检索结果-内蒙古大学图书馆

A Scattered Liquid Component Analysis Approach Based on Spectral visual encoding and Fusion

IEEE SENSORS JOURNAL 2024年第3期24卷 3072-3083页

作者： Liu, Tianhao Zhou, Can Fang, Chenyu Zhu, Hongqiu Li, Yonggang Wu, Jiali Cent South Univ Sch Automat Changsha 410083 Peoples R China

In recent decades, spectral analysis has become a key research field to determine product components. Ion concentrations in metallurgical liquid are crucial component parameters for guiding the stable process operation in zinc hydrometallurgy. Its rapid and accurate analysis plays a critical role in industrial informatization. However, on the one hand, due to the complex physical and chemical properties of metallurgical liquid, the suspended solid particles (SSPs) in the liquid cause incident light scattering, which violates Lambert-Beer's law and results in a considerable determination deviation in the traditional methods. On the other hand, optical-based particle modeling relies on precise optical parameters and complex calculation, which is a costly endeavor. To get around these issues, a scattered liquid component analysis method based on spectral visual encoding (SVE) and fusion is proposed. It unifies the traditional three spectrum analysis steps and provides a new perspective on spectral variation characterization. First, a multispectrum acquisition system based on region scanning was developed to mitigate the effects of SSP sensitivity. Second, a spectral visualization framework based on image encoding is established, and the dynamics variation of spectral curve shape and absorbance amplitude is characterized. Third, a multiple-channel mechanism is designed, which enables the proposed method to extract and fuse feature information of different encoded images. The experimental results proved that the proposed method yields higher determination accuracy.

关键词： Liquids Ions Zinc visualization Optical scattering encoding Optical sensors Metal ion determination spectral analysis suspended solid particle (SSP) visual encoding zinc hydrometallurgy

来源：评论

学校读者我要写书评

暂无评论

Towards real-time embodied AI agent: a bionic visual encoding framework for mobile robotics

引用

INTERNATIONAL JOURNAL OF INTELLIGENT ROBOTICS AND APPLICATIONS 2024年第4期8卷 1038-1056页

作者： Hou, Xueyu Guan, Yongjie Han, Tao Wang, Cong Univ Maine ECE Dept Orono ME 04469 USA New Jersey Inst Technol ECE Dept Newark NJ USA

Embodied artificial intelligence (AI) agents, which navigate and interact with their environment using sensors and actuators, are being applied for mobile robotic platforms with limited computing power, such as autonomous vehicles, drones, and humanoid robots. These systems make decisions through environmental perception from deep neural network (DNN)-based visual encoders. However, the constrained computational resources and the large amounts of visual data to be processed can create bottlenecks, such as taking almost 300 milliseconds per decision on an embedded GPU board (Jetson Xavier). Existing DNN acceleration methods need model retraining and can still reduce accuracy. To address these challenges, our paper introduces a bionic visual encoder framework, }Robye\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathsf \small {Robye}$$\end{document}, to support real-time requirements of embodied AI agents. The proposed framework complements existing DNN acceleration techniques. Specifically, we integrate motion data to identify overlapping areas between consecutive frames, which reduces DNN workload by propagating encoding results. We bifurcate processing into high-resolution for task-critical areas and low-resolution for less-significant regions. This dual-resolution approach allows us to maintain task performance while lowering the overall computational demands. We evaluate }Robye\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathsf \small {Robye}$$\end{document} across three robotic scenarios: autonomous driving, vision-and-language navigation, and drone navigation, using various DNN models and mobile pl

关键词： Mobile robotics visual encoding Embodied AI Computer vision

来源：评论

学校读者我要写书评

暂无评论

DPVis: Automatic visual encoding Based on Deep Learning

引用

IEEE ACCESS 2023年 11卷 118078-118087页

作者： Liu, Jia Wan, Gang Deng, Panke Li, Chu Wang, Shuai Yin, Yunxia Liu, Lei Mu, Yao Space Engn Univ Sch Space Informat Beijing 101416 Peoples R China

Automatic visual encoding is frequently employed in automatic visualization tools to automatically map data to visual elements. This paper proposed an automatic visual encoding approach based on deep learning. This approach constructs visual encoding datasets in a more comprehensive and reliable manner to extract and label widely available visualization graphics on the Internet in accordance with three essentials of visualization. The deep learning model is then trained to create a visual encoding model with powerful generalization performance, enabling automated effective visual encoding recommendations for visual designers. The results demonstrated that our approach extends the automatic visual encoding techniques used by existing visualization tools, enhances the functionality and performance of visualization tools, uncovers previously undiscovered data and increases the coverage of data variables.

