检索结果-内蒙古大学图书馆

14th International Space Syntax Symposium, SSS 2024

作者： Mara, Federico Altafini, Diego Hacar, Özge Öztürk Hacar, Müslüm Gülgen, Fatih Cutini, Valerio Department of Energy Systems Territory and Construction Engineering University of Pisa Italy Welsh School of Architecture Cardiff University United Kingdom Department of Geomatic Engineering Yildiz Technical University Turkey Knowledge Discovery and Data Mining Laboratory ISTI-CNR Italy Department of Energy Systems Territory and Construction Engineering University of Pisa Italy

ISBN: (纸本)9791256690329

The Space Syntax theoretical framework sustains that the urban spaces’ configuration possesses intrinsic information which allows to model and foresee patterns of human movement and social interaction. Critics argue, however, that there are several factors beyond configuration that influence pedestrian behaviour. In particular, critics focus on the absence of the temporal component by saying that, while Space Syntax can reveal systemic logics, it cannot depict the actual time-dependent movement variation in micro-urban scales and their causes. Nevertheless, if accounted pedestrian flows maintain their hierarchies over time and those coincide with the street hierarchies denoted by Space Syntax, this would reinforce the role of the configurational component in movement. Given this premise, the paper discusses pedestrian flow data and Visibility Graph Analysis in Piazza delle Vettovaglie, Pisa (Italy), to assess: a) if pedestrian flows hierarchy actually changes, by comparing people counts registered in different timestamps, along three days, at different access gates;b) if different Space Syntax metrics express the same gate hierarchy;c) if-and-how the modelled and real hierarchies differ from each other. This discussion aims to unveil the role of time in micro-urban spaces usage, and provide a first answer to the question: do changes in pedestrian movement across time follow the configurational hierarchy established with Space Syntax? Results inform that despite changing in flows, the hierarchy proved rather regular across time, thus confirming the Space Syntax premises and the role of configurational component in movement. © 14th International Space Syntax Symposium, SSS 2024.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

HUSS:A Heuristic Method for Understanding the Semantic Structure of Spreadsheets

引用

data Intelligence 2023年第3期5卷 537-559页

作者： Xindong Wu Hao Chen Chenyang Bu Shengwei Ji Zan Zhang Victor S.Sheng Key Laboratory of Knowledge Engineering with Big Data(the Ministry of Education of China) Hefei University of TechnologyChinaSchool of Computer Science and Information EngineeringHefei University of TechnologyHefeiChina Research Institute of Artificial Intelligence Zhejiang LabHangzhouChina Department of Computer Science Texas Tech UniversityLubbockTX 79409USA

Spreadsheets contain a lot of valuable data and have many practical *** key technology of these practical applications is how to make machines understand the semantic structure of spreadsheets,e.g.,identifying cell function types and discovering relationships between cell *** existing methods for understanding the semantic structure of spreadsheets do not make use of the semantic information of cells.A few studies do,but they ignore the layout structure information of spreadsheets,which affects the performance of cell function classification and the discovery of different relationship types of cell *** this paper,we propose a Heuristic algorithm for Understanding the Semantic Structure of spreadsheets(HUSS).Specifically,for improving the cell function classification,we propose an error correction mechanism(ECM)based on an existing cell function classification model[11]and the layout features of *** improving the table structure analysis,we propose five types of heuristic rules to extract four different types of cell pairs,based on the cell style and spatial location *** experimental results on five real-world datasets demonstrate that HUSS can effectively understand the semantic structure of spreadsheets and outperforms corresponding baselines.

关键词： Spreadsheet semantic structure Information extraction Heuristics Cell function analysis Table structure analysis

来源：评论

学校读者我要写书评

暂无评论

M2G4RTP: A Multi-Level and Multi-Task Graph Model for Instant-Logistics Route and Time Joint Prediction 39

M2G4RTP: A Multi-Level and Multi-Task Graph Model for Instan...

