检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Wang, Siqi Liang, Chao Gao, Yunfan Liu, Yang Li, Jing Wang, Haofen Tongji University Shanghai China Department of Computing The Hong Kong Polytechnic University Hong Kong Guangdong Guodi Institute of Resources and Environment Guangzhou China Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China College of Design and Innovation Tongji University Shanghai China Research Centre on Data Science & Artificial Intelligence Hong Kong

ISBN: (纸本)9798400706868

Industrial parks are critical to urban economic growth. Yet, their development often encounters challenges stemming from imbalances between industrial requirements and urban services, underscoring the need for strategic planning and operations. This paper introduces IndustryScopeKG, a pioneering large-scale multi-modal, multi-level industrial park knowledge graph, which integrates diverse urban data including street views, corporate, socio-economic, and geospatial information, capturing the complex relationships and semantics within industrial parks. Alongside this, we present the IndustryScopeGPT framework, which leverages Large Language Models (LLMs) with Monte Carlo Tree Search to enhance tool-augmented reasoning and decision-making in Industrial Park Planning and Operation (IPPO). Our work significantly improves site recommendation and functional planning, demonstrating the potential of combining LLMs with structured datasets to advance industrial park management. This approach sets a new benchmark for intelligent IPPO research and lays a robust foundation for advancing urban industrial development. The dataset and related code are available at https://***/Tongji-KGLLM/IndustryScope. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Truly Multivariate Structured Additive Distributional Regression

arXiv

引用

arXiv 2023年

作者： Kock, Lucas Klein, Nadja Department of Statistics and Data Science National University of Singapore Singapore Scientific Computing Center Karlsruhe Institute of Technology Germany

Generalized additive models for location, scale and shape (GAMLSS) are a popular extension to mean regression models where each parameter of an arbitrary parametric distribution is modelled through covariates. While such models have been developed for univariate and bivariate responses, the truly multivariate case remains extremely challenging for both computational and theoretical reasons. Alternative approaches to GAMLSS may allow for higher-dimensional response vectors to be modelled jointly but often assume a fixed dependence structure not depending on covariates or are limited with respect to modelling flexibility or computational aspects. We contribute to this gap in the literature and propose a truly multivariate distributional model, which allows one to benefit from the flexibility of GAMLSS even when the response has dimension larger than two or three. Building on copula regression, we model the dependence structure of the response through a Gaussian copula, while the marginal distributions can vary across components. Our model is highly parameterized but estimation becomes feasible with Bayesian inference employing shrinkage priors. We demonstrate the competitiveness of our approach in a simulation study and illustrate how it complements existing approaches along the examples of childhood malnutrition and a yet unexplored data set on traffic detection in Berlin. Copyright © 2023, The Authors. All rights reserved.

关键词： Additives

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Business data Fusion in the Engineering Management of Oil and Gas Storage and Transportation Station 4

Research on the Application of Business Data Fusion in the E...

引用

4th International Conference on Computer science and Management Technology, ICCSMT 2023

作者： Xie, Rui Fan, Bo Ma, Jianlin Pan, Meng Southwest Pipeline Ltd. PipeChina ChengDu610213 China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu610031 China Chengdu Aerospace Science and Industry Big Data Institute Ltd. Casic Chengdu610213 China National Engineering Laboratory of Industrial Big-Data Application Technology Casic Chengdu610218 China

ISBN: (纸本)9798400709517

Due to challenges such as complex contractor personnel, a large amount of scattered form data, a cumbersome business implementation process, low levels of digitalization and security, and difficult management in the engineering management business of oil and gas storage and transportation stations, this paper proposes a study on business data fusion application in the engineering management of oil and gas storage and transportation stations. Focused on the business processes and data of engineering management in oil and gas storage and transportation stations, this research establishes and analyzes an architecture for engineering management business in these stations. Using an Artifact-centric data fusion method, the research constructs an information model for the engineering management business, identifying the data topics for this area. Finally, the research applies and verifies the study of business data fusion through real-world business management scenarios. As researchers in the field of business data fusion, this study utilizes digital technologies and methods to enhance the overall safety management of engineering operations, thereby promoting the transformation and upgrading of engineering management business in oil and gas storage and transportation stations © 2023 ACM.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Meta-Path Based Social Relation Reasoning in a Deep and Robust Way 28th

Meta-Path Based Social Relation Reasoning in a Deep and R...

