Protein Complex Identification Algorithm B...

引用

2024 International Conference on Applied Mathematics, Modelling and Statistics Application, AMMSA 2024

作者： Liu, Guangming Dang, Fengqing Wang, Bin Peng, Yonghong Wang, Xiaofan Tan, Li School of Computer Science and Engineering Shaanxi Key Laboratory for Network Computing and Security Technology Xi'An University of Technology Shaanxi Xi'an China Faculty of Science and Engineering Computing and Information Science Cambridge United Kingdom School of Computer and Information Engineering Beijing Technology and Business University Beijing China

Recognising protein complexes in protein interaction networks is crucial, but poses a major challenge due to the frequency of noisy interactions. These networks typically involve numerous protein complexes, with each protein generally only participating in a few complexes. Current recognition models often ignore this aspect. To address this problem, we present a semi-supervised protein complex identification algorithm that extends non-negative matrix factorization (NMF) with sparsity constraints. In contrast to conventional approaches that apply a global sparsity constraint to the entire matrix, our method imposes individual sparsity constraints on protein membership indicator vectors. This targeted strategy controls the algorithm more effectively. Our experimental results with yeast and human protein interaction networks show that our algorithm achieves higher accuracy in identifying protein complexes than leading contemporary methods. © Published under licence by IOP Publishing Ltd.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Design of a new kind of chemical experiment container with virtual reality fusion

引用

Virtual Reality & Intelligent Hardware 2023年第4期5卷 317-337页

作者： Lurong YANG Zhiquan FENG Junhong MENG Department of Information Science and Engineering University of JinanJinan 250022China Shandong Provincial Key Laboratory of Network Based Intelligent Computing Jinan 250022China

Background At present,the teaching of experiments in primary and secondary schools is affected by cost and security *** research on virtual experiment platforms has alleviated these ***,the lack of real experimental equipment and use of a single channel to understand user intentions weaken these platforms operationally and degrade the naturalness of *** To solve these problems,we propose an intelligent experimental container structure and a situational awareness algorithm,both of which are verified and applied to a chemical experiment involving virtual-real ***,the acquired images are denoised in the visual channel using the maximum diffuse reflection chroma to remove ***,container situational awareness is realized by segmenting the image liquid level and establishing a relation-fitting ***,strategies for constructing complete behaviors and making priority comparisons among behaviors are adopted for information complementarity and independence,respectively.A multichannel intentional understanding model and an inter-active paradigm that integrates vision,hearing,and touch are *** The experimental results show that the accuracy of the intelligent container situation awareness proposed in this paper reaches 99%,and the accuracy of the proposed intention understanding algorithm reaches 94.7%.The test shows that the intelligent experimental system based on the new interaction paradigm also has better performance and a more realistic sense of operation experience in terms of experimental *** The results indicate that the proposed experimental container and algorithm can achieve a natural level of human-computer interaction in a virtual chemical experiment platform,enhance the user′s sense of operation,and achieve high levels of user satisfaction.

关键词： Multichannel intent fusion understanding Virtual-real fusion Natural interaction Remove image highlights Nonlinear curve fitting

来源：评论

学校读者我要写书评

暂无评论

An Improved YOLOv5s-Based Smoke Detection System for Outdoor Parking Lots

引用

Computers, Materials & Continua 2024年第8期80卷 3333-3349页

作者： Ruobing Zuo Xiaohan Huang Xuguo Jiao Zhenyong Zhang State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China School of Information and Control Engineering Qingdao University of TechnologyQingdao266520China State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhou310027China Key Laboratory of Computing Power Network and Information Security Ministry of EducationQilu University of Technology(Shandong Academy of Sciences)Jinan250353China Text Computing&Cognitive Intelligence Engineering Research Center of National Education Ministry Guizhou UniversityGuiyang550025China

In the rapidly evolving urban landscape,outdoor parking lots have become an indispensable part of the city’s transportation *** growth of parking lots has raised the likelihood of spontaneous vehicle combus-tion,a significant safety hazard,making smoke detection an essential preventative ***,the complex environment of outdoor parking lots presents additional challenges for smoke detection,which necessitates the development of more advanced and reliable smoke detection *** paper addresses this concern and presents a novel smoke detection technique designed for the demanding environment of outdoor parking ***,we develop a novel dataset to fill the gap,as there is a lack of publicly available *** dataset encompasses a wide range of smoke and fire scenarios,enhanced with data augmentation to ensure robustness against diverse outdoor ***,we utilize an optimized YOLOv5s model,integrated with the Squeeze-and-Excitation Network(SENet)attention mechanism,to significantly improve detection accuracy while maintaining real-time processing ***,this paper implements an outdoor smoke detection system that is capable of accurately localizing and alerting in real time,enhancing the effectiveness and reliability of emergency *** show that the system has a high accuracy in terms of detecting smoke incidents in outdoor scenarios.

