检索结果-内蒙古大学图书馆

Energy States of an Exciton in Truncated Paraboloid in the Intermediate Confinement Conditions

Bulletin of the Russian Academy of Sciences: Physics 2023年第Suppl 3期87卷 S386-S389页

作者： Dzyuba, V.P. Amosov, A.V. Institute of Automation and Control Processes Far Eastern Branch Russian Academy of Sciences Vladivostok690041 Russia

Abstract: Theoretical studies of bond or free quantum states dependency at nanovolume on its geometry and size are one of the most complex problems of modern physics. The boundary conditions on the nanovolume surface makes impossible an exact analytical solution. In this paper we using the parabolic coordinates had found the solution of Schrödinger equation boundary value problem with zero boundary conditions on the surface of a paraboloid of revolution and a cutting plane perpendicular to the rotation axis. The energy spectrum in the ground and first excited states was analyzed and the exciton wave functions of these states were determined. It turned out that under the condition of intermediate confinement each exciton state is possible for definite geometry and size of the paraboloid of revolution. © Pleiades Publishing, Ltd. 2023. ISSN 1062-8738, Bulletin of the Russian Academy of Sciences: Physics, 2023, Vol. 87, Suppl. 3, pp. S386–S389. Pleiades Publishing, Ltd., 2023.

关键词： Boundary value problems

来源：评论

学校读者我要写书评

暂无评论

BFuse-Net: Bonferroni Mean Operator-Aided Fusion of Neural Networks for Medical Image Classification 5th

BFuse-Net: Bonferroni Mean Operator-Aided Fusion of Neural ...

引用

5th International Conference on Medical Imaging and Computer Aided Diagnosis, MICAD 2024

作者： Ghosh, Triyas Chakraborty, Soham Kaplun, Dmitrii Gulvanskii, Vyacheslav Sarkar, Ram Department of Computer Science and Engineering Jadavpur University Kolkata700032 India Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China Department of Automation and Control Processes Saint Petersburg Electrotechnical University "LETI" Saint Petersburg Russia

ISBN: (纸本)9789819638628

In this paper, we have proposed a novel model, called Bonferroni Mean Operator-aided Fusion of Neural Networks (BFuse-Net). Here, we have taken advantage of the capabilities of four deep learning models as the base learners and then applied a customized attention method to prioritize different fine-grained features by passing their outputs via four parallel pipelines. Next, we have employed a novel aggregation method, a modified Bonferroni Mean operator, to merge the decision scores acquired from every pipeline, prioritizing their individual contributions above their interactions with others in the decision scores. Three medical image datasets— LC25000 (colon cancer), Oral Squamous Cell Carcinoma, and Malaria Cell Images have been used for experimentation. The model yields state-of-the-art outcomes for the three datasets. The source codes and additional results can be found at GitHub repository. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

control graph based problem solvers for knowledge based systems 7

Control graph based problem solvers for knowledge based syst...

引用

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

作者： Gribova, Valeria Moskalenko, Philip Shalfeeva, Elena Timchenko, Vadim Institute of Automation and Control Processes Intelligent Systems Lab Vladivostok Russia

ISBN: (纸本)9781665432177

A methodology for using declaratively defined control graph structures to develop problem solvers for systems with knowledge bases is proposed. Special attention is paid to the processing of knowledge base fragments and the possibility of placing architectural components of the solver on different computing nodes. The structure of such an information-and-control graph includes related constructs (operators), one of which is marked as 'beginning'. These structures can be divided into: computing control constructs and information processing constructs. The developer can group individual operators into blocks - for their repeated usage (including organization of recursive calculations). The structure of the graph also includes a description of the data. © 2021 IEEE.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Indoor 3D Positioning Based on Bluetooth Beacons

Indoor 3D Positioning Based on Bluetooth Beacons

引用

International Conference on SMART Automatics and Energy, SMART-ICAE 2021

作者： Grinyak, V. Devyatisilnyi, A. Shurygin, A. Information Technologies Vladivostok State University of Economics and Service VSUES Vladivostok Russia Navigation and Control Institute of Automation and Control Processes FEBRAS IACP FEBRAS Vladivostok Russia

ISBN: (纸本)9789811687587

The work is devoted to the problem of determining the indoor object location in cases where the signal of satellite (GPS, GLONASS, etc.) is not available. In this case, alternative sources of navigation data are used to position objects: inertial navigation devices (accelerometers, gyroscopes), Bluetooth and Wi-Fi data transmission devices, atmospheric pressure sensor, magnetometer, etc. The use of Bluetooth beacons for indoor positioning has many advantages. Firstly, it is the possibility of arbitrary configuration of sensors in the room due to their small size and autonomy. Secondly, it is possible to build a system based on inexpensive and widespread equipment that does not require special professional skills of the personnel. The paper discusses the problem of positioning an object in three-dimensional space according to the data of Bluetooth devices located in the room and forming a multi-position beacon surveillance system. It is noted that for the successful operation of such a system, it is necessary to estimate in advance the characteristic error in estimating the coordinates of positioned objects and if necessary, change the configuration of the beacons. A model interpretation of the positioning problem in the form of a system of algebraic linear equations is proposed. Such a representation allows one to construct a priori theoretical estimates of the error in determining the object coordinates to determine areas of space where the positioning accuracy is insufficient. The paper presents the expected accuracy calculations data of solving the problem in various typical situations and the results of field experiments that confirm the calculations. In general, the study is optimistic about the prospects for solving 3D indoor positioning problems using Bluetooth beacons. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Bluetooth

