检索结果-内蒙古大学图书馆

Hole detection in wireless sensor network with force-directed algorithm and contour tracing

INTERNATIONAL JOURNAL OF SENSOR NETWORKS 2022年第3期39卷 174-191页

作者： Cheong, Se-Hang Mok, Kuai-Un Si, Yain-Whar Univ Macau Dept Comp & Informat Sci Ave Univ Taipa Macau Peoples R China

Hole detection is an important task for preserving energy in wireless sensor networks. Distributed approaches are commonly used for detecting holes. In these approaches, complex calculations are performed at each node for determining the existence of holes in the network. In this paper, we propose a novel approach called FD-CT for detecting holes in wireless sensor networks by exploiting the power of force-directed algorithms for generating layouts from a given topology. The generated layouts are then processed with a contour tracing algorithm for identifying the sensors along the boundary of holes in the networks. By using force-directed and contour tracing algorithms, our approach is able to detect holes from a given topology without using location information or anchor nodes. The proposed approach is extensively evaluated on different type of networks and force-directed algorithms. Experiment results show that FD-CT with KK-MS-DS algorithm can achieve 95% sensitivity and 98% specificity among all the algorithms evaluated.

关键词： hole detection wireless sensor networks WSNs force-directed algorithm contour tracing

来源：评论

学校读者我要写书评

暂无评论

Coverage hole detection in WSN with force-directed algorithm and transfer learning

引用

APPLIED INTELLIGENCE 2022年第5期52卷 5435-5456页

作者： Lai, Yue-Hui Cheong, Se-Hang Zhang, Hui Si, Yain-Whar Univ Macau Macau Peoples R China BNU HKBU United Int Coll Zhuhai Peoples R China

Coverage hole detection is an important research problem in wireless sensor network research community. However, distributed approaches proposed in recent years for coverage hole detection problem have high computational complexity. In this paper, we propose a novel approach for coverage hole detection in wireless sensor networks called FD-TL (force-directed and Transfer-learning) which is based on layout generation capability of force-directed algorithms and image recognition power of Convolutional Neural Network with transfer learning. In contrast to existing approaches, the proposed approach is a pure topology-based approach since FD-TL can detect both triangular and non-triangular coverage holes from a wireless sensor network based on the input network topology without relying on the physical locations of the anchor nodes. In FD-TL, a force-directed algorithm is used to generate a series of possible layouts from a given input topology. Next, a Convolutional Neural Network is used to recognize potential coverage holes from the generated layouts. During the training phase, a transfer learning method is used to aid the recognition process. Experimental results show that FD-TL method can achieve 90% sensitivity and 96% specificity for coverage hole detection in wireless sensor networks.

关键词： Wireless sensor networks Coverage hole detection force-directed algorithm Convolutional neural network Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Thermal Design via Improved force-directed algorithm for IGCT Driver Board

Thermal Design via Improved Force-Directed Algorithm for IGC...

引用

2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

作者： Gao, Xuming Zhang, Aimin Wang, Shan Du, Yudong Li, Ying Huang, Jingjing Xi'an Jiaotong University School of Automation Science and Engineering Xi'an China

ISBN: (纸本)9781665471640

The power electronic device integrated gate commutated thyristor (IGCT) is currently being developed towards higher power density and reliability. As a crucial part of the IGCT, a highly integrated driver board is essential for the reliable turn-on and turn-off of the IGCT. However, thermal failure is the primary cause of failure for the IGCT driver board. Therefore, a reasonable thermal design of the driver board is imperative for the reliability of the IGCT. This paper proposes an improved force-directed algorithm suitable for the thermal layout of IGCT driver board components. Firstly, according to the requirements of the IGCT electrical characteristics, the driver board is divided into functional regions. Secondly, based on the size, adjacent spacing and heat flux gradient of the main heating components in each region, the displacement is iterated until the final layout results are output when the termination conditions are met. Finally, the simulation comparison results of the proposed and the traditional driver board show that the proposed algorithm can effectively improve the thermal performance of the IGCT driver board, realize the reasonable distribution of the overall temperature and reduce the local hot spot temperatures. © 2023 IEEE.

关键词： driver board force-directed algorithm functional regions division integrated gate commutated thyristor (IGCT) thermal layout

来源：评论

学校读者我要写书评

暂无评论

Multi-layer Network Visualization Based on force-directed algorithm 2021

Multi-layer Network Visualization Based on Force-Directed Al...

