检索结果-内蒙古大学图书馆

2nd International Seminar on Research of information technology and Intelligent Systems, ISRITI 2019

作者： Youneng, Kim Sulistyo, Selo Wayan Mustika, I. Universitas Gadjah Mada Dept. Electrical Engineering and Information Technology Yogyakarta Indonesia

ISBN: (纸本)9781728145204

Vehicular Ad-hoc Networks (VANETs) is consid-ered as an extension of Mobile Ad-hoc Networks (MANETs) which the vehicles have high mobility on the street and in-Termittent connectivity. The vehicles move on the street and communicate with each other to share the information such as traffic information, road condition, warning message at the corner, and browsing the internet at the car's backseat, etc. Because of the quick speed of vehicles and intermittent connectivity that making routing protocol plays a significant role in VANETs to deliver the packets among the nodes. There have bio-inspired routing protocols and traditional routing protocols, as well as mobility models, are proposed to obtain an optimal solution for this challenge. In this paper, we illustrate the essential information about the cluster-based technique in VANETs and do a comparative study on cluster-based routing protocols between ACO and AODV, and its mobility for the city environment. © 2019 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Towards complete tree crown delineation by instance segmentation with Mask R–CNN and DETR using UAV-based multispectral imagery and lidar data

引用

ISPRS Open Journal of Photogrammetry and Remote Sensing 2023年 8卷

作者： Dersch, S. Schöttl, A. Krzystek, P. Heurich, M. Dept. of Geoinformatics Munich University of Applied Sciences Munich 80333 Germany Faculty of Environment and Natural Resources University of Freiburg Germany Bavarian Forest National Park Dept. of Visitor Management and National Park Monitoring Grafenau 94481 Germany Institute of Forestry and Wildlife Management Inland Norway University of Applied Science Koppang NO-2480 Norway Dept. of Electrical Engineering and Information Technology Munich University of Applied Sciences Munich 80335 Germany Institute for Applications of Machine Learning and Intelligent Systems Munich University of Applied Sciences Munich 80335 Germany

Precise single tree delineation allows for a more reliable determination of essential parameters such as tree species, height and vitality. Methods of instance segmentation are powerful neural networks for detecting and segmenting single objects and have the potential to push the accuracy of tree segmentation methods to a new level. In this study, two instance segmentation methods, Mask R–CNN and DETR, were applied to precisely delineate single tree crowns using multispectral images and images generated from UAV lidar data. The study area was in Bavaria, 35 km north of Munich (Germany), comprising a mixed forest stand of around 7 ha characterised mainly by Norway spruce (Picea abies) and large groups of European beeches (Fagus sylvatica) with 181–236 trees per ha. The data set, consisting of multispectral images and lidar data, was acquired using a Micasense RedEdge-MX dual camera system and a Riegl miniVUX-1UAV lidar scanner, both mounted on a hexacopter (DJI Matrice 600 Pro). At an altitude of approximately 85 m, two flight missions were conducted at an airspeed of 5 m/s, leading to a ground resolution of 5 cm and a lidar point density of 560 points/m². In total, 1408 trees were marked by visual interpretation of the remote sensing data for training and validating the classifiers. Additionally, 125 trees were surveyed by tacheometric means used to test the optimized neural networks. The evaluations showed that segmentation using only multispectral imagery performed slightly better than with images generated from lidar data. In terms of F1 score, Mask R–CNN with color infrared (CIR) images achieved 92% in coniferous, 85% in deciduous and 83% in mixed stands. Compared to the images generated by lidar data, these scores are the same for coniferous and slightly worse for deciduous and mixed plots, by 4% and 2%, respectively. DETR with CIR images achieved 90% in coniferous, 81% in deciduous and 84% in mixed stands. These scores were 2%, 1%, and 2% worse, res

关键词： Instance segmentation Lidar Multispectral imagery Single tree delineation

来源：评论

学校读者我要写书评

暂无评论

The Research on Target Detection of MIMO Radar Based on Fornasini-Marchesini II Model 5

The Research on Target Detection of MIMO Radar Based on Forn...

引用

5th IEEE International Conference on Computer and Communications, ICCC 2019

作者： Cao, Zhongyong Hua, Cheng Xudongzi, Wu Chang, Liu Wuhan University of Science and Technology Dept. of Information Science and Engineering Wuhan China

ISBN: (纸本)9781728147437

This paper introduces the Fornasini-Marchesini second model (FM-II) realization problem for the target detection of multi-input and multi-output (MIMO) radar. A new operation approach to the realization of MIMO radar based on Fornasini-Marchesini second model will be presented. The constructive procedure that can generate a Fornasini-Marchesini state-space model realization for a given n-D system with lower order than the existing procedure. By utilizing the new method to reduce the dimension of the realization matrix of the multidimensional system which improve the radar's ability to detect dynamic targets. And a non-trival example will be given to show not only the details but also the effectiveness of the proposed approach. © 2019 IEEE.