引用

39th IEEE International Conference on data engineering, ICDE 2023

作者： Cai, Tianyue Wan, Huaiyu Wu, Fan Wen, Haomin Guo, Shengnan Wu, Lixia Hu, Haoyuan Lin, Youfang Beijing Jiaotong University School of Computer and Information Technology Beijing China Cainiao Network Artificial Intelligence Department Hangzhou China Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing China

ISBN: (纸本)9798350322279

Instant-logistics (e.g., food delivery and package pick-up) is increasingly calling for Route and Time Prediction (RTP), which aims to predict both future route and arrival time of a courier's unvisited locations. Accurate RTP can greatly benefit the platform, such as optimizing order dispatching and improving user experience. Although recent years have witnessed various works for solving the RTP problem, they still suffer from the following three limitations: i) Failing to consider the high-level transfer mode of couriers between AOIs (Areas Of Interest, such as residential quarters or office buildings), which can help to build more accurate RTP. ii) Failing to simultaneously make the route and time prediction. Existing works either separately predict route/time or predict them in a two-step way. However, since route and time are strongly correlated (nearby locations in the route should have similar arrival times), jointly predicting them should be more effective. iii) The widely adopted tree-based or sequence-based architecture fails to fully encode the spatial relationship between different locations. To address the above limitations, we propose a multi-level and multi-task graph model, named M2G4RTP, for instant-logistics route and time joint prediction. Specifically, we propose a multi-level graph encoder equipped with a newly-designed GAT-e encoding module to capture couriers' both high-level transfer modes between AOIs and low-level transfer modes between locations. Moreover, a multi-task decoder is presented to jointly predict the route and time at different levels. Finally, a loss weighting method based on homoscedastic uncertainty is designed to balance the two tasks adaptively. Extensive experiments on an industry-scale real-world dataset, as well as the online deployment on Cainiao Alibaba, demonstrate the superiority of our proposed model. © 2023 IEEE.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

An Efficient Multilevel Threshold Image Segmentation Approach Based on Rafflesia Optimization Algorithm 1

引用

18th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2022

作者： Zhou, Jin-Liang Chu, Shu-Chuan Weng, Shaowei Zheng, Wei-Min College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China College of Science and Engineering Flinders University Adelaide Australia Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China

ISBN: (数字)9789819901050

ISBN: (纸本)9789819901043

Segmentation is an important step from image processing to analysis. The thresholding technique based on entropy has become one of the most commonly used techniques in this field. Among the many thresholding techniques based on entropy, the minimum cross-entropy threshold (MCET) has been dramatically developed. The key to multilevel MCET technology is quickly finding the optimal threshold point. MCET is a relatively time-consuming technique, so we use optimization techniques to search for optimal multilevel thresholds. Rafflesia optimization algorithm (ROA) is an optimization algorithm inspired by rafflesia growth theory to solve real-world multi-parameter optimization problems. In this paper, Rafflesia optimization algorithm, particle swarm optimization, gray wolf optimization, whale optimization algorithm, and multi-version optimizer are used to segment six images and the peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and feature similarity index (FSIM) as evaluation metrics. The experimental results show that the ROA algorithm can achieve higher-quality image segmentation. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Are LLMs Aware that Some Questions are not Open-ended?

Are LLMs Aware that Some Questions are not Open-ended?

引用

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

作者： Yang, Dongjie Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

ISBN: (纸本)9798891761681

Large Language Models (LLMs) have shown the impressive capability of answering questions in a wide range of scenarios. However, when LLMs face different types of questions, it is worth exploring whether LLMs are aware that some questions have limited answers and need to respond more deterministically but some do not. We refer to this as question awareness of LLMs. The lack of question awareness in LLMs leads to two phenomena that LLMs are: (1) too casual to answer non-open-ended questions or (2) too boring to answer open-ended questions. In this paper, we first evaluate the question awareness in LLMs. The experimental results show that LLMs have the issues of lacking awareness of questions in certain domains, e.g. factual knowledge, resulting in hallucinations during the generation. To mitigate these, we propose a method called Question Awareness Temperature Sampling (QuATS). This method enhances the question awareness of LLMs by adaptively adjusting the output distributions based on question features. The automatic adjustment in QuATS eliminates the need for manual temperature tuning in text generation and consistently improves model performance in various benchmarks. © 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

An Effective Implementation of Detection and Retrieval Property of Episodic Memory 6

An Effective Implementation of Detection and Retrieval Prope...

