检索结果-内蒙古大学图书馆

Optimization Deployment of Temperature Measurement Points for CZ Silicon Single Crystal Growth Equipment Based on Improved Fuzzy C-Means Clustering

Optimization Deployment of Temperature Measurement Points fo...

引用

第43届中国控制会议

作者： Weichao Huang Siyuan Cao Ding Lui School of Automation and Information Engineering Xi'an University of Technology Shannxi Key Laboratory of Complex System Control and Intelligent Information Processing

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

The inverse heat transfer method is an effective inversion algorithm for solving the heat transfer at non-measurable places of the study object. However, the current inverse heat transfer inversion method has the problems of low accuracy and difficult selection of temperature measurement point locations. To solve this problem, this paper proposes an optimization algorithm for measurement point locations based on improved fuzzy c-means clustering(IFCM). The method first generates the initial clustering center through a specific density function and introduces the Mahalanobis distance to solve the problem that the traditional fuzzy c-means clustering results depend on the initial clustering center and the results are unstable. Then, an optimized deployment algorithm based on IFCM temperature measurement points is proposed and compared with other mean value clustering algorithms. Finally, the optimal temperature measurement position on the crystal surface is selected by the IFCM temperature measurement point optimization deployment algorithm on the CZ(Czochraski)silicon single crystal growth equipment, and the inversion results of the randomly selected temperature measurement point scheme and the optimized temperature measurement point scheme are compared by the real-time inversion algorithm based on the dynamic matrix control multi-boundary heat flux, and the results of the optimized temperature measurement point scheme are obtained to be better than that of the randomly selected temperature measurement point scheme.

关键词： Fuzzy c-means clustering IFCM Temperature measurement point optimization Inverse heat transfer

来源：评论

学校读者我要写书评

暂无评论

ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection 41

ESNet: Evolution and Succession Network for High-Resolution ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Hongyu Cong, Runmin Li, Hua Xu, Qianqian Huang, Qingming Zhang, Wei Institute of Information Science Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature;the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24. Copyright 2024 by the author(s)

关键词： Miocene

来源：评论

学校读者我要写书评

暂无评论

Improving Transferability of Adversarial Point Clouds with Model Commonalities

Improving Transferability of Adversarial Point Clouds with M...

引用

IEEE International Conference on Cyborg and Bionic Systems (CBS)

作者： Junting Lv Lianguang Liu Yutong Zhang Depeng Li 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 Wuhan China

Although deep learning of 3D point clouds has made significant progress, the robustness of 3D models has not been fully investigated. Existing 3D attack methods show satisfactory performance under the white-box setting but frequently suffer from a low transferability to attack black-box models. A key point to improve the transferability of attacks is to find the commonalities of multiple models. To this end, a novel attack method is proposed by only leveraging perturbations in local geometric feature areas termed FAP. Specifically, local perturbations are pertinently added by calculating the curvature to sample more points in the feature areas that 3D models potentially focus on. Moreover, to address the drawback of poor isometric robustness common to 3D models, we propose a generalized framework for diversifying input samples by adding random isometric transformations (DIT) in the attack process, which can be combined with other attack methods to improve their transferability. Evaluated on a variety of typical 3D models, the proposed attack method outperforms the current gradient-based methods in transferable black-box attacks, and the effectiveness of the proposed framework is demonstrated by extending it to other attack methods.