关键词： Automatic visualization visual encoding deep learning visual channels

来源：评论

学校读者我要写书评

暂无评论

Children with dyslexia show no deficit in exogenous spatial attention but show differences in visual encoding

引用

DEVELOPMENTAL SCIENCE 2024年第3期27卷 e13458-e13458页

作者： Ramamurthy, Mahalakshmi White, Alex L. Yeatman, Jason D. Stanford Univ Sch Med Div Dev Behav Pediat Stanford CA 94305 USA Stanford Univ Grad Sch Educ Stanford CA 94305 USA Barnard Coll Dept Neurosci & Behav New York NY USA

In the search for mechanisms that contribute to dyslexia, the term "attention" has been invoked to explain performance in a variety of tasks, creating confusion since all tasks do, indeed, demand "attention." Many studies lack an experimental manipulation of attention that would be necessary to determine its influence on task performance. Nonetheless, an emerging view is that children with dyslexia have an impairment in the exogenous (automatic/reflexive) orienting of spatial attention. Here we investigated the link between exogenous attention and reading ability by presenting exogenous spatial cues in the multi-letter processing task-a task relevant for reading. The task was gamified and administered online to a large sample of children (N = 187) between 6 and 17 years. Children with dyslexia performed worse overall at rapidly recognizing and reporting strings of letters. However, we found no evidence for a difference in the utilization of exogenous spatial cues, resolving two decades of ambiguity in the field. Previous studies that claimed otherwise may have failed to distinguish attention effects from overall task performance or found spurious group differences in small *** HighlightsWe manipulated exogenous visual spatial attention using pre-cues in a task that is relevant for reading and we see robust task effects of exogenous *** found no evidence for a deficit in utilizing exogenous spatial pre-cues in children with ***, children with dyslexia showed reduced recognition ability for all letter *** with dyslexia were just as likely to make letter transposition errors as typical readers.

关键词： dyslexia exogenous attention reading spatial attention visual encoding

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Image Analysis for Precision Diagnosis and Recognition Using Cutting-Edge visual encoding

Revolutionizing Image Analysis for Precision Diagnosis and R...

引用

2024 IEEE International Students' Conference on Electrical, Electronics and Computer Science, SCEECS 2024

作者： Rajalakshmi, D. Anita, C.S. Sasikumar, R. Sudharson, K. Alekhya, Badi Rose, S. Remya R.M.D. Engineering College Department of Computer Science and Engineering Chennai India R.M.D. Engineering College Department of Artificial Intelligence and Machine Learning Chennai India

ISBN: (纸本)9798350348460

This groundbreaking study introduces a revolutionary image analysis method, showcasing unprecedented accuracy in precision diagnosis and recognition. The innovative approach seamlessly integrates feature detection and description, demonstrating exceptional proficiency in identifying crucial local features. The advanced visual encoding architecture, surpassing conventional methods, utilizes intricate convolutional layers and the renowned Haar algorithm, achieving a remarkable 99% success rate. This comprehensive suite of advancements propels image analysis to new heights, with potential applications ranging from medical diagnostics to facial recognition. Strongly accepted for its cutting-edge techniques and impressive success rate. © 2024 IEEE.

关键词： facial recognition feature detection image analysis precision diagnosis visual encoding

来源：评论

学校读者我要写书评

暂无评论

''Impact of visual encoding on Automation Transparency in Drone Interface 7

''Impact of Visual Encoding on Automation Transparency in Dr...