引用

28th International Conference on database Systems for Advanced Applications, DASFAA 2023

作者： Jiang, Xuhui Shen, Yinghan Wang, Yuanzhuo Shen, Huawei Xu, Chengjin Ma, Shengjie Data Intelligent System Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology UCAS Gloucester United Kingdom Big Data Academy Zhongke Zhengzhou China International Digital Economy Academy Shenzhen China Gaoling School of Artificial Intelligence Renmin University of China Beijing China

ISBN: (纸本)9783031306747

Social relation reasoning in heterogeneous social networks (HSNs) should not only infer whether people are connected, but also why they know each other and what their relationship is. This task is challenging because the heterogeneous social network is non-trivial to leverage and the collected data is always noisy and incomplete, which leads that the existing rule-based and representation methods cannot efficiently and accurately reason social relations. To reason social relations in noisy and incomplete HSNs, we shift from simply inferring meta-path based social relations by rule-based methods to reasoning by social relation learning. Then, we present an inductive model named Heterogeneous Graph Variational AutoEncoders (HGVAE) towards robust social relation learning on noisy and incomplete HSN data. In HGVAE, the well-designed heterogeneous graph encoder, multi-signal decoder, and variational inference mechanism bring prominent robustness and significant performance improvement. Extensive experiments are conducted to compare our methods against a set of the most representative baseline methods. The efficiency analysis, robust analysis and ablation studies confirm the value of our proposed approach for modelling meta-path based social relations buried in various HSNs. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

A Unified Causal View of Instruction Tuning

arXiv

引用

arXiv 2024年

作者： Chen, Lu Huang, Wei Zhang, Ruqing Chen, Wei Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Instruction tuning on a mixture of tasks has improved zero-shot capabilities in natural language processing (NLP) . Nevertheless, existing methods often learn features that exhibit correlations between instruction-formatted samples and target labels, rather than causal relationships. Termed as "spurious correlation" in statistics, such a correlation may change drastically in a new task, making the effect from the learned features to be misleading. To this end, we develop a meta Structural Causal Model (meta-SCM) to integrate different NLP tasks under a single causal structure of the data. Specifically, the meta-SCM introduces multiple latent factors that represent properties of source context, only some of which causally influence the target labels for a specific task. The key idea is to learn task-required causal factors and only use those to make predictions for a given task. Theoretically, we prove the causal factor can be identified without mixing information from others. Guided by the identifiability, we propose a Structural Instruction Tuning (SIT) method to learn the task-required causal representations that can mimic the causal factors for each task. The utility of our approach is verified by improvements of zero-shot ability on a range of unseen datasets and tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Management of Scientific Agricultural Digital Ecosystems Based on Ecosystem Classification 16

Management of Scientific Agricultural Digital Ecosystems Bas...

引用

16th International Conference Management of Large-Scale System Development, MLSD 2023

作者： Kulba, Vladimir Medennikov, Viktor V.A. Trapeznikov Institute of Control Sciences of the Russian Academy of Sciences Laboratory of Modular Data Processing and Control Systems Moscow Russia Federal Research Center 'Computer Science and Control' of the Russian Academy of Sciences Information and Computing Systems Department Moscow Russia

ISBN: (纸本)9798350337907

The paper considers a mathematical model for managing a scientific digital ecosystem exemplified by the agriculture case;the model enables assessing the impact science exerts on the regions' socioeconomic position in order to build an adequate response to the advanced economies' regime of severe sanctions against Russia. For these purposes, a systemic analysis of the subject identification and classification of ecosystems was conducted to address the critical issue of determining the basic concepts and terms of the country's digitalization. © 2023 IEEE.

