检索结果-内蒙古大学图书馆

international conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)

作者： Tannmay Gupta Centre for Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

Machine Learning (ML) is used in many Artificial Intelligence (AI) applications to solve the complex problems. Concurrently, conceptual modeling is frequently used to generalize such real-world activities to the appropriate degree of detail, thereby capturing and representing the criteria for creating an effective information system to enable an application. AI is now pervasive in both personal and work lives. this study discusses some real-world risks associated with black-box artificial intelligence, the resulting demand for explainability, and earlier work on Explainable AI (XAI) in data science. Additionally, this study covers the definition of XAI, overall XAI goals, stakeholder categories, and excellence standards for personalized explanations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Homogeneous Multi-robot Patrolling Based on Humanoid Formation Configuration 17th

Homogeneous Multi-robot Patrolling Based on Humanoid Formati...

引用

17th international conference on Intelligent Robotics and Applications

作者： Wang, Fei Wang, Hongrun Zhou, Dianle Wang, Tao Sun Yat Sen Univ Sch Intelligent Syst Engn Shenzhen 518107 Peoples R China Natl Univ Def Technol Coll Adv Interdisciplinary Studies Changsha 410073 Peoples R China

ISBN: (纸本)9789819607730;9789819607747

Multi-robot patrolling is a key feature for various applications related to surveillance and security, and it has been studied from several different perspectives, ranging from techniques that devise optimal off-line strategies to implemented systems. this paper differs from other literature that seeks theoretically optimal patrol strategies. Instead, it focuses on multi-robot formation patrolling and online planning of patrol paths, drawing inspiration from the three-three principle in military tactics. Firstly, a three-vehicle cooperative patrol structure framework based on a leader and followers was constructed using reinforcement learning. Secondly, key technologies such as the reward function for autonomous cooperative formation and formation expansion were designed. the performance of the Adaptive Exploration Rate and e-greedy strategies, as well as the Q-learning and Sarsa algorithms, were studied in a two-dimensional simulation environment within the context of this paper. Finally, the feasibility and effectiveness of the designed three-vehicle formation and its extended formation patrolling were verified through simulations in the Webots environment. this provides a research foundation for multi-autonomous intelligent unmanned cluster formation patrolling, which is also the content of our future research.

关键词： multi-robot patrolling humanoid formation leader and follower reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A smart data holistic approach for context-aware data analytics (AEthER-UA) 42

A smart data holistic approach for context-aware data analyt...

引用

42nd international conference on Conceptual modeling: ER Forum, 7th Symposium on Conceptual modeling Education, SCME 2023, Project Exhibitions, Posters and Demos, and Doctoral Consortium, ER-Companion 2023

作者： Lavalle, Ana Maté, Alejandro Trujillo, Juan Teruel, Miguel A. Díaz, Alexander Sánchez Lucentia Research Group Department of Software and Computing Systems University of Alicante Carretera de San Vicent del Raspeig s/n San Vicent del Raspeig03690 Spain

A smart data holistic approach for context-aware data analytics (AEthER-UA) is one of the four sub-projects, developed in the University of Alicante, being part of the whole project AEthER. this project is being developed by four partners: (i) University of Malaga - Coordinator;(ii) University of Alicante, (iii) University of Castilla La-Mancha, and (iv) University of Seville. the project is funded by the Ministry of Science and Innovation. the main goal of this project is to advance towards a knowledge-based framework integrating novel solutions for data, process and business analytics. the research activities for designing and developing Aether will mainly focus on three main challenges: the characterization of the datasets, the improvement and automation of the algorithms, and the generation of mechanisms to enhance model explainability and interpretation of the results. the project is highly related to data processing, integration, analysis and modeling. More concretely, within the AEthER-UA project, several proposals are being developed for the modeling of user’s requirements for Machine Learning applications, the developing of a framework based on Model Driven Development (MDD) for eXplanable Artificial Intelligence and several approaches for the data bias analysis. © 2023 CEUR-WS. All rights reserved.

关键词： Conceptual modeling Data Bias Data Integration modeling of Machine Learning Applications Smart Data User’s requirements

来源：评论

学校读者我要写书评

暂无评论

Integrating Parametric modeling, BIM, and Building Performance Analysis into Augmented Reality for Architectural Design and Education 23

Integrating Parametric Modeling, BIM, and Building Performan...

引用

7th international conference on Virtual and Augmented Reality Simulations, ICVARS 2023

作者： Alhazzaa, Kifah Yan, Wei Department of Architecture College of Architecture Texas A&m University College StationTX United States The United States and Department of Architecture College of Architecture and Planning Qassim University Qassim Saudi Arabia

