检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yang, Siyuan Liu, Jun Lu, Shijian Hwa, Er Meng Kot, Alex C. Rapid-Rich Object Search Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore Singapore Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore Singapore School of Computer Science & Engineering Nanyang Technological University Singapore Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore

One-shot skeleton action recognition, which aims to learn a skeleton action recognition model with a single training sample, has attracted increasing interest due to the challenge of collecting and annotating large-scale skeleton action data. However, most existing studies match skeleton sequences by comparing their feature vectors directly which neglects spatial structures and temporal orders of skeleton data. This paper presents a novel one-shot skeleton action recognition technique that handles skeleton action recognition via multi-scale spatialtemporal feature matching. We represent skeleton data at multiple spatial and temporal scales and achieve optimal feature matching from two perspectives. The first is multi-scale matching which captures the scale-wise semantic relevance of skeleton data at multiple spatial and temporal scales simultaneously. The second is cross-scale matching which handles different motion magnitudes and speeds by capturing sample-wise relevance across multiple scales. Extensive experiments over three large-scale datasets (NTU RGB+D, NTU RGB+D 120, and PKU-MMD) show that our method achieves superior one-shot skeleton action recognition, and outperforms SOTA consistently by large margins. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

DCET-Net: Dual-Stream Convolution Expanded Transformer for Breast Cancer Histopathological Image Classification

DCET-Net: Dual-Stream Convolution Expanded Transformer for B...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Zou, Ying Chen, Shannan Sun, Qiule Liu, Bin Zhang, Jianxin Dalian University Key Lab of Advanced Design and Intelligent Computing Ministry of Education Dalian China Dalian University of Technology School of Information and Communication Engineering Dalian China Dalian China Dalian Minzu University School of Computer Science and Engineering Dalian China

ISBN: (纸本)9781665401265

Researches on breast cancer histopathological image classification have achieved a great breakthrough using deep backbones of Convolutional Neural Networks (CNNs) in recent years. However, due to the inductive bias of locality, CNNs are unable to effectively extract the global feature information of breast cancer histopathological images, limiting the improvement of the classification results. To overcome this shortcoming, this paper reasonably introduces an extra backbone stream of a pure transformer, which consists of a self-attention mechanism to capture global receptive fields of histopathological images, thereby compensating the locality characteristic of CNNs backbone. Based on two backbone streams of CNN and transformer, a dual-stream network called DCET-Net is proposed, which considers local features and global ones simultaneously, and progressively combines them from these two streams to form the final representations for classification. DCET-Net is extensively evaluated on the representative BreakHis histopathological image dataset, and experimental results demonstrate that it is highly competitive with the state-of-the-art CNN methods in breast cancer histopathological image classification task. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

AiGet: Transforming Everyday Moments into Hidden Knowledge Discovery with AI Assistance on Smart Glasses 25

AiGet: Transforming Everyday Moments into Hidden Knowledge D...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Cai, Runze Janaka, Nuwan Kim, Hyeongcheol Chen, Yang Zhao, Shengdong Huang, Yun Hsu, David Synteraction Lab School of Computing National University of Singapore Singapore Singapore Smart Systems Institute Synteraction Lab National University of Singapore Singapore Singapore College of Design and Engineering National University of Singapore Singapore Singapore School of Creative Media Department of Computer Science City University of Hong Kong Hong Kong School of Information Sciences University of Illinois at Urbana-Champaign Champaign IL United States School of Computing Smart Systems Institute National University of Singapore Singapore Singapore

ISBN: (纸本)9798400713941

Unlike the free exploration of childhood, the demands of daily life reduce our motivation to explore our surroundings, leading to missed opportunities for informal learning. Traditional tools for knowledge acquisition are reactive, relying on user initiative and limiting their ability to uncover hidden interests. Through formative studies, we introduce AiGet, a proactive AI assistant integrated with AR smart glasses, designed to seamlessly embed informal learning into low-demand daily activities (e.g., casual walking and shopping). AiGet analyzes real-time user gaze patterns, environmental context, and user profiles, leveraging large language models to deliver personalized, context-aware knowledge with low disruption to primary tasks. In-lab evaluations and real-world testing, including continued use over multiple days, demonstrate AiGet's effectiveness in uncovering overlooked yet surprising interests, enhancing primary task enjoyment, reviving curiosity, and deepening connections with the environment. We further propose design guidelines for AI-assisted informal learning, focused on transforming everyday moments into enriching learning experiences. © 2025 Copyright held by the owner/author(s).

