检索结果-内蒙古大学图书馆

2nd International Conference on Interactive Media, Smart Systems and Emerging Technologies, IMET 2022

作者： Souza, Adriana Freitas, Diamantino Bahia Federal Institute of Education Science and Technology Bahia Brazil Doctoral Program in Digital Media Faculty of Engineering of the University of Porto Porto Portugal Faculty of Engineering of the University of Porto Speech Processing Laboratory Electrical and Computer Engineering Department Porto Portugal

ISBN: (数字)9781665470162

ISBN: (纸本)9781665470162

Being one essential part of the solutions we are developing to provide accessibility for blind persons, synthesized speech of mathematical content, although having evolved in naturalness in recent years, still keeps a characteristic of generating very long outputs, which makes it difficult for a person who uses a screen reader to memorize. Eye-gaze tracking has been useful for studying cognitive processes and student's effort in performing tasks therefore it seems attractive as a means to understand how people analyze, process, and break down extensive math expressions into smaller ones. This understanding can help to build a similar model of auditory rendering of MathML capable of avoiding cognitive overload. Therefore, we carried out an experiment to do a gaze-based analysis of reading and memorizing mathematical expressions. Our sample consisted of fourteen participants, and seven mathematical expressions were used in the experiment. The results showed that the computed complexity of the expressions and the average duration of eye-gaze fixations have a strong and significant relationship. Therefore, we conclude that the complexity variable must always be considered in the speech synthesis process of mathematical expressions. However, when considering why participants requested the repetition of an expression with not larger complexity during the memorization process, a tentative interpretation based on the number of MathML tree nodes and the computed complexity of the expressions was not enough to explain it, indicating that other factors need to be investigated. Although some answers to the research questions were not yet conclusive, we consider this research relevant because it points to directions for the work in order to minimize the cognitive processing and mental load of the synthesized speech rendering of mathematical expressions. © 2022 IEEE.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

On the Generalization of Machine-Learning-aided QoT Estimation in Optical Networks 32

On the Generalization of Machine-Learning-aided QoT Estimati...

引用

32nd Wireless and Optical Communications Conference, WOCC 2023

作者： Gao, Hanyu Zhang, Liang Zhang, Bin Chen, Xiaoliang Li, Zhaohui School of Electronics and Information Technology Sun Yat-sen University Guangdong Provincial Key Labratory of Optoelectronic Information Processing Chips and Systems Guangzhou China Southern Marine Science and Engineering Guangdong Laboratory Zhuhai China George Mason University Department of Electrical and Computer Engineering FairfaxVA22030 United States

ISBN: (纸本)9798350337150

This paper presents a composable machine learning method for generalizing the quality-of-transmission (QoT) metric estimation in optical networks. The composable machine learning approach characterizes this metric for lightpaths of arbitrary lengths by compositions of launch, propagation and readout modules. Results verify the feasibility of the design and show its successful application in facilitating autonomous lightpath provisioning. © 2023 IEEE.

关键词： Fiber optic networks

来源：评论

学校读者我要写书评

暂无评论

EXLM: Rethinking the Impact of [MASK] Tokens in Masked Language Models

arXiv

引用

arXiv 2025年

作者： Zheng, Kangjie Yang, Junwei Liang, Siyue Feng, Bin Liu, Zequn Ju, Wei Xiao, Zhiping Zhang, Ming School of Computer Science National Key Laboratory for Multimedia Information Processing Peking University Anker Embodied AI Lab Peking University China Shenzhen China College of Computer Science Sichuan University Chengdu China Computer Science and Engineering Department University of Washington United States