关键词： Point cloud compression Solid modeling Three-dimensional displays Shape Perturbation methods Closed box Focusing

来源：评论

学校读者我要写书评

暂无评论

Model Predictive control Based on Amplitude Decaying Aggregation Strategy for Hydrogen Gas Turbine

Model Predictive Control Based on Amplitude Decaying Aggrega...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Ma, Aoyun Li, Dewei Xi, Yugeng Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Key Laboratory of System Control and Information Processing Department of Automation Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781665465335

The hydrogen gas turbine can be the key technology for carbon-neutral in the future. The flexibility of gas turbine under various operation conditions is an important issue. A state-space model of hydrogen gas turbine with different hydrogen volume ratio mixed fuel is constructed based on Rowen model, and a full-dimensional state observer is designed to obtain the states of state-space model. The model predictive control method based on amplitude decaying aggregation strategy is presented to stabilize the rotational speed of hydrogen gas turbine under various constraints, which are to ensure the safety of operation. The number of variables contained in the optimization problem to be solved online is reduced by aggregation strategy. The simulation results confirmed that the presented method works well, and the effects of the hydrogen volume ratio for the performance of hydrogen gas turbine are discussed. © 2022 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Online Learning Enabled Hierarchical Distributionally Robust Model Predictive control of Green-Hydrogen Microgrids under Uncertainties 5

Online Learning Enabled Hierarchical Distributionally Robust...

引用

5th IEEE International Electrical and Energy Conference, CIEEC 2022

作者： Ning, Chao Li, Longyan Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai China

ISBN: (数字)9781665411042

ISBN: (纸本)9781665411042

This paper proposes a novel online-learning enabled hierarchical operation framework for a green-hydrogen microgrid (MG) with a high penetration of renewable energy (RE) and hybrid energy storage. The operation framework features a bi-level multi-timescale structure which integrates a day-ahead optimal scheduling with online learning distributionally robust model predictive control (OL-DRMPC). Day-ahead scheduling optimization is employed at the high level to provide MG energy dispatch references, while the OL-DRMPC is carried out in the low level for reference-tracking under uncertainties incurred by RE and load forecast errors. To confront the imperfect knowledge of forecast-error distributions, distributionally robust conditional value-at-risk constraints are imposed on MG system states, namely the storage of battery and hydrogen, for a family of distributions called ambiguity set. By exploiting a Dirichlet process mixture model, a streaming-data-driven ambiguity set for uncertain parameters is devised over the runtime of controller and flexibly captures multimodal structure and fine-grained moment information of each mixture component. Enabled by online learning, the proposed strategy enjoys the merit of offering a reliable and intelligent MG operation. Case studies are used to demonstrate its effectiveness and superiority. © 2022 IEEE.

关键词： Energy storage

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation

arXiv

引用

arXiv 2023年

作者： Qing, Zhiwu Zhang, Shiwei Wang, Jiayu Wang, Xiang Wei, Yujie Zhang, Yingya Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China Fudan University China

Despite diffusion models having shown powerful abilities to generate photorealistic images, generating videos that are realistic and diverse still remains in its infancy. One of the key reasons is that current methods intertwine spatial content and temporal dynamics together, leading to a notably increased complexity of text-to-video generation (T2V). In this work, we propose HiGen, a diffusion modelbased method that improves performance by decoupling the spatial and temporal factors of videos from two perspectives, i.e., structure level and content level. At the structure level, we decompose the T2V task into two steps, including spatial reasoning and temporal reasoning, using a unified denoiser. Specifically, we generate spatially coherent priors using text during spatial reasoning and then generate temporally coherent motions from these priors during temporal reasoning. At the content level, we extract two subtle cues from the content of the input video that can express motion and appearance changes, respectively. These two cues then guide the model's training for generating videos, enabling flexible content variations and enhancing temporal stability. Through the decoupled paradigm, HiGen can effectively reduce the complexity of this task and generate realistic videos with semantics accuracy and motion stability. Extensive experiments demonstrate the superior performance of HiGen over the state-of-the-art T2V methods. Copyright © 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

A novel feature enhancement module for small object detection

A novel feature enhancement module for small object detectio...

