检索结果-内蒙古大学图书馆

Exploring and Exploiting Multi-Modality Uncertainty for Tumor Segmentation on PET/CT

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2024年第9期28卷 5435-5446页

作者： Kang, Susu Kang, Yixiong Tan, Shan Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Minist Educ China Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Innovat Inst Wuhan 430074 Peoples R China Qianjiang Peoples Hosp Qianjiang Peoples R China

Despite the success of deep learning methods in multi-modality segmentation tasks, they typically produce a deterministic output, neglecting the underlying uncertainty. The absence of uncertainty could lead to over-confident predictions with catastrophic consequences, particularly in safety-critical clinical applications. Recently, uncertainty estimation has attracted increasing attention, offering a measure of confidence associated with machine decisions. Nonetheless, existing uncertainty estimation approaches primarily focus on single-modality networks, leaving the uncertainty of multi-modality networks a largely under-explored domain. In this study, we present the first exploration of multi-modality uncertainties in the context of tumor segmentation on PET/CT. Concretely, we assessed four well-established uncertainty estimation approaches across various dimensions, including segmentation performance, uncertainty quality, comparison to single-modality uncertainties, and correlation to the contradictory information between modalities. Through qualitative and quantitative analyses, we gained valuable insights into what benefits multi-modality uncertainties derive, what information multi-modality uncertainties capture, and how multi-modality uncertainties correlate to information from single modalities. Drawing from these insights, we introduced a novel uncertainty-driven loss, which incentivized the network to effectively utilize the complementary information between modalities. The proposed approach outperformed the backbone network by 4.53 and 2.92 Dices in percentages on two PET/CT datasets while achieving lower uncertainties. This study not only advanced the comprehension of multi-modality uncertainties but also revealed the potential benefit of incorporating them into the segmentation network.

关键词： Tumor segmentation multi-modality uncertainty estimation PET/CT deep learning Tumor segmentation multi-modality uncertainty estimation PET/CT deep learning

来源：评论

学校读者我要写书评

暂无评论

Regulating the Polymerization of DNA Structures via Allosteric control of Monomers

引用

ACS NANO 2023年第2期17卷 1505-1510页

作者： Xie, Chun Chen, Zhekun Chen, Kuiting Hu, Yingxin Pan, Linqiang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Informat Proc & Intelligent Control Wuhan 430074 Hubei Peoples R China Shijiazhuang Tiedao Univ Coll Informat Sci & Technol Shijiazhuang 050043 Hebei Peoples R China

Regulation of self-assembly is crucial in constructing structural biomaterials, such as tunable DNA nanostructures. Traditional tuning of self-assembled DNA nanostructures was mainly conducted by introducing external stimuli after the assembly process. Here, we explored the allosteric assembly of DNA structures via introducing external stimuli during the assembly process to produce structurally heterogeneous polymerization products. We demonstrated that ethidium bromide (EB), a DNA intercalator, could increase the left-handed out-of-plane chirality of curved DNA structures. Then, EB and double strands were introduced as competing stimuli to transform monomers into allosteric conformations, leading to three different polymerization products. The steric trap between different polymerization products promoted the polymerized structures to keep their geometric properties, like chirality, under varying intensity of external stimuli. Our strategy harnesses allosteric effects for assembly of DNA-based materials and is expected to expand the design space for advanced control in synthetic materials.

关键词： allosteric assembly DNA structures intercalations chirality steric hindrance

来源：评论

学校读者我要写书评

暂无评论

Distributed algorithm for mixed equilibrium problems with event-triggered strategy

引用

NEURAL COMPUTING & APPLICATIONS 2022年第19期34卷 16463-16472页

作者： Zhou, Hongtao Xia, Liang Su, Housheng Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Educ Minist China Luoyu Rd 1037 Wuhan 430074 Peoples R China

A new iterative method based on the event-triggered strategy for finding a solution to a mixed equilibrium problem (MEP) is introduced in this paper. The target of the MEP is to find a point in a closed convex set, guaranteeing that the sum of bifunctions about this point is non-negative. To decrease the cost of communication, the MEP is investigated with an event-triggered protocol. Furthermore, it is the first attempt to combine the MEP with an event-triggered strategy. Although there exist difficulties caused by the asymmetry of the network structure associated with directed graphs, nonlinearity and strong coupling of the MEP, the novel algorithm for directed graphs, two event-triggered conditions and the range of the solution associated with the MEP are obtained to handle these challenges. Under the directed time-varying graph, the designed algorithm can converge to a solution to the MEP and reach average consensus. Finally, a numerical example is presented to illustrate the effectiveness of the above algorithm.