引用

7th CAA International Conference on Vehicular Control and Intelligence, CVCI 2023

作者： Huang, Hao Zhang, Qixiang Geng, Keke Yin, Guodong School of Mechanical Engineering Southeast University Nanjing China

ISBN: (纸本)9798350340488

With the civilianization of consumer drones, the market of drone apps is expanding. As a key medium of human-machine interaction, the well-designed interface can reduce accident rate and boost mission success rate. Automation transparency is a descriptive metric of interface usability in unmanned systems, reflecting the interface's ability to improve users' situation awareness. This study investigated the impact of various levels of visual encoding on automation transparency. First, three typical flight modalities were selected as test scenarios, including obstacle avoidance, dynamic tracking, and waypoint flight. Then, each of the three modes were all visually encoded at three levels by introducing more visual channels. A single-factor independent experiment was conducted, in which participants completed the corresponding tasks. The experiment results showed that the level of visual encoding had a significant impact on interface automation transparency. Participants achieved better performance in most of the test tasks as the level of visual encoding rose. However, the upward trend from level 2 to 3 tended to level off. Meanwhile, the cognitive load of the participants showed a slight rebound following a decline. This research also revealed disparities in the efficacy of the several visual channels, with the position being more potent than color, texture, and shape. © 2023 IEEE.

关键词： automation transparency consumer drone interface situation awareness visual encoding

来源：评论

学校读者我要写书评

暂无评论

Evaluating visual encoding quality of a mixed reality user interface for human-machine co-assembly in complex operational terrain

引用

ADVANCED ENGINEERING INFORMATICS 2023年 58卷

作者： Wang, Zhuo Zhang, Xiangyu Li, Liang Zhou, Yiliang Lu, Zexin Dai, Yuwei Liu, Chaoqian Su, Zekun Bai, Xiaoliang Billinghurst, Mark Univ Shanghai Sci & Technol Sch Mech Engn Shanghai 200093 Peoples R China Univ Shanghai Sci & Technol Sch Environm & Architecture Shanghai 200093 Peoples R China Cyber Real Innovat Ctr China Nanjing 211200 Peoples R China Univ Auckland Auckland Bioengn Inst 70 Symonds St Auckland 1010 New Zealand

During human-machine collaboration in manufacturing activities, it is important to provide real-time annota-tions in the three-dimensional workspace for local workers who may lack relevant experience and knowledge. For example, in MR assembly, workers need to be alerted to avoid entering hazardous areas when manually replacing components. Recently, many researchers have explored various visual cues for expressing physical task progress information in the MR interface of intelligent systems. However, the relationship between the im-plantation of visual cues and the balance of interface cognition has not been well revealed, especially in tasks that require annotating hazardous areas in complex operational terrains. In this study, we developed a novel MR interface for an intelligent assembly system that supports local scene sharing based on dynamic 3D recon-struction, remote expert behavior intention recognition based on deep learning, and local personnel operational behavior visual feedback based on external bounding box. We compared the encoding results of the proposed MR interface with 3D annotations combined with 3D sketch cues (3DS), which combines 3D spatial cues (3DSC) and 3DS combined with adaptive cues (AVC), through a case study. We found that for physical tasks that require specific area annotations, 3D annotations with context (3DAC) can better improve the quality of manual work and regulate the cognitive load distribution of the MR interface more reasonably.

关键词： visual encoding Mixed reality User interface Co-assembly Complex operational terrain

来源：评论

学校读者我要写书评

暂无评论

visual encoding, consolidation, and retrieval in amyotrophic lateral sclerosis: executive function as a mediator, and predictor of performance

引用

AMYOTROPHIC LATERAL SCLEROSIS AND FRONTOTEMPORAL DEGENERATION 2017年第3-4期18卷 193-201页

作者： Burke, Tom Lonergan, Katie Pinto-Grau, Marta Elamin, Marwa Bede, Peter Madden, Caoifa Hardiman, Orla Pender, Niall Beaumont Hosp Dept Psychol Dublin 9 Ireland Trinity Biomed Sci Inst Acad Unit Neurol Dublin Ireland Beaumont Hosp Dept Neurol Dublin Ireland Royal Coll Surg Dept Psychol Dublin Ireland