引用

6th International Conference on Advances in Artificial Intelligence, ICAAI 2022

作者： Sharma, Aniket Singh, Pramod Kumar Prakash, Jay Computational Intelligence and Data Mining Research Laboratory ABV-Indian Institute of Information Technology and Management Gwalior India Department of Computer Science and Engineering National Institute of Technology Calicut India

ISBN: (纸本)9781450396943

A deep understanding of the brain can lead to significant breakthroughs in Artificial Intelligence. Many researchers concentrate their efforts on simulating the human mind to comprehend its complexities better. With the intention of better understanding the episodic memory aspect of the human mind, we propose a deep learning model to implement the detection and retrieval properties of human episodic memory, a part of long-term memory. A model based on LSTM and CNN is proposed, which follows the architectural methodology of Rosenblatt's experiential memory model. A comparison of detection efficiency and accuracy and the proposed model's retrieval property with a recently suggested method demonstrate its effectiveness and superiority. © 2022 Association for Computing Machinery.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impact of Security Measures on Wi-Fi Quality of Service 2

Analyzing the Impact of Security Measures on Wi-Fi Quality o...

引用

2nd International Conference on Artificial Intelligence, Blockchain, and Internet of Things, AIBThings 2024

作者： Kopcho, Thomas J. Fouda, Mostafa M. Krome, Cameron J. Quach, Anna T. Olaveson, Israel G. Idaho State University Department of Computer Science PocatelloID United States Idaho State University Department of Electrical and Computer Engineering PocatelloID United States Ai Data & Visualization Idaho National Laboratory Idaho FallsID United States

ISBN: (纸本)9798331529529

This study examines the relationship between Quality of Service (QoS) and security in Wi-Fi networks. Using a detailed dataset consisting of QoS metrics of file transfers under various security configurations, we analyze the impact of these settings on network performance. Our findings provide a quantification to accurately show that different encryption protocols, such as TKIP and CCMP, significantly affect QoS, with disabling security generally improving performance. The study provides a framework for optimizing security settings to enhance both security and QoS in future wireless networks. © 2024 IEEE.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

A Lightweight AI Model for Anomaly Detection in Wireless Networks 2

A Lightweight AI Model for Anomaly Detection in Wireless Net...

引用

2nd International Conference on Artificial Intelligence, Blockchain, and Internet of Things, AIBThings 2024

作者： Kopcho, Thomas J. Fouda, Mostafa M. Krome, Cameron J. Idaho State University Department of Computer Science PocatelloID United States Idaho State University Department of Electrical and Computer Engineering PocatelloID United States Idaho National Laboratory Ai Data & Visualization Idaho FallsID United States

ISBN: (纸本)9798331529529

Detecting network anomalies is critical for wireless network security and reliability. Traditional AI methods often require substantial computational resources, particularly when deployed on cloud servers, leading to increased network load and latency. In contrast, deploying AI models directly on end devices enables real-time data processing at the source, facilitating faster anomaly detection and mitigation. We propose a lightweight hierarchical AI model where initial inferences are made by a simple model and outputs confidence scores. Using a modified TOPSIS-based method, we determine an optimal confidence score threshold. Inferences below this threshold are forwarded to a more complex model for accurate analysis, reducing overall computational demands while maintaining high detection performance. Our approach is tested on a 5 G network dataset, demonstrating competitive performance compared to other anomaly detection models. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Balancing Usability and Security Innovative Approaches to Privacy in Digital Environments

Balancing Usability and Security Innovative Approaches to Pr...

