检索结果-内蒙古大学图书馆

Erato: Cooperative data Story Editing via Fact Interpolation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sun, Mengdi Cai, Ligan Cui, Weiwei Wu, Yanqiu Shi, Yang Cao, Nan Intelligent Big Data Visualization Lab Tongji University China Microsoft Research Asia China

关键词： Interpolation

Affective visualization Design: Leveraging the Emotional Impact of data

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lan, Xingyu Wu, Yanqiu Cao, Nan The Research Group of Computational and AI Communication Institute for Global Communications and Integrated Media China Intelligent Big Data Visualization Lab Tongji University China

In recent years, more and more researchers have reflected on the undervaluation of emotion in data visualization and highlighted the importance of considering human emotion in visualization design. Meanwhile, an increasing number of studies have been conducted to explore emotion-related factors. However, so far, this research area is still in its early stages and faces a set of challenges, such as the unclear definition of key concepts, the insufficient justification of why emotion is important in visualization design, and the lack of characterization of the design space of affective visualization design. To address these challenges, first, we conducted a literature review and identified three research lines that examined both emotion and data visualization. We clarified the differences between these research lines and kept 109 papers that studied or discussed how data visualization communicates and influences emotion. Then, we coded the 109 papers in terms of how they justified the legitimacy of considering emotion in visualization design (i.e., why emotion is important) and identified five argumentative perspectives. Based on these papers, we also identified 61 projects that practiced affective visualization design. We coded these design projects in three dimensions, including design fields (where), design tasks (what), and design methods (how), to explore the design space of affective visualization design. © 2023, CC BY.

关键词： data visualization

ChartKG: A Knowledge-Graph-Based Representation for Chart Images

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Zhiguang Wang, Haoxuan Zhao, Zhengqing Zheng, Fengling Wang, Yongheng Chen, Wei Wang, Yong School of Media and Design Hangzhou Dianzi University CO Hangzhou310018 China School of Media and Design Hangzhou Dianzi University China Big Data Visualization and Human Computer Collaborative Intelligent Laboratory Hangzhou Dianzi University China Research Center of Big Data Intelligence Zhejiang Lab Hangzhou China State Key Lab of CAD&CG Zhejiang University China College of Computing and Data Science Nanyang Technological University Singapore

Chart images, such as bar charts, pie charts, and line charts, are explosively produced due to the wide usage of data visualizations. Accordingly, knowledge mining from chart images is becoming increasingly important, which can benefit downstream tasks like chart retrieval and knowledge graph completion. However, existing methods for chart knowledge mining mainly focus on converting chart images into raw data and often ignore their visual encodings and semantic meanings, which can result in information loss for many downstream tasks. In this paper, we propose ChartKG, a novel knowledge graph (KG) based representation for chart images, which can model the visual elements in a chart image and semantic relations among them including visual encodings and visual insights in a unified ***, we develop a general framework to convert chart images to the proposed KG-based representation. It integrates a series of image processing techniques to identify visual elements and relations, e.g., CNNs to classify charts, yolov5 and optical character recognition to parse charts, and rule-based methods to construct graphs. We present four cases to illustrate how our knowledge-graph-based representation can model the detailed visual elements and semantic relations in charts, and further demonstrate how our approach can benefit downstream applications such as semantic-aware chart retrieval and chart question answering. We also conduct quantitative evaluations to assess the two fundamental building blocks of our chart-to-KG framework, i.e., object recognition and optical character recognition. The results provide support for the usefulness and effectiveness of ChartKG. © 2024, CC BY.

关键词： Knowledge graph

Stock Price Prediction and Portfolio Optimization Using Hidden Markov Model and Quadratic Programming

学校读者我要写书评

暂无评论

Stock Price Prediction and Portfolio Optimization Using Hidd...

Integrated Intelligence and Communication Systems (ICIICS), International Conference on

作者： August C. Thio-Ac Daniel D. Cabrales Drexanne E. Calibara Maries V. Madrazo Agustine Christian C. Matawaran Genesis E. Micaller Edmon O. Fernandez Timothy M. Amado Romeo L. Jorda Lean Karlo S. Tolentino Lejan Alfred C. Enriquez Department of Electronics Engineering Technological University of the Philippines Manila Philippines Integrated Research and Training Center Technological University of the Philippines Manila Philippines Intelligent Systems Applications and Circuits Laboratory (ISAAC) Integrated Research and Training Center Technological University of the Philippines Manila Philippines Data Analytics Visualization Information Driven (DAVID) Research Lab Integrated Research and Training Center Technological University of the Philippines Manila Philippines Center for Artificial Intelligence and Nanoelectronics (CAIN) Integrated Research and Training Center Technological University of the Philippines Manila Philippines

This study introduces a decision support system for optimizing stock portfolios. It employs a Hidden Markov Model for 95% accurate stock price forecasts over a five-day period. The system utilizes Quadratic Programming to refine allocation, focusing on up to 15 blue-chip companies. Key indicators like MACD, RSI, and Bollinger Bands offer clear buy, sell, or hold recommendations. It actively monitors the Philippine Stock Exchange, notifying users of significant deviations. Developed in Python and C#, both models were trained on a consistent 5-year dataset for reliable performance. Results show high prediction accuracy, averaging 98.923% (high price) and 98.741% (low price), benefiting investment strategies. The study compared SPOT-allocated portfolios to random ones, revealing a notable difference in profit/loss allocation. This underscores its value for informed and profitable decision-making in stock trading.

