Search

Your search keyword '"Liu Zeyuan"' showing total 678 results
Start Over Author "Liu Zeyuan"
678 results on '"Liu Zeyuan"'

1. Backstepping control of three‐degree‐of‐freedom hybrid magnetic bearing based on non‐linear disturbance observer

Author

Liu Chengzi, Zhao Yucheng, Yang Yan, and Liu Zeyuan

Subjects
Applications of electric power, TK4001-4102
Abstract

Abstract A backstepping controller based on a non‐linear disturbance observer (NDOB) was created to enhance the dynamic performance and reliability of three‐degree‐of‐freedom hybrid magnetic bearings. After the structure of three‐degree‐of‐freedom hybrid magnetic bearings is introduced, the mathematical model is established, and the equation of the state is derived by the equivalent magnetic circuit technique. Based on the mathematical model, non‐linear disturbance observer (NDOB) is designed and is used to predict the system disturbance, and the backstepping control algorithm is compensated. To verify the effectiveness of the proposed controller, the backstepping controller, proportion integration differentiation controller, and backstepping controller based on a NDOB were compared by simulation and experiment. Results show that the backstepping controller based on a NDOB has better dynamic performance and robustness.

Published
2023
Full Text
View/download PDF

2. The Impact of Pipe Inclination on Sediment Deposition at the Sedimentation Basin in the Yellow River

Author

ZHA Yingdong, HOU Peng, LIU Zeyuan, WANG Keyuan, LI Yunkai, and WANG Chunxia

Subjects
yellow river sediment, sediment basin, inclined pipe, inclined pipe layout form, Agriculture (General), S1-972, Irrigation engineering. Reclamation of wasteland. Drainage, TC801-978
Abstract

【Objective】 This paper aims to study the optimal layout of inclined pipes in sedimentation basins in attempts to improve sediment removal efficiency in the Yellow River. 【Method】 Three different layouts of inclined pipes were compared: a single layer (Fs), and two double-layer layouts (Fv1, Fv2), in a gravity-operated sedimentation basin. Sediment distribution of three typical particle sizes in the upstream (Su), middle stream (Sm), and downstream (Sd) was measured. Sediment tests were conducted under a low (Qq) and a high (Qs) flow rate to compare the impact of pipe inclination on sedimentation in the three layouts. 【Result】 The large granular sediment settled prior to entering the inclined pipes, while the fine particle sediment (

Published
2023
Full Text
View/download PDF

3. Identifying two pathogenic variants in a patient with pigmented paravenous retinochoroidal atrophy

Author

Liu Zeyuan, Wang He, He Xiaoli, Tao Dan, and Li Li

Subjects
rpgrip1, pigmented paravenous retinochoroidal atrophy, whole-exome sequencing, pathogenic variants, Biology (General), QH301-705.5
Abstract

Little is known about the genetic background of pigmented paravenous retinochoroidal atrophy (PPRCA) due to rarity of patients. In this study, we identified two pathogenic variants in RPGRIP1 in a 2-year-old boy with PPRCA screened by whole-exome sequencing (WES). The patient presented to our department with photophobia for 17 months, and then he underwent fundus photography and fluorescein fundus angiography. Genomic DNA was extracted from peripheral blood of the proband and the parents. Trio-WES strategy was utilized to identify the causal variants from the proband and the parents, followed by validation based on Sanger sequencing. The patient was finally diagnosed with PPRCA after differential diagnosis. Two heterozygous pathogenic variants were detected by WES according to the American college of medical genetics and genomics guidelines, including NM_020366.4: c.2592T > G: p.Y864* and NM_020366.4: c.154C > T: p.R52* in RPGRIP1 located in exon 17 and exon 3, leading to termination codon, respectively. This is the first study reporting pathogenic variants within RPGRIP1 as causal for PPRCA.

Published
2023
Full Text
View/download PDF

4. CDSA: Conservative Denoising Score-based Algorithm for Offline Reinforcement Learning

Author

Liu, Zeyuan, Yang, Kai, and Li, Xiu

Subjects
Computer Science - Machine Learning
Abstract

Distribution shift is a major obstacle in offline reinforcement learning, which necessitates minimizing the discrepancy between the learned policy and the behavior policy to avoid overestimating rare or unseen actions. Previous conservative offline RL algorithms struggle to generalize to unseen actions, despite their success in learning good in-distribution policy. In contrast, we propose to use the gradient fields of the dataset density generated from a pre-trained offline RL algorithm to adjust the original actions. We decouple the conservatism constraints from the policy, thus can benefit wide offline RL algorithms. As a consequence, we propose the Conservative Denoising Score-based Algorithm (CDSA) which utilizes the denoising score-based model to model the gradient of the dataset density, rather than the dataset density itself, and facilitates a more accurate and efficient method to adjust the action generated by the pre-trained policy in a deterministic and continuous MDP environment. In experiments, we show that our approach significantly improves the performance of baseline algorithms in D4RL datasets, and demonstrate the generalizability and plug-and-play capability of our model across different pre-trained offline RL policy in different tasks. We also validate that the agent exhibits greater risk aversion after employing our method while showcasing its ability to generalize effectively across diverse tasks.

