检索结果-内蒙古大学图书馆

Engineering 2025年第1期 44-50页

作者：欧阳敏程泽楷马佳欣王红卫 Stergios Aristoteles Mitoulis School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education Huazhong University of Science and Technology School of Management Huazhong University of Science and Technology School of Engineering University of Birmingham

The complexity of coupled risks, which refer to the compounded effects of interacting uncertainties across multiple interdependent objectives, is inherent to cities functioning as dynamic, interdependent systems. A disruption in one domain ripples across various urban systems, often with unforeseen consequences. Central to this complexity are people, whose behaviors, needs, and vulnerabilities shape risk evolution and response effectiveness. Realizing cities as complex systems centered on human needs and behaviors is essential to understanding the complexities of coupled urban risks. This paper adopts a complex systems perspective to examine the intricacies of coupled urban risks, emphasizing the critical role of human decisions and behavior in shaping these dynamics. We focus on two key dimensions: cascading hazards in urban environments and cascading failures across interdependent exposed systems in cities. Existing risk assessment models often fail to capture the complexity of these processes, particularly when factoring in human decision-making. To tackle these challenges, we advocate for a standardized taxonomy of cascading hazards, urban components, and their interactions. At its core is a people-centric perspective, emphasizing the bidirectional interactions between people and the systems that serve them. Building on this foundation, we argue the need for an integrated, people-centric risk assessment framework that evaluates event impacts in relation to the hierarchical needs of people and incorporates their preparedness and response capacities. By leveraging real-time data, advanced simulations, and innovative validation methods, this framework aims to enhance the accuracy of coupled urban risk modeling. To effectively manage coupled urban risks, cities can draw from proven strategies in real complex systems. However, given the escalating uncertainties and complexities associated with climate change, prioritizing people-centric strategies is crucial. This ap

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prompt-guided consistency learning for multi-label classification with incomplete labels

引用

NEURAL NETWORKS 2025年 190卷 107604页

作者： Wang, Shouwen Wan, Qian Zhang, Zihan Zeng, Zhigang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Minist Educ Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

Addressing insufficient supervision and improving model generalization are essential for multi-label classification with incomplete annotations, i.e., partial and single positive labels. Recent studies incorporate pseudo-labels to provide additional supervision and enhance model generalization. However, the noise in pseudo-labels generated by the model tends to accumulate, resulting in confirmation bias during training. Self-correction methods, commonly used approaches for mitigating confirmation bias, rely on model predictions but remain susceptible to confirmation bias caused by visual confusion, including both visual ambiguity and similarity. To reduce visual confusion, we propose a prompt-guided consistency learning (PGCL) framework designed for two incomplete labeling settings. Specifically, we introduce an intra-category supervised contrastive loss, which imposes consistency constraints on reliable positive class samples in the feature space of each category, rather than across the feature space of all categories, as in traditional inter-category supervised contrastive loss. Building on this, the distinction between true positive and visual confusion samples for each category is enhanced through label-level contrasting of the same category. Additionally, we develop a class-specific semantic decoupling module that leverages CLIP's strong vision-language alignment capability, since the proposed contrastive loss requires high-quality label-level representations as contrastive samples. Extensive experimental results on multiple datasets demonstrate that our method can effectively address the problems of two incomplete labeling settings and achieve state-of-the-art performance.

关键词： Multi-label classification Incomplete labels Confirmation bias Contrastive learning Semantic decoupling Pseudo-labeling

来源：评论

学校读者我要写书评

暂无评论

ImPLoc: a multi-instance deep learning model for the prediction of protein subcellular localization based on immunohistochemistry images

引用

BIOINFORMATICS 2020年第7期36卷 2244-2250页

作者： Long, Wei Yang, Yang Shen, Hong-Bin Shanghai Jiao Tong Univ Ctr Brain Comp & Machine Intelligence Dept Comp Sci & Engn Shanghai 200240 Peoples R China Key Lab Shanghai Educ Commiss Intelligent Interac Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Key Lab Syst Control & Informat Proc Minist Educ China Shanghai 200240 Peoples R China