引用

2nd International Conference on Artificial Intelligence and Information Systems (ICAIIS )

作者： An Shenhao Yu Ronghuan Space Engn Univ Sci & Technol Complex Elect Syst Simulat Lab Beijing Peoples R China

ISBN: (纸本)9781450390200

In order to show the community structure and hierarchical structure of multi-layer networks, a multi-layer network visualization method based on force-directed algorithm is proposed. Firstly, the traditional force-directed algorithm is improved to generate a multi-force guidance network layout result with obvious community characteristics. On this basis, a hierarchical clustering algorithm is used to establish a network hierarchy from bottom to top, allowing users to observe hierarchical network topology through multiple interactive operations hierarchical network topology. In order to verify the effectiveness of the method, two multi-layer network instance data are selected for experiments. The visualization results show that the method can effectively display the community structure and hierarchical structure of the multi-layer network, and help users understand and analyze its structural characteristics.

关键词： Complex networks multi-layer networks force-directed algorithm network topology hierarchical structure community structure

来源：评论

学校读者我要写书评

暂无评论

3D geometric modelling of discontinuous fibre composites using a force-directed algorithm

引用

JOURNAL OF COMPOSITE MATERIALS 2017年第17期51卷 2389-2406页

作者： Harper, L. T. Qian, C. C. Luchoo, R. Warrior, N. A. Univ Nottingham Div Mat Mech & Struct Fac Engn Nottingham NG7 2RD England

A geometrical modelling scheme is presented to produce representative architectures for discontinuous fibre composites, enabling downstream modelling of mechanical properties. The model generates realistic random fibre architectures containing high filament count bundles (>3k) and high (approximate to 50%) fibre volume fractions. Fibre bundles are modelled as thin shells using a multidimensional modelling strategy, in which fibre bundles are distributed and compacted to simulate pressure being applied from a matched mould tool. Finite element simulations are performed to benchmark the in-plane mechanical properties obtained from the numerical model against experimental data, with a detailed study presented to evaluate the tensile properties at various fibre volume fractions and specimen thicknesses. Tensile modulus predictions are in close agreement (less than 5% error) with experimental data at volume fractions below 45%. Ultimate tensile strength predictions are within 4.2% of the experimental data at volume fractions between 40 and 55%. This is a significant improvement over existing 2D modelling approaches, as the current model offers increased levels of fidelity, capturing dominant failure mechanisms and the influence of out-of-plane fibres.

关键词： Discontinuous composite finite element analysis force-directed algorithm

来源：评论

学校读者我要写书评

暂无评论

A CUSTOMIZED force-directed LAYOUT algorithm WITH GENETIC algorithm TECHNIQUES FOR BIOLOGICAL GRAPHS WHOSE VERTICES HAVE ENZYME COMMISSION ATTRIBUTES

A CUSTOMIZED FORCE-DIRECTED LAYOUT ALGORITHM WITH GENETIC AL...

引用

作者： FIRAT AKSOYDAN MIDDLE EAST TECHNICAL UNIVERSITY

学位级别：硕士

A pathway can be visualized as a graph whose layout is drawn by a force-directed algorithm. In our previous study, we have described EClerize which is a customized and improved Kamada Kawai force-directed algorithm in order to visualize path- ways that contain nodes with attributes as EC numbers. EClerize creates clusters of vertices with enzymes that belong to the same EC class. Here, we make use of genetic algorithm (GA) to obtain a global optimum solution for EClerize and we integrate undirected graph layout drawing with GA. To provide diversity, 5 tech- niques in mutation phase and for crossover 2 techniques are employed. In mu- tation, vertices of a selected graph are moved randomly within a limited area or selected edges/vertices are exchanged according the routines of a technique. In crossover, the operation of exchanging vertices is performed between two selected graphs. In each iteration, fitness values of individuals are calculated by 6 different fitness measurements ranging from edge crossing number to drawing area. Over- all relative fitness values are used to choose parent individuals. We have applied this method to 3 pathways and the results are better than those of the base study.

关键词： Graph Visualization Clustering force-directed algorithm Enzyme Commission Numbers Genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

A force directed Partitioning algorithm for 3D Floorplanning 12

A Force Directed Partitioning Algorithm for 3D Floorplanning

引用

2017 IEEE 12th International Conference on ASIC

作者： Linquan Lyu Takeshi Yoshimura Graduate School of IPS Waseda University

ISBN: (纸本)9781509066261;9781509066254

Partitioning is very important to 3 D IC physical ***,h Metis(most famous partitioning software package) is widely used for ***,h Metis is for partitioning of hyper *** the method is used for layer assignment of 3 D floorplan/placement,some net might be too *** paper develops a partitioning algorithm for 3 D *** proposed combines a cost-based heuristic and force directed algorithm,which places the nodes considering attractive force and repulsive force,in order to solve the long net *** consider both the wire length and the number of TSVs in this *** second part of the algorithm has two kinds according to the different *** experimental results demonstrated our algorithms can effectively reduce the wire length and the number of *** comparing the experimental results of two focuses,we can get the differences and strengths of the two algorithms separately.