关键词： AI HMD human-ai interaction incidental learning informal learning knowledge discovery large language model multimodal information smart glasses wearable-AI assistance

来源：评论

学校读者我要写书评

暂无评论

A Study on Educational Data Analysis and Personalized Feedback Report Generation Based on Tags and ChatGPT

arXiv

引用

arXiv 2025年

作者： Zhou, Yizhou Zhang, Mengqiao Jiang, Yuan-Hao Gao, Xinyu Liu, Naijie Jiang, Bo School of Design and Engineering National University of Singapore Singapore Lab for Artificial Intelligence for Education East China Normal University China Shanghai Institute of Artificial Intelligence for Education East China Normal University China School of Computer Science and Technology East China Normal University China National Institute of Education Nanyang Technological University Singapore College of Education Science and Technology Zhejiang University of Technology China School of Management Science and Engineering Shandong University of Finance and Economics China

This study introduces a novel method that employs tag annotation coupled with the ChatGPT language model to analyze student learning behaviors and generate personalized feedback. Central to this approach is the conversion of complex student data into an extensive set of tags, which are then decoded through tailored prompts to deliver constructive feedback that encourages rather than discourages students. This methodology focuses on accurately feeding student data into large language models and crafting prompts that enhance the constructive nature of feedback. The effectiveness of this approach was validated through surveys conducted with over 20 mathematics teachers, who confirmed the reliability of the generated reports. This method can be seamlessly integrated into intelligent adaptive learning systems or provided as a tool to significantly reduce the workload of teachers, providing accurate and timely feedback to students. By transforming raw educational data into interpretable tags, this method supports the provision of efficient and timely personalized learning feedback that offers constructive suggestions tailored to individual learner needs. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Mm-Wave to Sub-THz Frequencies for Non-Invasive Melamine Detection in Food Safety

Mm-Wave to Sub-THz Frequencies for Non-Invasive Melamine Det...

引用

IEEE Conference on Antenna Measurements & Applications (CAMA)

作者： Nguyen Ngoc Mai-Khanh Shitaro Takada Keizo Inagaki Ahmad Alkasimi Anh-Vu Pham Akio Higo Bich-Yen Nguyen Tetsuya Kawanishi Systems Design Lab (d.lab) The University of Tokyo Tokyo Japan Faculty of Science and Engineering Waseda University Tokyo Japan National Inst. Of Information and Conmmunications Technology (NICT) Tokyo Japan Department of Electrical and Computer Engineering King Abdulaziz University Jeddah Saudi Arabia Electrical and Computer Engineering University of California Davis California U.S. Soitec France Waseda University Tokyo Japan

This paper presents the exploration of the detection of melamine, a harmful substance, across a wide mm-wave frequency range for food safety applications. The experiment investigates the presence of melamine impurities in rice and milk powders. To conduct the experiment, two different approaches are utilized: a 77-GHz radar approach and a vector network analyzer connected to frequency extenders and standard horn antennas. These approaches cover two frequency bands, namely 220-330 GHz and then 330-500 GHz. The substances involved in the measurements are melamine, milk, rice, and their mixtures. In addition, we propose a technique for the quantitative determination of melamine in mixtures. This method was validated through measurements taken mm-wave frequency range. The results demonstrate the feasibility of determining melamine concentrations in mixtures across diverse mm-wave and sub-THz frequency bands.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Unfolding Neural Networks for Fluid Antenna-Enhanced Vehicular Communication

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Feng, Biqian Feng, Chenyuan Wong, Kai-Kit Quek, Tony Q. S. University of Macau State Key Laboratory of Internet of Things for Smart City The Department of Computer and Information Science China EURECOM Sophia Antipolis 06410 France University College London Department of Electronic and Electrical Engineering Torrington Place WC1E 7JE United Kingdom Yonsei University Yonsei Frontier Lab Seoul Korea Republic of Singapore University of Technology and Design Information Systems Technology and Design Pillar Singapore487372 Singapore

