检索结果-内蒙古大学图书馆

7th International Conference on Information, Control, and Communication Technologies, ICCT 2023

作者： Zeifman, Alexander Usov, Ilya Kryukova, Anastasia Satin, Yacov Shilova, Galina Department of Applied Mathematics Vologda State University Vologda Russia Moscow Center for Fundamental and Applied Mathematics Lomonosov Moscow State University 1 Leninskie Gory GSP-1 Moscow Russia Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Moscow Russia Vologda Research Center of the Russian Academy of Sciences Vologda Russia Department of Mathematics and Informatics Vologda State University Vologda Russia

ISBN: (纸本)9798350340945

An approach is considered for obtaining perturbation bounds for inhomogeneous birth and death processes. We also considered the situation when the monotonicity conditions are satisfied for two homogeneous Markov chains $X$ and $X$, and for a non-homogeneous Markov chain $\tilde{X}(t)$. Under these conditions, some limiting characteristics $\tilde{X}(t)$ were studied. This approach is reduced to the study of the forward Kolmogorov system of the corresponding processes, and it can be generalized for a more general class of Markov chains with continuous time for the study of limiting characteristics. A numerical example is also considered, in which the forward Kolmogorov system was solved by the Runge-Kutta method of the 4th order. © 2023 IEEE.

关键词： Runge Kutta methods

来源：评论

学校读者我要写书评

暂无评论

Boltzmann Equation without the Molecular Chaos Hypothesis

引用

Mathematical Models and computer Simulations 2021年第5期13卷 743-755页

作者： Bogomolov, S.V. Zakharova, T.V. Lomonosov Moscow State University Moscow Russian Federation Institute of Informatics Problems Federal Research Center “Computer Science and Control” Russian Academy of Sciences Moscow Russian Federation

Abstract: A physically clear probabilistic model of a gas from hard spheres is considered using the theory of random processes and in terms of the classical kinetic theory for the densities of distribution functions in the phase space: from the system of nonlinear stochastic differential equations (SDEs), first the generalized and then the random and nonrandom Boltzmann integro-differential equations are derived, taking into account the correlations and fluctuations. The main feature of the original model is the random nature of the intensity of the jump measure and its dependence on the process itself. For the sake of completeness, we briefly recall the transition to increasingly rough approximations in accordance with a decrease in the dimensionless parameter, the Knudsen number. As a result, stochastic and nonrandom macroscopic equations are obtained that differ from the system of Navier–Stokes equations or systems of quasi-gas dynamics. The key difference of this derivation is a more accurate averaging over the velocity due to the analytical solution of the SDE with respect to the Wiener measure, in the form of which the intermediate meso-model in the phase space is presented. This approach differs significantly from the traditional one, which uses not the random process itself, but its distribution function. The emphasis is on the transparency of the assumptions when moving from one level of detail to another, rather than on numerical experiments, which contain additional approximation errors. © 2021, Pleiades Publishing, Ltd.

关键词： Boltzmann equation equations of stochastic gas dynamics and quasi gas dynamics Kolmogorov–Fokker–Planck equation Navier–Stokes equation particle method random processes SDE for Bernoulli and Wiener measures

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach to Estimate SpO2 from PPG Signals 22

A Deep Learning Approach to Estimate SpO2 from PPG Signals

引用

Proceedings of the 9th International Conference on Bioinformatics Research and Applications

作者： Bojana Koteska Ana Madevska Bodanova Hristina Mitrova Marija Sidorenko Fedor Lehocki Faculty of Computer Science and Engineering Ss. Cyril and Methodius University North Macedonia Faculty of Informatics and Information Technologies STU Slovakia and Institute of Measurement Science Slovak Academy of Sciences Slovakia

ISBN: (纸本)9781450396868

Blood oxygen saturation level (SpO2) is one of the vital parameters determining the hemostability of a patient, besides heart rate (HR), respiratory rate (RR) and blood preasure (BP). In emergency situations with a high number of injured persons, during the second triage until arrival to a medical facility, continuously following the SpO2 level in real time is of outmost importance. Using a smart patch-like device attached to a injured’s chest that contains a Photoplethysmogram (PPG) sensor, one can obtain the SpO2 parameter. Our interest in the process of the smart patch prototype development is to investigate the monitoring of a blood oxygen saturation level by using the embedded PPG sensor. We explore acquiring the SpO2 by extracting the set of features from the PPG signal utilizing Python toolkit HeartPy in order to model a Deep neural network regressor. The PPG signal is preprocessed by various filtering techniques to remove low/high frequency noise. The model was trained and tested using the clinical data collected from 52 subjects with SpO2 levels varying from 83 - 100%. The best experimental results considering the SpO2 interval [83,95) were achieved with a PPG signal of 10 seconds length (MAPE 2.00% and 7.21% of big errors defined as absolute percentage errors (APE) equal or greater than 5).

