检索结果-内蒙古大学图书馆

Correction to: On the use of adjoint gradients for time-optimal control problems regarding a discrete control parameterization

引用

Multibody System Dynamics 2023年第3期59卷 335-336页

作者： Lichtenecker, Daniel Rixen, Daniel Eichmeir, Philipp Nachbagauer, Karin TUM School of Engineering and Design Department of Mechanical Engineering Chair of Applied Mechanics Munich Institute of Robotics and Machine Intelligence (MIRMI) Technical University of Munich Munich Germany Institute of Mechanics and Mechatronics Vienna University of Technology Wien Austria Faculty of Engineering and Environmental Sciences University of Applied Sciences Upper Austria Wels Austria Institute for Advanced Study Technical University of Munich Garching Germany

来源：评论

学校读者我要写书评

暂无评论

Algorithm to Technology Co-Optimization for CiM-Based Hyperdimensional Computing

Algorithm to Technology Co-Optimization for CiM-Based Hyperd...

引用

design, Automation and Test in Europe Conference and Exhibition

作者： Mahta Mayahinia Simon Thomann Paul R. Genssler Christopher Münch Hussam Amrouch Mehdi B. Tahoori Department of Computer Science and Informatics Karlsruhe Institute of Technology Karlsruhe Germany Chair of AI Processor Design TUM School of Computation Information and Technology Technical University of Munich Munich Institute of Robotics and Machine Intelligence Munich Germany Semiconductor Test and Reliability University of Stuttgart Stuttgart Germany

ISBN: (数字)9783981926385

ISBN: (纸本)9798350348606

Hyperdimensional computing (HDC) has been recognized as an efficient machine learning algorithm in recent years. Robustness against noise and simple computational operations, while being limited by the memory bandwidth, make it a perfect fit for the concept of computation in memory (CiM) with emerging nonvolatile memory (NVM) technologies. For an HDC accelerator based on NVM-CiM, there are different parameters from the algorithm all the way down to the technology that interact with each other and affect the overall inference accuracy as well as the energy efficiency of the accelerator. Therefore, in this paper, we propose, for the first time, a full-stack co-optimization method and use it to design an HDC accelerator based on NVM-based content addressable memory (CAM). By incorporating the device manufacturing variability and co-optimizing the algorithm and hardware design, HDC inference on our proposed NVM-based CiM accelerator can reduce the energy consumption by 3.27x, while compared to the purely software-based implementation, the inference accuracy loss is merely 0.125%.

关键词： Associative memory Energy consumption machine learning algorithms Nonvolatile memory Noise Inference algorithms Hardware

来源：评论

学校读者我要写书评

暂无评论

machine learning with Monarch Butterfly Optimization for Prediction of Emergency Patient Admission Status 5

Machine learning with Monarch Butterfly Optimization for Pre...

引用

5th IEEE International Conference on Electrical, Computer and Communication Technologies, ICECCT 2023

作者： Vijayarangam, S. Vasundhara, S. Beherac, Nihar Ranjan Das, Shyamali Chandre, Shanker Rajagopal, R. Sri Indu College of Engineering and Technology Department of Computer Science and Engineering Telangana Hyderabad India G.Narayanamma Institute of Technology and Science Department of Humanities and Mathematics Telangana Hyderabad India Swiss School of Business and Management Geneva Petit-Lancy1213 Switzerland CMR Institute of Technology AECS Layout Department of Artificial Intelligence and Machine Learning Karnataka Bangalore India SR University Department of Computer Science & Artificial Intelligence Telangana Warangal India Alliance College of Engineering & Design Department of Computer Science & Engineering Alliance University Karnataka Bengaluru India

ISBN: (纸本)9781665493604

Emergency admission is one of the most important resources of healthcare expenditure. The accessibility of predictive methods is support to recognize the admission status of arriving patients and the patient mix that supports managing downstream resources and decreasing overpopulation at emergency department (ED) by restriction boarding delays. In recent times, machine learning (ML) techniques are well enhanced and executed in several applications like health protection, cancer detection, and hospital operations. But, most difficult problem with ML is that each technique has parameter and without optimizing the parameter, attaining a higher accuracy method develops very complex. This study introduces machine learning with Monarch Butterfly Optimization for Prediction of Emergency Patient Admission Status (MLMBO-PEP A) technique. The presented MLMBO-PEP A technique can predict the admission status of the emergency patient. In the presented MLMBO-PEP A technique, data normalization is initially performed to scale the medical data. For predictive process, the MLMBO-PEP A technique uses Dendritic Neuron Model (DRN). The MBO technique is used to optimize the forecasting outcomes of the DRN model. A widespread simulation study is performed for ensuring the better performance of the MLMBO-PEP A technique. The resultant values implied the improved efficacy of the MLMBO-PEP A technique under different evaluation metrics. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