Fluid antenna (FA) technology has emerged as a promising technology to achieve higher spectral and energy efficiency by introducing a new dimension. However, the antenna position configuration inevitably increases computational complexity, presenting challenges under real-time configuration requirements, especially in vehicular communication systems characterized by rapidly time-varying channels. To address these issues, this paper investigates the classical weighted sum rate maximization problem and proposes an optimization-empowered neural network framework designed to accelerate convergence without compromising accuracy. Extensive simulations demonstrate that the proposed approach effectively mitigates the computational burdens associated with FAs, delivering superior performance in terms of convergence rate and system performance, thus paving the way for the deployment of next-generation FA-enabled communication systems. © 2025 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization

arXiv

引用

arXiv 2023年

作者： Yang, Siyuan Liu, Jun Lu, Shijian Hwa, Er Meng Hu, Yongjian Kot, Alex C. The Rapid-Rich Object Search Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore The Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore The School of Computer Science & Engineering Nanyang Technological University Singapore The School of Electrical and Electronic Engineering Nanyang Technological University Singapore The South China University of Technology Guangzhou China

3D Skeleton-based human action recognition has attracted increasing attention in recent years. Most of the existing work focuses on supervised learning which requires a large number of labeled action sequences that are often expensive and time-consuming to annotate. In this paper, we address self-supervised 3D action representation learning for skeleton-based action recognition. We investigate self-supervised representation learning and design a novel skeleton cloud colorization technique that is capable of learning spatial and temporal skeleton representations from unlabeled skeleton sequence data. We represent a skeleton action sequence as a 3D skeleton cloud and colorize each point in the cloud according to its temporal and spatial orders in the original (unannotated) skeleton sequence. Leveraging the colorized skeleton point cloud, we design an auto-encoder framework that can learn spatial-temporal features from the artificial color labels of skeleton joints effectively. Specifically, we design a two-steam pretraining network that leverages fine-grained and coarse-grained colorization to learn multi-scale spatial-temporal features. In addition, we design a Masked Skeleton Cloud Repainting task that can pretrain the designed auto-encoder framework to learn informative representations. We evaluate our skeleton cloud colorization approach with linear classifiers trained under different configurations, including unsupervised, semi-supervised, fully-supervised, and transfer learning settings. Extensive experiments on NTU RGB+D, NTU RGB+D 120, PKU-MMD, NW-UCLA, and UWA3D datasets show that the proposed method outperforms existing unsupervised and semi-supervised 3D action recognition methods by large margins and achieves competitive performance in supervised 3D action recognition as well. Copyright © 2023, The Authors. All rights reserved.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

Short-Term Time Series State of Charge Prediction in Electric Vehicle LGM50 Batteries: A Rolling Forecasting Approach

Short-Term Time Series State of Charge Prediction in Electri...

引用

International Conference on Sensing Technology, ICST

作者： Zeyang Zhou Angelo Greco Fenix Huang Karthick Thiyagarajan Jun Li Mukesh Prasad Faulty of Engineering and Information Technology School of Computer Science University of Technology Sydney Australia Clarios Varta Hannover GmbH Hannover Germany KERF Technology Limited Taipei Taiwan Smart Sensing and Robotics Laboratory (SensR Lab) Centre for Advanced Manufacturing Technology School of Engineering Design and Built Environment Western Sydney University Penrith NSW Australia

ISBN: (数字)9798350374827

ISBN: (纸本)9798350374834

The prediction of the state of charge (SOC) for battery management systems has become increasingly important with the rapid growth of the electric vehicle industry. Traditional methods for SOC prediction often depend on extensive historical data from vehicles, which can be unreliable due to various uncontrollable factors such as driving behavior, weather, and road conditions. To overcome these limitations, we propose a rolling forecasting model that leverages month-by-month data from electric vehicles to predict the SOC for the subsequent month. This approach to short-term SOC prediction aims to enhance intelligent mechatronic monitoring systems, enabling the delivery of personalized driving and charging strategies to customers.

