Selecting effective features on prediction of delay in servicing ships arriving to ports using a combination of Clonal Selection and Grey Wolf Optimization algorithms—Case study: Shahid Rajaee port in Bandar Abbas

Predicting the delay in servicing incoming ships to ports is crucial for maritime transportation. In this study, we use support vector regression (SVR) in order to accurately predict this delay for ships arriving to the terminal No. 1 of Shahid Rajaee's port in Bandar Abbas. To achieve this goal, a combination of Clonal Selection and Grey Wolf Optimization algorithms (named as CLOGWO) is used for two purposes: (i) selecting the most important features among the features that affect prediction of this delay and (ii) optimizing SVR parameters for a more accurate prediction. Performance of the proposed method was compared with Genetic Algorithm (GA), Clonal Selection (CS), Grey Wolf Optimization (GWO), and Particle Swarm Optimization (PSO) algorithms on the following metrics: correlation, rate of feature reduction, root mean square error (RMSE), and normalized RMSE (NRMSE). Evaluations on Shahid Rajaee dataset showed that the mean value of these metrics in 10 independent runs of the proposed method were 0.867, 74.45%, 0.080, and 9.02, respectively. These results and evaluations on standard datasets indicate that the proposed method provides competitive results with other evolutionary algorithms.     

Mitigation of the impact of transformer inrush current on voltage sag by TCSC

Thyristor Controlled Series Capacitor (TCSC) as a dynamic system, besides its capability in increasing power transfer in transmission lines, can be used to enhance different power system issues. In this paper, the effect of TCSC on voltage sag following transformer inrush current is investigated. It is shown that excessive transient inrush current occurring during transformer energizing can be mitigated by TCSC. Hence, voltage sag as one of the key components of the power quality is alleviated for the sensitive loads that are connected to the same bus which the power transformer is energized from. During a fault, TCSC can improve the voltage sag by limiting the current and help to keep the voltage as high as possible. Moreover, the inrush currents and the associated voltage sags that usually occur after clearing heavy single- or multistage faults are mitigated by the presence of TCSC. The model used for simulating inrush current is based on the characteristics of the major hysteresis loop out of which the internal trajectories are defined using the translation principal and a linear compensation to generate closed loops. An arctangent relation between the flux and the exciting current is defined. The expression parameters are deduced by curve fitting empirical data defining the major loop or the single-valued saturation characteristic.     

Electrodeposition of nickel oxide nanoparticles on glassy carbon surfaces: application to the direct electron transfer of tyrosinase

This work describes the performance of a tyrosinase/nickel oxide nanoparticles/glassy carbon (Tyr/NiO NPs/GC) electrode. This electrode was prepared by first applying a NiO NPs electrochemical deposition onto the GC electrode surface and then tyrosinase immobilization was applied to the surface of electrodeposited NiO NPs. Scanning electron microscopy (SEM) and atomic force microscopy (AFM) procedures demonstrated the existence of different NiO NP geometrical structures. These geometrical structures could lead to better immobilization of proteins on their surfaces. The copper containing enzyme tyrosinase successfully achieved electrical contact with the electrode because of the unique structural alignment of tyrosinase enzyme on the nanometer-scale nickel oxide surfaces. This method could be suitable for application to nanofabricated devices facilitating better performance. It was concluded that tyrosinase can be effectively applied to nanometer-scale nickel oxide surfaces.     

Risk-constrained self-scheduling of a fuel and emission constrained power producer using rolling window procedure

This work addresses a relevant methodology for self-scheduling of a price-taker fuel and emission constrained power producer in day-ahead correlated energy, spinning reserve and fuel markets to achieve a trade-off between the expected profit and the risk versus different risk levels based on Markowitz’s seminal work in the area of portfolio selection. Here, a set of uncertainties including price forecasting errors and available fuel uncertainty are considered. The latter uncertainty arises because of uncertainties in being called for reserve deployment in the spinning reserve market and availability of power plant. To tackle the price forecasting errors, variances of energy, spinning reserve and fuel prices along with their covariances which are due to markets correlation are taken into account using relevant historical data. In order to tackle available fuel uncertainty, a framework for self-scheduling referred to as rolling window is proposed. This risk-constrained self-scheduling framework is therefore formulated and solved as a mixed-integer non-linear programming problem. Furthermore, numerical results for a case study are discussed.     

Learning gender with support faces

Nonlinear support vector machines (SVMs) are investigated for appearance-based gender classification with low-resolution "thumbnail" faces processed from 1,755 images from the FERET (FacE REcognition Technology) face database. The performance of SVMs (3.4% error) is shown to be superior to traditional pattern classifiers (linear, quadratic, Fisher linear discriminant, nearest-neighbor) as well as more modern techniques, such as radial basis function (RBF) classifiers and large ensemble-RBF networks. Furthermore, the difference in classification performance with low-resolution "thumbnails" (21×12 pixels) and the corresponding higher-resolution images (84×48 pixels) was found to be only 1%, thus demonstrating robustness and stability with respect to scale and the degree of facial detail