检索结果-内蒙古大学图书馆

8th International Conference on Information Technology and Nanotechnology, ITNT 2022

作者： Semenova, Valentina Smirnov, Sergei Laboratory for Analysis and Modeling of Complex Systems Samara Federal Research Scientific Center RAS Institute for the Control of Complex Systems RAS Samara Russia

ISBN: (数字)9781665485715

ISBN: (纸本)9781665485715

The paper considers the problem of building a semantic model of the object under study, which determines its attributes, *** composition of the properties inherent in the object. The set of these attributes is a subset of all measured (in a broad sense) properties of the object under study. Processing the results of such multidimensional measurements, observations, registration of expert opinions, etc. gives the initial empirical material in the form of generally logically many-valued assessments of judgments truth of the form 'the property x is inherent in the object g'. On the other hand, the subject may have a priori knowledge about the coexistence variants of various attributes in the object under study. For such circumstances, a method is proposed for identifying all admissible sets of object attributes, including a logical-combinatorial method for choosing the 'best' of these sets, which is taken as a semantic model of the object. The paper considers examples of applications of the developed models and methods, indicates the tasks of additional research of the problem to substantiate the proposed methodology for the semantic identification of an object based on empirical data. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Mask-guided Multi-scale Spatial-Spectral Transformer for Snapshot Compressive Imaging

Mask-guided Multi-scale Spatial-Spectral Transformer for Sna...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Yin, Heyuan Yang, Jingxiang Liu, Jia Xiao, Liang School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Key Laboratory of Analysis of Mathematical Theory and Modeling of Complex Systems Ministry of Industry and Information Technology China

ISBN: (纸本)9798350368741

Effectively reconstructing 3D hyperspectral images (HSIs) from 2D measurements presents a significant challenge in Coded Aperture Snapshot Spectral Imaging (CASSI) systems. While recent transformers exhibit potential in HSI reconstruction, they often suffer from inadequate exploration of multi-scale spatial-spectral self-similarity, leading to mean effects and information loss. Additionally, these methods struggle with insufficient modeling of the degradation inherent in the compressive imaging process. To address these issues, we propose a novel Mask-guided Multi-scale Spatial-Spectral Transformer (MMSST). Specifically, we introduce a Degradation Aware Mask Attention (DAMA) module to incorporate degradation information of the compressive imaging process. Furthermore, MMSST leverages Local-Regional SpAtial attention (LRSA) and Global-Regional SpEctral attention (GRSE) to effectively exploit multi-scale self-similarity across spatial and spectral dimensions. Extensive experimental results demonstrate the effectiveness of our MMSST. © 2025 IEEE.

关键词： hyperspectral reconstruction Snapshot Compressive Imaging spatial-spectral transformer

来源：评论

学校读者我要写书评

暂无评论

Universal method of accounting the properties existence constraints it problems of deriving formal concepts from fuzzy object-attributive data 7

Universal method of accounting the properties existence cons...

引用

7th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2021

作者： Samoilov, Alexandr Smirnov, Sergey Samara Federal Research Scientific Center of RAS Institute for the Control of Complex Systems RAS Laboratory for Analysis and Modeling of Complex Systems Samara Russia

ISBN: (纸本)9781665432177

Object of research is the processing of fuzzy object-attributive data - empirically established 'object-properties' relation - in order to identify formal concepts and construct a lattice that fixes a partial ordered generalization relation on a set of formal concepts. The paper is devoted to implementation of the method of preprocessing the initial fuzzy 'object-properties' relation proposed earlier by the authors, which provides for taking into account the properties existence constraints - a priori subjective attitudes that fix the permissible variants of the intent of formal concepts. The method is suitable for all types of biclustering tasks: to derive distinct and fuzzy concepts from the threshold cross-section of the source data, to derive fuzzy concepts based on the fuzzy closure of the source data. Implementation of the method involves the representation of a fuzzy set of properties for each object in the training sample as a composition of a finite kit of distinct sets, filtering this kit of sets for accounting properties existence constraints and approximation of a fuzzy set of properties of the object of training sample based on the composition of the filtered sets of properties. The effectiveness of the proposed implementation provides by the rational organization of each of these actions and in fact their partial combination. © 2021 IEEE.