关键词： Mechatronics Roads Time series analysis Battery management systems Predictive models Electric vehicles State of charge Forecasting Monitoring Meteorology

来源：评论

学校读者我要写书评

暂无评论

Analysis of Age of Information for A Discrete-time Dual-Queue System

arXiv

引用

arXiv 2024年

作者： Chen, Zhengchuan Qu, Yi Pappas, Nikolaos Tang, Chaowei Wang, Min Quek, Tony Q.S. School of Microelectronics and Communication Engineering Chongqing University Chongqing China Department of Computer and Information Science Linköping University Linköping58183 Sweden School of Optoelectronics Engineering Chongqing University of Posts and Telecommunications Chongqing China Singapore University of Technology and Design Singapore487372 Singapore Yonsei Frontier Lab Yonsei University Korea Republic of

Using multiple sensors to update the status process of interest is promising in improving the information freshness. The unordered arrival of status updates at the monitor end poses a significant challenge in analyzing the timeliness performance of parallel updating systems. This work investigates the age of information (AoI) of a discrete-time dual-sensor status updating system. Specifically, the status update is generated following the zero-waiting policy. The two sensors are modeled as a geometrically distributed service time queue and a deterministic service time queue in parallel. We derive the analytical expressions for the average AoI and peak AoI using the graphical analysis method. Moreover, the connection of average AoI between discrete-time and continuous-time systems is also explored. It is shown that the AoI result of the continuous-time system is a limit case of that of the corresponding discrete-time system. Hence, the AoI result of the discrete-time system is more general than the continuous one. Numerical results validate the effectiveness of our analysis and further show that randomness of service time contributes more AoI reduction than determinacy of service time in dual-queue systems in most cases, which is different from what is known about the single-queue system. © 2024, CC BY.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Automated Segmentation of Fiber Breaks in Advanced Composites 38

Deep Learning-Based Automated Segmentation of Fiber Breaks i...

引用

38th Technical Conference of the American Society for Composites, ASC 2023

作者： Jain, Sudhir Li, Carina Xiaochen Vuong, Daniel McGllick, Matthew Saifaee, Saeed Furtado, Carolina Kopp, Reed Joseph, Joshua Adjodah, Dhaval Rosini, Sebastian Sinclair, Ian Spearing, S. Mark Wardle, Brian L. Integrated Design and Management Program Massachusetts Institute of Technology CambridgeMA02139 United States Department of Aeronautics and Astronautics Massachusetts Institute of Technology CambridgeMA02139 United States Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology CambridgeMA02139 United States MIT Media Lab Massachusetts Institute of Technology CambridgeMA02139 United States Department of Mechanical Engineering University of Southampton SouthamptonSO17 1BJ United Kingdom Departments of Aeronautics and Astronautics and Mechanical Engineering Massachusetts Institute of Technology CambridgeMA02139 United States

ISBN: (纸本)9781605956916

The heterogeneity of the microstructure and the anisotropy of the mechanical properties of carbon fiber reinforced polymer composites (CFRP) are associated with complex damage mechanisms that make failure prediction highly challenging. Typical damage mechanisms for CFRP include: (i) interlaminar cracking (delamination), (ii) matrix cracking, and (iii) fiber breakage. X-ray computed tomography (CT) has been utilized recently to identify the complex damage in progressive failure of CFRP in 3D and 4D (3D spatial and 1D temporal). However, these scans contain a large amount of data (≈10 GB/mm3), which makes it challenging to extract mechanistic insights in a reasonable time frame. In previous work, we presented the first deep learning (DL) convolutional neural network (CNN) segmentation of multiclass microscale matrix damage in CFRP. The trained CNN segments complex and sparse composite matrix damage mechanism to ≈ 99.99% agreement, with nearly 100% of human time eliminated, providing higher accuracy compared to human segmentation. In this work, we developed CNN-based method for the automated segmentation of fiber breaks using synchrotron radiation-based CT (SRCT) scans that have been human-labeled. The model employed a U-Net full CNN as the high-level encoder (feature extraction)-decoder (feature localization) structure, and VGG16 as the deep CNN backbone via the publicly available Segmentation Models GitHub repository. An unbiased evaluation was performed comparing the machine vs. the human-labeled ground truth. Finally, active learning was presented for the machine-assisted relabeling of datasets containing fiber breaks. The deep learning-based automated segmentation method demonstrated accurate identification (> 90%) of fiber breakage for CFRP. © 2023 by DEStech Publications, Inc. and American Society for Composites. All rights reserved.

关键词： Complex networks

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：