Motivation: The tissue atlas of the human protein atlas (HPA) houses immunohistochemistry (IHC) images visualizing the protein distribution from the tissue level down to the cell level, which provide an important resource to study human spatial proteome. Especially, the protein subcellular localization patterns revealed by these images are helpful for understanding protein functions, and the differential localization analysis across normal and cancer tissues lead to new cancer biomarkers. However, computational tools for processing images in this database are highly underdeveloped. The recognition of the localization patterns suffers from the variation in image quality and the difficulty in detecting microscopic targets. Results: We propose a deep multi-instance multi-label model, ImPLoc, to predict the subcellular locations from IHC images. In this model, we employ a deep convolutional neural network-based feature extractor to represent image features, and design a multi-head self-attention encoder to aggregate multiple feature vectors for subsequent prediction. We construct a benchmark dataset of 1186 proteins including 7855 images from HPA and 6 subcellular locations. The experimental results show that ImPLoc achieves significant enhancement on the prediction accuracy compared with the current computational methods. We further apply ImPLoc to a test set of 889 proteins with images from both normal and cancer tissues, and obtain 8 differentially localized proteins with a significance level of 0.05.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Visual SLAM Based on Dynamic Object Detection

Visual SLAM Based on Dynamic Object Detection

引用

第33届中国控制与决策会议

作者： Bocheng Chen Gang Peng Dingxin He Cheng Zhou Bin Hu School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Shantui Construction Machinery Co. Ltd.

On the one hand,traditional visual SLAM does not consider dynamic objects in the scene,on the other hand,deep learning technology has been widely used in computer *** paper combines the two organically,and proposes an algorithm that uses dynamic object detection to improve the robustness of visual SLAM in a dynamic ***,we use the object detection network integrated into the attention mechanism to detect the dynamic target in the key ***,we follow the optical flow detection to further determine the dynamic feature points in the scene and eliminate ***,we use the static feature points for camera tracking to achieve highly robust monocular visual *** method described in this paper can not only eliminate dynamic feature points,but also retain as many static feature points as *** method described in this paper is compared with the original ORB-SLAM2 algorithm and DS-SLAM algorithm,and tested with public data *** results show that the method described in this paper can effectively eliminate the influence of dynamic objects on the visual SLAM algorithm.

关键词： Visual SLAM dynamic object detection deep learning optical flow detection attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Exploiting learnable joint groups for hand pose estimation

arXiv

引用

arXiv 2020年

作者： Li, Moran Gao, Yuan Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Tencent AI Lab United States

In this paper, we propose to estimate 3D hand pose by recovering the 3D coordinates of joints in a group-wise manner, where less-related joints are automatically categorized into different groups and exhibit different features. This is different from the previous methods where all the joints are considered holistically and share the same feature. The benefits of our method are illustrated by the principle of multi-task learning (MTL), i.e., by separating less-related joints into different groups (as different tasks), our method learns different features for each of them, therefore efficiently avoids the negative transfer (among less related tasks/groups of joints). The key of our method is a novel binary selector that automatically selects related joints into the same group. We implement such a selector with binary values stochastically sampled from a Concrete distribution, which is constructed using Gumbel softmax on trainable parameters. This enables us to preserve the differentiable property of the whole network. We further exploit features from those less-related groups by carrying out an additional feature fusing scheme among them, to learn more discriminative features. This is realized by implementing multiple 1x1 convolutions on the concatenated features, where each joint group contains a unique 1x1 convolution for feature fusion. The detailed ablation analysis and the extensive experiments on several benchmark datasets demonstrate the promising performance of the proposed method over the state-of-the-art (SOTA) methods. Besides, our method achieves top-1 among all the methods that do not exploit the dense 3D shape labels on the most recently released FreiHAND competition at the submission date. The source code and models are available at https://***/moranli-aca/LearnableGroups-Hand. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Multi-Level Thresholding image Segmentation Based on an Improved Artificial Bee Colony Algorithm 2nd

A Multi-Level Thresholding Image Segmentation Based on an Im...