关键词： Mixed equilibrium problem Event-triggered protocol Directed graph Average consensus

来源：评论

学校读者我要写书评

暂无评论

Distributed Event-Triggered Synchronization of Interconnected Linear Two-Time-Scale Systems With Switching Topology

引用

IEEE TRANSACTIONS ON CYBERNETICS 2022年第12期52卷 13714-13726页

作者： Lei, Yan Wang, Yan-Wu Liu, Xiao-Kang Liu, Zhi-Wei Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Minist Educ Key Lab Image Proc & Intelligent Control Wuhan Peoples R China

This article investigates the synchronization problem of interconnected linear two-time-scale systems (TTSSs) with switching topology. By utilizing the Chang transformation, a distributed synchronization protocol is proposed with event-triggered communication. Static and dynamic event-triggered mechanisms are proposed successively, which both contain two separated event-triggering conditions corresponding to the slow and the fast subsystems. The existence of a strictly positive time period between any two successive transmissions is ensured regardless of the initial states. The main difficulty of this study lies in that the state jump and parametric uncertainty appear because of the system transformation. To overcome the difficulty, the system is first modeled as an uncertain hybrid system. Then, the control gain is properly designed by solving Riccati-like equations dependent on the rough bounds of the eigenvalues of communication graph Laplacians, and a piecewise quadratic Lyapunov function is proposed with which the jump caused by the switching topology is subtly evaluated. Sufficient conditions are thus established to achieve the event-triggered synchronization. Furthermore, the results are also extended to solve the synchronization problem of the interconnected impulsive linear TTSSs. Finally, three numerical examples are provided to demonstrate the effectiveness of the proposed theoretical results.

关键词： Switches Topology Synchronization Analytical models control systems Symmetric matrices Lyapunov methods Event-triggered communication switching topology two-time-scale system (TTSS)

来源：评论

学校读者我要写书评

暂无评论

Neuroadaptive Impulsive control on Consensus of Uncertain Multiagent Systems Using Continuous and Sampled Information

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第8期34卷 5086-5098页

作者： Han, Yiyan Xiao, Qiang Zeng, Zhigang Huazhong Univ Sci & Technol Educ Minist China Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Inst Artificial Intelligence Wuhan 430074 Peoples R China

This article considers the consensus problem of uncertain multiagent systems, which is addressed by neuroadaptive impulsive control schemes. The proposed control schemes indicate that the communication among agents only occurs impulsively, while the dynamics uncertainty is addressed by adaptive schemes using neural networks. Based on such approaches, two specific control schemes are designed. One is that with impulsive feedback, the control scheme uses continuous-time information, which implies that the adaptive process is continuous over time. Another is that by adopting sampled information, the update of all systems, including the feedbacks on agents, the update of neural networks, and the estimation for uncertainty, can be executed only at impulsive instants. The latter case can reduce the energy cost for communication and control, but extra assistant systems are required. The estimation and consensus prove to be achieved with errors if some conditions are fulfilled. Numerical simulations, including a practical system example, are presented.

关键词： Multi-agent systems Neural networks Estimation Costs Uncertainty Protocols Directed graphs Consensus neuroadaptive impulsive control sampled information uncertain system

来源：评论

学校读者我要写书评

暂无评论

Sparse representation and modified density peak clustering-based state identification for multimode processes

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2023年第2期34卷 025016-025016页

作者： Wang, Zhaojing Chen, Bin Zheng, Ying Wang, Yang Yan, Xiaoyun Wuhan Text Univ Hubei Prov Engn Res Ctr Intelligent Text & Fash Sch Comp Sci & Artificial Intelligence Wuhan 430200 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Minist Educ Wuhan 430074 Peoples R China

Industrial processes with high-dimensional data are generally operated with mixed normal/faulty states in different modes, making it difficult to automatically and accurately identify the faults. In this paper, a state identification framework is proposed for multimode processes. First, a key variable selection approach is presented based on sparse representation to eliminate redundant variables. Then, modified density peak clustering is proposed to identify different states, in which a distance measurement with a time factor is constructed to select all the possible cluster centers. Then, the sum of squared errors-based approach is developed to determine the optimal cluster centers automatically. Further, considering that the mode attributes may be mixed with the fault attributes, a two-step 'coarse-to-fine identification' strategy is designed to precisely identify the modes and the faults in each mode. Finally, three cases including a numerical simulation, Tennessee Eastman benchmark process and an actual semiconductor manufacturing process are presented to show the feasibility of the proposed method.

关键词： multimode process state identification modified density peak clustering sparse representation

来源：评论

学校读者我要写书评

暂无评论

Degradation-oriented real-time power control of fuel cell hybrid vehicles under uncertain driving conditions

引用

INTERNATIONAL JOURNAL OF HYDROGEN ENERGY 2023年第78期48卷 30556-30569页

作者： Fu, Jun Zeng, Linghong Sheng, Chuang Guo, Ziang Li, Beijia Deng, Zhonghua Li, Xi Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Educ Minist Wuhan 430074 Hubei Peoples R China Huazhong Univ Sci & Technol Shenzhen Res Inst Shenzhen 518055 Peoples R China

This work provides a real-time power allocation algorithm to address uncertain actual driving situations for fuel cell hybrid vehicles. To predict the vehicle speed under nondeterministic driving conditions, a fusion prediction model is developed based on the advantages of the Markov chain and neural network. The optimal power splitting decision in each receding horizon is then solved using the Pontryagin's minimum principle (PMP) method, considering fuel consumption, State of Charge (SOC), and performance degradation. A degradation model of electrochemical active surface area (ECSA) based on Pt catalyst dissolution was developed. Then the effect of the energy management algorithm on fuel cell degradation was evaluated using the degradation model. Compared with the two conventional real-time power splitting strategies, the approach suggested in this research can better reduce the fuel consumption and maintain the stability of battery SOC with a lower fluctuation while taking into account the degradation of the fuel cell. (c) 2023 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.