来源：评论

学校读者我要写书评

暂无评论

Formation control of AUV on the Base of Visual Tracking of AUV-Leader

Formation Control of AUV on the Base of Visual Tracking of A...

引用

2021 International Russian automation Conference, RusAutoCon 2021

作者： Filaretov, Vladimir Yukhimets, Dmitry Institute of Automation and Control Processes Feb Ras Robotics Laboratory Vladivostok Russia Institute of Marine Technology Problem Feb Ras Institute of Automation and Control Processes Feb Ras Vladivostok Russia

ISBN: (纸本)9780738131566

In this paper, a method for the synthesis of a group control system for AUV moving in the leader-follower mode was proposed. The position of the follower relative to the leader is proposed to be determined using an on-board video camera, which recognized the light beacons installed on the leader's body. The obtained information is used to form an estimate of the position of the target point in the coordinate system of the follower with a frequency sufficient for the implementation of high-precision robust control systems. A method for synthesizing a control system that provides a desired quality of control independently from changes in the parameters of the AUV-follower was proposed. The results of mathematical simulation confirmed the high quality of control provided by the proposed system. © 2021 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Development of Method of Generating a Reference Movement Speed of a Group of UAVs

Development of Method of Generating a Reference Movement Spe...

引用

2024 International Conference on Ocean Studies, ICOS 2024

作者： Gubankov, Anton Gornostaev, Igor Institute of Automation and Control Processes FEB RAS M.D. Ageev Institute of Marine Technology Problems Admiral G.I. Nevelskoy Maritime State University Robotics Laboratory Laboratory of Intelligent Information Systems for Marine Robots Laboratory of Marine Unmanned Aviation and Marine Aviation Systems Vladivostok Russia Institute of Automation and Control Processes FEB RAS M.D. Ageev Institute of Marine Technology Problems Admiral G.I. Nevelskoy Maritime State University Robotics Laboratory Laboratory of Robotic Systems Laboratory of Marine Unmanned Aviation and Marine Aviation Systems Vladivostok Russia

ISBN: (纸本)9798331532307

The article presents the results of the development of a method for the automatic formation of reference speeds for autonomous unmanned aerial vehicles of multirotor type, performing specified missions (such as monitoring of the sea and coastal territory in order to track populations of rare and endangered species, as well as evaluating the potential volumes of biological resources) singly or as part of a group (in formation). At the same time, the trajectories of these aircraft are set by smooth spatial curves - parametric splines of the third order, which makes it easy to adjust the specified trajectories during the mission. In order to maintain a high speed of movement of vehicles along trajectories with high accuracy of movement and saving formation, it is proposed to adjust the specified speed directly during the mission in such a way that the thrusters can ensure their required movements, taking into account the restrictions on the thrust vectors. At the same time, a simplified model of the dynamics of a quadcopter was used to calculate the values of reference speeds, taking into account the influence of wind force, environmental resistance, gravity and the total thrust vector of the propellers. The systems synthesized on the basis of this method can be implemented even on low-power onboard computing devices of unmanned aerial vehicles. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

AUV Inspection of Subsea Pipelines Using Information from an Onboard Stereo Camera

AUV Inspection of Subsea Pipelines Using Information from an...

引用

Ocean Studies (ICOS), International Conference on

作者： Valery Bobkov Mikhail Morozov Alexander Inzartsev Mikhail Panin Institute of Automation and Control Processes Far Eastern Branch of RAS Vladivostok Russian Federation M.D. Ageev Institute of Marine Technology Problems Far Eastern Branch of RAS Institute of Automation and Control Processes Far Eastern Branch of RAS Vladivostok Russian Federation

ISBN: (数字)9798331532307

ISBN: (纸本)9798331532314

Inspection of underwater pipelines (UP) condition by means of autonomous underwater vehicles (AUVs) requires high precision of vehicle localization relative to UP. One of the possible solutions to the problem is recognition of UP using the optical images from AUV onboard stereocamera. Applied in this work method is based on recognition of visible borders at 2D photographs with subsequent recovery of spatial parameters of a scene, including location and orientation of UP in AUVcentered coordinate system. Computational experiments were conducted to test the presented methods. They consisted of debugging the model of the AUV behavior during the inspection of UP, evaluating the effectiveness of the developed methods on virtual scenes, as well as on the real data obtained by a monocamera via the AUV tracking along pipeline. The results of estimating the accuracy of UP localization on real data and also in computational experiments have shown that proposed methods could provide the required navigation accuracy of the AUV relative to pipeline during inspection.

