检索结果-内蒙古大学图书馆

Two-Stage Robust Optimization Under Decision Dependent Uncertainty

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1295-1306页

作者： Yunfan Zhang Feng Liu Yifan Su Yue Chen Zhaojian Wang João P.S.Catalão State Key Laboratory of Power System and Generation Equipment the Department of Electrical EngineeringTsinghua UniversityBeijing 100084China Department of Mechanical and Automation Engineering the Chinese University of Hong KongHong Kong SARChina Ministry of Education Key Laboratory of System Control and Information Processing the Department of AutomationShanghai Jiao Tong Universityand also with Shanghai Engineering Research Center of Intelligent Control and ManagementShanghai 200240China Faculty of Engineering of the University of Porto and Institute for Systems and Computer Engineering Technology and Science(INESC TEC)Porto 4200-465Portugal IEEE

In the conventional robust optimization(RO)context,the uncertainty is regarded as residing in a predetermined and fixed uncertainty *** many applications,however,uncertainties are affected by decisions,making the current RO framework *** paper investigates a class of two-stage RO problems that involve decision-dependent *** introduce a class of polyhedral uncertainty sets whose right-hand-side vector has a dependency on the here-and-now decisions and seek to derive the exact optimal wait-and-see decisions for the second-stage problem.A novel iterative algorithm based on the Benders dual decomposition is proposed where advanced optimality cuts and feasibility cuts are designed to incorporate the uncertainty-decision *** computational tractability,robust feasibility and optimality,and convergence performance of the proposed algorithm are guaranteed with theoretical *** motivating application examples that feature the decision-dependent uncertainties are ***,the proposed solution methodology is verified by conducting case studies on the pre-disaster highway investment problem.

关键词： Benders decomposition decision-dependent uncertainty endogenous uncertainty robust optimization(RO)

来源：评论

学校读者我要写书评

暂无评论

Hard Exudate Segmentation Supplemented by Super-Resolution with Multi-scale Attention Fusion Module

Hard Exudate Segmentation Supplemented by Super-Resolution w...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Zhang, Jiayi Chen, Xiaoshan Qiu, Zhongxi Yang, Mingming Hu, Yan Liu, Jiang Southern University of Science and Technology Department of Computer Science and Engineering Guangdong Shenzhen51805 China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Guangdong Shenzhen51805 China Shenzhen People's Hospital Department of Ophthalmology Guangdong China

ISBN: (纸本)9781665468190

Hard exudates (HE) is the most specific biomarker for retina edema. Precise HE segmentation is vital for disease diagnosis and treatment, but automatic segmentation is challenged by its large variation of characteristics including size, shape and position, which makes it difficult to detect tiny lesions and lesion boundaries. Considering the complementary features between segmentation and super-resolution tasks, this paper proposes a novel hard exudates segmentation method named SSMAF with an auxiliary super-resolution task, which brings in helpful detailed features for tiny lesion and boundaries detection. Specifically, we propose a fusion module named Multi-scale Attention Fusion (MAF) module for our dual-stream framework to effectively integrate features of the two tasks. MAF first adopts split spatial convolutional (SSC) layer for multi-scale features extraction and then utilize attention mechanism for features fusion of the two tasks. Considering pixel dependency, we introduce region mutual information (RMI) loss to optimize MAF module for tiny lesions and boundary detection. We evaluate our method on two public lesion datasets, IDRiD and E-Ophtha. Our method shows competitive performance with low-resolution inputs, both quantitatively and qualitatively. On E-Ophtha dataset, the method can achieve ge 3% higher dice and recall compared with the state-of-the-art methods. © 2022 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference

arXiv

引用

arXiv 2025年

作者： Yuan, Cheng Liu, Zhening Lv, Jiashu Shao, Jiawei Jiang, Yufei Zhang, Jun Li, Xuelong of China Telecom China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong School of Software and Microelectronics Peking University China School of Electronic and Information Engineering Harbin Institute of Technology Shenzhen China

With the rapid development of large multimodal models (LMMs), multimodal understanding applications are emerging. As most LMM inference requests originate from edge devices with limited computational capabilities, the predominant inference pipeline involves directly forwarding the input data to an edge server which handles all computations. However, this approach introduces high transmission latency due to limited uplink bandwidth of edge devices and significant computation latency caused by the prohibitive number of visual tokens, thus hindering delay-sensitive tasks and degrading user experience. To address this challenge, we propose a task-oriented feature compression (TOFC) method for multimodal understanding in a device-edge co-inference framework, where visual features are merged by clustering and encoded by a learnable and selective entropy model before feature projection. Specifically, we employ density peaks clustering based on K nearest neighbors to reduce the number of visual features, thereby minimizing both data transmission and computational complexity. Subsequently, a learnable entropy model with hyperprior is utilized to encode and decode merged features, further reducing transmission overhead. To enhance compression efficiency, multiple entropy models are adaptively selected based on the characteristics of the visual features, enabling a more accurate estimation of the probability distribution. Comprehensive experiments on seven visual question answering benchmarks validate the effectiveness of the proposed TOFC method. Results show that TOFC achieves up to 60% reduction in data transmission overhead and 50% reduction in system latency while maintaining identical task performance, compared with traditional image compression methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Online Distributed Learning with Quantized Finite-Time Coordination

arXiv

引用

arXiv 2023年

作者： Bastianello, Nicola Rikos, Apostolos I. Johansson, Karl H. The School of Electrical Engineering and Computer Science and Digital Futures KTH Royal Institute of Technology Sweden The Department of Electrical and Computer Engineering Division of Systems Engineering Boston University BostonMA02215 United States

