检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Xing, Lei Liu, Yufei Xu, Linhai Chen, Badong National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi’an China

Robust estimation is a fundamental task in statistical analysis, aimed at identifying models that can effectively eliminate the impact of noise, especially in the presence of outliers. The Least Trimmed Squares (LTS) estimation approach is widely recognized for its robustness in such scenarios. However, selecting a representative subset of samples for LTS estimation is a computationally demanding task, and the effectiveness of LTS is sensitive to the number of samples selected. In this study, we propose a novel approach, continuously differentiable LTS (CD-LTS), which employs a continuous function to approximate the original LTS. Due to its continuity and differentiability properties, CD-LTS can be used as a cost function for a range of learning models and avoids the need for additional sorting steps, thereby addressing the difficulty of applying traditional LTS directly. We utilize the CD-LTS to develop four robust learning algorithms, including the random vector functional link (RVFL), principal component analysis (PCA), iterative closest point (ICP), and orthogonal iterative (OI). The experimental results indicate that the proposed algorithms exhibit superior performance compared to existing methods. © 2024, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Self-consistency training for density-functional-theory hamiltonian prediction 24

Self-consistency training for density-functional-theory hami...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： He Zhang Chang Liu Zun Wang Xinran Wei Siyuan Liu Nanning Zheng Bin Shao Tie-Yan Liu National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University and Microsoft Research AI for Science Microsoft Research AI for Science National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University

Predicting the mean-field Hamiltonian matrix in density functional theory is a fundamental formulation to leverage machine learning for solving molecular science problems. Yet, its applicability is limited by insufficient labeled data for training. In this work, we highlight that Hamiltonian prediction possesses a self-consistency principle, based on which we propose self-consistency training, an exact training method that does not require labeled data. It distinguishes the task from predicting other molecular properties by the following benefits: (1) it enables the model to be trained on a large amount of unlabeled data, hence addresses the data scarcity challenge and enhances generalization; (2) it is more efficient than running DFT to generate labels for supervised training, since it amortizes DFT calculation over a set of queries. We empirically demonstrate the better generalization in data-scarce and out-of-distribution scenarios, and the better efficiency over DFT labeling. These benefits push forward the applicability of Hamiltonian prediction to an ever-larger scale.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LSTM with AhI-Model Based Kalman Filter for Lithium-ion Battery State of Charge Estimation

LSTM with AhI-Model Based Kalman Filter for Lithium-ion Batt...

引用

Chinese Automation Congress (CAC)

作者： Xiangyong Luo Lujuan Dang Meng Yang Badong Chen National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Accurate state of charge (SOC) estimation of lithium-ion battery in battery management system (BMS) is important for the safety and reliability of electronic devices and electric vehicles. This paper proposes a LSTM-extended Kalman filter based on AhI-model (LSTM-EA), which constrains SOC result from LSTM with an AhI-model based Kalman filter. AhI-model is based on Ampere-hour integration method and requires simpler structure to obtain estimated SOC with higher accuracy and robustness. In the experiments, the public datasets from the center for Advanced Life Cycle engineering (CALCE) are used to validate the SOC estimation performance. The mean absolute error (MAE) and maximum error of the proposed method are less than 2.51% and 8.82% respectively.

关键词： Lithium-ion batteries Accuracy Fluctuations Estimation Electric vehicles Robustness Safety State of charge Kalman filters Long short term memory

来源：评论

学校读者我要写书评

暂无评论

An Effective Two-time Scale Composite Control Contraction Based Chaotic Trajectory Tracking of Two-link Flexible Manipulator

An Effective Two-time Scale Composite Control Contraction Ba...

引用

IEEE Conference on Decision and Control

作者： Kshetrimayum Lochan Asim Khan Binoy Krishna Roy Bidyadhar Subudhi Lakmal Seneviratne Irfan Hussain Department of Mechanical Engineering Khalifa University Center for Robotics and Autonomous Systems (KUCARS) Khalifa University United Arab Emirates Department of Electrical Engineering National Institute of Technology Silchar India Department of Electrical Engineering National Institute of Technology Warangal India

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

In this paper, a two-link flexible manipulator n-dimensional model is developed using the assumed modes method. Based on this model, the manipulator dynamics are segregated into two subsystems by the two-time scale decomposition method of singular perturbation. Subsequently, a contraction-based control theory and a backstepping control of composite controller are investigated for the desired chaotic trajectory tracking along with tip deflection vibration suppression. In the two subsystems, the slow subsystem is involved in the modelling of the joint angles, and the fast subsystem is for corrected flexible modes of vibration suppression. In order to guarantee strict stability, Lyapunov’s stability is realized for closed-loop system uniform boundedness. Thus, by choosing the control parameters appropriately, the system states converge to a neighborhood of asymptotic stability. Eventually, extensive validation by comparative simulations of the Quanser model of the two-link flexible manipulator is carried out to demonstrate and indicate the effectiveness of the proposed composite controller in terms of faster tip deflection vibration suppression and better trajectory tracking.