ISBN: (纸本)9781450397469

In 2020, about 38% of annual global carbon dioxide emissions come from buildings. Energy-efficient buildings that help mitigate the effects of climate change need a novel strategy to bridge the knowledge gap between construction practitioners and the advancement in building design methodology and environmental analysis. Parameters and forms of the building envelope have a major impact on energy efficiency, and Passive design methods are the most practical and cost-effective means of thermal and energy management in buildings if designed correctly during the preliminary stages. the purpose of this research is to determine whether the current augmented reality (AR) platform can successfully show the potential and significance of parametric design, as well as present a dynamic environmental analysis from the earliest stage of architectural design. In order to enhance the form finding phase of the design process and getting architecture students and professionals aware of the potential of parametric design for design alterations and optimization. the project aims to deliver the subject matter in a clear and engaging manner by the use of AR. In the developed AR app (ParametricAR) users will be able to sense scale, volume, and context, by placing virtual objects in the physical environment. Users will be able to study and evaluate the geometric and spatial design by walking around their building virtually in 1:1 scale. the innovative combination of parametric modeling, BIM, and real-time shadow analysis that was accomplished by ParametricAR served to enhance the user experience and resulted in the production of a package that expanded the user's capacity to develop and assess building forms. ParametricAR was successful in combining parametric modeling, BIM, and shadow analysis into a seamless AR experience that is compatible with the mobile AR hardware that is widely available now. © 2023 Owner/Author.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Modal Analysis and Sound Field modeling of a Permanent Magnet Axial Flux Machine with One Stator and Two Rotors 7

Modal Analysis and Sound Field Modeling of a Permanent Magne...

引用

7th international conference on Environment Friendly Energies and Applications, EFEA 2022

作者： Nikolic, Mateja Ivanovic, Mateja Terzic, Mladen Ristic, Leposava Pavlovic, Dragana Sumarac Bjelic, Milos University of Belgrade School of Electrical Engineering Belgrade Serbia

ISBN: (纸本)9798350333213

there is a potential for increasing torque density, as well as energy efficiency of modern electric vehicle systems by incorporating axial flux machines for certain applications where these characteristics are of interest. High torque density electric machines have inherently worse acoustic behavior, while axial flux machines are still not thoroughly investigated in this area, or produced for mass applications. Single stator double rotor yokeless AFM has a high potential for automotive applications, and has to be investigated in this context, while fulfilling ever-increasing acoustic requirements. the paper presents analytical and model-based considerations of acoustic behavior of an axial flux machine, completed by combining force excitation results obtained by finite element analysis and sound field output from analytical vibratory and acoustic models. © 2022 IEEE.

关键词： Acoustic fields

来源：评论

学校读者我要写书评

暂无评论

Active Learning for Capturing Human Decision Policies in a Data Frugal context 7th

Active Learning for Capturing Human Decision Policies in a D...

引用

7th international conference on Machine Learning, Optimization, and Data Science (LOD) / 1st Symposium on Artificial Intelligence and Neuroscience (ACAIN)

作者： Grossetete, Loic Marois, Alexandre Chatelais, Benedicte Gagne, Christian Lafond, Daniel Enseirb Matmeca Engn Sch Bordeaux France Thales Res & Technol Canada Toronto ON Canada Univ Laval Quebec City PQ Canada

ISBN: (纸本)9783030954703;9783030954697

modeling human expert decision patterns can potentially help create training and decision support systems when no ground truth data is available. A cognitive modeling approach presented herein uses a combination of supervised learning methods to mimic expert strategies. Yet without historical data logs on human expert judgments in a given domain, training machine learning algorithms with new examples to be labelled one by one by human experts can be time-consuming and costly. this paper investigates the use of active learning methods for example selection in policy capturing sessions with an oracle in order to optimize frugal learning efficiency. It also introduces a new hybrid method aimed at improving predictive accuracy based on a better management of the exploration/exploitation tradeoff. Analyses on three datasets evaluated data exploration, data exploitation and finally hybrid methods. Results highlight different tradeoffs of those methods and show the benefits of using a hybrid approach.

关键词： Active learning Frugal learning Policy capturing Cognitive systems engineering Cognitive modeling Decision support

来源：评论

学校读者我要写书评

暂无评论

Predictive Coding and Surprisal Effects on N400 Amplitude: An ERP Study using BERT-Based Language Models in Japanese contexts

Predictive Coding and Surprisal Effects on N400 Amplitude: A...

引用

Biomedical Engineering international conference (BMEiCON)

作者： Yutaro Nakada Hiroyuki Iwata Keiji Iramina Graduate School of Systems Life Sciences Kyushu University Fukuoka Japan Graduate School of Systems Life Sciences School of Interdisciplinary Science and Innovation Kyushu University Fukuoka Japan

ISBN: (数字)9798331505431

ISBN: (纸本)9798331505448

this study aims to reevaluate the role of the N 400 component in language processing from the perspective of predictive coding theory and investigate the impact of surprisal on N400 amplitude. An ERP experiment was conducted using three surprisal conditions (Best Completion, Unrelated, Implausible) with a BERT-based model optimized for Japanese contexts. Analysis of EEG data revealed distinct N400 amplitudes and brain connectivity patterns across the surprisal conditions. Notably, changes in alpha-band phase synchronization reflected cognitive processes related to the degree of mismatch between predicted and actual input in each context. these findings suggest that higher levels of surprisal lead to increased cognitive load, manifesting as dynamic changes in brain network activity.