关键词： 3D IC IC partitioning force-directed algorithm TSV wire length

来源：评论

学校读者我要写书评

暂无评论

Clustering-based force-directed algorithms for 3D graph visualization

引用

JOURNAL OF SUPERCOMPUTING 2020年第12期76卷 9654-9715页

作者： Lu, Jiawei Si, Yain-Whar Univ Macau Dept Comp & Informat Sci Ave Univ Taipa Macau Peoples R China

force-directed algorithm is one of the most commonly used methods for visualization of 2D graphs. These algorithms can be applied to a plethora of applications such as data visualization, social network analysis, crypto-currency transactions, and wireless sensor networks. Due to their effectiveness in visualization of topological data, various force-directed algorithms for 2D graphs were proposed in recent years. Although force-directed algorithms for 2D graphs were extensively investigated in research community, the algorithms for 3D graph visualization were rarely reported in the literature. In this paper, we propose four novel clustering-based force-directed (CFD) algorithms for visualization of 3D graphs. By using clustering algorithms, we divide a large graph into many smaller graphs so that they can be effectively processed by force-directed algorithms. In addition, weights are also introduced to further enhance the calculation for clusters. The proposed CFD algorithms are tested on 3 datasets with varying numbers of nodes. The experimental results show that proposed algorithms can significantly reduce edge crossings in visualization of large 3D graphs. The results also reveal that CFD algorithms can also reduce Kamada and Kawai energy and standardized variance of edge lengths in 3D graph visualization.

关键词： 3D graphs Visualization Clustering algorithm force-directed algorithm

来源：评论

学校读者我要写书评

暂无评论

An image classification approach for hole detection in wireless sensor networks

引用

JOURNAL OF SUPERCOMPUTING 2022年第6期78卷 8774-8809页

作者： Cheong, Se-Hang Ng, Kim-Hou Si, Yain-Whar Univ Macau Fac Sci & Technol Macau Peoples R China

Hole detection is a crucial task for monitoring the status of wireless sensor networks (WSN) which often consist of low-capability sensors. Holes can form in WSNs due to the problems during placement of the sensors or power/hardware failure. In these situations, sensing or transmitting data could be affected and can interrupt the normal operation of the WSNs. It may also decrease the lifetime of the network and sensing coverage of the sensors. The problem of hole detection is especially challenging in WSNs since the exact location of the sensors is often unknown. In this paper, we propose a novel hole detection approach called FD-CNN which is based on force-directed (FD) algorithm and Convolutional Neural Network (CNN). In contrast to existing approaches, FD-CNN is a centralized approach and is able to detect holes from WSNs without relying on the information related to the location of the sensors. The proposed approach also alleviates the problem of high computational complexity in distributed approaches. The proposed approach accepts the network topology of a WSN as an input and generates the identity of the nodes surrounding each detected hole in the network as the final output. In the proposed approach, an FD algorithm is used to generate the layout of the wireless sensor networks followed by the identification of the holes in the layouts using a trained CNN model. In order to prepare labeled datasets for training the CNN model, an unsupervised pre-processing method is also proposed in this paper. After the holes are detected by the CNN model, two algorithms are proposed to identify the regions of the holes and corresponding nodes surrounding the regions. Extensive experiments are conducted to evaluate the proposed approach based on different datasets. Experimental results show that FD-CNN can achieve 80% sensitivity and 93% specificity in less than 2 minutes.

关键词： Wireless sensor networks Hole detection force-directed algorithm Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Supervised force directed algorithm for the generation of flow maps 22

Supervised force directed algorithm for the generation of fl...

引用

22nd International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, WSCG 2014 - in co-operation with EUROGRAPHICS Association

作者： Debiasi, Alberto Simões, Bruno De Amicis, Raffaele Fondazione Graphitech Via alla Cascata 56/C Trento38123 Italy

ISBN: (纸本)9788086943701

Cartographic flow maps are graphical representations for portraying the movement of objects, such as people, goods or traffic network, from one location to another. On the one hand, flow maps can reduce visual clutter by merging single representations of movement. On the other hand, flow maps are also fast to produce and simple to understand. In this paper, we present a new method for the automatic generation of flow maps. Our method is based on a theoretically grounded physical system to describe the motion and forces of attraction and repulsion between data points. Additionally, support for an optional supervision of the graph layout is also available. Finally, the cost of our algorithm is evaluated and a comparison with existing implementations is provided. Results have shown a good balance between computational complexity and the visual quality of the generated maps.

关键词： Flow maps force-directed algorithm Geovisualization Graphical interaction

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：