关键词： Location awareness Autonomous underwater vehicles Accuracy TV Shape Computational modeling Surface resistance Pipelines Inspection Data models

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Multiview Top-k Pooling with Deep-Q-Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2985-2996页

作者： Li, Zhi-Peng Su, Hai-Long Wu, Yong- Zhang, Qin-Hu Yuan, Chang-An Gribova, Valeriya Filaretov, Vladimir Fedorovich Huang, De-Shuang Eastern Institute of Technology Zhejiang Ningbo315201 China University of Science and Technology of China School of Life Sciences Anhui Hefei230026 China Tongji University Institute of Machine Learning and Systems Biology School of Electronics and Information Engineering Shanghai201804 China Guangxi Academy of Sciences Institute of Big Data and Intelligent Computing Research Center Nanning530007 China Far Eastern Branch of the Russian Academy of Sciences Institute of Automation and Control Processes Vladivostok690041 Russia

Graph neural networks (GNNs) are extensions of deep neural networks to graph-structured data. It has already attracted widespread attention for various tasks such as node classification and link prediction. Existing research focuses more on graph convolutional neural networks (GCNs). However, it is usually overlooked that graph pooling can obtain graph representations by summarizing and down-sampling node information. Meanwhile, existing graph pooling methods mainly use top-k for node selection, but most of them consider only single view information when scoring nodes, and the k values in top-k are usually selected empirically. This work proposes the hierarchical multiview top-k pooling (HMTPool) with deep-Q-networks, which scores nodes taking into account multiview information (considering graph structure and features) and does not rely on the empirical adaptive selection of the best k value. HMTPool is a two-stage process. It first uses a variant GCN and multilayer perceptron to score the nodes from structural and feature perspectives, respectively and then performs fusion operations on the multiview information scores of the nodes. In addition, to select the optimal pooling ratio of top-k, we propose a deep-Q-network-based top-k (DTop-k) node selection method, which can adaptively select the best pooling ratio without prior knowledge. Experimental results on six TUDatasets and two Benchmarking GNNs datasets demonstrate the effectiveness of our proposed approach. © 2020 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Algorithms of the AUV control system for operation under the lower ice edge

Algorithms of the AUV control system for operation under the...

引用

2022 International Conference on Ocean Studies, ICOS 2022

作者： Inzartsev, Alexander Bagnitckii, Andrey Panin, Mikhail Institute of Automation and Control Processes Far Eastern Branch of Ras Vladivostok Russia Institute of Marine Technology Problems Far Eastern Branch of Ras Vladivostok Russia

ISBN: (纸本)9781665473729

One of the urgent tasks for autonomous underwater vehicles (AUV) is monitoring of marine biological resources and survey of the lower edge of the ice in the circumpolar zones. The main problems for AUV movement during such work are the uneven lower surface of the ice and the need to search for an ice hole for surfacing, which may be required either in accordance with the mission program or in an emergency situation. The report discusses the algorithms of the AUV information and control system, designed to solve these problems. These algorithms ensure the movement of the AUV under the ice at various horizons, with the stabilization of a given distance from the lower edge of the ice, as well as in ice-covered shallow waters. To obtain information about the ice situation, an echolocation system is used in AUV, including several sonars with fixed directional patterns in the front hemisphere of the vehicle. The correctness of the algorithms was investigated using mathematical modeling methods. © 2022 IEEE.

关键词： Autonomous underwater vehicles

来源：评论

学校读者我要写书评

暂无评论

Automatic Brightness Correction Method for Side Scan Sonar Echograms

Automatic Brightness Correction Method for Side Scan Sonar E...

引用

2022 International Conference on Ocean Studies, ICOS 2022

作者： Pavin, Alexander Khodorenko, Maxim Institute of Automation and Control Processes Far Eastern Branch of Ras Vladivostok Russia Institute of Marine Technology Problems Far Eastern Branch of Ras Vladivostok Russia

ISBN: (纸本)9781665473729

Side-scan sonar is very important in marine survey such as seafloor exploration, topography, underwater pipeline investigation and so on. SSS-echograms classification and mosaicking are essential during those tasks. Initial side-scan sonar images have uneven brightness distribution. Mosaicking proved difficult due to grayscale gradients on sonar echograms. Brightness equalizing is necessary prior to processing of SSS-echograms. This article discusses methods for brightness equalizing of the echogram images from side-scan sonar in order to identify local inhomogeneities of the seafloor. It provides results of comparative experiments using different approaches to solve this problem. The paper also evaluates the possibility of using these methods on board autonomous underwater robots in real time. © 2022 IEEE.

关键词： Image enhancement

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：