关键词： Neuroscience Biological system modeling Predictive models Predictive coding Brain modeling Reproducibility of results Synchronization Reliability context modeling Load modeling

来源：评论

学校读者我要写书评

暂无评论

Embracing Subjectivity in Affective Research: Naturalistic and Controlled Settings

Embracing Subjectivity in Affective Research: Naturalistic a...

引用

international conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)

作者： Dominika Kunc Joanna Komoszyńska Stanisław Saganowski Przemysław Kazienko Karen S. Quigley Lisa Feldman Barrett Department of Artifcial Intelligence Wrocław University of Science and Technology Wrocław Poland Department of Psychology Northeastern University Boston MA USA Department of Psychiatry the Martinos Center for Biomedical Imaging Massachusetts General Hospital

ISBN: (数字)9798331516451

ISBN: (纸本)9798331516468

this paper suggests cultivating and modeling individual variation in research on affect and emotion, emphasizing the importance of studying real-world contexts to reveal their individualized nature. We propose a new standard for study design using more flexible and context-aware methods that emphasize modeling of high-dimensional signal arrays within individuals and then inductively learning generalizations rather than presuming their existence. We compare laboratory and real-life settings for the study of affect and emotion and highlight opportunities for studying individual variation structured by context. We discuss current challenges and future directions therein and emphasize the need for interdisciplinary and international collaboration and leveraging new technologies.

关键词： Affective computing Databases Annotations conferences Data collection international collaboration Standards context modeling

来源：评论

学校读者我要写书评

暂无评论

Aspect-Level Sentiment Analysis using Cross Attention Mechanism

Aspect-Level Sentiment Analysis Using Cross Attention Mechan...

引用

international conference on Big Data and Artificial Intelligence (BDAI)

作者： Lei Han Liangbo Jiao Zhan Shi Mengxi Xu School of Computer Engineering Nanjing Institute of Technology Nanjing China Jiangsu Province Engineering Research Center of IntelliSense Technology and System Nanjing Institute of Technology Nanjing China

ISBN: (数字)9798350352009

ISBN: (纸本)9798350352016

Aspect-level sentiment analysis is a challenging task that involves classifying emotions towards specific aspects mentioned in a sentence. Despite notable progress in previous research, this task remains highly complex. the key focus is on effectively encoding semantics and capturing the interaction between aspect items and context. To address these challenges, this paper proposes a novel sentiment classification method called ALSA-CA. By leveraging the BERT model for semantic encoding and incorporating a cross-attention mechanism to model aspect-item-context interactions, our approach demonstrates improved performance. Additionally, we introduce a positional weighting method that considers the relative positions of words and aspect items within sentences. through extensive experiments conducted on three public datasets, we demonstrate the effectiveness of our method compared to current state-of-the-art techniques.

关键词： Sentiment analysis Analytical models Attention mechanisms Semantics Buildings Bidirectional control Big Data Encoding Data models context modeling

来源：评论

学校读者我要写书评

暂无评论

the values and barriers of Building Information modeling (BIM) implementation combination evaluation in smart building energy and efficiency

引用

ENERGY REPORTS 2022年 8卷 96-111页

作者： Chen, Yansheng Cai, Xiaotong Li, Jie Zhang, Weiping Liu, Zhonghao Guangdong Ind Polytech Dept Inst Big Data & Artificial Intelligence Appl Guangzhou 510300 Peoples R China Guangdong Univ Finance Sch Accounting Guangzhou 510150 Peoples R China Guangdong Ind Polytech Sch Finance & Trade Guangzhou 510300 Peoples R China Guangdong Ind Polytech Dept Acad Affairs Guangzhou 510300 Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong 999077 Peoples R China

With the continuous increase in the number of buildings, the phenomenon of excessively high energy consumption becomes more and more serious. It is particularly important to reduce the energy consumption during the operation of the whole life cycle of the building. Building Information modeling (BIM) technology is based on the relevant parameters of construction projects, and uses digital information simulation to establish building information models. It is one of the technical means of building energy consumption analysis and energy saving management, that can be explained as the main reason for stakeholders to guide energy and efficiency changes of the driving factor in buildings. We start co-occurrence statistics and type analysis based on the co-occurrence context analysis, construct the co-occurrence information that affects the values and barriers combination of BIM implementation for smart building energy and efficiency, and chose the expert database of the Green Construction and Intelligent Building Branch (GCIBB) of China Construction Association, that obtained 104 samples through modified snowball sampling, using exploratory factor analysis with factor load linear functions, and combined factor variance contribution rate weights. We created index function of the values and barriers combination of BIM implementation in smart building energy and efficiency, and classified and calculated the comprehensive score of each factor according to the ranking evaluation index, and mapped its practical significance. the results show that the 18 combined evaluation indicators proposed in this paper are suitable for evaluating the three elements of benefit, efficiency and quality of smart buildings, and can achieve continuous optimization of building energy consumption. the constructed multi-factor combination evaluation model, the extracted common factor variance cumulative contribution rate is greater than 80%. (C) 2022 the Author(s). Published by Elsevier Ltd.

关键词： BIM Energy and efficiency the values of BIM implementation the barriers of BIM implementation Combination 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：