关键词： Vibrations Asymptotic stability Backstepping Trajectory tracking Perturbation methods Stability analysis Robustness Control theory Complexity theory Manipulator dynamics

来源：评论

学校读者我要写书评

暂无评论

Autonomous Exploration of Mobile Robot Equipped with Lidar for High-Quality Reconstruction in Large-Scale Indoor Environments

SSRN

引用

SSRN 2025年

作者： Shih, Pin-Chu Chiang, Yun-Chi Hu, Jun-Jie Fu, Li-Chen Department of Electrical Engineering National Taiwan University Taipei100 Taiwan NTU Center for Artificial Intelligence and Advanced Robotics National Taiwan University Taipei100 Taiwan

High-quality 3D reconstruction is essential for ap- plications such as autonomous driving, AR/VR, and smart cities. Traditional methods using handheld sensors often result in incomplete and misaligned models. While autonomous explo- ration can improve these results, it often sacrifices quality for speed. In this paper, we propose a system for high-quality 3D reconstruction of large-scale indoor environments through autonomous exploration using a mobile robot equipped with a solid-state LiDAR on a 2-degree-of-freedom gimbal. This system not only controls the mobile robot to visit unknown places and areas with insufficient reconstruction quality but also facilitates high-frequency, real-time exploration path planning. This paper concludes with various simulations and real-world experiments to validate the effectiveness of our system. © 2025, The Authors. All rights reserved.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Towards Optimal Lane-changing Coordination of CAVs in Multi-lane Mixed Traffic Scenarios

Towards Optimal Lane-changing Coordination of CAVs in Multi-...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Yan Ding Yijun Mao Chongshan Jiao Pengju Ren National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Lane changing is a fundamental but challenging operation for moving vehicles. Connected and Automated Vehicles(CAVs) enable autonomous vehicles to cooperate with each other to accomplish the lane changing tasks, profiting from their communication ability. However, dispatching CAVs in mixed traffic remains difficult due to the stochastic behaviors and uncertain intentions of Human-Driven Vehicles(HDVs). To tackle this issue, this paper devises a coordination approach based on Conflict-Based Search(CBS) theory. Firstly, HDVs are accurately modeled as constraints to enable usage of CBS in the mixed traffic. Additionally, virtual goals are introduced to search CAVs’ priority and outlets along with path finding. Furthermore, we optimize the performance of CBS in dense traffic by defining the concept of following vehicles. Experiments show that performance is improved by utilizing new conflict prioritizing rules and a heuristic value calculation method that derived from following vehicles. Finally, we introduce grouping vehicles to extend the proposed method for solving extremely dense and large instances at a scale of more than one hundred without significant loss in efficiency.

关键词： Bellows Transportation Stochastic processes Dispatching Planning Numerical models Resource management

来源：评论

学校读者我要写书评

暂无评论

A Step Ahead Students CGPA Prediction Based on Support Vector Machines 2

A Step Ahead Students CGPA Prediction Based on Support Vecto...

引用

2nd IEEE International Conference on Artificial Intelligence in Everything, AIE 2022

作者： Mubarak, Mubarak Dauda Ameen, Zubaida Said Mubarak, Auwalu Saleh Al-Turjman, Fadi Ai and Robotics Institute Near East University Artificial Intelligence Engineering Dept. Mersin 10 Nicosia Turkey University of Kyrenia Research Center for Ai and IoT Faculty of Engineering Mersin 10 Kyrenia Cyprus Research Center for Ai and IoT Al and Robotics Institute Near East University Artificial Intelligence Dept. Mersin 10 Turkey

ISBN: (数字)9781665474009

ISBN: (纸本)9781665474009

For university students, the CGPA forecast is useful. Through this method, students will simply be able to estimate their final result. The students will be able to prepare themselves for a positive outcome as a conclusion. Students occupy their time by taking part in a range of activities. Machine learning is an application of Al that enables systems to learn and improve from experience without being explicitly programmed. No matter how intelligent a student is, planning is a necessary step in achieving a respectable GPA. On the other hand, the majority of the students are not good at managing their studies, time, and a good GPA, this aims to bring ease to their responsibilities with easy access to paramount information and other academic activities simplified. SVM regression, linear regression, and simple linear regression are all used in educational data mining. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Optimal Design of Vibrating Screen Parameters Based on Neural Network 21

Optimal Design of Vibrating Screen Parameters Based on Neura...