引用

2024 International Conference on Communication, computer Sciences and engineering, IC3SE 2024

作者： Baswaraju, Swathi Yadav, M. Geeta Nijhawan, Ginni Rana, Ajay Rani, T. K. Pushpa Al-Rubaye, Taqi Mohammed Khattab New Horizon College Of Engineering Department Of Computer Science - Data Science Bangalore India Institute Of Aeronautical Engineering Department Of Computer Science And Engineering Telangana Hyderabad India Lovely Professional University Phagwara India Amity School Of Engineering And Technology Amity University Greater Noida India Mlr Institute Of Technology Department Of Computer Science And Engineering Telangana Hyderabad India College Of Medical Technologies The Islamic University Department Of Medical Laboratory Technology Najaf Iraq

ISBN: (纸本)9798350366846

data analysis, private protection, detecting unusual things, identifying people, and transferring data are part of the study's unique security design. The major system method is AUA. Your authentication level depends on your activity, device, and location. Context-aware Privacy uses AUA to tailor user privacy options. Encrypting AES data transfers with Secure data Transfer (SDT) is offered. Machine learning anomaly detection (ADML) analyzes user behavior and implements security measures to uncover vulnerabilities rapidly. DPDA employs controlled noise to make it statistically tougher to identify a person while processing data to safeguard privacy. Ablation study indicates adaptive security design strategies function better together. The recommended design may be safer and easier to employ with visual models and performance testing. With this knowledge, managers may be able to create business-friendly security solutions. Finally, the framework's extensive and adaptable security models boost digital safety. It offers new privacy protection in the internet age. © 2024 IEEE.

关键词： data Analytics

来源：评论

学校读者我要写书评

暂无评论

Previs-Real:Interactive virtual previsualization system for news shooting rehearsal and evaluation

引用

虚拟现实与智能硬件（中英文） 2024年第6期6卷 527-549页

作者： Che QU Shaocong WANG Chao ZHOU Tongchen ZHAO Rui GUO Cheng Wa WONG Chi DENG Bin JI Yuhui WEN Yuanchun SHI Yong-Jin LIU Department of Film and Television Technology Beijing Film AcademyBeijing 100088China Department of Computer Science and Technology MOE-Key Laboratory of Pervasive ComputingTsinghua UniversityBeijing 100084China School of Social Sciences Tsinghua UniversityBeijing 100084China News Production and Broadcasting First Division China Media GroupBeijing 100038China School of Computer and Information Technology Bejing Jiaotong UniversityBejing 100044China Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong UniversityBeijing 100044China

Background In the demanding field of live news broadcasting,the intricate studio production procedures and tight schedules pose significant challenges for physical rehearsals by *** paper explores the design and implementation of a lightweight virtual news previsualization system,leveraging virtual production technology and interaction design methods to address the lack of fidelity in presentations and manipulations,and the quantitative feedback of rehearsal effects in previous virtual *** Our system,Previs-Real,is informed by user investigation with professional cameramen and studio technicians,and adheres to principles of high fidelity,accurate replication of actual hardware operations,and real-time feedback on rehearsal *** system's software and hardware development are implemented based on Unreal Engine and accompanying toolsets,incorporating cutting-edge modeling and camera calibration *** We validated Previs-Real through a user study,demonstrating superior performance in previsualization shooting tasks using the virtual system compared to traditional camera *** findings,supported by both objective performance metrics and subjective responses,underline Previs-Real's effectiveness and potential in transforming news broadcasting *** Previs-Real eliminates the requirement for complex equipment interconnections and team coordination inherent in a physical studio by implementing methodologies complying the above principles,objectively resulting in a lightweight design of applicable version of virtual news previsualization *** offers a novel solution to the challenges in news studio previsualization by focusing on key operational features rather than full environment *** design approach is equally effective in the process of designing lightweight systems in other fields.

关键词： News broadcast Previsualization Human computer interaction design User-centered design Interface evaluation

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：