检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Ziwei Li, Siyang Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Brain-inspired Intelligent Systems School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Epilepsy significantly impacts global health, affecting about 65 million people worldwide, along with various animal species. The diagnostic processes of epilepsy are often hindered by the transient and unpredictable nature of seizures. Here we propose a multi-space alignment approach based on cross-species and cross-modality electroencephalogram (EEG) data to enhance the detection capabilities and understanding of epileptic seizures. By employing deep learning techniques, including domain adaptation and knowledge distillation, our framework aligns cross-species and cross-modality EEG signals to enhance the detection capability beyond traditional within-species and within-modality models. Experiments on multiple surfaces and intracranial EEG datasets of humans and canines demonstrated substantial improvements in detection accuracy, achieving over 90% AUC scores for cross-species and cross-modality seizure detection with extremely limited labeled data from the target species/modality. To our knowledge, this is the first study that demonstrates the effectiveness of integrating heterogeneous data from different species and modalities to improve EEG-based seizure detection performance. This is a pilot study that provides insights into the challenges and potential of multi-species and multi-modality data integration, offering an effective solution for future work to collect huge EEG data to train large brain models. © 2024, CC BY.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Streaming-Data-Driven Multi-Objective Optimal Operation for Ammonia-based Integrated Energy Chemical Systems:An Event-Triggered Scheme

Streaming-Data-Driven Multi-Objective Optimal Operation for ...

引用

第42届中国控制会议

作者： Longyan Li Chao Ning Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of EducationEast China University of Science and Technology

As an important component in the industry sector,the integrated energy chemical system is inescapably responsible for carbon reduction in addition to economic and reliability *** propose a novel streaming-data-driven multi-objective optimal operation for ammonia-based integrated energy chemical systems（AIECS）.In the day ahead scheduling,a detailed mathematical model for AIECS is presented,upon which a multi-objective optimization considering cost,CO emission and reliability is *** the intra-day operation,an event-triggered mechanism is firstly developed in the real-time operation of AIECS,and it enables the AIECS to be risk-aware just in *** monitoring the difference between the predicted state of charge and the capacity limitations of battery,the AIECS identifies whether it is in hazardous ***,the intelligent switch between certainty equivalence model predictive control and online-learning based distributionally robust model predictive control is proposed,such that their respective advantages are *** studies demonstrate that the proposed approach guarantees the system safety,and brings good revenue.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Distributionally Robust Planning of Energy Hub Coupled with Carbon Capture Utilization and Storage Facilities

Data-Driven Distributionally Robust Planning of Energy Hub C...

引用

第42届中国控制会议

作者： Xutao Ma Chao Ning Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education East China University of Science and Technology

Toward carbon peaking and carbon neutrality goals in China, a transition from traditional fossil power to renewable energy becomes an imperative need. This paper aims to address the planning problem of a highly renewable-energy penetrated energy hub system, coupled with carbon capture facilities and downstream production processes of hydrogen and methanol,under the uncertainty of renewable power output. To this end, we propose a two-stage distributionally robust optimal planning model, where investment decisions are the first-stage variables and operation variables are determined at the second stage after the realization of uncertainty. In the proposed model, we utilize historical data samples to construct a strengthened ambiguity set that leverages both Wasserstein distance and moment information for a better characterization of renewable generation uncertainty. Moreover, to efficiently solve the proposed planning problem, we develop a simplified affine decision rule method in a general setting with both moment and Wasserstein ambiguity, and then apply it to reformulate the distributionally robust planning problem. The derived reformulation possesses the favorable property that its scale is free from the sample size, thus greatly reducing the computational complexity. Computational results validate the effectiveness of the proposed planning model and the computational efficiency of the solution methodology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Probabilistic Topology Inference Method for Networked Dynamical System via Single Excitation

A Probabilistic Topology Inference Method for Networked Dyna...