In this paper we consider online distributed learning problems. Online distributed learning refers to the process of training learning models on distributed data sources. In our setting a set of agents need to cooperatively train a learning model from streaming data. Differently from federated learning, the proposed approach does not rely on a central server but only on peer-to-peer communications among the agents. This approach is often used in scenarios where data cannot be moved to a centralized location due to privacy, security, or cost reasons. In order to overcome the absence of a central server, we propose a distributed algorithm that relies on a quantized, finite-time coordination protocol to aggregate the locally trained models. Furthermore, our algorithm allows for the use of stochastic gradients during local training. Stochastic gradients are computed using a randomly sampled subset of the local training data, which makes the proposed algorithm more efficient and scalable than traditional gradient descent. In our paper, we analyze the performance of the proposed algorithm in terms of the mean distance from the online solution. Finally, we present numerical results for a logistic regression task. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A Machine-Learning-based Surrogate Modeling Methodology for Submodel Integration in the Holistic Railway Digital Twin Platform 33

A Machine-Learning-based Surrogate Modeling Methodology for ...

引用

33rd CIRP Design Conference

作者： Zhou, Shiyang Meierhofer, Alexander Kugu, Ozan Xia, Yuxi Grafinger, Manfred TU Wien Institute of Engineering Design and Product Development Lehargasse 6/307 Vienna1060 Austria Virtual Vehicle Research GmbH Co-Simulation and Software Group Inffeldgasse 21a Graz8010 Austria University of Vienna Faculty of Computer Science Kolingasse 14-16 Vienna1090 Austria

A holistic railway infrastructure digital twin (DT) platform is sophisticated and consists of a series of submodels (e.g., turnouts, tracks, vehicles, etc.) that are built through various methodologies and software. However, integrating these submodels into the DT platform is tremendously challenging due to considerable computational complexity, software and interface restrictions. To this end, we designed a machine learning (ML) based surrogate modeling methodology for the submodel integration in the holistic railway infrastructure DT platform and illustrated the methodology through a case study. In this case study, an ML-based surrogate model for multibody simulation of railway vehicle-track dynamics is created, which can replace the railway vehicle-track simulation executed with the Multibody Dynamics (MBD) Simulation commercial software SimPACK. The well-built ML model can accurately and quickly predict the vehicle-track system's dynamic responses to different track irregularities. Besides, the integration process of the ML-based surrogate model into the DT platform through a standardized open-source Functional Mock-up Interface (FMI) is also proposed. The developed surrogate modeling methodology shows great promise owing to its high fidelity, which is verified by the measurement data collected from the Austrian national railway track system. The main contribution of our work lies in the well-built ML-based surrogate modeling methodology for reducing the computation complexity and time of different submodels, which facilitates the unification and integration of different submodels. Furthermore, this approach can also be applied to other submodels and help to build the holistic railway DT platform collaboratively. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models

arXiv

引用

arXiv 2024年

作者： Zhu, Yinghao Ren, Changyu Xie, Shiyun Liu, Shukai Ji, Hangyuan Wang, Zixiang Sun, Tao He, Long Li, Zhoujun Zhu, Xi Pan, Chengwei Institute of Artificial Intelligence Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Software Beihang University Beijing China China Mobile Research Institute Beijing China

The integration of multimodal Electronic Health Records (EHR) data has significantly improved clinical predictive capabilities. Leveraging clinical notes and multivariate time-series EHR, existing models often lack the medical context relevent to clinical tasks, prompting the incorporation of external knowledge, particularly from the knowledge graph (KG). Previous approaches with KG knowledge have primarily focused on structured knowledge extraction, neglecting unstructured data modalities and semantic high dimensional medical knowledge. In response, we propose REALM, a Retrieval-Augmented Generation (RAG) driven framework to enhance multimodal EHR representations that address these limitations. Firstly, we apply Large Language Model (LLM) to encode long context clinical notes and GRU model to encode time-series EHR data. Secondly, we prompt LLM to extract task-relevant medical entities and match entities in professionally labeled external knowledge graph (PrimeKG) with corresponding medical knowledge. By matching and aligning with clinical standards, our framework eliminates hallucinations and ensures consistency. Lastly, we propose an adaptive multimodal fusion network to integrate extracted knowledge with multimodal EHR data. Our extensive experiments on MIMIC-III mortality and readmission tasks showcase the superior performance of our REALM framework over baselines, emphasizing the effectiveness of each module. REALM framework contributes to refining the use of multimodal EHR data in healthcare and bridging the gap with nuanced medical context essential for informed clinical predictions. Copyright © 2024, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion

arXiv

引用

arXiv 2024年

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024, CC BY.