引用

2nd EAI International Conference on Robotic Sensor Networks, ROSENET 2018

作者： Xia, Xingyu Gao, Hao Hu, Haidong Lan, Rushi Pun, Chi-Man The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China Department of Computer and Information Science University of Macau China Beijing Institute of Control Engineering Beijing China Key Laboratory of Intelligent Processing of Computer Image and Graphics Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9783030177621

As a popular evolutionary algorithm, artificial bee colony (ABC) algorithm has been successfully applied into the threshold-based image segmentation problem. Based on our analysis, we find that the Otsu segmentation function is separable which means each variable is independent. Due to its one-dimensional search strategy and relative power global but poorer local search abilities, ABC could find an acceptable but not precise segmentation results. For making more precise search and further enhancing the achievements on image segmentation, we propose an Otsu segmentation method based on a new ABC algorithm with an improved scout bee strategy. Different from the traditional scout bee strategy, we use a local search strategy when a bee stagnates for a defined value. The experimental results on Berkeley segmentation database demonstrate the effectiveness of our algorithm. © 2020, Springer Science and Business Media Deutschland GmbH. All rights reserved.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Model Reference Adaptive controller with Feedforward Decoupling for Active Magnetic Bearing Rotor System 4

A Model Reference Adaptive Controller with Feedforward Decou...

引用

4th IEEE Advanced Information Technology, Electronic and Automation control Conference, IAEAC 2019

作者： Yi, Jian Ren, Gui-Ping Zhang, Hai-Tao Wu, Yue Huazhong University of Science and Technology School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control Wuhan430074 China

ISBN: (纸本)9781728119076

Active magnetic bearing (AMB) rotor system is widely applied in the industry for its remarkable advantages. However, it is a typical open-loop unstable mechatronics system suffering from nonlinear and couple characteristic. In this paper, the feedforward decoupling method is used to deal with the couple relationship of different axes. And the model reference adaptive control (MRAC) method is applied to improve the control performance and robustness and overcome the uncertainties. This control method makes the system output reach to the reference model by the designed adaptive law. Simulation results illustrate the effectiveness of the proposed scheme. © 2019 IEEE.

关键词： Model reference adaptive control

来源：评论

学校读者我要写书评

暂无评论

Topology Prediction Improvement of α-helical Transmembrane Proteins Through Helix-tail Modeling and Multiscale Deep Learning Fusion

引用

JOURNAL OF MOLECULAR BIOLOGY 2020年第4期432卷 1279-1296页

作者： Feng, Shi-Hao Zhang, Wei-Xun Yang, Jing Yang, Yang Shen, Hong-Bin Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Shanghai 200240 Peoples R China Minist Educ China Key Lab Syst Control & Informat Proc Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Dept Comp Sci Shanghai 200240 Peoples R China Key Lab Shanghai Educ Commiss Intelligent Interac Shanghai 200240 Peoples R China

Transmembrane proteins (TMPs) play important roles in many biological processes, such as cell recognition and communication. Their structures are crucial for revealing complex functions but are hard to obtain. A variety of computational algorithms have been proposed to fill the gap by predicting structures from primary sequences. In this study, we mainly focus on alpha-helical TMP and develop a multiscale deep learning pipeline, MemBrain 3.0, to improve topology prediction. This new protocol includes two submodules. The first module is transmembrane helix (TMH) prediction, which features the capability of accurately predicting TMH with the tail part through the incorporation of tail modeling. The prediction engine contains a multiscale deep learning model and a dynamic threshold strategy. The deep learning model is comprised of a small-scale residue based residual neural network and a large-scale entire-sequence-based residual neural network. Dynamic threshold strategy is designed to binarize the raw prediction scores and solve the under-split problem. The second module is orientation prediction, which consists of a support vector machine (SVM) classifier and a new Max-Min assignment (MMA) strategy. One typical merit of MemBrain 3.0 is the decision mode composed of the dynamic threshold strategy and the MMA strategy, which makes it more effective for hard TMHs, such as half-TMH, back-to-back TMH, and long-TMH. Systematic experiments have demonstrated the efficacy of the new model, which is available at: ***/bioinf/MemBrain/. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： membrane protein bioinformatics structure prediction topology deep learning