DynamicAvatars: Accurate Dynamic Facial Avatars Reconstruction and Precise Editing with Diffusion Models

arXiv

引用

arXiv 2024年

作者： Qian, Yangyang Sun, Yuan Guo, Yu School of Software Engineering Xi’an Jiaotong University China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Xi’an Jiaotong University China National Engineering Research Center for Visual Information and Applications Xi’an Jiaotong University China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

Generating and editing dynamic 3D head avatars are crucial tasks in virtual reality and film production. However, existing methods often suffer from facial distortions, inaccurate head movements, and limited fine-grained editing capabilities. To address these challenges, we present DynamicAvatars, a dynamic model that generates photorealistic, moving 3D head avatars from video clips and parameters associated with facial positions and expressions. Our approach enables precise editing through a novel prompt-based editing model, which integrates user-provided prompts with guiding parameters derived from large language models[26] (LLMs). To achieve this, we propose a dual-tracking framework based on Gaussian Splatting and introduce a prompt preprocessing module to enhance editing stability. By incorporating a specialized GAN algorithm and connecting it to our control module, which generates precise guiding parameters from LLMs, we successfully address the limitations of existing methods. Additionally, we develop a dynamic editing strategy that selectively utilizes specific training datasets to improve the efficiency and adaptability of the model for dynamic editing tasks. Copyright © 2024, 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 Generalizable Multi-Object Tracking

arXiv

引用

arXiv 2024年

作者： Qin, Zheng Wang, Le Zhou, Sanping Fu, Panpan Hua, Gang Tang, Wei 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 China School of Software Engineering Xi’an Jiaotong University China Wormpex AI Research University of Illinois Chicago United States

Multi-Object Tracking (MOT) encompasses various tracking scenarios, each characterized by unique traits. Effective trackers should demonstrate a high degree of generalizability across diverse scenarios. However, existing trackers struggle to accommodate all aspects or necessitate hypothesis and experimentation to customize the association information (motion and/or appearance) for a given scenario, leading to narrowly tailored solutions with limited generalizability. In this paper, we investigate the factors that influence trackers’ generalization to different scenarios and concretize them into a set of tracking scenario attributes to guide the design of more generalizable trackers. Furthermore, we propose a "point-wise to instance-wise relation" framework for MOT, i.e., GeneralTrack, which can generalize across diverse scenarios while eliminating the need to balance motion and appearance. Thanks to its superior generalizability, our proposed GeneralTrack achieves state-of-the-art performance on multiple benchmarks and demonstrates the potential for domain generalization. https://***/qinzheng2000/*** Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Compositional Safety Verification of Infinite Networks: A Data-Driven Approach

Compositional Safety Verification of Infinite Networks: A Da...

引用

European Control Conference (ECC)

作者： Ali Aminzadeh Abdalla Swikir Sami Haddadin Abolfazl Lavaei University of Technology Iran Munich Institute of Robotics and Machine Intelligence Technical University of Munich Germany Department of Electrical and Electronic Engineering Omar Al-Mukhtar University (OMU) Albaida Libya School of Computing Newcastle University United Kingdom

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

This paper develops a compositional framework for formal safety verification of an interconnected network comprised of a countably infinite number of discrete-time nonlinear subsystems with unknown mathematical models. Our proposed scheme involved subdividing the infinite network problem into individual subsystems, wherein the safety concept is modelled through a robust optimization program (ROP) via a notion of local-barrier certificates (L-BC). To address the difficulties associated with solving the ROP directly, primarily due to the absence of a mathematical model, we gather finite data from subsystem trajectories and leverage them to provide a scenario optimization program (SOP). We proceed with solving the resulted SOP and construct a local-barrier certificate for each unknown subsystem with a guarantee of correctness. Finally, in accordance with some small-gain conditions, we construct a global-barrier certificate (G-BC) derived from individual local certificates of subsystems, thus guaranteeing the safety of the infinite network within infinite time horizons. The practicality of our compositional findings becomes evident through a vehicle platooning scenario, characterized by a countably infinite number of vehicles with a single leader and an unlimited number of followers.

关键词： Europe Mathematical models Safety Trajectory Arrays Optimization

来源：评论

学校读者我要写书评

暂无评论

HSIDMamba: Exploring Bidirectional State-Space Models for Hyperspectral Denoising

arXiv

引用

arXiv 2024年

作者： Liu, Yang Xiao, Jiahua Guo, Yu Jiang, Peilin Yang, Haiwei Wang, Fei 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 Shaanxi Xi’an710049 China School of software Xi’an Jiaotong University Shaanxi Xi’an710049 China