关键词：

Satori: Towards Proactive AR Assistant with Belief-Desire-Intention User Modeling

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Chenyi Wu, Guande Chan, Gromit Yeuk-Yin Turakhia, Dishita G. Quispe, Sonia Castelo Li, Dong Welch, Leslie Silva, Claudio Qian, Jing Tandon School of Engineering New York University New YorkNY United States Tandon School of Engineering New York University New York CityNY United States Adobe Research San JoseCA United States Visualization and Data Analytics Lab New York University New YorkNY United States Tandon School of Engineering New York University BrooklynNY United States Brown University ProvidenceRI United States New York University New York CityNY United States

Augmented Reality assistance are increasingly popular for supporting users with tasks like assembly and cooking. However, current practice typically provide reactive responses initialized from user requests, lacking consideration of rich contextual and user-specific information. To address this limitation, we propose a novel AR assistance system, Satori, that models both user states and environmental contexts to deliver proactive guidance. Our system combines the Belief-Desire-Intention (BDI) model with a state-of-the-art multi-modal large language model (LLM) to infer contextually appropriate guidance. The design is informed by two formative studies involving twelve experts. A sixteen within-subject study find that Satori achieves performance comparable to an designer-created Wizard-of-Oz (WoZ) system without relying on manual configurations or heuristics, thereby enhancing generalizability, reusability and opening up new possibilities for AR assistance. © 2024, CC BY.

关键词： Augmented reality

Satori 悟り: Towards Proactive AR Assistant with Belief-Desire-Intention User Modeling 25

学校读者我要写书评

暂无评论

Satori 悟り: Towards Proactive AR Assistant with Belief-Desi...

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Chenyi Li Guande Wu Gromit Yeuk-Yin Chan Dishita Gdi Turakhia Sonia Castelo Quispe Dong Li Leslie Welch Claudio Silva Jing Qian Tandon School of Engineering New York University New York New York USA Tandon School of Engineering New York University New York CIty New York USA Adobe Research San Jose California USA Tandon School of Engineering New York University New York City New York USA Visualization and Data Analytics Lab New York University New York New York USA Tandon School of Engineering Brooklyn New York USA Brown University Providence Rhode Island USA New York University New York City New York USA Tandon School of Engineering New York University Brooklyn New York USA

A generative artificial intelligence framework based on a molecular diffusion model for the design of metal–organic frameworks for carbon capture

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Park, Hyun Yan, Xiaoli Zhu, Ruijie Huerta, Eliu A. Chaudhuri, Santanu Cooper, Donny Foster, Ian Tajkhorshid, Emad Data Science and Learning Division Argonne National Laboratory LemontIL60439 United States Theoretical and Computational Biophysics Group NIH Resource Center for Macromolecular Modeling and Visualization Beckman Institute for Advanced Science and Technology University of Illinois at Urbana-Champaign UrbanaIL61801 United States Center for Biophysics and Quantitative Biology University of Illinois at Urbana-Champaign UrbanaIL61801 United States Multiscale Materials and Manufacturing Lab University of Illinois Chicago ChicagoIL60607 United States Department of Materials Science and Engineering Northwestern University EvanstonIL60208 United States Department of Computer Science University of Chicago ChicagoIL60637 United States Department of Physics University of Illinois at Urbana-Champaign UrbanaIL61801 United States Computational Science and Engineering Data Science and AI Department TotalEnergies EP Research & Technology USA LLC HoustonTX77002 United States Department of Biochemistry University of Illinois at Urbana-Champaign UrbanaIL61801 United States

Metal–organic frameworks (MOFs) exhibit great promise for CO2 capture. However, finding the best performing materials poses computational and experimental grand challenges in view of the vast chemical space of potential building blocks. Here, we introduce GHP-MOFassemble, a generative artificial intelligence (AI), high performance framework for the rational and accelerated design of MOFs with high CO2 adsorption capacity and synthesizable linkers. GHP-MOFassemble generates novel linkers, assembled with one of three pre-selected metal nodes (Cu paddlewheel, Zn paddlewheel, Zn tetramer) into MOFs in a primitive cubic topology. GHP-MOFassemble screens and validates AI-generated MOFs for uniqueness, synthesizability, structural validity, uses molecular dynamics simulations to study their stability and chemical consistency, and crystal graph neural networks and Grand Canonical Monte Carlo simulations to quantify their CO2 adsorption capacities. We present the top six AI-generated MOFs with CO2 capacities greater than 2m molg−1, i.e., higher than 96.9% of structures in the hypothetical MOF dataset. Copyright © 2023, The Authors. All rights reserved.