Masked Language Models (MLMs) have achieved remarkable success in many self-supervised representation learning tasks. MLMs are trained by randomly masking portions of the input sequences with [MASK] tokens and learning to reconstruct the original content based on the remaining context. This paper explores the impact of [MASK] tokens on MLMs. Analytical studies show that masking tokens can introduce the corrupted semantics problem, wherein the corrupted context may convey multiple, ambiguous meanings. This problem is also a key factor affecting the performance of MLMs on downstream tasks. Based on these findings, we propose a novel enhanced-context MLM, EXLM. Our approach expands [MASK] tokens in the input context and models the dependencies between these expanded states. This enhancement increases context capacity and enables the model to capture richer semantic information, effectively mitigating the corrupted semantics problem during pre-training. Experimental results demonstrate that EXLM achieves significant performance improvements in both text modeling and SMILES modeling tasks. Further analysis confirms that EXLM enriches semantic representations through context enhancement, and effectively reduces the semantic multimodality commonly observed in MLMs. © 2025, CC BY-NC-SA.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Wearable and interactive multicolored photochromic fiber display

引用

Light(Science & Applications) 2024年第3期13卷 454-465页

作者： Pan Li Yuwei Wang Xiaoxian He Yuyang Cui Jingyu Ouyang Ju Ouyang Zicheng He Jiayu Hu Xiaojuan Liu Hang Wei Yu Wang Xiaoling Lu Qian Ji Xinyuan Cai Li Liu Chong Hou Ning Zhou Shaowu Pan Xiangru Wang Huamin Zhou Cheng-Wei Qiu Yan-Qing Lu Guangming Tao State Key Laboratory of Material Processing and Die&Mould Technology School of Materials Science and Engineering and Wuhan National Laboratory for OptoelectronicsHuazhong University of Science and TechnologyWuhan 430074China Key Laboratory of Vascular Aging(HUST) Ministry of EducationWuhan 430030China School of Optoelectronic Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore National Laboratory of Solid State Microstructures Key Laboratory of Intelligent Optical Sensing and ManipulationCollege of Engineering and Applied Sciencesand Collaborative Innovation Center of Advanced MicrostructuresNanjing UniversityNanjing 210023China School of Performing Arts Wuhan Conservatory of MusicWuhan 430060China School of Mechanical Science and Engineering Huazhong University of Science and TechnologyWuhan 430074China School of Architecture and Urban Planning Huazhong University of Science and TechnologyWuhan 430074China School of Fashion Beijing Institute of Fashion TechnologyBeijing 100029China School of Optical and Electronic Information Huazhong University of Science and TechnologyWuhan 430074China Tongji Medical College Huazhong University of Science and TechnologyWuhan 430074China State Key Laboratory for Modification of Chemical Fibers and Polymer Materials College of Materials Science and EngineeringDonghua UniversityShanghai 201620China

Endowing flexible and adaptable fiber devices with light-emitting capabilities has the potential to revolutionize the current design philosophy of intelligent,wearable interactive ***,significant challenges remain in developing fiber devices when it comes to achieving uniform and customizable light effects while utilizing lightweight ***,we introduce a mass-produced,wearable,and interactive photochromic fiber that provides uniform multicolored light *** designed independent waveguides inside the fiber to maintain total internal reflection of light as it traverses the *** impact of excessive light leakage on the overall illuminance can be reduced by utilizing the saturable absorption effect of fluorescent materials to ensure light emission uniformity along the transmission *** addition,we coupled various fluorescent composite materials inside the fiber to achieve artificially controllable spectral radiation of multiple color systems in a single *** prepared fibers on mass-produced kilometer-long using the thermal drawing *** fibers can be directly integrated into daily wearable devices or clothing in various patterns and combined with other signal input components to control and display patterns as *** work provides a new perspective and inspiration to the existing field of fiber display interaction,paving the way for future human–machine integration.