关键词： Tracking radar

来源：评论

学校读者我要写书评

暂无评论

Passivity-Based Analysis and Nudging Design for Dynamic Social Model with Bounded Rationality

引用

IFAC-PapersOnLine 2020年第5期53卷 338-343页

作者： Shunya Yamashita Takeshi Hatanaka Yasuaki Wasa Naoki Hayashi Kenji Hirata Kenko Uchida Dept. of Systems and Control Engineering Tokyo Institute of Technology Tokyo Japan Dept. of Electrical Engineering and Bioscience Waseda University Tokyo Japan Division of Electrical Electronic and Infocommunications Engineering Osaka University Osaka Japan Dept. of Electric and Electronic Engineering University of Toyama Toyama Japan

In this paper, we address a design problem of nudging mechanism for dynamical decision makers with bounded rationality. We first present a mathematical model for dynamic decision makers with psychological biases. We then analyze the dynamics based on so-called δ -passivity, and reveal that the bias violates passivity of decision makers. We moreover propose a nudging mechanism based on the passivity paradigm to achieve desired social behavior. The presented mechanism is finally demonstrated through numerical simulation.

关键词： population dynamics bounded rationality nudge passivity

来源：评论

学校读者我要写书评

暂无评论

Graph neural network based service function chaining for automatic network control

arXiv

引用

arXiv 2020年

作者： Heo, Dong Nyeong Lange, Stanislav Kim, Hee-Gon Choi, Heeyoul Dept. of Information and Communication Engineering Handong Global University Pohang Korea Republic of Dept. of Information Security and Communication Technology Norwegian University of Science and Technology Trondheim Norway Dept. of Computer Science and Engineering Pohang University of Science and Technology Pohang Korea Republic of

Software-defined networking (SDN) and the network function virtualization (NFV) led to great developments in software based control technology by decreasing expenditures. Service function chaining (SFC) is an important technology to find efficient paths in network servers to process all of the requested virtualized network functions (VNF). However, SFC is challenging since it has to maintain high Quality of Service (QoS) even for complicated situations. Although some works have been conducted for such tasks with high-level intelligent models like deep neural networks (DNNs), those approaches are not efficient in utilizing the topology information of networks and cannot be applied to networks with dynamically changing topology since their models assume that the topology is fixed. In this paper, we propose a new neural network architecture for SFC, which is based on graph neural network (GNN) considering the graph-structured properties of network topology. The proposed SFC model consists of an encoder and a decoder, where the encoder finds the representation of the network topology, and then the decoder estimates probabilities of neighborhood nodes and their probabilities to process a VNF. In the experiments, our proposed architecture outperformed previous performances of DNN based baseline model. Moreover, the GNN based model can be applied to a new network topology without re-designing and re-training. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Tinyradarnn: Combining spatial and temporal convolutional neural networks for embedded gesture recognition with short range radars

arXiv

引用

arXiv 2020年

作者： Scherer, Moritz Magno, Michele Erb, Jonas Mayer, Philipp Eggimann, Manuel Benini, Luca The Dept. of Information Technology and Electrical Engineering ETH Zürich Switzerland The Dept. of Project-based Learning ETH Zürich Switzerland The Dept. of Electrical Electronic and Information Engineering University of Bologna Italy

This work proposes a low-power high-accuracy embedded hand-gesture recognition algorithm targeting battery-operated wearable devices using low power short-range RADAR sensors. A 2D Convolutional Neural Network (CNN) using range frequency Doppler features is combined with a Temporal Convolutional Neural Network (TCN) for time sequence prediction. The final algorithm has a model size of only 46 thousand parameters, yielding a memory footprint of only 92 KB. Two datasets containing 11 challenging hand gestures performed by 26 different people have been recorded containing a total of 20'210 gesture instances. On the 11 hand gesture dataset, accuracies of 86.6% (26 users) and 92.4% (single user) have been achieved, which are comparable to the state-of-the-art, which achieves 87% (10 users) and 94% (single user), while using a TCN-based network that is 7500× smaller than the state-of-the-art. Furthermore, the gesture recognition classifier has been implemented on a Parallel Ultra-Low Power Processor, demonstrating that real-time prediction is feasible with only 21 mW of power consumption for the full TCN sequence prediction network, while a system-level power consumption of less than 120 mW is achieved. We provide open-source access to example code and all data collected and used in this work on ***. © 2020, CC BY-SA.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

RAMNe: Realtime Animal Monitoring over Network with Age of information

RAMNe: Realtime Animal Monitoring over Network with Age of I...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Yu Nakayama Yoshiaki Inoue Marie Katsurai Institute of Engineering Tokyo University of Agriculture and Technology Tokyo Japan Dept. of Information and Communications Technology Osaka University Osaka Japan Dept. of Intelligent Information Engineering and Sciences Doshisha University Kyoto Japan