关键词： Carbon dioxide

An Activatable Near-Infrared Fluorescent Probe for Precise Detection of the Pulmonary Metastatic Tumors: A Traditional Molecule Having a Stunning Turn

学校读者我要写书评

暂无评论

Angewandte Chemie 2023年第48期135卷

作者： Qian Jia Ruili Zhang Haohao Yan Yanbin Feng Fang Sun Zuo Yang Chaoqiang Qiao Xiaocheng Mou Prof. Jie Tian Prof. Zhongliang Wang Lab of Molecular Imaging and Translational Medicine (MITM) Engineering Research Center of Molecular & Neuroimaging Ministry of Education School of Life Science and Technology Xidian University Xi'an Shaanxi 710126 China Contribution: Data curation (lead) Formal analysis (equal) Funding acquisition (supporting) Investigation (lead) Methodology (lead) Visualization (equal) Writing - original draft (supporting) Writing - review & editing (supporting) Contribution: Conceptualization (supporting) Formal analysis (equal) Project administration (supporting) Supervision (supporting) Writing - original draft (lead) Writing - review & editing (supporting) Contribution: Data curation (equal) Formal analysis (supporting) Methodology (equal) Validation (equal) Writing - review & editing (supporting) Contribution: Validation (equal) Visualization (supporting) Writing - review & editing (supporting) Contribution: Formal analysis (supporting) Validation (equal) Visualization (supporting) Writing - review & editing (supporting) Contribution: Visualization (equal) Writing - review & editing (supporting) Contribution: Validation (supporting) Visualization (supporting) Writing - review & editing (supporting) Contribution: Validation (supporting) Contribution: Conceptualization (supporting) Supervision (supporting) Contribution: Conceptualization (lead) Formal analysis (equal) Funding acquisition (lead) Project administration (lead) Supervision (lead) Writing - review & editing (lead)

An accurate detection of lung metastasis is of great significance for making better treatment choices and improving cancer prognosis, but remains a big challenge in clinical practice. In this study, we propose a reinventing strategy to develop a pH-activatable near-infrared (NIR) fluorescent nanoprobe, pulmonary metastasis tracer (denoted as PMT), based on assembly of NIR dye IR780 and calcium phosphate (CaP). By delicately tuning the intermolecular interactions during the assembly process and dye doping content, as well as the synthetic condition of probe, the fluorescence of PMT could be finely adjusted via the tumor acidity-triggered disassembly. Notably, the selected PMT9 could sharply convert subtle pH variations into a distinct fluorescence signal to generate high fluorescence ON/OFF contrast, dramatically reducing the background signals. Benefiting from such preferable features, PMT9 is able to precisely identify not only the tumor sites in orthotopic lung cancer models but also the pulmonary metastases in mice with remarkable signal-to-background ratio (SBR). This study provides a unique strategy to turn shortcomings of traditional dye IR780 during in vivo imaging into advantages and further expand the application of fluorescent probe to image lung associated tumor lesions.

关键词： Assembly Molecular Probes NIR Fluorescence Pulmonary Metastatic Tumors

Quantitative Single-Molecule Electrochemiluminescence Bioassay

学校读者我要写书评

暂无评论

Angewandte Chemie 2022年第7期135卷

作者： Wenxin Zhu Jinrun Dong Guoxiang Ruan Yuan Zhou Prof. Jiandong Feng Laboratory of Experimental Physical Biology Department of Chemistry Zhejiang University Hangzhou 310027 China Contribution: Data curation (lead) Formal analysis (lead) Investigation (lead) Methodology (lead) Validation (equal) Visualization (lead) Writing - original draft (equal) Writing - review & editing (supporting) Contribution: Data curation (equal) Formal analysis (equal) Investigation (equal) Methodology (equal) Validation (equal) Department of Laboratory Medicine Key Laboratory of Clinical In Vitro Diagnostic Techniques of Zhejiang Province Institute of Laboratory Medicine the First Affiliated Hospital School of Medicine Zhejiang University Hangzhou 310003 China Contribution: Data curation (supporting) Formal analysis (supporting) Resources (lead) Validation (supporting) Contribution: Investigation (supporting) Validation (lead) Research Center for Quantum Sensing Research Institute of Intelligent Sensing Zhejiang Lab Hangzhou 311121 China Contribution: Conceptualization (lead) Funding acquisition (lead) Methodology (lead) Supervision (lead) Validation (lead) Writing - review & editing (lead)

A single-molecule electrochemiluminescence bioassay is developed here which allows imaging and direct quantification of single biomolecules. Imaging single biomolecules is realized by localizing the electrochemiluminescence events of the labeled molecules. Such an imaging system allows mapping the spatial distribution of biomolecules with electrochemiluminescence and contains quantitative single-molecule insights. We further quantify biomolecules by spatiotemporally merging the repeated reactions at one molecule site and then counting the clustered molecules. The proposed single-molecule electrochemiluminescence bioassay is used to detect carcinoembryonic antigen, showing a limit of detection of 67 attomole concentration which is 10 000 times better than conventional electrochemiluminescence bioassays. This spatial resolution and sensitivity enable single-molecule electrochemiluminescence bioassay a new toolbox for both specific bioimaging and ultrasensitive quantitative analysis.

关键词： Electrochemiluminescence Quantitative Imaging Single-Molecule Bioassay Super-Resolution Microscopy