A web interface for WMN-PSODGA hybrid intelligent simulation system: performance evaluation for different mesh client distributions

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Admir Barolli ◽  
Shinji Sakamoto
Keyword(s):  
Intelligent System ◽  
Research Work ◽  
Simulation System ◽  
Web Interface ◽  
Placement Problem ◽  
Content Type ◽  
Node Placement ◽  
Hybrid Intelligent System ◽  
Intelligent Simulation ◽  
Mesh Clients

Purpose The purpose of this paper is to implement a web interface for a hybrid intelligent system. By using the implemented web interface, one can find optimal assignments of mesh routers in wireless mesh networks (WMNs). This study evaluates the implemented system considering three distributions of mesh clients to solve the node placement problem in WMNs. Design/methodology/approach The node placement problem in WMNs is well known to be a computationally hard problem. Therefore, intelligent algorithms are used for solving this problem. The implemented system is a hybrid intelligent system based on meta-heuristics algorithms: particle swarm optimization (PSO) and distributed genetic algorithm (DGA). The proposed system is called WMN-PSODGA. Findings This study carried out simulations using the implemented simulation system. From the simulations results, it was found that the WMN-PSODGA system performs better for chi-square distribution of mesh clients compared with Weibull and exponential distributions. Research limitations/implications For simulations, three different distributions of mesh clients were considered. In the future, other mesh client distributions, number of mesh nodes and communication distance need to be considered. Originality/value This research work, different from other research works, implemented a hybrid intelligent simulation system for WMNs. This study also implemented a web interface for the proposed system, which make the simulation system user-friendly.

scholarly journals A comparison study of chi-square and uniform distributions of mesh clients for different router replacement methods using WMN-PSODGA hybrid intelligent simulation system

2021 ◽  
pp. 1-16
Author(s):  
Admir Barolli ◽  
Kevin Bylykbashi ◽  
Ermioni Qafzezi ◽  
Shinji Sakamoto ◽  
Leonard Barolli ◽  
...  
Keyword(s):  
Load Balancing ◽  
Uniform Distribution ◽  
Simulation System ◽  
Placement Problem ◽  
Chi Square ◽  
Node Placement ◽  
Inertia Weight ◽  
Uniform Distributions ◽  
Weight Method ◽  
Mesh Clients

Wireless Mesh Networks (WMNs) are gaining a lot of attention from researchers due to their advantages such as easy maintenance, low upfront cost and high robustness. Connectivity and stability directly affect the performance of WMNs. However, WMNs have some problems such as node placement problem, hidden terminal problem and so on. In our previous work, we implemented a simulation system to solve the node placement problem in WMNs considering Particle Swarm Optimization (PSO) and Distributed Genetic Algorithm (DGA), called WMN-PSODGA. In this paper, we compare chi-square and uniform distributions of mesh clients for different router replacement methods. The router replacement methods considered are Constriction Method (CM), Random Inertia Weight Method (RIWM), Linearly Decreasing Inertia Weight Method (LDIWM), Linearly Decreasing Vmax Method (LDVM) and Rational Decrement of Vmax Method (RDVM). The simulation results show that for chi-square distribution the mesh routers cover all mesh clients for all router replacement methods. In terms of load balancing, the method that achieves the best performance is RDVM. When using the uniform distribution, the mesh routers do not cover all mesh clients, but this distribution shows good load balancing for four router replacement methods, with RIWM showing the best performance. The only method that shows poor performance for this distribution is LDIWM. However, since not all mesh clients are covered when using uniform distribution, the best scenario is chi-square distribution of mesh clients with RDVM as a router replacement method.

Implementation of a Web interface for hybrid intelligent systems

2019 ◽  
Vol 15 (4) ◽  
pp. 420-431 ◽  
Author(s):  
Shinji Sakamoto ◽  
Admir Barolli ◽  
Leonard Barolli ◽  
Shusuke Okamoto
Keyword(s):  
Intelligent Systems ◽  
Hill Climbing ◽  
Web Interface ◽  
Placement Problem ◽  
Swarm Optimization ◽  
Content Type ◽  
Node Placement ◽  
Hybrid Intelligent Systems ◽  
Distributed Genetic Algorithm ◽  
Two Hybrid

