Research of service selection algorithm for net-centric simulation task community

Being a new-generation C4ISR system simulation method,the construction approach of net-centric simulation(NCS)is developing toward net-centric from the traditional approach of platform-centric.NCS is mainly completed by the construction of the simulation task community(STC),the key to which being the dynamic integration of the various services spread in the network in order to form a new STC that meets the requirements of different users.In this study,a simulation task community service selection algorithm(STCSSA)is proposed.The main idea of this algorithm is to transform the construction of STC to the searching of optimal multi-objectives services with QoS global constraints.This paper first introduces the QoS model of STC and evaluates the service composition process,then presents the detailed operating process of STCSSA and design of the dynamic inertia weight strategy of the algorithm,and also proposes an optional variation method.Comparative tests were performed on STCSSA with other particle swarm optimization algorithms.It was validated from the perspective of performance that the proposed algorithm has advantages in improving the rate of convergence and avoiding local optimum,and from the perspective of practical application STCSSA also demonstrated feasibility in the construction of large-scale NCS task community.

Resource allocation optimization of equipment development task based on MOPSO algorithm

Resource allocation for an equipment development task is a complex process owing to the inherent characteristics,such as large amounts of input resources,numerous sub-tasks,complex network structures,and high degrees of uncertainty.This paper presents an investigation into the influence of resource allocation on the duration and cost of sub-tasks.Mathematical models are constructed for the relationships of the resource allocation quantity with the duration and cost of the sub-tasks.By considering the uncertainties,such as fluctuations in the sub-task duration and cost,rework iterations,and random overlaps,the tasks are simulated for various resource allocation schemes.The shortest duration and the minimum cost of the development task are first formulated as the objective function.Based on a multi-objective particle swarm optimization(MOPSO)algorithm,a multi-objective evolutionary algorithm is constructed to optimize the resource allocation scheme for the development task.Finally,an uninhabited aerial vehicle(UAV)is considered as an example of a development task to test the algorithm,and the optimization results of this method are compared with those based on non-dominated sorting genetic algorithm-II(NSGA-II),non-dominated sorting differential evolution(NSDE)and strength pareto evolutionary algorithm-II(SPEA-II).The proposed method is verified for its scientific approach and effectiveness.The case study shows that the optimization of the resource allocation can greatly aid in shortening the duration of the development task and reducing its cost effectively.

Prediction of Point in Time with High Crash Risk by Integration of Bayesian Estimation of Drowsiness, Tracking Error, and Subjective Drowsiness

The aim of this study was to predict drivers＇ drowsy states with high risk of encountering a crash and prevent drivers from continuing to drive under such drowsy states with high risk of crash. While the participants were required to carry out a simulated driving task, EEG （Electro encephalography） （EEG-MPF and EEG-α/β）, ECG （Electrocradiogram） （RRV3）, t racking error, an d subjective rating on drowsiness were measured. On the basis of such measurements, an attempt was made to predict the point in time with high crash risk using Bayesian estimation of posterior probability of drowsiness, tracking error, and subjective drowsiness. As a result of applying the proposed method to the data of each participant, it was verified that the proposed method could predict the point in time with high crash risk before the point in time of crash.