Objective: This study aimed to illustrate the variation of non-executive cognitive processes, i.e. visual memory, considering executive dysfunction in amyotrophic lateral sclerosis (ALS).Methods: Patients with ALS (n=203), and matched healthy controls (n=117) completed a battery of neuropsychological tests. Sub-stratification was based on whether cognitive assessment detected no cognitive abnormalities (NCA: n=117), multiple executive cognitive deficits (ALS-Exec;n=56), or a comorbid frontotemporal dementia process (ALS-FTD;n=30). The Rey-Osterrieth Complex Figure Test (ROCFT) was the main dependent variable for visual memory in this ***: Patients and controls significantly differed on the Copy trial (p<0.0001: omega(2) =0.317) immediate recall (p<0.0001: omega(2) =0.272) and delayed recall (p<0.0001: omega(2) =0.308) of the ROCFT. Sub-stratification based on executive dysfunction revealed an association with greater executive dysfunction and lower ROCFT performance. Regression analysis predicted that premorbid IQ, executive function, and demographics predict performance on the ROCFT delayed recall trial (R-2=0.833).Conclusions: These findings illustrate that patients without executive dysfunction do not show visual memory impairments within this cohort;that patients with executive dysfunction have poorer performance on visual memory tasks;and that the severity of executive dysfunction, as per cognitive categorisation, is related to increased visual memory impairment as tested with the ROCFT.

关键词： ALS neuropsychology visual encoding memory executive function

来源：评论

学校读者我要写书评

暂无评论

An Approach to Classify visual Semantic Based on visual encoding With The Convolutional Neural Network 12

An Approach to Classify Visual Semantic Based on Visual Enco...

引用

12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD)

作者： Zheng, Zaizhou Bu, Haibing He, Wenjie Tong, Li Yan, Bin Wang, Linyuan Natl Digital Switching Syst Engn & Technol R&D Ctr Zhengzhou Peoples R China

ISBN: (纸本)9781467376822

visual encoding models and visual decoding models are all used for revealing the relationship of external visual stimuli and brain activities. On the view of the goal, visual encoding and decoding are opposite, but they are also complementary. With further researching, we could not use a simple decoding model to excavate more complex information. The combination of visual encoding model and decoding model is becoming a trend of visual research. This paper has built a visual encoding model based on a convolutional neural network and has proposed an approach to select features based on the visual encoding model. The results show that our predicted voxels are similar to the selected real voxels, the correlation coefficients of them are pretty high. On the other hand, the classification results are better than those of t-value method and principal feature analysis (PFA) method. Our approach provides a reference to the combination of visual encoding and decoding models.

关键词： visual encoding visual decoding convolutional neural network feature selection multi-voxel pattern analysis

来源：评论

学校读者我要写书评

暂无评论

Advancing Precision Equipment Co-Assembly: An Innovative VR/MR Interface Strategy

引用

INTERNATIONAL JOURNAL OF HUMAN-COMPUTER INTERACTION 2025年第7期41卷 4350-4361页

作者： Li, Xiaoru Chen, Shisong Wang, Yang Wang, Zhuo Guo, Zihan Li, Weichu Zhang, Jiacheng Du, Xiaoting Liu, Fucheng Univ Shanghai Sci & Technol Sch Mech Engn Shanghai 200093 Peoples R China Univ Shanghai Sci & Technol Inst Underwater Vehicles & Intelligent Syst Shanghai Peoples R China AVIC Airborne Syst Co Ltd Civil Aircraft Engn Res & Dev Ctr Shanghai Peoples R China

Recent research indicates that inappropriate visual coding exacerbates the side effects of cognitive load imbalance in the recognition of graphical symbols on VR/MR interfaces, leading to severe issues in individuals' understanding of task processes. In response to this situation, a VR/MR interface strategy supporting precision equipment collaborative assembly is proposed. This strategy revolves around interactive cues such as virtual-real scene registration tracking, spatiotemporal data synchronization, eye gaze, and motion capture, aiming to construct a visual coding design mechanism for VR/MR interfaces. The goal is to enhance the quality of assembly intent expression and slow down the accumulation rate of individual mental fatigue. This study designs an experimental VR/MR interface coding prototype system. Through case study experiments, direct evidence is found that the proposed MR interface coding strategy has advantages in assembly completion time, decision-making ability, visual perception experience, and operational interaction experience. The experimental results of this study will be beneficial for guiding the assessment of VR/MR manual micro-operation quality processes, especially in the field of precision assembly.

关键词： Virtual reality mixed reality co-assembly visual encoding visual interface

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：