PurposeThe purpose of this paper is to implement a Web interface for hybrid intelligent systems. Using the implemented Web interface, this paper evaluates two hybrid intelligent systems based on particle swarm optimization, hill climbing and distributed genetic algorithm to solve the node placement problem in wireless mesh networks (WMNs).Design/methodology/approachThe node placement problem in WMNs is well-known to be a computationally hard problem. Therefore, the authors use intelligent algorithms to solve this problem. The implemented systems are intelligent systems based on meta-heuristics algorithms: Particle Swarm Optimization (PSO), Hill Climbing (HC) and Distributed Genetic Algorithm (DGA). The authors implement two hybrid intelligent systems: WMN-PSODGA and WMN-PSOHC-DGA.FindingsThe authors carried out simulations using the implemented Web interface. From the simulations results, it was found that the WMN-PSOHC-DGA system has a better performance compared with the WMN-PSODGA system.Research limitations/implicationsFor simulations, the authors considered Normal distribution of mesh clients. In the future, the authors need to consider different client distributions, patterns, number of mesh nodes and communication distance.Originality/valueIn this research work, the authors implemented a Web interface for hybrid intelligent systems. The implemented interface can be extended for other metaheuristic algorithms.

Intelligent recognition system for viewpoint variations on gait and speech using CNN-CapsNet

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
G. Merlin Linda ◽  
N.V.S. Sree Rathna Lakshmi ◽  
N. Senthil Murugan ◽  
Rajendra Prasad Mahapatra ◽  
V. Muthukumaran ◽  
...  
Keyword(s):  
Spatial Information ◽  
Intelligent System ◽  
Gait Recognition ◽  
Research Work ◽  
Recognition System ◽  
Multimodal Fusion ◽  
Content Type ◽  
Surveillance Videos ◽  
Sensor Devices ◽  
Intelligent Recognition

PurposeThe paper aims to introduce an intelligent recognition system for viewpoint variations of gait and speech. It proposes a convolutional neural network-based capsule network (CNN-CapsNet) model and outlining the performance of the system in recognition of gait and speech variations. The proposed intelligent system mainly focuses on relative spatial hierarchies between gait features in the entities of the image due to translational invariances in sub-sampling and speech variations.Design/methodology/approachThis proposed work CNN-CapsNet is mainly used for automatic learning of feature representations based on CNN and used capsule vectors as neurons to encode all the spatial information of an image by adapting equal variances to change in viewpoint. The proposed study will resolve the discrepancies caused by cofactors and gait recognition between opinions based on a model of CNN-CapsNet.FindingsThis research work provides recognition of signal, biometric-based gait recognition and sound/speech analysis. Empirical evaluations are conducted on three aspects of scenarios, namely fixed-view, cross-view and multi-view conditions. The main parameters for recognition of gait are speed, change in clothes, subjects walking with carrying object and intensity of light.Research limitations/implicationsThe proposed CNN-CapsNet has some limitations when considering for detecting the walking targets from surveillance videos considering multimodal fusion approaches using hardware sensor devices. It can also act as a pre-requisite tool to analyze, identify, detect and verify the malware practices.Practical implicationsThis research work includes for detecting the walking targets from surveillance videos considering multimodal fusion approaches using hardware sensor devices. It can also act as a pre-requisite tool to analyze, identify, detect and verify the malware practices.Originality/valueThis proposed research work proves to be performing better for the recognition of gait and speech when compared with other techniques.

Application of WMN-SA Simulation System for Node Placement in Wireless Mesh Networks

2014 ◽  
Vol 6 (2) ◽  
pp. 13-21 ◽  
Author(s):  
Shinji Sakamoto ◽  
Algenti Lala ◽  
Tetsuya Oda ◽  
Vladi Kolici ◽  
Leonard Barolli ◽  
...  
Keyword(s):  
Wireless Mesh Networks ◽  
Mesh Networks ◽  
Network Connectivity ◽  
Simulation System ◽  
Placement Problem ◽  
Node Placement ◽  
Wireless Mesh ◽  
User Coverage ◽  
Router Node Placement ◽  
Cost Efficient

One of the key advantages of Wireless Mesh Networks (WMNs) is their importance for providing cost-efficient broadband connectivity. In WMNs, there are issues for achieving the network connectivity and user coverage, which are related with the node placement problem. In this work, the authors consider the router node placement problem in WMNs. The objective is to find the optimal distribution of router nodes in order to provide the best network connectivity (the maximal number of connected routers) and coverage (maximal number of covered clients). The authors apply their proposed WMN-SA simulation system in a realistic scenario of the distribution of mesh clients considering Itoshima City, Fukuoka Prefecture, Japan. From simulation results, they found many insights that can be very important for real deployment of WMNs.

Sign in / Sign up

Export Citation Format

Share Document