A new feature selection algorithm and composite neural network for electricity price forecasting

In a competitive electricity market, the forecasting of energy prices is an important activity for all the market participants either for developing bidding strategies or for making investment decisions. In this paper, a new forecast strategy is proposed for day ahead prediction of electricity price, which is a complex signal with nonlinear, volatile and time dependent behavior. Our forecast strategy includes a new two stage feature selection algorithm, a composite neural network (CNN) and a few auxiliary predictors. The feature selection algorithm has two filtering stages to remove irrelevant and redundant candidate inputs, respectively. This algorithm is based on mutual information (MI) criterion and selects the input variables of the CNN among a large set of candidate inputs. The CNN is composed of a few neural networks (NN) with a new data flow among its building blocks. The CNN is the forecast engine of the proposed strategy. A kind of cross-validation technique is also presented to fine-tune the adjustable parameters of the feature selection algorithm and CNN. Moreover, the proposed price forecast strategy is equipped with a few auxiliary predictors to enrich the candidate set of inputs of the forecast engine. The whole proposed strategy is examined on the PJM, Spanish and Californian electricity markets and compared with some of the most recent price forecast methods.     

Synthesis of highly isotactic poly 1-hexene using Fe-doped Mg(OEt)2/TiCl4/ED Ziegler–Natta catalytic system

In this article, polymerization of 1-hexene with FeCl_3-doped Mg(OET)₂/TiCl₄/electron donor (ED) catalytic system is presented. For this purpose, first a number of TiCl₄ catalysts supported on Mg(OEt)₂ and Fe-doped Mg(OEt)₂ supports were prepared with ethylbenzoate or dibutylphthalate as the internal EDs. After successive catalysts synthesis, they were employed in 1-hexene polymerization using cyclohexyl methyl dimethoxysilane as external ED as well as without it. The catalysts activity and molecular weight distribution (MWD) of poly 1-hexenes (PHs) were influenced strongly by both FeCl₃ doping and donor presence so that a remarkable increase in the catalyst activity was seen in doped catalysts. Deconvolution of MWD curves revealed that increase in the type of active centers by introducing FeCl₃ into the support should be responsible for the broadening of MWD of PHs. ¹³CNMR analysis indicated that while isotacticity does not change considerably by Fe doping, EDs increase its amount as high as 8–21%. Second, the stereoselective behavior of active Ti species in doped and undoped catalysts was fully explored by molecular modeling using density functional theory (DFT) method. Finally, with the aid of rheological measurements, the processability of polymers were evaluated and then the gel permeation chromatography (GPC) results were approved through the values obtained from model fitting as well as changes in moduli crossover modulus.     

Influence of TiN dopant on microstructure of TiB2 ceramic sintered by spark plasma

In this study, the impact of TiN as a sintering aid on the relative density and microstructure of TiB₂ ceramic was investigated. Monolithic TiB₂ and TiB₂ doped with 5?wt% TiN were sintered at 1900?°C for 7?min dwell time under the pressure of 40?MPa by spark plasma. The addition of TiN affected the microstructure of TiB₂-based sample considerably depicting the finer grains in the as-sintered ceramic. X-ray diffraction evaluation indicated that no interaction occurred between the initial materials. However, detail investigation by the map analysis and energy dispersive spectroscopy results revealed the formation of in-situ nano-sized hBN secondary phase in the TiN-doped TiB₂. In addition, TiN played a remarkable role on increasing the relative density of TiN-doped TiB₂ ceramic producing a nearly fully dense ceramic with relative density of 99.9% in comparison with the monolithic ceramic having 96.7% relative density.     

Parkinson’s Disease Detection Using Biogeography-Based Optimization

In recent years, Parkinson's Disease (PD) as a progressive syndrome of the nervous system has become highly prevalent worldwide. In this study, a novel hybrid technique established by integrating a Multi-layer Perceptron Neural Network (MLP) with the Biogeography-based Optimization (BBO) to classify PD based on a series of biomedical voice measurements. BBO is employed to determine the optimal MLP parameters and boost prediction accuracy. The inputs comprised of 22 biomedical voice measurements. The proposed approach detects two PD statuses: 0-disease status and 1- good control status. The performance of proposed methods compared with PSO, GA, ACO and ES method. The outcomes affirm that the MLP-BBO model exhibits higher precision and suitability for PD detection. The proposed diagnosis system as a type of speech algorithm detects early Parkinson’s symptoms, and consequently, it served as a promising new robust tool with excellent PD diagnosis performance.     