关键词： Color image processing

来源：评论

学校读者我要写书评

暂无评论

An EEG-based Intelligent Neuromarketing System for Predicting Consumers’ Choice 4th

An EEG-based Intelligent Neuromarketing System for Predicti...

引用

International Conference on 4th Industrial Revolution and Beyond, IC4IR 2021

作者： Mashrur, Fazla Rabbi Rahman, Khandoker Mahmudur Miya, Mohammad Tohidul Islam Vaidyanathan, Ravi Anwar, Syed Ferhat Sarker, Farhana Mamun, Khondaker A. Advanced Intelligent Multidisciplinary Systems Lab Institute of Advanced Research United International University Dhaka Bangladesh School of Business and Economics United International University Dhaka Bangladesh Department of Mechanical Engineering Imperial College London London United Kingdom Institute of Business Administration University of Dhaka Dhaka Bangladesh Department of Computer Science and Engineering University of Liberal Arts Bangladesh Dhaka Bangladesh

ISBN: (纸本)9789811980312

Marketers use different marketing strategies to elicit the desired response from the target customers. To measure customer engagement, they usually conduct one-on-one interviews, surveys, broad polls, and focus group discussions. However, these are costly and sometimes unreliable. On the other hand, neuromarketing measures customer response to marketing stimuli by measuring the electrical activity of the brain and has the potential to address these drawbacks. which can be overcome by neuromarketing. In this work, we proposed a prediction algorithm that can identify consumer affective attitude (AA) and purchase intention (PI) from EEG signals from the brain. At first, the raw EEG signals are initially preprocessed to remove noise. After that, three features are extracted: time, frequency, and time frequency domain features. Wavelet packet transform is used to separate the EEG bands in time-domain feature extraction. Then, for feature selection, wrapper-based SVM-RFE is utilized. Finally, we use SVM to distinguish the classes in AA and PI. Results show that for SVM with radial basis function kernel performs better to classify positive and negative AA with an accuracy of 90 ± 4.33 and PI with an accuracy of 75 ± 2.5. So, EEG-based neuromarketing solutions can assist companies and organizations in accurately predicting future consumer preferences. As a result, neuromarketing based-solutions have the potential to increase sales by overcoming the constraints of traditional marketing. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Effort Allocation for Deadline-Aware Task and Motion Planning: A Metareasoning Approach

arXiv

引用

arXiv 2024年

作者： Sung, Yoonchang Shperberg, Shahaf S. Wang, Qi Stone, Peter The Department of Computer Science The University of Texas at Austin AustinTX78712 United States The Department of Software and Information Systems Engineering Ben-Gurion University of the Negev Be’er Sheva Israel Sony AI United States

In robot planning, tasks can often be achieved through multiple options, each consisting of several actions. This work specifically addresses deadline constraints in task and motion planning, aiming to find a plan that can be executed within the deadline despite uncertain planning and execution times. We propose an effort allocation problem, formulated as a Markov decision process (MDP), to find such a plan by leveraging metareasoning perspectives to allocate computational resources among the given options. We formally prove the NP-hardness of the problem by reducing it from the knapsack problem. Both a model-based approach, where transition models are learned from past experience, and a model-free approach, which overcomes the unavailability of prior data acquisition through reinforcement learning, are explored. For the model-based approach, we investigate Monte Carlo tree search (MCTS) to approximately solve the proposed MDP and further design heuristic schemes to tackle NP-hardness, leading to the approximate yet efficient algorithm called DP_Rerun. In experiments, DP_Rerun demonstrates promising performance comparable to MCTS while requiring negligible computation time. © 2024, CC BY.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Towards Consistent and Explainable Motion Prediction using Heterogeneous Graph Attention

Towards Consistent and Explainable Motion Prediction using H...

引用

IEEE Symposium on Intelligent Vehicle

作者： Tobias Demmler Andreas Tamke Thao Dang Karsten Haug Lars Mikelsons Robert Bosch GmbH Stuttgart Germany Department of Computer Science and Engineering Institute for Intelligent Systems Esslingen University Germany Leads the Chair of Mechatronics University of Augsburg Germany

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

In autonomous driving, accurately interpreting the movements of other road users and leveraging this knowledge to forecast future trajectories is crucial. This is typically achieved through the integration of map data and tracked trajectories of various agents. Numerous methodologies combine this information into a singular embedding for each agent, which is then utilized to predict future behavior. However, these approaches have a notable drawback in that they may lose exact location information during the encoding process. The encoding still includes general map information. However, the generation of valid and consistent trajectories is not guaranteed. This can cause the predicted trajectories to stray from the actual lanes. This paper introduces a new refinement module designed to project the predicted trajectories back onto the actual map, rectifying these discrepancies and leading towards more consistent predictions. This versatile module can be readily incorporated into a wide range of architectures. Additionally, we propose a novel scene encoder that handles all relations between agents and their environment in a single unified heterogeneous graph attention network. By analyzing the attention values on the different edges in this graph, we can gain unique insights into the neural network’s inner workings leading towards a more explainable prediction.

关键词： Measurement Tracking Roads Encoding Trajectory Autonomous vehicles

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：