引用

IEEE Conference on Decision and control

作者： Qing Jiao Yushan Li Jianping He Dept. of Automation Key Laboratory of System Control and Information Processing Ministry of Education of China and Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

A growing number of works have investigated inferring the topology of networked dynamical systems from observations, such as to better understand the system behaviour. Despite the tremendous advances, most of them require the observations to be abundant. This paper focuses on inferring the topology by injecting single excitation on a node and collecting several steps of noisy observations. The problem is challenging because the noises cannot be depressed in several observations and are mixed with the injected excitation, making it hard to directly reveal the topology. To practice, we develop a probabilistic method based on the hypothesis test framework. First, we infer the neighbors that are within h-hop of the excited node and derive the accuracy guarantees. Then, we extend the method to infer the exact h-hop neighbors. A computable lower bound for the accuracy probability is established to provide confidence support in the inference procedures. Furthermore, we give the conditions of excitation input to ensure a desired inference probability, which provides guidance for the input design. Numerical simulations are conducted to verify the effectiveness of the proposed method.

关键词： Lower bound Accuracy Network topology Noise Probabilistic logic Numerical simulation Topology Noise measurement Reliability Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal De-Deviation for Enhancing Few-Shot Classification

SSRN

引用

SSRN 2023年

作者： Pan, Mei-Hong Shen, Hong-Bin School of Electronic Information and Electrical Engineering Shanghai Jiaotong University China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China

Few-shot learning poses a critical challenge due to the deviation problem caused by the scarcity of available samples. In this work, we aim to address deviations in both feature representations and prototypes. To achieve this, we propose a cross-modal de-deviation framework that leverages class semantic information to provide robust prior knowledge for the samples. This framework begins with a visual-to-semantic autoencoder trained on the labeled samples to predict semantic features for the unlabeled samples. Then, we devise a binary linear programming model to incorporate the initial prototypes with the cluster centers of the unlabeled samples. To avoid mismatch between the cluster centers and the initial prototypes, we conduct the label assignment process in the semantic space using the class ground truth semantic features as the reference points, with the cluster centers transformed into semantic representations. Moreover, we model a linear classifier with the concatenation of the refined prototypes and the class ground truth semantic features serving as the initial weights. Then we propose a novel optimization strategy based on the alternating least squares (ALS) model. From the ALS model, we can derive two closed-form solutions regarding to the features and weights, facilitating alternative optimization of them. Extensive experiments conducted on three standard benchmarks demonstrate the competitive advantages of our CMDD method over the state-of-the-art few-shot classification methods, confirming its effectiveness in reducing deviation. © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

UniAnimate: Taming Unified Video Diffusion Models for Consistent Human image Animation

arXiv

引用

arXiv 2024年

作者： Wang, Xiang Zhang, Shiwei Gao, Changxin Wang, Jiayu Zhou, Xiaoqiang Zhang, Yingya Yan, Luxin Sang, Nong Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Alibaba Group Hangzhou310052 China University of Science and Technology of China Hefei230026 China

Recent diffusion-based human image animation techniques have demonstrated impressive success in synthesizing videos that faithfully follow a given reference identity and a sequence of desired movement poses. Despite this, there are still two limitations: i) an extra reference model is required to align the identity image with the main video branch, which significantly increases the optimization burden and model parameters;ii) the generated video is usually short in time (e.g., 24 frames), hampering practical applications. To address these shortcomings, we present a UniAnimate framework to enable efficient and long-term human video generation. First, to reduce the optimization difficulty and ensure temporal coherence, we map the reference image along with the posture guidance and noise video into a common feature space by incorporating a unified video diffusion model. Second, we propose a unified noise input that supports random noised input as well as first frame conditioned input, which enhances the ability to generate long-term video. Finally, to further efficiently handle long sequences, we explore an alternative temporal modeling architecture based on state space model to replace the original computation-consuming temporal Transformer. Extensive experimental results indicate that UniAnimate achieves superior synthesis results over existing state-of-the-art counterparts in both quantitative and qualitative evaluations. Notably, UniAnimate can even generate highly consistent one-minute videos by iteratively employing the first frame conditioning strategy. Code and models will be publicly available. Project page: https://***/. Copyright © 2024, The Authors. All rights reserved.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

DAFormer: Depth-aware 3D Object Detection Guided by Camera Model via Transformers

DAFormer: Depth-aware 3D Object Detection Guided by Camera M...