引用

2022 IEEE International Conference on Industrial Technology, ICIT 2022

作者： Wang, Ruogu Li, Ning Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai China

ISBN: (纸本)9781728119489

Generic object detection has made great progress in recent years, yet small object detection is still facing a serious problem of missed detection. The problem is caused by two reasons: low resolution in small targets and feature loss during deep convolution downsampling. Some previous studies used feature pyramid structures and multi-scale training predictions to alleviate this problem, but still cannot efficiently utilise the feature information of small targets. In this paper, firstly we propose a novel and effective feature enhancement module to extract more features;secondly, a filter size design method is presented to extract features of matching objects and incorporate context information;finally, an adaptive fusion method is used to process outputs of our module and improve model robustness. We select YOLOv3 as base model and carry out several experiments on a special Small Object Dataset and the results show that our work can achieve an increase of about seven percentage points (35.73%) compared to 28.78% on baseline. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Global Convergence Guarantees of (A)GIST for a Family of Nonconvex Sparse Learning Problems

引用

IEEE Transactions on Cybernetics 2022年第5期52卷 3276-3288页

作者： Zhang, Hengmin Qian, Feng Shang, Fanhua Du, Wenli Qian, Jianjun Yang, Jian East China University of Science and Technology Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education School of Information Science and Engineering Shanghai200237 China Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai200092 China Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xi'an710071 China Peng Cheng Laboratory Shenzhen518066 China Nanjing University of Science and Technology Pca Laboratory Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education Nanjing210094 China Nanjing University of Science and Technology Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing210094 China

In recent years, most of the studies have shown that the generalized iterated shrinkage thresholdings (GISTs) have become the commonly used first-order optimization algorithms in sparse learning problems. The nonconvex relaxations of the \ell _{0} -norm usually achieve better performance than the convex case (e.g., \ell _{1} -norm) since the former can achieve a nearly unbiased solver. To increase the calculation efficiency, this work further provides an accelerated GIST version, that is, AGIST, through the extrapolation-based acceleration technique, which can contribute to reduce the number of iterations when solving a family of nonconvex sparse learning problems. Besides, we present the algorithmic analysis, including both local and global convergence guarantees, as well as other intermediate results for the GIST and AGIST, denoted as (A)GIST, by virtue of the Kurdyka-Lojasiewica (KL) property and some milder assumptions. Numerical experiments on both synthetic data and real-world databases can demonstrate that the convergence results of objective function accord to the theoretical properties and nonconvex sparse learning methods can achieve superior performance over some convex ones. © 2013 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

An Expansion-based Document Ranking Framework Incorporated with Core Concern Capturing 5

An Expansion-based Document Ranking Framework Incorporated w...

引用

5th International Conference on intelligent Autonomous Systems, ICoIAS 2022

作者： Qi, Yinqiao Xin, Jinghao Li, Ning Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Department of Automation Shanghai China

ISBN: (数字)9781665498388

ISBN: (纸本)9781665498388

Entity-based ranking is a popular research area in document ranking as knowledge graphs can introduce additional evidence for ranking systems. In most entity-based ranking framework, the original query is transformed into a set of entities and candidate documents are ranked according to their relevance to the entity set. However, mistakes can easily occur during the transformation process, which introduce noise to the ranking system. This paper represents an expansion-based ranking framework, which expand the original query with high-quality candidate entities to mitigate the impact of transformation mistakes and enrich the semantics of the query in the meanwhile. Compared with existing query expansion methods, our expansion method is lightweight as it reduces much computational burden and requests little extra information. However, the core concerns of the users might be covered up after query expansion. To alleviate this dilemma, a core concern capturing method is pro-posed, wherein the attention weight of each inter-entity relation is measured to capture the core entity pairs in the expanded query. Experiments on the S2-CS dataset demonstrate the effectiveness of our lightweight query expansion method and the superiority of our core concern capturing method. Compared with a classical retrieval model, our method provides 11% improvements in terms of NDCG@15. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Canine EEG Helps Human: Cross-Species and Cross-Modality Epileptic Seizure Detection via Multi-Space Alignment

arXiv

引用

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

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：