来源：评论

学校读者我要写书评

暂无评论

Global Ultimate Mittag-Leffler Lag Quasi-Synchronization of Delayed Fractional-Order Memristive Neural Networks with Switching Jumps Mismatch via Pinning control

Global Ultimate Mittag-Leffler Lag Quasi-Synchronization of ...

引用

第三十九届中国控制会议

作者： Jia Jia Zhigang Zeng School of Artificial Intelligence and Automation the Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology School of Control Science and Engineering Shandong University

In this paper, a novel pinning controller, which is applied to the selected partial neurons with partial errors needed, is designed for global ultimate Mittag-Leffler lag quasi-synchronization(GUMLQS) of delayed fractional-order memristive neural networks(FMNNs) with switching jumps mismatch. Since the right-hand sides of the equations of FMNNs are discontinuous,FMNNs have no solution in the ordinary sense, and Filippov solutions are adopted for FMNNs. With the assistance of fractional Halanay inequality, a Lyapunov function in quadratic form and the theory of fractional derivative, an LMI-based GUMLQS criterion is derived. For a prescribed GUMLQS error bound, the control gain matrices can be calculated out via a group of ***, the sufficient condition for the feasibility of the LMIs is obtained, which is an important basis for the selection of controlled neurons. Finally, a numerical example shows that the designed pinning controller can achieve GUMLQS between master-slave FMNNs with the prescribed ultimate error bound.

关键词： Memristive Neural Networks(MNNs) Fractional-Order Pinning control Global Ultimate Mittag-Leffler Lag Quasi-Synchronization(GUMLQS)

来源：评论

学校读者我要写书评

暂无评论

Value of resilience-based solutions on critical infrastructure protection: Comparing with robustness-based solutions

引用

RELIABILITY ENGINEERING & SYSTEM SAFETY 2019年 190卷

作者： Min, Ouyang Chuang, Liu Min, Xu Huazhong Univ Sci & Technol Sch Automat Wuhan 430074 Hubei Peoples R China Key Lab Image Proc & Intelligent Control Wuhan 430074 Hubei Peoples R China

Additional consideration of recovery rapidity makes resilience-based solutions on critical infrastructure protection conceptually more advantageous than robustness-based solutions, but existing studies have not uncovered how large their differences could be. By considering a pre-event protection strategy frequently adopted both in practice and in the literature, i.e., protecting or retrofitting a set of weak components under a limited budget, this paper introduces four mathematical models and their solution algorithms for exactly identifying the optimal robustness-based and resilience-based protection strategies for critical infrastructure systems against worst-case malicious attacks and natural hazards, respectively. By comparing with the optimal robustness-based protection strategy, the value of resilience-based solution is then quantified by how much the system resilience can be improved and how much the system loss can be mitigated. Taking the electric power transmission system in Shelby County, USA as an example, results show that the optimal resilience-based solutions improve the worst-case system resilience by at most 1.29% and reduce the worst-case system loss by at most 13.25%, and enhance the seismic resilience by at most 0.16% and mitigate the system loss by at most 5.27% under seismic hazards at a 2% probability of being exceeded in 50 years. Other model parameters and several other systems are also investigated.

关键词： Critical infrastructure protection Robustness Resilience Worst-case malicious attack Natural hazards

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：