引用

5th International Conference on Electronic Information Technology and Computer engineering, EITCE 2021

作者： Li, Shipei Wang, Chunlei Ning, Yeyan Ma, Baoping Robotics Engineering Center The 21st Research Institute of CETC Shanghai China

ISBN: (纸本)9781450384322

In order to improve the screening efficiency of the vibrating screen, this article takes the material particles as the research object, uses the orthogonal experiment method to design multiple sets of tests, and uses the discrete element method (DEM) to determine the amplitude, frequency and inclination of the vibrating screen. The kinematic parameters that affect the screening efficiency are analyzed, and the change law of the screening efficiency with the three parameters is obtained. Multivariate nonlinear fitting was performed on the orthogonal test results, and the neural network was used to find the parameter values corresponding to the best screening efficiency on the basis of the fitting function. The result indicated that the best parameters found were consistent with the simulation results. © 2021 ACM.

关键词： Finite difference method

来源：评论

学校读者我要写书评

暂无评论

High Performance Soft Electrochemical Actuators Based on Hierarchical Conductive Polymer Ionogels

引用

Journal of Bionic engineering 2023年第6期20卷 2755-2763页

作者： Hongwei Hu Shengtao Zhang Yan Li Xinghao Hu Lin Xu Aixin Feng Guanggui Cheng Jianning Ding Zhejiang Provincial Key Laboratory of Laser Processing Robotics College of Mechanical and Electrical EngineeringWenzhou UniversityWenzhou325035China Institute of Intelligent Flexible Mechatronics Jiangsu UniversityZhenjiang212013China School of Mechanical Engineering Jiangsu University of Science and TechnologyZhenjiang212100China School of Mechanical Engineering Yangzhou UniversityYangzhou225127China Jiangsu Collaborative Innovation Center of Photovoltaic Science and Engineering Changzhou UniversityChangzhou213164China Ruian Graduate School of Wenzhou University Ruian325207ZhejiangChina

Electrochemical actuators based on conductive polymers are emerging as a strong competitive in the field of soft actuators because of their intrinsically conformable/elastic nature,low cost,low operating voltage and air-working *** development has shown that adding electroactive materials,such as CNT and graphene,can improve their actuation *** the complex material systems used,their output strains(one of the key factors)are generally lower than 1%,which limited further applications of them in multiple ***,we report soft electrochemical actuators based on conductive polymer ionogels by embedding polyaniline particles between the PEDOT:PSS *** show that such a hierarchical structure not only leads to a high conductivity(1250 S/cm)but also improved electrochemical *** a low operating voltage of 1 V,the maximum strain of these soft actuators reaches an exceptional value of 1.5%,with a high blocking force of 1.3 *** these high-performance electrochemical actuators,we demonstrate soft grippers for manipulating object and a bionic flower stimulated by an electrical *** work sets an important step towards enabling the enhanced performance of electrochemical actuators based on conductive polymers with designed microstructures.

关键词： Conductive polymer Soft actuator Polyaniline PEDOT:PSS Bioinspired actuator

来源：评论

学校读者我要写书评

暂无评论

Diffusion model with cross attention as an inductive bias for disentanglement 24

Diffusion model with cross attention as an inductive bias fo...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Tao Yang Cuiling Lan Yan Lu Nanning Zheng National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University China Microsoft Research Asia

ISBN: (纸本)9798331314385

Disentangled representation learning strives to extract the intrinsic factors within the observed data. Factoring these representations in an unsupervised manner is notably challenging and usually requires tailored loss functions or specific structural designs. In this paper, we introduce a new perspective and framework, demonstrating that diffusion models with cross-attention itself can serve as a powerful inductive bias to facilitate the learning of disentangled representations. We propose to encode an image into a set of concept tokens and treat them as the condition of the latent diffusion model for image reconstruction, where cross attention over the concept tokens is used to bridge the encoder and the U-Net of the diffusion model. We analyze that the diffusion process inherently possesses the time-varying information bottlenecks. Such information bottlenecks and cross attention act as strong inductive biases for promoting disentanglement. Without any regularization term in the loss function, this framework achieves superior disentanglement performance on the benchmark datasets, surpassing all previous methods with intricate designs. We have conducted comprehensive ablation studies and visualization analyses, shedding a light on the functioning of this model. We anticipate that our findings will inspire more investigation on exploring diffusion model for disentangled representation learning towards more sophisticated data analysis and understanding.

关键词：

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：