关键词： fiber interactive colored

来源：评论

学校读者我要写书评

暂无评论

VoroNav: voronoi-based zero-shot object navigation with large language model 24

VoroNav: voronoi-based zero-shot object navigation with larg...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Pengying Wu Yao Mu Bingxian Wu Yi Hou Ji Ma Shanghang Zhang Chang Liu Department of Advancded Manufacturing and Robotics College of Engineering Peking University Beijing China The University of Hong Kong and OpenGVLab Shanghai AI Laboratory National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Beijing China

In the realm of household robotics, the Zero-Shot Object Navigation (ZSON) task empowers agents to adeptly traverse unfamiliar environments and locate objects from novel categories without prior explicit training. This paper introduces VoroNav, a novel semantic exploration framework that proposes the Reduced Voronoi Graph to extract exploratory paths and planning nodes from a semantic map constructed in real time. By harnessing topological and semantic information, VoroNav designs text-based descriptions of paths and images that are readily interpretable by a large language model (LLM). In particular, our approach presents a synergy of path and farsight descriptions to represent the environmental context, enabling LLM to apply commonsense reasoning to ascertain waypoints for navigation. Extensive evaluation on HM3D and HSSD validates VoroNav surpasses existing benchmarks in both success rate and exploration efficiency (absolute improvement: +2.8% Success and +3.7% SPL on HM3D, +2.6% Success and +3.8% SPL on HSSD). Additionally introduced metrics that evaluate obstacle avoidance proficiency and perceptual efficiency further corroborate the enhancements achieved by our method in ZSON planning. Project page: https://***

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Belief Propagation Approach for Direct Multipath-Based SLAM

A Belief Propagation Approach for Direct Multipath-Based SLA...

引用

Asilomar Conference on Signals, Systems & computers

作者： Mingchao Liang Erik Leitinger Florian Meyer Department of Electrical and Computer Engineering University of California San Diego USA Signal Processing and Speech Communication Laboratory Graz University of Technology Austria

In this work, we develop a multipath-based simultaneous localization and mapping (SLAM) method that can directly be applied to received radio signals. In existing multipath-based SLAM approaches, a channel estimator is used as a preprocessing stage that reduces data flow and computational complexity by extracting features related to multipath components (MPCs). We aim to avoid any preprocessing stage that may lead to a loss of relevant information. The presented method relies on a new statistical model for the data generation process of the received radio signal that can be represented by a factor graph. This factor graph is the starting point for the development of an efficient belief propagation (BP) method for multipath-based SLAM that directly uses received radio signals as measurements. Simulation results in a realistic scenario with a single-input single-output (SISO) channel demonstrate that the proposed direct method for radio-based SLAM outperforms state-of-the-art methods that rely on a channel estimator.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fire Security Systems Analysis and Internet of Things Implications

Fire Security Systems Analysis and Internet of Things Implic...

引用

IEEE International Conference on Electro-Information Technology

作者： Susana Rodriguez Fuerte Xinrui Yu Jafar Saniie Department of Electrical and Computer Engineering Embedded Computing and Signal Processing Research Laboratory Illinois Institute of Technology Chicago IL U.S.A.

This paper presents the current use of the Internet of Things (IoT) in fire evacuation and extinction. It examines the different approaches to the problem and technologies like Building Information Modeling (BIM) and mathematical algorithms that can be used to determine the optimal evacuation route. It also evaluates existing fire security solutions such as smoke, flame, motion, and gas sensors, LED lights, buzzers, and SMS modules. Entities that specialize in Residential and Commercial Security Systems and Home Automation are also discussed, along with the services they offer. The main objective of this study is to understand current systems and resources regarding fire evacuation and extinction systems and to analyze different developments in smart buildings to create an efficient system for fire detection and evacuation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Point Cloud Generation with Stereo and Monocular Depth Estimation on FPGA

Point Cloud Generation with Stereo and Monocular Depth Estim...