ISBN: (数字)9781728174402

ISBN: (纸本)9781728174419

The ever-improving Internet of things (IoT) and computer vision technologies have enabled automated monitoring of animals, which is essential for understanding animal behavior and conservation of ecosystem. The tradeoff between survey cost and sampling variability is a significant issue in designing a camera survey considering the risk of losing informative images; the monitoring accuracy tends to decrease in accordance with data reduction. However, there has been no designing method for time-lapse realtime monitoring over networks to guarantee monitoring accuracy. To address this problem, this paper proposes a Realtime Animal Monitoring over Network (RAMNe). The goal of RAMNe is to efficiently detect target animals in realtime using network cameras. We propose a determination method for the monitoring interval to guarantee the target value of monitoring accuracy based on a formal theoretical analysis using the Age of information (AoI). The proposed scheme can minimize the amount of transferred data to enable efficient and stable monitoring even in resource-limited environments. The performance of RAMNe was evaluated with ns-3 simulations to confirm the relationship between monitoring accuracy and interval.

关键词： Monitoring Cameras Animals Image edge detection Servers Delays Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Live Demo: E2P–Events to Polarization Reconstruction from PDAVIS Events

Live Demo: E2P–Events to Polarization Reconstruction from P...

引用

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Tobi Delbruck Zuowen Wang Haiyang Mei Germain Haessig Damien Joubert Justin Haque Yingkai Chen Moritz B. Milde Viktor Gruev Sensors Group Institute of Neuroinformatics Univ. of Zurich and ETH Zurich Switzerland AIT Austrian Institute of Technology Center for Vision Automation & Control High-Performance Vision Systems Vienna Austria Intl. Centre for Neuromorphic Systems The MARCS Institute Western Sydney University Sydney Australia Dept. of Electrical and Computer Engineering University of Illinois at Urbana-Champaign Urbana IL USA

This demonstration shows live operation of of PDAVIS polarization event camera reconstruction by the E2P DNN reported in the main CVPR conference paper Deep Polarization Reconstruction with PDAVIS Events (paper 9149 [...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Resilient Graph Games for State-Dependent Jamming Attacks Analysis on Multi-Agent Systems

引用

IFAC-PapersOnLine 2020年第2期53卷 3421-3426页

作者： Yurid Nugraha Ahmet Cetinkaya Tomohisa Hayakawa Hideaki Ishii Quanyan Zhu Dept. of Systems and Control Engineering Tokyo Institute of Technology Tokyo 152-8552 Japan Information Systems Architecture Science Research Division National Institute of Informatics Tokyo 101-8430 Japan Dept. of Computer Science Tokyo Insitute of Technology Yokohama 226-8502 Japan Dept. of Electrical and Computer Engineering New York University Brooklyn NY 11201 USA

A cybersecurity problem for a multi-agent consensus problem is investigated through a dynamic game formulation. Specifically, we consider a game repeatedly played between a jamming attacker and a defender. The attacker attempts to jam the links between a number of agents to delay their consensus. On the other hand, the defender tries to maintain the connection between agents by attempting to recover some of the jammed links with the goal of achieving faster consensus. In each game, the players decide which links to attack/recover and for how long to continue doing so based on a Lyapunov-like function representing the largest difference between the states of the agents. We analyze the subgame perfect equilibrium of the game and obtain an upper bound of the consensus time that is influenced by the strategies of the players. The results are illustrated with a numerical example.

关键词： Multi-agent systems Consensus problem Game theory Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Output feedback control of radially-dependent reaction-diffusion PDEs on balls of arbitrary dimensions 21st

Output feedback control of radially-dependent reaction-diffu...

引用

21st IFAC World Congress 2020

作者： Vazquez, Rafael Zhang, Jing Krstic, Miroslav Qi, Jie Dept. of Aerospace Engineering Universidad de Sevilla Camino de los Descubrimiento s.n. Sevilla41092 Spain College of Information Science and Technology Donghua University Shanghai201620 China Dept. of Mechanical and Aerospace Engineering University of California San Diego San DiegoCA92093-0411 United States

Recently, the problem of boundary stabilization and estimation for unstable linear constant-coefficient reaction-diffusion equation on n-balls (in particular, disks and spheres) has been solved by means of the backstepping method. However, the extension of this result to spatially-varying coefficients is far from trivial. Some early success has been achieved under simplifying conditions, such as radially-varying reaction coefficients under revolution symmetry, on a disk or a sphere. These particular cases notwithstanding, the problem remains open. The main issue is that the equations become singular in the radius;when applying the backstepping method, the same type of singularity appears in the kernel equations. Traditionally, well-posedness of these equations has been proved by transforming them into integral equations and then applying the method of successive approximations. In this case, with the resulting integral equation becoming singular, successive approximations do not easily apply. This paper takes a different route and directly addresses the kernel equations via a power series approach, finding in the process the required conditions for the radially-varying coefficients and stating the existence of the series solution. This approach provides a direct numerical method that can be readily applied, despite singularities, to both control and observer boundary design problems. Copyright © 2020 The Authors. This is an open access article under the CC BY-NC-ND license

关键词： Integral equations

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：