The authors have proposed a new automatic classification scheme based on the conjoint use of the multi-layer perceptron (MLP) neural network and an enhancedparticleswarmoptimisation (EPSO) algorithm for its trainin...
详细信息
The authors have proposed a new automatic classification scheme based on the conjoint use of the multi-layer perceptron (MLP) neural network and an enhancedparticleswarmoptimisation (EPSO) algorithm for its training. In this work, six predominant categories of heartbeats from MIT-BIH database are considered, which are: normal, premature ventricular contraction, atrial premature contraction, right bundle branch block, left bundle branch block and paced beats. First, the authors have applied the standard particleswarmoptimisation (PSO) algorithm to select the network structure for each features vector. Then, the relevant electrocardiogram (ECG) features to the studied arrhythmias were chosen, which suited to the optimised training performance of the classifier. The recognition performance of the proposed EPSO-MLP classification system is evaluated considering two different versions of the EPSO algorithm. In the first version (EPSOw), the inertia weight factor of the PSO algorithm is proposed to be a variable with iterations. However, two PSO parameters are taken to be variables in the second version of the improved learning algorithm (EPSOwc). The obtained experimental results prove the enhancement of the convergence ability of the MLP neural network and confirm the superiority of the proposed EPSO-MLP classification scheme on comparison with the other last published classification systems.
A transactive energy framework can provide an integral management scheme that facilitates power delivery with high efficiency and reliability. To close the gap between wholesale and retail markets, this study presents...
详细信息
A transactive energy framework can provide an integral management scheme that facilitates power delivery with high efficiency and reliability. To close the gap between wholesale and retail markets, this study presents a two-stage optimal scheduling model for distributed energy resources in the form of a virtual power plant (VPP) participating in the day-ahead (DA) and real-time (RT) markets. In the first stage, the hourly scheduling strategy of the VPP is optimised, in order to maximise the total profit in the DA market. In the second stage, the outputs of the VPP are optimally adjusted, in order to minimise the imbalance cost in the RT market. The conditional-value-at-risk is used to assess the risk of profit variability due to the presence of uncertainties. Furthermore, formulated two-stage models are solved by the enhanced particle swarm optimisation algorithm and a commercial solver. Case study results show that the proposed approach can identify optimal and accurate scheduling results, and is a useful decision-making tool.
暂无评论