Effectively discerning spatial-spectral dependencies in HSI denoising is crucial, but prevailing methods using convolution or transformers still face computational efficiency limitations. Recently, the emerging Selective State Space Model(Mamba) has risen with its nearly linear computational complexity in processing natural language sequences, which inspired us to explore its potential in handling long spectral sequences. In this paper, we propose HSIDMamba(HSDM), tailored to exploit the linear complexity for effectively capturing spatial-spectral dependencies in HSI denoising. In particular, HSDM comprises multiple Hyperspectral Continuous Scan Blocks, incorporating BCSM(Bidirectional Continuous Scanning Mechanism), scale residual, and spectral attention mechanisms to enhance the capture of long-range and local spatial-spectral information. BCSM strengthens spatial-spectral interactions by linking forward and backward scans and enhancing information from eight directions through SSM, significantly enhancing the perceptual capability of HSDM and improving denoising performance more effectively. Extensive evaluations against HSI denoising benchmarks validate the superior performance of HSDM, achieving state-of-the-art results in performance and surpassing the efficiency of the latest transformer architectures by 30%. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Structure Consistent Unsupervised Domain Adaptation for Driver Behavior Recognition

Structure Consistent Unsupervised Domain Adaptation for Driv...

引用

International Conference on Intelligent Transportation

作者： Yuying Liu Shaoyi Du Qinbo Guo Zhiyue Zhao Zhiqiang Tian 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 Xi'an China School of Software Engineering Xi'an Jiaotong University Xi'an China

Driver distraction recognition is critical for assisted driving and intelligent vehicles, while often fails in cross-domain scenarios. Previous studies only focus on behavior recognition on a single data set, ignoring the case of inconsistent distribution between training and test sets (domains). To eliminate the domain gap caused by different persons or scenarios, we propose a domain adaptation framework for cross-domain distracted driver recognition, which aims to reduce the domain gap by constraining the feature separability of the source and target domains and maximizing the similarity of the feature structures of the two domains. Firstly, we represent the structure of the domain-level distribution by the spatial relationship between classes in the feature space, where the class is represented by class prototypes to avoid the perturbation of noise samples. Secondly, we utilize the structure consistency across domains by defining the spatial relationship between classes in terms of sample-to-class distances and encourage this relationship to be consistent when adapting from source to target domain. Thirdly, we build a new cross-domain dataset for driver distraction behavior, which contains two public datasets and one self-collected dataset. Experiments demonstrate that the proposed method can effectively alleviate the driver-distracted behavior recognition problem across datasets and obtain distinguishable results compared to existing UDA methods. Code is available at: https://***/seizetheday00/Structure_consist_UDA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Return of Small-Scale Crowd Counting via Fast and Accurate Semi-Supervised Least Squares Model

Return of Small-Scale Crowd Counting via Fast and Accurate S...

引用

IEEE Symposium Series on Computational intelligence (SSCI)

作者： Hao Luo Shaoyi Du Zhiqiang Tian School of Software Engineering Xi'an Jiaotong University Xi'an China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence Institute of Artificial Intelligence and Robotics National Engineering Research Center for Visual Information and Applications Xi'an Jiaotong University Xi'an China

Existing crowd counting techniques have achieved significant progress with the emergence of deep learning. During development, emerging crowd counting methods have generally become more and more complex and enormous, enabling them to understand and process more prior knowledge from input data. However, they suffer from two major drawbacks: 1) they generally require a significant amount of labeled training samples, which is labor-intensive, and 2) they require increasing computational hardware resources, making it luxurious and impractical to apply directly in small-scale scenes. To address these issues, we formulate crowd counting as a classification problem and leverage least squares model with a novel semi-supervised strategy. Technically, we construct the least squares model based on only two regularization terms: a regression term and a discriminative relaxation term. Moreover, we propose a semi-supervised soft label correcting strategy incorporated in the model. As a result, a fast and accurate crowd counting method is achieved. Experimental results on five small-scale benchmarks demonstrate the proposed method outperforms the other competitors in terms of both regression metrics and consumed time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-View fMRI Model with Voxel Inner State for Vision Encoding

A Multi-View fMRI Model with Voxel Inner State for Vision En...

引用

Chinese Automation Congress (CAC)

作者： Yueying Li Hao Wu 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 School of Electrical Engineering Xi'an University of Technology Xi'an China

Visual encoding and decoding is an important tool to explore brain neural function, how to establish an efficient and accurate encoding model is an important issue in fMRI brain visual encoding tasks. However, due to the low signal-to-noise ratio and the high-dimensional characteristics of fMRI signal, it is difficult to extract response component from voxels which has high correlation with external image stimulus. Traditional fMRI encoding models ignore the voxel inner state and noise components in fMRI response, In this work, We present a novel approach of encoding by adding voxel mode into the encoding stage, which is ignored in previous study. We propose a multi-view voxel-wise encoding model with two input modes, independently extract voxel features and stimuli features. Our multi-view encoding model takes voxel inner state into encoding stage, and uses feature-irrelevant voxels to perform noise reduction for feature-relevant voxels simultaneously, thus reach a higher explain variance (R 2 ) of encoding result and higher image identification accuracy of decoding result. Our work is helpful for further exploring the characteristics of visual cortex and understanding the mechanism of brain visual pathway.

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：