Day-ahead price forecasting of electricity markets by a new feature selection algorithm and cascaded neural network technique

With the introduction of restructuring into the electric power industry, the price of electricity has become the focus of all activities in the power market. Electricity price forecast is key information for electricity market managers and participants. However, electricity price is a complex signal due to its non-linear, non-stationary, and time variant behavior. In spite of performed research in this area, more accurate and robust price forecast methods are still required. In this paper, a new forecast strategy is proposed for day-ahead price forecasting of electricity markets. Our forecast strategy is composed of a new two stage feature selection technique and cascaded neural networks. The proposed feature selection technique comprises modified Relief algorithm for the first stage and correlation analysis for the second stage. The modified Relief algorithm selects candidate inputs with maximum relevancy with the target variable. Then among the selected candidates, the correlation analysis eliminates redundant inputs. Selected features by the two stage feature selection technique are used for the forecast engine, which is composed of 24 consecutive forecasters. Each of these 24 forecasters is a neural network allocated to predict the price of 1 h of the next day. The whole proposed forecast strategy is examined on the Spanish and Australia’s National Electricity Markets Management Company (NEMMCO) and compared with some of the most recent price forecast methods.     

Modeling the micro-scale static friction coefficient of the MEMS silicon surfaces affected by Ag and Au deposition using the thermal evaporation method

In different macro-scale applications, regarding what should be done, many of the prepared surfaces are immediately used after machining with no limitation. Since the micro-electromechanical applications have different conditions, their different properties, such as friction and adherence, must be checked. In the present study, using the thermal evaporation method, the silver and gold layers with different thicknesses were deposited on the silicon surfaces widely used in micromechanical systems (e.g. micro-assembly). Thereafter, the effects of the deposition on the geometrical properties of the surfaces were studied. Also, the effects of the deposition on the adherence and friction properties of the surfaces were examined by modeling the geometrical condition. To this end, the height function distribution was used to exploit the surface friction model in conjunction with the DMT surface adhesion model. The results show the extent to which gold affects the adhesion and friction properties of the coated surfaces.     

Machine learning applications for COVID-19 outbreak management

Neural Computing and Applications - Recently, the COVID-19 epidemic has resulted in millions of deaths and has impacted practically every area of human life. Several machine learning (ML)...     

Exploiting the Cellular Redox-Control System for Activatable Photodynamic Therapy

Photodynamic therapy (PDT) has been successfully used to treat a variety of cancers. However, one drawback has been the adverse side effects experienced by patients during therapy, as a result of the destruction of normal tissues upon irradiation. Herein, we describe the design, synthesis and characterisation of a photosensitiser to overcome this issue that, in addition to light, is also dependent on the overactive redox system present in cancer cells for its activation. Our probe consists of the photosensitiser, protoporphyrin IX, and a FRET-based quencher dye, BHQ-3, on a scaffold containing a disulfide bond. The close proximity of BHQ-3 to protoporphyrin IX quenches its ability to fluoresce and produce reactive oxygen species, whereas nonenzymatic or enzymatic reduction can recover its native properties. We further demonstrate its ability to be activated in cancer cells in a thiol-dependent manner and destroy breast and lung cancer cells upon red-light irradiation.     

Assembly of gelatin biopolymer to fibrous sepiolite clay for efficient dye removal from wastewater

This work aimed to fabricate nanocomposites using low-cost and natural materials for fast and efficient dye adsorption from wastewater. To achieve this, fibrous sepiolite clay was incorporated into the gelatin (GE) biopolymer. The obtained nanocomposites were characterized by Fourier transform infrared spectroscopy and scanning electron microscope techniques. The effects of sepiolite/GE ratio, adsorbent dosage, solution pH, contact time, and initial dye concentration on the adsorption capacity of nanocomposites were well studied and optimized through batch adsorption study. Kinetics, isotherms, and thermodynamics analysis were also performed for methylene blue adsorption. The adsorption data were better fitted with the pseudo-second-order and Langmuir isotherm models. The prepared nanocomposites demonstrated a fast and efficient adsorption performance toward the MB dye with the maximum adsorption capacity as high as 684.8 mg g⁻¹ within only an equilibrium time of 30 min, which revealed their promising potential in wastewater treatment. © 2019 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2019 , 136, 48266.     

Evaluating orthotropic continuum analysis of stress wave propagation through a jointed rock mass

Bulletin of Engineering Geology and the Environment - Continuum modeling and discontinuum modeling are two approaches that are used to study the problem of stress wave propagation in jointed rock...     

A new three-level fault tolerance arithmetic and logic unit based on quantum dot cellular automata

Microsystem Technologies - Quantum-dot cellular automata (QCA) as a technology in the nanoscale is used for designing the future circuits. It has high density, speed, and low power dissipation....