关键词： Formal concept analysis

来源：评论

学校读者我要写书评

暂无评论

Mask-guided Multi-scale Spatial-Spectral Transformer for Snapshot Compressive Imaging

Mask-guided Multi-scale Spatial-Spectral Transformer for Sna...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Heyuan Yin Jingxiang Yang Jia Liu Liang Xiao School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Key Laboratory of Analysis of Mathematical Theory and Modeling of Complex Systems The Ministry of Industry and Information Technology China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

关键词： Degradation Three-dimensional displays Computational modeling Imaging Transformer cores Signal processing Transformers Speech processing Image reconstruction Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

On the Efficiency of the Evolutionary Approach to Dynamic Objects Identification in the Form of Differential Equations systems 38

On the Efficiency of the Evolutionary Approach to Dynamic Ob...

引用

38th International Conference on Information Technologies, InfoTech 2024

作者： Karaseva, Tatiana Sergeevna Semenkin, Eugene Stanislavovich Institute of Business Process Management Siberian Federal University Department of Business Informatics and Business Process Modeling Academic Kirensky St. 26a Krasnoyarsk Russia Reshetnev Siberian State University of Science and Technology Institute of Informatics and Telecommunications Department of System Analysis and Operations Research Krasnoyarsky Rabochy Av. 31 Krasnoyarsk Russia Siberian Federal University Laboratory "Hybrid Methods of Modeling and Optimization in Complex Systems" Academic Kirensky St. 26a Krasnoyarsk Russia

ISBN: (纸本)9798350365689

The study of dynamic systems often assumes building a model based on numerical data describing the system's behavior, i.e., its identification. This problem is relevant, since it is impossible to study properties of a real object, make predictions and select correct control without an adequate mathematical model. The representation of the object's model in a symbolic form as differential equations or their systems is the most common and convenient for further application. The paper examines the efficiency of the evolutionary approach to the structural-parametric identification on test problems, the problem of modeling the longitudinal perturbed motion of an aircraft and the problem of modeling the viscous fluid movement when heated it from below. © 2024 IEEE.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Decision Tree Pruning Method Using Delayed Sampling 38

Decision Tree Pruning Method Using Delayed Sampling

引用

38th International Conference on Information Technologies, InfoTech 2024

作者： Mitrofanov, Sergei Alexandrovich Semenkin, Eugene Stanislavovich Reshetnev Siberian State University of Science and Technology Institute of Informatics and Telecommunications Department of System Analysis and Operations Research Krasnoyarsky Rabochy Av. 31 Krasnoyarsk Russia Bauman Moscow State Technical University Scientific and Educational Center "Artificial Intelligence Technologies" 2nd Baumanskaya St. 5 Moscow Russia Siberian Federal University Laboratory "Hybrid Methods of Modeling and Optimization in Complex Systems" Academic Kirensky St. 26a Krasnoyarsk Russia

ISBN: (纸本)9798350365689

Algorithms based on decision trees have been around for quite some time, however, they are still one of the most popular because of their efficiency and the interpretability of their results. One of the main problems of decision trees is their high tendency to overfit. There are various ways to solve this problem, but this paper proposes a new method based on tree pruning using delayed sampling. The tree is trained using the Separation Measure and Differential Evolution algorithms. The proposed approach improves the standard method and is compared with it. The proposed approach demonstrates higher efficiency than the standard algorithm, and also improves the interpretability of the resulting trees. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

On the Efficiency of the Evolutionary Approach to Dynamic Objects Identification in the Form of Differential Equations systems

On the Efficiency of the Evolutionary Approach to Dynamic Ob...

引用

International Conference on Information Technologies (InfoTech)

作者： Tatiana Sergeevna Karaseva Eugene Stanislavovich Semenkin Department of Business Informatics and Business Process Modeling Institute of Business Process Management Siberian Federal University Krasnoyarsk Russian Federation Department of System Analysis and Operations Research Institute of Informatics and Telecommunications Reshetnev Siberian State University of Science and Technology Krasnoyarsk Russian Federation Laboratory "Hybrid Methods of Modeling and Optimization in Complex Systems" Siberian Federal University Krasnoyarsk Russian Federation

ISBN: (数字)9798350365689

ISBN: (纸本)9798350365696

The study of dynamic systems often assumes building a model based on numerical data describing the system’s behavior, i.e., its identification. This problem is relevant, since it is impossible to study properties of a real object, make predictions and select correct control without an adequate mathematical model. The representation of the object’s model in a symbolic form as differential equations or their systems is the most common and convenient for further application. The paper examines the efficiency of the evolutionary approach to the structural-parametric identification on test problems, the problem of modeling the longitudinal perturbed motion of an aircraft and the problem of modeling the viscous fluid movement when heated it from below.

