Search

Your search keyword '"Pan, Yichen"' showing total 117 results
Start Over Author "Pan, Yichen"
117 results on '"Pan, Yichen"'

1. WebCanvas: Benchmarking Web Agents in Online Environments

Author

Pan, Yichen, Kong, Dehan, Zhou, Sida, Cui, Cheng, Leng, Yifei, Jiang, Bing, Liu, Hangyu, Shang, Yanyi, Zhou, Shuyan, Wu, Tongshuang, and Wu, Zhengyang

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, 68T50, I.2.7
Abstract

For web agents to be practically useful, they must adapt to the continuously evolving web environment characterized by frequent updates to user interfaces and content. However, most existing benchmarks only capture the static aspects of the web. To bridge this gap, we introduce WebCanvas, an innovative online evaluation framework for web agents that effectively addresses the dynamic nature of web interactions. WebCanvas contains three main components to facilitate realistic assessments: (1) A novel evaluation metric which reliably capture critical intermediate actions or states necessary for task completions while disregarding noise caused by insignificant events or changed web-elements. (2) A benchmark dataset called Mind2Web-Live, a refined version of original Mind2Web static dataset containing 542 tasks with 2439 intermediate evaluation states; (3) Lightweight and generalizable annotation tools and testing pipelines that enables the community to collect and maintain the high-quality, up-to-date dataset. Building on WebCanvas, we open-source an agent framework with extensible modules for reasoning, providing a foundation for the community to conduct online inference and evaluations. Our best-performing agent achieves a task success rate of 23.1% and a task completion rate of 48.8% on the Mind2Web-Live test set. Additionally, we analyze the performance discrepancies across various websites, domains, and experimental environments. We encourage the community to contribute further insights on online agent evaluation, thereby advancing this field of research., Comment: Our platform, tool and dataset are publically available at https://www.imean.ai/web-canvas/ and https://huggingface.co/datasets/iMeanAI/Mind2Web-Live/

Published
2024

3. Review of Progress in Proactive Health Research

Author

Zou, Lin, Cao, Licong, Li, Weiping, Pan, Yichen, Liang, Rui, Chen, Jianxiong, Striełkowski, Wadim, Editor-in-Chief, Black, Jessica M., Series Editor, Butterfield, Stephen A., Series Editor, Chang, Chi-Cheng, Series Editor, Cheng, Jiuqing, Series Editor, Dumanig, Francisco Perlas, Series Editor, Al-Mabuk, Radhi, Series Editor, Scheper-Hughes, Nancy, Series Editor, Urban, Mathias, Series Editor, Webb, Stephen, Series Editor, Rad, Dana, editor, Chew, Fong Peng, editor, Hutagalung, Fonny Dameaty, editor, and Birkök, Cüneyt, editor

Published
2024
Full Text
View/download PDF

4. The Concept and Framework Construction of Proactive Health

Author

Zou, Lin, Cao, Licong, Li, Weiping, Pan, Yichen, Liang, Rui, Chen, Jianxiong, Striełkowski, Wadim, Editor-in-Chief, Black, Jessica M., Series Editor, Butterfield, Stephen A., Series Editor, Chang, Chi-Cheng, Series Editor, Cheng, Jiuqing, Series Editor, Dumanig, Francisco Perlas, Series Editor, Al-Mabuk, Radhi, Series Editor, Scheper-Hughes, Nancy, Series Editor, Urban, Mathias, Series Editor, Webb, Stephen, Series Editor, Rad, Dana, editor, Chew, Fong Peng, editor, Hutagalung, Fonny Dameaty, editor, and Birkök, Cüneyt, editor

Published
2024
Full Text
View/download PDF

5. A 24-Pulse Aviation Rectifier Based on Auto-Fed Half-Bridge Auxiliary Circuit

Author

Tu, Wenhao, Wang, Yongshuai, Ge, Hongjuan, Pan, Yichen, Shi, Yanbo, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Zhang, Junjie James, Series Editor, Tan, Kay Chen, Series Editor, Dong, Xuzhu, editor, and Cai, Li, editor