引用

2022 IEEE International Conference on Electro Information Technology, eIT 2022

作者： Perez-Vicente, Alejandro Hernandez, David Fang, Tianyang Saniie, Jafar Illinois Institute of Technology Embedded Computing and Signal Processing Department of Electrical and Computer Engineering Research Laboratory ChicagoIL60616 United States Universidad Politécnica de Madrid Etsi Industriales Madrid Spain

ISBN: (纸本)9781665480093

This research proposes a system that leverages stereo vision and monocular depth estimation to form a depth map from which a 3D point cloud scene is extracted. The emergence of competitive neural networks for depth map estimation presents an opportunity for deployment on embedded systems. Both stereo and monocular depth algorithms were tested on multiple FPGA hardware platforms. To perform acceleration on configurable hardware, a Deep Learning processing Unit (DPU) IP was used for processing AI workloads, together with a Pseudo-LiDAR reprojection for 3D reconstruction on the Arm® processor. The DPU performance configuration will depend on the logic resources the targeted board has. This paper highlights the performance, resource utilization, and bottlenecks that came across different tested combinations of both hardware and neural network architectures. © 2022 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Smart Infant Monitoring System Using computer Vision and AI

Smart Infant Monitoring System Using Computer Vision and AI

引用

IEEE International Conference on Electro-Information Technology

作者： Gurpreet Singh Abhishek Raj Shekhar Xinrui Yu Jafar Saniie Department of Electrical and Computer Engineering Embedded Computing and Signal Processing Research Laboratory Illinois Institute of Technology Chicago IL U.S.A.

The new era of technology is being greatly influenced by the field of artificial intelligence. computer vision and deep learning have become increasingly important due to their ability to process vast amounts of data and provide insights and solutions in a variety of fields. computer vision, deep learning and signal analysis have been used in a growing number of applications and services including smart devices, image, and speech recognition, healthcare, etc., one such device is an infant monitoring system. It monitors the daily activities of the infant such as their sleeping patterns, sounds, and movements. In this paper, deep learning and computer vision libraries were used to develop algorithms to detect whether the infant was in any uncomfortable situation such as sleeping on its back, face being covered and whether the infant was awake. The smart infant monitoring system detects the infant's unsafe resting situation in real time and sent immediate alerts to the caretaker's device. This paper presents the design flow of a smart infant monitoring system consisting of a night vision camera, a Jetson Nano, and a Wi-Fi internet connection. The pose estimation and awake detection algorithms were developed and tested successfully for different infant resting/sleeping situations. The smart infant monitoring system provides significant benefits for safety and an improved understanding of infants' sleep patterns and behavior.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrating HL7 FHIR into Clinical Decision Support Systems: A Real-World Application with Pepper Humanoid Robot in Hospital During Doctor Visits 9

Integrating HL7 FHIR into Clinical Decision Support Systems:...

引用

9th International Conference on Mathematics and computers in Sciences and Industry, MCSI 2024

作者： Safran, Valentino Horvat, Samo Ilijevec, Bojan Roj, Igor Rober Flis, Vojko Mlakar, Izidor University of Maribor Faculty of Electrical Engineering and Computer Science Laboratory of Digital Signal Processing Maribor Slovenia University Medical Centre Maribor Department of Thoracic Surgery Maribor Slovenia University Medical Centre Maribor Clinical Department of Abdominal and General Surgery Maribor Slovenia University Medical Centre Maribor Department of Nurses in Clinic for Surgery Maribor Slovenia University Medical Centre Maribor Clinical Department of Cardiac Surgery Maribor Slovenia

ISBN: (纸本)9798350377224

This study explores the integration of HL7 Fast Healthcare Interoperability Resources (FHIR) into a Clinical Decision Support System (CDSS) utilizing a Pepper robot to enhance doctor visits in a hospital setting. We evaluate a real-world implementation where the Pepper robot acts as an interface for data collection from patients, clinical monitors, and hospital information systems. The CDSS leverages FHIR to seamlessly integrate this data and present it visually, aiming to improve clinical decision-making processes for doctors. Our research investigates the potential of this FHIR-based CDSS with a robot interface to optimize healthcare delivery and potentially improve patient outcomes. © 2024 IEEE.

关键词： Anthropomorphic 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：