关键词： Agriculture

来源：评论

学校读者我要写书评

暂无评论

Learning discretized neural networks under Ricci flow

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 18901-18944页

作者： Jun Chen Hanwen Chen Mengmeng Wang Guang Dai Ivor W. Tsang Yong Liu Institute of Cyber-Systems and Control Zhejiang University China and School of Computer Science and Technology Zhejiang Normal University China Institute of Cyber-Systems and Control Zhejiang University China SGIT AI Lab State Grid Corporation of China China Centre for Frontier Artificial Intelligence Research Agency for Science Technology and Research (A*STAR) Singapore and Institute of High Performance Computing Agency for Science Technology and Research (A*STAR) Singapore and College of Computing and Data Science Nanyang Technological University Singapore

In this paper, we study Discretized Neural Networks (DNNs) composed of low-precision weights and activations, which suffer from either infinite or zero gradients due to the nondifferentiable discrete function during training. Most training-based DNNs in such scenarios employ the standard Straight-Through Estimator (STE) to approximate the gradient w.r.t. discrete values. However, the use of STE introduces the problem of gradient mismatch, arising from perturbations in the approximated gradient. To address this problem, this paper reveals that this mismatch can be interpreted as a metric perturbation in a Riemannian manifold, viewed through the lens of duality theory. Building on information geometry, we construct the Linearly Nearly Euclidean (LNE) manifold for DNNs, providing a background for addressing perturbations. By introducing a partial differential equation on metrics, i.e., the Ricci flow, we establish the dynamical stability and convergence of the LNE metric with the L2-norm perturbation. In contrast to previous perturbation theories with convergence rates in fractional powers, the metric perturbation under the Ricci ow exhibits exponential decay in the LNE manifold. Experimental results across various datasets demonstrate that our method achieves superior and more stable performance for DNNs compared to other representative training-based methods.

关键词： discretized neural networks gradient perturbation information geometry ricci flow riemannian manifold

来源：评论

学校读者我要写书评

暂无评论

Task-Oriented Semantic Communication in Large Multimodal Models-based Vehicle Networks

引用

IEEE Transactions on Mobile computing 2025年

作者： Du, Baoxia Du, Hongyang Niyato, Dusit Li, Ruidong Kanazawa University Institute of Science and Engineering Kanazawa920-1192 Japan University of Hong Kong Department of Electrical and Electronic Engineering Pok Fu Lam Hong Kong Nanyang Technological University College of Computing and Data Science Singapore

Task-oriented semantic communication has emerged as a fundamental approach for enhancing performance in various communication scenarios. While recent advances in Generative Artificial Intelligence (GenAI), such as Large Language Models (LLMs), have been applied to semantic communication designs, the potential of Large Multimodal Models (LMMs) remains largely unexplored. In this paper, we investigate an LMM-based vehicle AI assistant using a Large Language and Vision Assistant (LLaVA) and propose a task-oriented semantic communication framework to facilitate efficient interaction between users and cloud servers. To reduce computational demands and shorten response time, we optimize LLaVA's image slicing to selectively focus on areas of utmost interest to users. Additionally, we assess the importance of image patches by combining objective and subjective user attention, adjusting energy usage for transmitting semantic information. This strategy optimizes resource utilization, ensuring precise transmission of critical information. We construct a Visual Question Answering (VQA) dataset for traffic scenarios to evaluate effectiveness. Experimental results show that our semantic communication framework significantly increases accuracy in answering questions under the same channel conditions, performing particularly well in environments with poor Signal-to-Noise Ratios (SNR). Accuracy can be improved by 13.4% at an SNR of 12dB and 33.1% at 10dB, respectively. © 2002-2012 IEEE.