Published
2024
Full Text
View/download PDF

11. Feature Extraction via Recurrent Random Deep Ensembles and its Application in Gruop-level Happiness Estimation

Author

Tang, Shitao and Pan, Yichen

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Learning
Abstract

This paper presents a novel ensemble framework to extract highly discriminative feature representation of image and its application for group-level happpiness intensity prediction in wild. In order to generate enough diversity of decisions, n convolutional neural networks are trained by bootstrapping the training set and extract n features for each image from them. A recurrent neural network (RNN) is then used to remember which network extracts better feature and generate the final feature representation for one individual image. Several group emotion models (GEM) are used to aggregate face fea- tures in a group and use parameter-optimized support vector regressor (SVR) to get the final results. Through extensive experiments, the great effectiveness of the proposed recurrent random deep ensembles (RRDE) is demonstrated in both structural and decisional ways. The best result yields a 0.55 root-mean-square error (RMSE) on validation set of HAPPEI dataset, significantly better than the baseline of 0.78.

Published
2017

23. Review of Predicting Synergistic Drug Combinations.

Author

Pan, Yichen, Ren, Haotian, Lan, Liang, Li, Yixue, and Huang, Tao

Subjects
*DEEP learning, *STOMACH ulcers, *HYPERTENSION, *SEARCH algorithms, *MACHINE learning, *DRUG resistance
Abstract

The prediction of drug combinations is of great clinical significance. In many diseases, such as high blood pressure, diabetes, and stomach ulcers, the simultaneous use of two or more drugs has shown clear efficacy. It has greatly reduced the progression of drug resistance. This review presents the latest applications of methods for predicting the effects of drug combinations and the bioactivity databases commonly used in drug combination prediction. These studies have played a significant role in developing precision therapy. We first describe the concept of synergy. we study various publicly available databases for drug combination prediction tasks. Next, we introduce five algorithms applied to drug combinatorial prediction, which include traditional machine learning methods, deep learning methods, mathematical methods, systems biology methods and search algorithms. In the end, we sum up the difficulties encountered in prediction models. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

33. Two-Stage Adaptive Constrained Particle Swarm Optimization Based on Bi-Objective Method

Author

Qing Li, Yongfeng Feng, Heng Wang, Pan Yichen, and Feng Qian

Subjects
Mathematical optimization, General Computer Science, Computer science, bi-objective optimization, Feasible region, General Engineering, Process (computing), adaptive, Particle swarm optimization, particle swarm optimization algorithm, Term (time), Constraint (information theory), Set (abstract data type), Benchmark (computing), General Materials Science, lcsh:Electrical engineering. Electronics. Nuclear engineering, Constrained optimization, lcsh:TK1-9971
Abstract

For the sake of better balancing the relationship between diversity and convergence when handling constrained optimization problems, a two-stage adaptive constrained particle swarm optimization algorithm based on bi-objective method (TABC-PSO) is proposed. In accordance with different phases of the constraint process, the target-constraint space derived from the angle is partitioned adaptively, and simultaneously the global best particle is selected and the external archive set is safeguarded. In the first stage, the whole space is divided adaptively in term of the angular distribution of individual, and the feasible region is explored comprehensively. In the second stage, local regions are adaptively compartmentalized and in-depth exploitation is carried out. Primary and secondary external archive sets are established to maintain population diversity and accelerate convergence. The two phases are switched adaptively in light of the storage status of the two external archive sets. We evaluated TABC-PSO algorithm on the benchmark functions in CEC 2006 and CEC 2017. The experimental results show that TABC-PSO algorithm compared with other state-of-the-art algorithms can be superior to applied to test functions with different types of constraints and possesses a competitive search capability.

Published
2020

36. Ni/Ni12P5 Heterostructure Decorated on Multi‐channel Carbonized Wood Frameworks for Efficient Hydrogen Evolution.

Author

Wang, Zhiqiang, Pan, Yichen, Yang, Caixia, Zhang, Jiancheng, Li, Caicai, and Sun, Qingfeng

Subjects
*WOOD, *HYDROGEN evolution reactions, *ELECTROCATALYSIS, *HYDROGEN content of metals, *ELECTRIC conductivity, *CHARGE exchange, *CATALYTIC activity
Abstract