关键词： oxygen saturation deep learning PPG neural networks

来源：评论

学校读者我要写书评

暂无评论

Applying Model-Driven Approach for Data Model Unification 2nd

Applying Model-Driven Approach for Data Model Unification

引用

2nd International Workshop on Modelling to Program, M2P 2020

作者： Stupnikov, Sergey Institute of Informatics Problems Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Vavilova Street 44-2 Moscow119333 Russia

ISBN: (纸本)9783030726959

A lot of scientific data sources currently are concentrated within data infrastructures supporting the whole cycle of data processing and management. Heterogeneous data are represented using various data models from the relational model to various NoSQL models. That is why data integration issues within data infrastructures become more and more important. This paper is devoted to the implementation of data model unification techniques considered as a formal basis for data interoperability, integration, and reuse within data infrastructures. The implementation applies a model-driven engineering approach, namely, formal methods allowing us to define data model syntax and semantic transformations of one data model to the other. To emphasize the advantages of the model-driven approach MDE-based implementation is compared with previous implementation utilizing metacompilation and term rewriting techniques. © 2021, Springer Nature Switzerland AG.

关键词： Data integration

来源：评论

学校读者我要写书评

暂无评论

SyNet: A Synergistic Network for 3D Object Detection through Geometric-Semantic-based Multi-Interaction Fusion

引用

IEEE Transactions on Multimedia 2025年

作者： Zhang, Xiaoqin Bi, Kenan Chan, Sixian Lu, Shijian Zhou, Xiaolong Wenzhou University Key Laboratory of Intelligent Informatics for Safety and Emergency of Zhejiang Province Wenzhou325035 China Zhejiang University of Technology College of Computer Science and Technology Hangzhou310023 China Chinese Academy of Sciences Hefei Institutes of Physical Science Hefei230031 China Nanyang Technological University School of Computer Science and Engineering China Quzhou University The College of Electrical and Information Engineering Quzhou324000 China

Driven by rising demands in autonomous driving, robotics, etc., 3D object detection has recently achieved great advancement by fusing optical images and LiDAR point data. On the other hand, most existing optical-LiDAR fusion methods straightly overlay RGB images and point clouds without adequately exploiting the synergy between them, leading to suboptimal fusion and 3D detection performance. Additionally, they often suffer from limited localization accuracy without proper balancing of global and local object information. To address this issue, we design a synergistic network (SyNet) that fuses geometric information, semantic information, as well as global and local information of objects for robust and accurate 3D detection. The SyNet captures synergies between optical images and LiDAR point clouds from three perspectives. The first is geometric, which derives high-quality depth by projecting point clouds onto multi-view images, enriching optical RGB images with 3D spatial information for a more accurate interpretation of image semantics. The second is semantic, which voxelizes point clouds and establishes correspondences between the derived voxels and image pixels, enriching 3D point clouds with semantic information for more accurate 3D detection. The third is balancing local and global object information, which introduces deformable self-attention and cross-attention to process the two types of complementary information in parallel for more accurate object localization. Extensive experiments show that SyNet achieves 70.7% mAP and 73.5% NDS on the nuScenes test set, demonstrating its effectiveness and superiority as compared with the state-of-the-art. © 2025 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Continual Learning of a Time Series Model Using a Mixture of HMMs with Application to the IoT Fuel Sensor Verification 18

Continual Learning of a Time Series Model Using a Mixture of...

引用

18th Conference on computer science and Intelligence Systems, FedCSIS 2023

作者： Glomb, Przemyslaw Cholewa, Michal Foszner, Pawel Bularz, Jakub Institute of Theoretical and Applied Informatics Polish Academy of Sciences Batycka 5 Gliwice44-100 Poland Department of Computer Graphics Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 2A Gliwice44-100 Poland Aiut Sp. Z O.o. ul. Wyczókowskiego 113 Gliwice44-109 Poland

ISBN: (纸本)9788396744784

This paper presents an application of a mixture of Hidden Markov Models (HMMs) as a tool for verification of IoT fuel sensors. The IoT fuel sensors report the level of fuel in tanks of a petrol station, and are a key component for monitoring system reliability (billing), safety (fuel/oil leak detection) and security (theft prevention). We propose an algorithm for learning a mixture of HMMs based on a continual learning principle, i.e. it adapts the model while monitoring a sensor over time, signalling unexpected or anomalous sensor reports. We have tested the proposed approach on a real-life data of 15 fuel tanks being monitored with the FuelPrime system, where it has shown a very good performance (average area under ROC curve of 0.94) of detecting anomalies in the sensor data. Additionally we show that the proposed method can be used for trend monitoring and present qualitative analysis of the short and long term learning performance. The proposed method has promising performance score, the resulting model has a high degree of explainability, limited memory and computation requirements and can be easily generalized to other domains of sensor verification. © 2023 Polish Information Processing Society.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

HyperMask: Adaptive Hypernetwork-based Masks for Continual Learning

arXiv

引用

arXiv 2023年

作者： Ksiązek, Kamil Spurek, Przemyslaw Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice Poland Jagiellonian University Faculty of Mathematics and Computer Science Cracow Poland IDEAS NCBR Warsaw Poland

Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. Many continual learning (CL) strategies are trying to overcome this problem. One of the most effective is the hypernetwork-based approach. The hypernetwork generates the weights of a target model based on the task's identity. The model's main limitation is that, in practice, the hypernetwork can produce completely different architectures for subsequent tasks. To solve such a problem, we use the lottery ticket hypothesis, which postulates the existence of sparse subnetworks, named winning tickets, that preserve the performance of a whole network. In the paper, we propose a method called HyperMask, which dynamically filters a target network depending on the CL task. The hypernetwork produces semi-binary masks to obtain dedicated target subnetworks. Moreover, due to the lottery ticket hypothesis, we can use a single network with weighted subnets. Depending on the task, the importance of some weights may be dynamically enhanced while others may be weakened. HyperMask achieves competitive results in several CL datasets and, in some scenarios, goes beyond the state-of-the-art scores, both with derived and unknown task *** Codes 68T07 Copyright © 2023, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

InsightDrive: Insight Scene Representation for End-to-End Autonomous Driving

arXiv

引用

arXiv 2025年

作者： Song, Ruiqi Guo, Xianda Wu, Hangbin Wei, Qinggong Chen, Long College of Surveying and Geo-informatics Tongji University China Institute of Automation Chinese Academy of Sciences China School of Computer Science Wuhan University China The School of Artificial Intelligence University of Chinese Academy of Sciences China Waytous China IAIR Xi’an Jiaotong University China

Directly generating planning results from raw sensors has become increasingly prevalent due to its adaptability and robustness in complex scenarios. Scene representation, as a key module in the pipeline, has traditionally relied on conventional perception, which focus on the global scene. However, in driving scenarios, human drivers typically focus only on regions that directly impact driving, which often coincide with those required for end-to-end autonomous driving. In this paper, a novel end-to-end autonomous driving method called InsightDrive is proposed, which organizes perception by language-guided scene representation. We introduce an instance-centric scene tokenizer that transforms the surrounding environment into map- and object-aware instance tokens. Scene attention language descriptions, which highlight key regions and obstacles affecting the ego vehicle’s movement, are generated by a vision-language model that leverages the cognitive reasoning capabilities of foundation models. We then align scene descriptions with visual features using the vision-language model, guiding visual attention through these descriptions to give effectively scene representation. Furthermore, we employ self-attention and cross-attention mechanisms to model the ego-agents and ego-map relationships to comprehensively build the topological relationships of the scene. Finally, based on scene understanding, we jointly perform motion prediction and planning. Extensive experiments on the widely used nuScenes benchmark demonstrate that the proposed InsightDrive achieves state-of-the-art performance in end-to-end autonomous driving. The code is available at https://***/songruiqi/InsightDrive Copyright © 2025, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Formalisation of Motion Description in Microscopy Images 1

引用

15th International Conference on Pattern Recognition and Information Processing, PRIP 2021

作者： Nedzved, Olga Gurevich, Igor Yashina, Vera Tiaojuan, Ren Fangfang, Ye Ablameyko, Sergey Belarusian State University Minsk Minsk Belarus Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Moscow Moscow Russia Zhejiang Shuren University Hangzhou Hangzhou China United Institute of Informatics Problems of NASB Minsk Belarus

ISBN: (数字)9783030988838

ISBN: (纸本)9783030988821

In this paper, a formalization of the task of monitoring cell population movement in microscopic video-sequences is proposed. The method for solving the task is proposed that is based on integral optical flow and motion maps to identify different types of cell movements. Three types of motion are analyzed: directional motion, aggregation and dispersion. Integral optical flow is used to create motion maps and these maps are used to analyze and describe motions in any region of interest. The results of experiments for cell population analysis in video sequences obtained are presented. © 2022, Springer Nature Switzerland AG.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Intervals and Possibility Degree Formulae for Usage Prioritization of Cartagena Coastal Military Batteries 19th

Intervals and Possibility Degree Formulae for Usage Priori...

引用

19th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, IPMU 2022

作者： Sánchez-Lozano, Juan Miguel Fernández-Martínez, Manuel Cabrera-Cuevas, Marcelino Pelta, David A. University Centre of Defence at the Spanish Air Force Academy MDE-UPCT San Javier Murcia Spain Department of Languages and Informatics Systems Universidad de Granada Granada Spain Department of Computer Science and AI Universidad de Granada Granada Spain

ISBN: (纸本)9783031089732

Several projects have been proposed in recent years with the goal of restoring some of Cartagena’s (a Spanish city) old military batteries so that they can be turned into touristic, scientific, or cultural sites. In previous work, a combination of AHP and TOPSIS (A+T, hereafter) was applied to prioritize such batteries. In this paper, we address the following question: would it be possible to obtain the same prioritization using a simpler approach? In this regard, we are focused on an approach that relies on assigning score intervals (rather than single values) to the alternatives and compares them using a possibility degree formulae (we shall denote as I+P in the sequel). That approach’s main advantage is that it does not require explicit weights but it only relies on a linear ordering of criteria to reflect the user’s preferences, instead. Our results show that the prioritization obtained by means of I+P, A+T, and a simple additive weighting scheme (SAW) are nearly identical, thus providing a positive response to the question posed above. © 2022, Springer Nature Switzerland AG.

关键词： Decision making

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：