Spark plasma sintering of Al-doped ZrB2–SiC composite

This research presents the influence of Al addition on microstructure and mechanical behavior of ZrB₂–SiC ultra-high temperature ceramic matrix composite (UHTCMC) fabricated by spark plasma sintering (SPS). A 2.5?wt% Al-doped ZrB₂–20?vol% SiC UHTCMC was produced by SPS method at 1900?°C under a pressure of 40?MPa for 7?min. The microstructural and phase analysis of the composite showed that aluminum-containing compounds were formed in-situ during the SPS as a result of chemical reactions between Al and surface oxide films of the raw materials (i.e. ZrO₂ and SiO₂ on the surfaces of ZrB₂ and SiC particles, respectively). The Al dopant was completely consumed and converted to the intermetallic Al₃Zr and Al₄Si compounds as well as Al₂O₃ and Al₂SiO₅. A relative density of 99.8%, a hardness (HV5) of 21.5?GPa and a fracture toughness (indentation method) of 6.3?MPa?m^1/2 were estimated for the Al-doped ZrB₂–SiC composite. Crack bridging, branching, and deflection were identified as the main toughening mechanisms.     

Quantitative characterization of carrier injection across metal–organic interfaces using Bardeen theory

We have investigated the contact between a metal and an organic/polymeric (o/p) material and we have introduced a relation for carrier injection using Bardeen theory. A series of narrow barriers is considered in the semiconductor side to account for the localized nature of the carriers in the o/p material. As an application of the model, we have calculated the hopping rate of carriers in terms of the contact parameters. Also, we have discussed the hopping of carriers deep into the organic dielectric. Finally, we have explored the hopping rate in practical contacts between polyfluorene-based polymers and different electrodes.     

Novel NGR anchored pullulan micelles for controlled and targeted delivery of doxorubicin to HeLa cancerous cells

Doxorubicin (DOX) is used to treat different kinds of cancers, including cervix carcinoma. However, it has various side effects such as cardiotoxicity. Nano-sized controlled releasing carriers such as polymeric micelles are of interesting approaches to overcome these side effects of doxorubicin in cancer chemotherapy. Regarding the up-regulation of CD13/APN receptors on the cervix carcinoma cells, which can bind to peptide sequences specially NGR (asparagine–glycine–arginine) with high affinity, peptide sequence (NGR) targeted micelles would lead to effective treatment of this carcinoma. In this study, the NGR peptide sequence was synthesized using the solution-phase strategy from asparagine, glycine, and arginine residues. The pullulan–retinoic acid conjugate and pullulan–retinoic acid–NGR conjugate were prepared by the amide and ester bond formation between the hydroxyl groups of pullulan and carboxylic acid groups of retinoic acid and peptide sequence. Pullulan–retinoic acid–NGR micelles were prepared by the direct dissolution method. The optimized micelles, according to their particle size (124.5 nm), zeta potential (? 3.65 mV), entrapment efficiency (85%), and release of DOX (70%, within 72 h) were assessed for their cytotoxicity on HeLa cells using MTT assay. NGR-targeted pullulan/retinoic acid micelles had higher cytotoxicity than the free DOX in cell culture studies on the HeLa cell line, and this can be a promising result in the treatment of cervix carcinoma.     

Thermosensitive folic acid-targeted poly (ethylene-<Emphasis Type="Italic">co</Emphasis>-vinyl alcohol) hemisuccinate polymeric nanoparticles for delivery of epirubicin to breast cancer cells

A novel thermosensitive folic acid (FA)-targeted succinylated poly (ethylene-co-vinyl alcohol) (EVOH) (EVOHS-FA) nanocarrier was synthesized for the specific delivery of epirubicin (EPI) to MCF-7 breast cancer cell line. Three different ratios of synthesized EVOH-Suc were reacted with FA. The structure of the desired products (EVOHS₄₀-FA, EVOHS₆₀-FA and EVOHS₈₀-FA) was confirmed by ¹H NMR and FTIR techniques. Nanoparticles were obtained by nano-precipitation procedure using DMSO/H₂O as solvent/anti-solvent. The particle size, zeta potential, entrapment efficacy and in vitro release profile of the final formulations in different temperatures were measured. The optimized nanoparticles had the particle size of 214 ± 8.5 nm, zeta potential of ?29.6 mV, PDI of 0.198 ± 0.04, and a high encapsulation efficiency that released the drug efficiently within 450 h at the temperature of 40 °C compared to 37 °C. The morphology of nanoparticles was studied by scanning electron microscopy. The in vitro cytotoxicity was evaluated using the MTT assay on MCF-7 cell lines in response to temperatures of 37 and 40 °C. The MTT assay indicated that the targeted nanoparticles carrying EPI were significantly more cytotoxic than the non-targeted nanoparticles and the free drug at 40 °C.