Published
2024

5. World Models with Hints of Large Language Models for Goal Achieving

Author

Liu, Zeyuan, Huan, Ziyu, Wang, Xiyao, Lyu, Jiafei, Tao, Jian, Li, Xiu, Huang, Furong, and Xu, Huazhe

Subjects
Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

Reinforcement learning struggles in the face of long-horizon tasks and sparse goals due to the difficulty in manual reward specification. While existing methods address this by adding intrinsic rewards, they may fail to provide meaningful guidance in long-horizon decision-making tasks with large state and action spaces, lacking purposeful exploration. Inspired by human cognition, we propose a new multi-modal model-based RL approach named Dreaming with Large Language Models (DLLM). DLLM integrates the proposed hinting subgoals from the LLMs into the model rollouts to encourage goal discovery and reaching in challenging tasks. By assigning higher intrinsic rewards to samples that align with the hints outlined by the language model during model rollouts, DLLM guides the agent toward meaningful and efficient exploration. Extensive experiments demonstrate that the DLLM outperforms recent methods in various challenging, sparse-reward environments such as HomeGrid, Crafter, and Minecraft by 27.7\%, 21.1\%, and 9.9\%, respectively.

Published
2024

6. Adaptive Boosting with Fairness-aware Reweighting Technique for Fair Classification

Author

Song, Xiaobin, Liu, Zeyuan, and Jiang, Benben

Subjects
Computer Science - Machine Learning, Computer Science - Computers and Society, Electrical Engineering and Systems Science - Systems and Control
Abstract

Machine learning methods based on AdaBoost have been widely applied to various classification problems across many mission-critical applications including healthcare, law and finance. However, there is a growing concern about the unfairness and discrimination of data-driven classification models, which is inevitable for classical algorithms including AdaBoost. In order to achieve fair classification, a novel fair AdaBoost (FAB) approach is proposed that is an interpretable fairness-improving variant of AdaBoost. We mainly investigate binary classification problems and focus on the fairness of three different indicators (i.e., accuracy, false positive rate and false negative rate). By utilizing a fairness-aware reweighting technique for base classifiers, the proposed FAB approach can achieve fair classification while maintaining the advantage of AdaBoost with negligible sacrifice of predictive performance. In addition, a hyperparameter is introduced in FAB to show preferences for the fairness-accuracy trade-off. An upper bound for the target loss function that quantifies error rate and unfairness is theoretically derived for FAB, which provides a strict theoretical support for the fairness-improving methods designed for AdaBoost. The effectiveness of the proposed method is demonstrated on three real-world datasets (i.e., Adult, COMPAS and HSLS) with respect to the three fairness indicators. The results are accordant with theoretic analyses, and show that (i) FAB significantly improves classification fairness at a small cost of accuracy compared with AdaBoost; and (ii) FAB outperforms state-of-the-art fair classification methods including equalized odds method, exponentiated gradient method, and disparate mistreatment method in terms of the fairness-accuracy trade-off.

Published
2024

10. Research on Radar Target Recognition Based on Deep Learning

Author

Ren, Wenchao, Liu, Zeyuan, Lv, Rongxin, Ge, Yilin, 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, Hung, Jason C., editor, Yen, Neil, editor, and Chang, Jia-Wei, editor

Published
2024
Full Text
View/download PDF

11. Multi-Agent Coordination via Multi-Level Communication

Author

Ding, Ziluo, Liu, Zeyuan, Fang, Zhirui, Su, Kefan, Zhu, Liwen, and Lu, Zongqing

Subjects
Computer Science - Multiagent Systems, Computer Science - Machine Learning
Abstract

The partial observability and stochasticity in multi-agent settings can be mitigated by accessing more information about others via communication. However, the coordination problem still exists since agents cannot communicate actual actions with each other at the same time due to the circular dependencies. In this paper, we propose a novel multi-level communication scheme, Sequential Communication (SeqComm). SeqComm treats agents asynchronously (the upper-level agents make decisions before the lower-level ones) and has two communication phases. In the negotiation phase, agents determine the priority of decision-making by communicating hidden states of observations and comparing the value of intention, obtained by modeling the environment dynamics. In the launching phase, the upper-level agents take the lead in making decisions and then communicate their actions with the lower-level agents. Theoretically, we prove the policies learned by SeqComm are guaranteed to improve monotonically and converge. Empirically, we show that SeqComm outperforms existing methods in various cooperative multi-agent tasks., Comment: NeurIPS 2024