关键词： Hybrid power system Uncertain operating conditions Fusion velocity prediction Predictive control Degradation assessment

来源：评论

学校读者我要写书评

暂无评论

Geometric Renormalization Reveals the Self-Similarity of Weighted Networks

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2023年第2期10卷 426-434页

作者： Chen, Dan Su, Housheng Zeng, Zhigang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Educ Minist China Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Educ Minist China Wuhan 430074 Peoples R China

The geometric renormalization (GR) group of complex networks based on hidden metric space provides a powerful framework for studying the self-similarity of networks. Recent studies have shown that this framework can significantly reduce the size and complexity of the initial system. In this sense, the smaller-scale replica can be used as an alternative or guidance to the original large-scale network. In this article, we extend the GR framework to the weighted network and prove that this framework can sustain the self-similarity of synthetic weighted networks and real-world weighted networks. Furthermore, we assign the corresponding weights to all edges of reconstructed human connectomes at five different resolutions, and the results show that topological features of these networks exhibit self-similar behaviors. Remarkably, our results also suggest that the GR transform group can generate a series of low-resolution replica networks that are similar to the initial highest-resolution human connectome networks, which greatly promotes the network science, neuroscience, and physics understanding of brain mechanisms, and is of great significance to the research of brain science. Finally, a typical spin-like model is used to further verify the rationality of this framework.

关键词： Brain modeling Topology Solid modeling Neurons Integrated circuit modeling Geometric modeling Fractals Geometric renormalization (GR) self-similarity spin-like model weighted networks

来源：评论

学校读者我要写书评

暂无评论

Expanding Hyperspherical Space for Few-Shot Class-Incremental Learning

Expanding Hyperspherical Space for Few-Shot Class-Incrementa...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Yao Deng Xiang Xiang Key Lab of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

In today’s ever-changing world, the ability of machine learning models to continually learn new data without forgetting previous knowledge is of utmost importance. However, in the scenario of few-shot class-incremental learning (FSCIL), where models have limited access to new instances, this task becomes even more challenging. Current methods use prototypes as a replacement for classifiers, where the cosine similarity of instances to these prototypes is used for prediction. However, we have identified that the embedding space created by using the relu activation function is incomplete and crowded for future classes. To address this issue, we propose the Expanding Hyperspherical Space (EHS) method for FSCIL. In EHS, we utilize an odd-symmetric activation function to ensure the completeness and symmetry of embedding space. Additionally, we specify a region for base classes and reserve space for unseen future classes, which increases the distance between class distributions. Pseudo instances are also used to enable the model to anticipate possible upcoming samples. During inference, we provide rectification to the confidence to prevent bias towards base classes. We conducted experiments on benchmark datasets such as CIFAR100 and miniimageNet, which demonstrate that our proposed method achieves state-of-the-art performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bimodal Feature Propagation and Fusion for Real-time Semantic Segmentation on RGB-D images 7

Bimodal Feature Propagation and Fusion for Real-time Semanti...

引用

7th International Conference on intelligent Computing and Signal processing, ICSP 2022

作者： He, Ying Xiao, Li Sun, Zhigang Wang, Zhuo Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Wuhan China

ISBN: (纸本)9781665478571

Semantic Segmentation is the foundation of scene understanding and automatic driving tasks. One of the challenges of semantic segmentation is the reduction of feature resolution as the network goes deep. In this paper, the low-resolution features are integrated into high-resolution features progressively, enabling high-resolution prediction. Currently, incorporating the auxiliary depth information into a semantic segmentation framework has proven to be helpful to improve accuracy. However, additional process of depth data immensely increases computational complexity, resulting in limitation for practical application. Here, a real-time bimodal semantic segmentation network that effectively extracts and fuses complementary information is investigated. Our network extends a light-weight architecture which can seamlessly take advantage of various prevalent backbone networks. Our model extracts RGB and depth features from two branches in parallel and integrates multi-level features of two modalities through bimodal feature fusion blocks. To reduce computation complexity, we employ depth-wise separable convolution while keep performance intact. Meanwhile, an attention mechanism is exploited to recalibrate the fusion modality features adaptively. Refinement components are retained to refine multi-resolution feature maps. We conduct ablative study to demonstrate the availability of our bimodal fusion blocks. Comprehensive experiments validate that the proposed network outperforms the state-of-the-arts and achieves 18 FPS on the challenging RGB-D dataset, NYUDv2. © 2022 IEEE.

关键词： Semantic Segmentation

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：