关键词： large multimodal models (LMMs) resource allocation Semantic communication user attention

来源：评论

学校读者我要写书评

暂无评论

A Conceptual Evaluation of the data as Partner (DAP) Framework

A Conceptual Evaluation of the Data as Partner (DAP) Framewo...

引用

IEEE International Smart Cities Conference (ISC2)

作者： Sonia Hassan Drishty Sobnath Esther Snell Olufemi Isiaq Department of Science and Engineering Solent University Southampton England Department of Computer and Data Science and AI Creative Computing Institute Universiy of Arts London

This paper explores the innovative data As Partner (DAP) philosophy as a transformative approach to organisational data strategy, drawing upon established concepts of information value, technology acceptance, and inclusivity for people with disabilities (PwD) in smart cities. The study conducted a comprehensive systematic review, after meticulous screening, 20 eligible papers were selected, forming the foundation for deriving the key components of the DAP framework. Subsequently, a qualitative focus group study engaged 18 participants from diverse sectors to evaluate the practical applicability of the DAP conceptual framework. Thematic analysis of the focus group sessions revealed five key themes: practical value, pragmatic performance, ethical perspective, clarity of the framework, and enhancement tools. These findings offer valuable insights for refining the DAP framework and optimising its integration into real-world scenarios, in empowering individuals in smart cities, especially those with disabilities. Future research should explore larger and more diverse samples to generalise findings and assess the framework's long-term impact through longitudinal evaluations. By adopting user-centred methodologies, the DAP framework can be further enhanced as a strategic tool, empowering data to actively participate in organisational decision-making processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning in Cognitive Robots for Autonomous Path Planning

Reinforcement Learning in Cognitive Robots for Autonomous Pa...

引用

data Intelligence and Cognitive Informatics (ICDICI), International Conference on

作者： Archana Das R. Indu Poornima G. Gokila Deepa K. Selva Sheela Akshya J Mani Deepak Choudhry Department of Information Science and Engineering New Horizon College of Engineering Bengaluru Department of Information Technology KGiSL Institute of Technology Coimbatore Department of Artificial Intelligence and Data Science PPG Institute of Technology Coimbatore Department of Artificial Intelligence and Data Science KGiSL Institute of Technology Coimbatore Department of Computational Intelligence SRM Institute of Science and Technology Chennai Department of Computing Technologies SRM Institute of Science and Technology Chennai

ISBN: (数字)9798350389609

ISBN: (纸本)9798350389616

Cognitive robots are intelligent systems that learn from their environment, adapt to dynamic changes, and make decisions without a human's direct intervention. This research studies the integration of Reinforcement Learning in cognitive robots with Q-Learning for autonomous path planning. The study addresses the most critical issues in traditional A* and Dynamic Programming algorithms by devising path-planning techniques, mainly the lack of adaptability and computational efficiency in real-time and unpredictable environments. Our approach is based on Q-Learning, which is a model-free RL algorithm allowing the robots to find paths autonomously by optimizing their paths and avoiding obstacles. The Q-Learning algorithm provides the possibility of learning optimal policies for the robot through iterative interaction with its environment balanced between exploration and exploitation of the decision process. A reward system is utilized by the proposed model, encouraging the robot to explore shorter, collision-free paths and adjust based on feedback in real time from its surroundings. The model was found to be significantly better than its counterparts. In this context, as indicated, the Q-Learning model runs at 11.5 seconds, faster than A* at 18.3 seconds and Dynamic Programming at 16.7 seconds, yet with an accuracy of 94% and was found to have the highest collision avoidance rate at 98%. Additionally, the adaptability of the model about the environment presents a marked difference in terms of path length optimization, having done so with a mean path length of 12.3, compared to approaches or models. The robustness and scalability of the Q-Learning model make it highly applicable in real-world applications.

关键词： Adaptation models Q-learning Accuracy Navigation Heuristic algorithms Real-time systems Dynamic programming Cognitive robotics Collision avoidance Robots

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：