For exploiting high‐efficiency and stable non‐noble metal hydrogen evolution reaction (HER) electrocatalysts, rationally design and optimizing the electrode structures are extremely essential. Herein, inspired by the abundant pores and highly ordered multi‐channel structures of natural wood, a typical electrode with Ni/Ni12P5 heterostructure embedded in the multi‐channel carbonized wood frameworks (Ni/Ni12P5/CW) was designed and fabricated. The open micro‐channel structure and electrical conductivity of carbonized wood (CW) facilitates electron transfer, electrolyte penetration, and gas diffusion. Meanwhile, formation of the Ni/Ni12P5 heterostructure is beneficial to improve the activity of pristine nickel phosphide. As expected, the Ni/Ni12P5/CW electrode exhibited excellent HER catalytic activity, which merely needed overpotentials of 86, 138 and 173 mV to drive 10, 50 and 100 mA cm−2 in alkaline media, respectively. In addition, it showed superior durability with no significant degradation for more than 60 h of continuous operation at different current densities. This work will enlighten the development and utilization of wood‐based materials for application in electrocatalysis. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

42. Geographical Dispersion and Investment Efficiency.

Author

Wang, Junjie, Liu, Chen, Pan, Yichen, and Liu, Siyi

Subjects
MEASUREMENT errors, KNOWLEDGE transfer
Abstract

Our study reconciles the mixed effects of geographical dispersion within corporations on investment efficiency based on listed firms in China from 2007–2019. The results show that geographical dispersion of subsidiaries can effectively improve the overall investment efficiency for the corporation, which support the hypothesis of mitigating the attenuation effect of operating distance. Then, we carry out cross-sectional tests from the perspectives of information transfer costs and institutional differences. The results show that the above influence is more significant when either the parent and subsidiary firms are not located in the high-spee5d rail network or the institutional background difference between the parent and subsidiary firms is big. After controlling the endogenous problem and measurement error, the baseline results remain the same. Furthermore, we verify the inverted U-shaped relationship between geographical dispersion and investment efficiency. The conclusions not only supplement the related literature on geographical distance and investment efficiency, but also provide important inspiration for management, policy makers. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

43. Design and Implementation of Intelligent Home Power Control Systems by Using Raspberry Pi and AWS Cloud Service

Author

Pan Yichen and Jae-Soo Kim

Subjects
business.industry, Computer science, Control (management), 020206 networking & telecommunications, Cloud computing, 02 engineering and technology, Computer security, computer.software_genre, Data sharing, Home automation, Smart city, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Electricity, business, computer, Power control
Abstract

In the early years many fire disasters caused by electrical appliance which is dangerous and seriously influence people's daily life. With the development of technology in the field of Internet of things, more and more intelligent electric appliances are appearing. In this situation, how to effectively and securely control different devices has become an important research direction. In this paper, we design and implement an intelligent home power control system to manage electric appliances and share collected data by using Raspberry pi and amazon cloud service. It greatly improves the security of electric appliances and provides data support for the establishment of a smart city. Different to other studies, this paper redefines intelligent home power control systems from three aspects: low-energy, security and data sharing. By analyzing and processing the collected sensor information, it can provide an accurate prediction for the safety of household and regional electricity consumption.

Published
2019

50. Design of a Wind Sensor Based on Cylinder Diametrical Pressure Differences for Boundary Layer Meteorological Observation

Author

Xianghua Niu, Zhen Fang, Lidong Du, Zhan Zhao, Rongjian Zhao, Hong Wu, and Pan Yichen

Subjects
Microelectromechanical systems, Quadcopter, Acoustics, Astrophysics::High Energy Astrophysical Phenomena, meteorological observation, Relative velocity, lcsh:A, pressure difference, Wind speed, two-dimensional wind sensor, wind speed and direction, Boundary layer, Physics::Space Physics, Range (statistics), Cylinder, lcsh:General Works, Geology, Physics::Atmospheric and Oceanic Physics, Wind tunnel
Abstract

Wind speed and direction are important parameters in meteorological observation. Solid wind sensor has needed with small Quadcopter for boundary layer meteorological observation. In this paper the principle of a cylindrical two-dimensional wind sensor is reported by analyzing the data from wind tunnel experiments. A model is proposed to describe the distribution of the pressure difference across a diameter of a cylinder and the wind sensor is fabricated with MEMS differential pressure sensors. In wind tunnel tests in range of 1~40 m/s, the relative speed measuring errors and the direction measuring errors of the prototype are no more than ±(0.2 + 0.03 V) m/s and 5° respectively.

Published
2018

Catalog

Books, media, physical & digital resources
See catalog results