关键词： YOLOv5s smoke detection deep learning SENet

来源：评论

学校读者我要写书评

暂无评论

Deep-reinforcement-learning-based robot motion strategies for grabbing objects from human hands

引用

Virtual Reality & Intelligent Hardware 2023年第5期5卷 407-421页

作者： Zeyuan CAI Zhiquan FENG Liran ZHOU Xiaohui YANG Tao XU School of Information Science and Engineering University of JinanJinan 250022China Shandong Provincial Key Laboratory of Network Based Intelligent Computing Jinan 250022China

Background Robot grasping encompasses a wide range of research areas;however, most studies have been focused on the grasping of only stationary objects in a scene;only a few studies on how to grasp objects from a user's hand have been conducted. In this paper, a robot grasping algorithm based on deep reinforcement learning (RGRL) is proposed. Methods The RGRL takes the relative positions of the robot and the object in a user's hand as input and outputs the best action of the robot in the current state. Thus, the proposed algorithm realizes the functions of autonomous path planning and grasping objects safely from the hands of users. A new method for improving the safety of human-robot cooperation is explored. To solve the problems of a low utilization rate and slow convergence of reinforcement learning algorithms, the RGRL is first trained in a simulation scene, and then, the model para-meters are applied to a real scene. To reduce the difference between the simulated and real scenes, domain randomization is applied to randomly change the positions and angles of objects in the simulated scenes at regular intervals, thereby improving the diversity of the training samples and robustness of the algorithm. Results The RGRL's effectiveness and accuracy are verified by evaluating it on both simulated and real scenes, and the results show that the RGRL can achieve an accuracy of more than 80% in both cases. Conclusions RGRL is a robot grasping algorithm that employs domain randomization and deep reinforcement learning for effective grasping in simulated and real scenes. However, it lacks flexibility in adapting to different grasping poses, prompting future research in achieving safe grasping for diverse user postures.

关键词： Robot grasping Deep reinforcement learning Domain randomization Human-to-robot handovers Human-machine collaboration

来源：评论

学校读者我要写书评

暂无评论

Forecasting of Groundwater Level in Multiple Wells using Machine Learning Models 17

Forecasting of Groundwater Level in Multiple Wells using Mac...

引用

17th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2023

作者： Baba, Naima Fazziki, Abdelaziz El Jarir, Zahi Cadi Ayyad University Computing Systems Engineering Laboratory Computer Science Dept Marrakesh Morocco

ISBN: (纸本)9798350370911

Accurate forecasting of groundwater levels is crucial for sustainable water resource management and environmental planning. This article explores the use of machine learning for accurate groundwater level predictions. In this study three machine learning models including artificial neural network ANN, long-short term memory LSTM and Extreme Gradient Boosting decision tree XGBoost technique were used to predict ground water level. We incorporate deep water surface measurements and meteorological data as key parameters to enhance forecasting accuracy. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Balancing Crop Priorities: PSO-Based Equitable Irrigation Water Distribution for Efficient Resource Management 17

Balancing Crop Priorities: PSO-Based Equitable Irrigation Wa...

引用

17th International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2023

作者： Ikidid, Abdelouafi Fazziki, Abdelaziz El Baba, Naima Cadi Ayyad University Computer Science Dept Computing Systems Engineering Laboratory Marrakesh Morocco

ISBN: (纸本)9798350338904

Agriculture consumes a significant proportion of water reserves in irrigated areas. Improving irrigation is becoming essential to reduce this high-water consumption by adapting supplies to crop needs and avoiding losses. This global issue has prompted many scientists to think about sustainable solutions using innovative technologies. This study aims to solve the problem of equitable distribution of irrigation water to crops using the PSO (Particle Swarm Optimization) algorithm. The problem involves the allocation of water between N crops, taking into account the priorities of each crop, the minimum and maximum water thresholds required, and the total amount of water available. A precise modeling of the problem is proposed, followed by a description of the PSO algorithm adapted to this situation. The implementation of the algorithm in Python is also presented. The results and performance of the algorithm are discussed, showing its ability to find a fair and efficient solution for irrigation water allocation. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

NCRE: A Benchmark for Document-level Nominal Compound Relation Extraction 31

NCRE: A Benchmark for Document-level Nominal Compound Relati...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Cao, Jincheng Li, Bobo Liu, Jiang Ji, Donghong Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan China

ISBN: (纸本)9798891761964

Entity and relation extraction is a conventional task in the field of information extraction. Existing work primarily focuses on detecting specific relations between entities, often constrained to particular fields and lacking general applicability. In response, we propose a novel task: nominal compound relation extraction (NCRE), which concentrates on abstract and broadly applicable relation extraction between noun phrases. This task diverges significantly from traditional entity and relation extraction in two key respects. Firstly, our task involves general nominal compounds rather than named entities, which are longer and encompass a broader scope, presenting significant challenges for extraction. Secondly, relation extraction in NCRE demands an in-depth understanding of context to detect abstract relations. We manually annotate a high-quality Chinese dataset for the NCRE task and develop a model incorporating the rotary position-enhanced word pair (RoWP) detection schema. Experimental results demonstrate the efficiency of our RoWP model over previous baselines, while the suboptimal F1 scores indicate that NCRE remains a challenging task. Our code and data are available at https://***/yeecjc/NCRE. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Parallel finite element computation of incompressible magnetohydrodynamics based on three iterations

引用

Applied Mathematics and Mechanics(English Edition) 2022年第1期43卷 141-154页

作者： Qili TANG Yunqing HUANG Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing&Information Processing of Ministry of EducationSchool of Mathematics and Computational ScienceXiangtan UniversityXiangtanHunan Province411105China

Based on local algorithms,some parallel finite element(FE)iterative methods for stationary incompressible magnetohydrodynamics(MHD)are *** approaches are on account of two-grid skill include two major phases:find the FE solution by solving the nonlinear system on a globally coarse mesh to seize the low frequency component of the solution,and then locally solve linearized residual subproblems by one of three iterations(Stokes-type,Newton,and Oseen-type)on subdomains with fine grid in parallel to approximate the high frequency *** error estimates with regard to two mesh sizes and iterative steps of the proposed algorithms are *** numerical examples are implemented to verify the algorithm.

关键词： local and parallel algorithm finite element(FE)method iteration stationary incompressible magnetohydrodynamics(MHD)

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：