引用

IEEE International Conference on Cyborg and Bionic Systems (CBS)

作者： Junbin Gao Hao Ruan Bingrong Xu Zhigang Zeng School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China School of Automation Wuhan University of Technology Wuhan China

3D object detection plays a critical role in autonomous driving perception. Although multi-view-based perception solutions have made significant progress, their performance is still far from being ready for practical use. The estimation of pixel depth is dependent on camera intrinsic properties, which led us to explore a depth-aware model guided by camera parameters. Our contribution in this paper is the DAFormer, which incorporates camera parameters and position-aware image features to detect 3D objects. The depthaware module uses camera parameters to reweight image features and estimate depth, enhancing and offsetting the 3D position embedding. The object query uses depth information enhanced features for end-to-end 3D detection by Attention layers. DAFormer achieves impressive results on the standard nuScenes dataset without any additional embellishments.

关键词： Solid modeling Three-dimensional displays Estimation Object detection Detectors Cameras Feature extraction

来源：评论

学校读者我要写书评

暂无评论

State-of-Charge Balancing control for Battery Energy Storage Systems of Near-Space Vehicles with An Electric-Thermal-Aging Coupling Model

State-of-Charge Balancing Control for Battery Energy Storage...

引用

第42届中国控制会议

作者： Zhiqiang Zuo Yunhao Du Yijing Wang Zhicheng Zhang Peng Li Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System School of Electrical and Information Engineering Tianjin University Key Laboratory of System Control and Information Processing Ministry of Education

State-of-charge(SoC) balancing is crucial for improving the efficiency and lifetime of the battery energy storage system in near-space vehicles. In this paper, the So C balancing control problem is investigated by a coupling battery model with electric-thermal-aging dynamics. Firstly, a system identification experiment is carried out to obtain the internal parameters of the battery. Secondly, a weight optimization index is designed by integrating the balancing speed and battery state-of-health(SoH). Then, a receding horizon control algorithm is proposed to realize multi-unit battery SoC balancing with partial swarm optimization(PSO). Finally, the effectiveness of the proposed strategy is verified by simulation results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online Identification of Boost Converter Components with Multiple Updating RLS Algorithm

Online Identification of Boost Converter Components with Mul...

引用

第42届中国控制会议

作者： Tong Zhou Zhicheng Zhang Zhiqiang Zuo Yijing Wang Peng Li Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System School of Electrical and Information EngineeringTianjin University Key Laboratory of System Control and Information Processing Ministry of Education

In this paper,component parameters of the boost converter are identified online using a multiple updating recursive least squares(MURLS) *** component parameters,such as resistance,inductor inductance and capacitor capacitance,are obtained directly through the identification procedure rather than transfer function *** MURLS algorithm is applied to improve the rapidity of system identification compared to the traditional recursive least squares(RLS) algorithm,which is verified by a comparative simulation between MURLS and RLS and the simulation of a load-switching scenario.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Load Prediction of Multiple Buildings Using Multi-Task Learning with Selected-Shared-Private Mechanism

SSRN

引用

SSRN 2023年

作者： Cao, Minghui Xiao, Jiang-Wen Fang, Hongliang Li, Yuan-Zheng Wang, Yan-Wu School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Ministry of Education Wuhan430074 China

Short-term load forecasting for residential buildings is of great significance to ensure the safe and economic operation of power grid. However, most of the existing prediction methods focus on the temporal characteristics of individual buildings and ignore the importance of spatial characteristics between different buildings. To tackle this problem and realize joint prediction for multiple buildings, a novel multi-task learning model with the selected-shared-private mechanism is proposed in this paper. Firstly, the temporal and spatial characteristics hidden in electricity consumption patterns are analyzed and represented by auto-correlation and cross-correlation, respectively. Then, a correlation-oriented combination strategy considering the auto-correlation and time dependency is proposed to build input set for the prediction model, and the temporal convolutional network is adopted to extract features. Furthermore, this paper designs a novel selected-shared-private mechanism based on the cross-correlation, which can selectively utilize information from related tasks while focusing on private features to improve prediction accuracy. The proposed model is compared with other methods on the public dataset, and the results demonstrate the superiority of this model in load prediction for multiple buildings. © 2023, The Authors. All rights reserved.

关键词： Forecasting

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：