关键词： Heating systems Fluids Atmospheric modeling Dynamics Differential equations Mathematical models Numerical models Object recognition Information technology Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Distributed Cluster Flow Control for a Group of Autonomous Robots*

引用

IFAC-PapersOnLine 2023年第2期56卷 8690-8695页

作者： V. Erofeeva V. Ershov O. Granichin V. Pankov D. Uzhva O. Granichina Laboratory “Control of Complex Systems” Institute for Problems in Mechanical Engineering V.O. Bolshoy 61 199178 Saint Petersburg Faculty of Mathematics and Mechanics Research Laboratory for Analysis and Modeling of Social Processes Saint Petersburg State University 7/9 Universitetskaya Emb. 199034 Saint Petersburg Institute of Childhood Herzen State Pedagogical University 48 Moika Embankment 191186 Saint Petersburg

Conventional multiagent control strategies rely either on pre-defined operational patterns, or complex inter-agent communications. While the former provides simple yet compelling results, the latter allows to achieve goals in complex environments with unpredictable disturbances. However, designing local networked control solutions for large-scale robotic systems is extremely challenging. A novel way to control complex systems by manipulating system clusters as sub-systems is proposed. The relation between sparsity and cluster flows is manifested in the new developed approach to estimate cluster structure of a group of robots based only on a few local observations of their states. Aiming to perform necessary measurements of all N agent states, the compressed sensing methodology is used to obtain ∼ logN randomized aggregated measurements, followed by the corresponding series of local voting protocols for the network to reach a common aggregated state with randomized weights. Thus, the cluster control synthesis by these compressed measurements is computationally efficient, and yet precise. Effectiveness of the proposed method is illustrated in numeric simulations, where adaptive observation feedback cluster control outperforms conventional strategies.

关键词： Adaptive control of multi-agent systems Networked robotic systems Distributed optimization for large-scale systems

来源：评论

学校读者我要写书评

暂无评论

Decision Tree Pruning Method Using Delayed Sampling

Decision Tree Pruning Method Using Delayed Sampling

引用

International Conference on Information Technologies (InfoTech)

作者： Sergei Alexandrovich Mitrofanov Eugene Stanislavovich Semenkin Department of System Analysis and Operations Research Institute of Informatics and Telecommunications Reshetnev Siberian State University of Science and Technology Krasnoyarsk Russian Federation Scientific and Educational Center "Artificial Intelligence Technologies" Bauman Moscow State Technical University Moscow Russian Federation Laboratory "Hybrid Methods of Modeling and Optimization in Complex Systems" Siberian Federal University Krasnoyarsk Russian Federation

ISBN: (数字)9798350365689

ISBN: (纸本)9798350365696

关键词： Visualization Machine learning algorithms Accuracy Measurement uncertainty Machine learning Sampling methods Decision trees Stakeholders Information technology Standards

来源：评论

学校读者我要写书评

暂无评论

Background-Driven and Foreground-Refined Network for Weakly-Supervised Change Detection

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Liu, Fang Zhang, Peng Liu, Jia Yang, Jingxiang Tang, Xu Xiao, Liang Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China Jiangsu Province Engineering Research Center of Airborne Detecting and Intelligent Perceptive Technology Nanjing210049 China Ministry of Industry and Information Technology Key Laboratory of Analysis of Mathematical Theory and Modeling of Complex Systems Nanjing210094 China Xidian University School of Artificial Intelligence Xi’an710071 China

Change detection (CD) in remote sensing aims to reveal meaningful surface changes and has been flourishing in recent years. Compared with fully-supervised methods based on pixel-level labels, image-level labels are easy to acquire, which reduces manual labor to a large extent. However, image-level labels lack spatial-and-shape information while containing the least semantic information, which poses a great challenge to the weakly-supervised CD task. Motivated by the prior that bi-temporal images have background semantic consistency, we propose Background-Driven and Foreground-Refined (BDFR-Net) to ameliorate the above problem. Specifically, there are two key components in the proposed method: the Background-Driven Reconstruction (BDR) with image-level supervision and the Foreground-Refined Learning (FRL) with affinity learning. The former generates changed regions of foreground and background separation, which activates the foreground from image-level supervision and constrains the foreground by maintaining spatial and semantic consistency in background regions. The latter introduces Complementary Fusion and Label Adaption (CFLA) strategies to further refine the foreground, which can mine complementary information from foreground sequences and suppress false activations. In addition, affinity learning is proposed to stabilize and supervise the above process. Complementary relationships between foreground and background are fully utilized. Tested on two popular CD datasets, the results demonstrate that our proposed BDFR-Net produces completely changed regions with clear boundaries and outperforms state-of-the-art weakly-supervised methods. © 1980-2012 IEEE.

关键词： Change detection

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：