Published
2022

32. MTHFR C677T and MTR A2756G polymorphisms and the homocysteine lowering efficacy of different doses of folic acid in hypertensive Chinese adults

Author

Qin Xianhui, Li Jianping, Cui Yimin, Liu Zeyuan, Zhao Zhigang, Ge Junbo, Guan Deming, Hu Jian, Wang Yanni, Zhang Fumin, Xu Xin, Wang Xiaobin, Xu Xiping, and Huo Yong

Subjects
Folic acid supplementation, MTHFR C677T polymorphism, MTR A2756G polymorphism, Homocysteine-lowering efficacy, Nutrition. Foods and food supply, TX341-641, Nutritional diseases. Deficiency diseases, RC620-627
Abstract

Abstract Background This study aimed to investigate if the homocysteine-lowering efficacy of two commonly used physiological doses (0.4 mg/d and 0.8 mg/d) of folic acid (FA) can be modified by individual methylenetetrahydrofolate reductase (MTHFR) C677T and/or methionine synthase (MTR) A2756G polymorphisms in hypertensive Chinese adults. Methods A total of 480 subjects with mild or moderate essential hypertension were randomly assigned to three treatment groups: 1) enalapril only (10 mg, control group); 2) enalapril-FA tablet [10:0.4 mg (10 mg enalapril combined with 0.4 mg of FA), low FA group]; and 3) enalapril-FA tablet (10:0.8 mg, high FA group), once daily for 8 weeks. Results After 4 or 8 weeks of treatment, homocysteine concentrations were reduced across all genotypes and FA dosage groups, except in subjects with MTR 2756AG /GG genotype in the low FA group at week 4. However, compared to subjects with MTHFR 677CC genotype, homocysteine concentrations remained higher in subjects with CT or TT genotype in the low FA group (P < 0.05 for either of these genotypes) and TT genotype in the high FA group (P < 0.05). Furthermore, subjects with TT genotype showed a greater homocysteine-lowering response than did subjects with CC genotype in the high FA group (mean percent reduction of homocysteine at week 8: CC 10.8% vs. TT: 22.0%, P = 0.005), but not in the low FA group (CC 9.9% vs. TT 11.2%, P = 0.989). Conclusions This study demonstrated that MTHFR C677T polymorphism can not only affect homocysteine concentration at baseline and post-FA treatment, but also can modify therapeutic responses to various dosages of FA supplementation.

Published
2012
Full Text
View/download PDF

44. Information Extraction of Air-Traffic Control Instructions via Pre-trained Models

Author

Wang, Xuan, Ding, Hui, Xu, Qiucheng, Liu, Zeyuan, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, 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, Hirche, Sandra, 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, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, 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, Wang, Wei, editor, Mu, Jiasong, editor, Liu, Xin, editor, and Na, Zhenyu, editor

Published
2022
Full Text
View/download PDF

45. Generation Method of Control Strategy for Aircrafts Based on Hierarchical Reinforcement Learning

Author

Liu, Zeyuan, Xu, Qiucheng, Shi, Yanyang, Xu, Ke, Tan, Qingqing, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, 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, Hirche, Sandra, 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, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, 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, Wang, Wei, editor, Mu, Jiasong, editor, Liu, Xin, editor, and Na, Zhenyu, editor

Published
2022
Full Text
View/download PDF

46. Generation and Verification of Flight Forbidden Area in Convective Weather Based on Real Data

Author

Chen, Xi, Liu, Zeyuan, Tian, Yungang, Huang, Jibo, Ding, Hui, Chinese Society of Aeronautics and Astronautics, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, 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, Hirche, Sandra, 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, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, 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, and Zhang, Junjie James, Series Editor

Published
2022
Full Text
View/download PDF

47. Driving Signal Judgment of Track Circuit Based on Neural Network

Author

Lu, Jiao, Wu, Jingli, Jia, Zhiao, Liu, Zeyuan, Yu, Jianli, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, 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, Hirche, Sandra, 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, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, 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, and Deng, Zhidong, editor

Published
2022
Full Text
View/download PDF

48. The reliability and integrity of overall survival data based on follow-up records only and potential solutions to the challenges

Author

Huang, Huiyao, Tang, Yu, Yu, Yue, Yu, Anqi, Wu, Dawei, Fang, Hong, Wang, Shuhang, Sun, Chao, Wang, Xin, Fan, Qi, Fang, Yuan, Tang, Qiyu, Jiang, Ning, Du, Jingting, Miao, Huilei, Bai, Ying, Ma, Peiwen, Xing, Shujun, Cui, Dandan, Miao, Shuangman, Jiang, Yale, Zhu, Jingxiao, Zhu, Qi, Leng, Ye, Guo, Lan Wei, Liao, Shanmei, Shao, Yaguang, Song, Yinyin, Liu, Zeyuan, Hong, Minghuang, Luo, Suxia, Xu, Binghe, Lan, Gongtao, and Li, Ning

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results