Sentiment Analysis of Persian Movie Reviews Using Deep Learning

Sentiment analysis aims to automatically classify the subject’s sentiment (e.g., positive, negative, or neutral) towards a particular aspect such as a topic, product, movie, news, etc. Deep learning has recently emerged as a powerful machine learning technique to tackle the growing demand for accurate sentiment analysis. However, the majority of research efforts are devoted to English-language only, while information of great importance is also available in other languages. This paper presents a novel, context-aware, deep-learning-driven, Persian sentiment analysis approach. Specifically, the proposed deep-learning-driven automated feature-engineering approach classifies Persian movie reviews as having positive or negative sentiments. Two deep learning algorithms, convolutional neural networks (CNN) and long-short-term memory (LSTM), are applied and compared with our previously proposed manual-feature-engineering-driven, SVM-based approach. Simulation results demonstrate that LSTM obtained a better performance as compared to multilayer perceptron (MLP), autoencoder, support vector machine (SVM), logistic regression and CNN algorithms.     

Spectral Analysis of Large Scale Structures in Fully Developed Turbulent Pipe Flow

The present work focuses on spectral analysis of the streamwise velocity fluctuations obtained, utilizing the Cottbus Large Pipe (CoLaPipe) test facility for R⁺ ≤ 3500, where R⁺ is the Reynolds number based on the wall friction velocity, u_τ, and the pipe radius, R. Measurements of the streamwise spectra have been conducted using a single hot-wire probe. Few runs have been also performed using Particle Image Velocimetry (PIV) as a structure visualization evidence and for spatial correlation purposes. The spectral analysis is being carried out to reveal few insights into pipe flow structure, allowing to follow the foot prints of such structures as well as providing estimates of their energy contents. The cumulative energy is examined as a function of the streamwise wavelength, describing the most energetic motions found in spectral data at various wall normal locations. For the current Reynolds number range, the Very Large Scale Motions (VLSM) and the Large Scale Motions (LSM) were evident as localized peaks in pre-multiplied spectra, having mean wavelengths approximately of 12R, and 3R, respectively. (© 2017 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim)     

Erratum to: Chemical and electrochemical grafting of polythiophene onto poly(vinyl chloride): synthesis,characterization, and materials properties

Journal of Solid State Electrochemistry -     

Spontaneous Switching between Permeability Enhancement and Degradation in Fractures in Carbonate: Lumped Parameter Representation of Mechanically- and Chemically-Mediated Dissolution

Principal mechanical and chemical processes contributing to the observed spontaneous switching from net decrease in permeability to net increase in a fracture in carbonate are examined. The evolution of permeability, and related fracture aperture, is represented through a lumped parameter model. The significant processes of pressure solution beneath bridging asperities, transport of dissolved mass to the fracture void, and subsequent precipitation or dissolution within the fracture void enable the principal characteristics of observed behavior to be followed. The evolution of dissolved mass concentration in the pore fluid is followed for arbitrary applied stress, temperature, and pH conditions, with appropriate feedback to the evolution of fracture permeability. Comparisons with experimental measurements in limestone (Polak et al., 2004, Water Resour. Res. Vol. 40, W03502, doi: 10.1029/2003GL017575) show satisfactory agreement for the evolution of fracture aperture and to a lesser degree in calcium concentrations in the effluent pore fluid. Importantly, the spontaneous switching in permeability change, from aperture reducing to aperture increasing, with no change in environmental conditions, is replicated without the need for an ad hoc trigger. Although this switch is accurately replicated, the lumped parameter model is incapable of replicating the rapid observed growth in permeability that directly follows. This inability results from the assumed form of the lumped asperity model, that is incapable of representing the spatially distributed change in aperture that is seen to occur within the fracture. Despite this inconsistency, the model is shown capable of representing the principal behaviors evident in the response.     

Thermodynamics assessment on cooling photovoltaic modules by phase change materials (PCMs) in critical operating temperature

Journal of Thermal Analysis and Calorimetry - Increasing the temperature of photovoltaic (PV) cells decreases their electricity generation. The use of phase change materials (PCMs) is one of the...     

Experimental study on convective heat transfer and entropy generation of carbon black nanofluid turbulent flow in a helical coiled heat exchanger

Journal of Thermal Analysis and Calorimetry - The convective heat transfer coefficient (CHTC) of a fluid is one of the most effective factors on the performance of a fluid in heat transfer...     

Transient thermal stress analysis for a short thick hollow FGM cylinder with nonlinear temperature-dependent material properties

Journal of Thermal Analysis and Calorimetry - In this study, nonlinear transient thermo-elastic analysis for a thick hollow 1D-FGM (functionally graded material) axisymmetric cylinder with finite...     

High-temperature creep resistant ternary blends based on polyethylene and polypropylene for thermoplastic power cable insulation

The impact of a small amount of polystyrene-b-poly(ethylene-co-butylene)-b-polystyrene (SEBS) on the thermomechanical and electrical properties of blends comprising low-density polyethylene (LDPE) and isotactic polypropylene (PP) is investigated. SEBS is found to assemble at the PP:LDPE interface as well as within isolated PP domains. The addition of 10 wt% SEBS significantly increases the storage modulus between the melting temperatures of the two polyolefins, 110 and 160°C, and results in improved resistance to creep during both tensile deformation as well as compression. Furthermore, the ternary blends display a very low direct-current (DC) conductivity as low as 3.4 × 10⁻¹⁵ S m⁻¹ at 70°C and 30 kV mm⁻¹, which is considerably lower than values measured for neat LDPE. The here presented type of ternary blend shows potential as an insulation material for high-voltage direct current power cables.     

二氧化硅包覆NiFe_2O_4担载Preyssler杂多酸用于合成双(二氢嘧啶酮)苯和3,4-二氢嘧啶-2(1H)-酮（英文）

A novel magnetic acidic catalyst comprising Preyssler(H14[Na P5W30O110]) heteropoly acid support‐ed on silica coated nickel ferrite nanoparticles (Ni Fe2O4@Si O2) was prepared.The catalyst was characterized by Fourier transform infrared,scanning electron microscopy,transmission electron microscopy,X‐ray diffraction,energy dispersive spectrum,VSM and particle size neasurement.Its catalytic activity was investigated for the synthesis of bis(dihydropyrimidinone)benzene and 3,4‐dihydropyrimidin‐2(1H)‐ones derivatives by the Biginelli reaction.With the catalyst,the reac‐tions occurred in less than 1 h with good to excellent yields.More importantly,the catalyst was easily separated from the reaction mixture by an external magnet and reused at least five times without degradation in the activity.     

Supramolecular Translation of Enzymatically Triggered Disassembly of Micelles into Tunable Fluorescent Responses

The need for advanced fluorescent imaging and delivery platforms has motivated the development of smart probes that change their fluorescence in response to external stimuli. Here a new molecular design of fluorescently labeled PEG–dendron hybrids that self‐assemble into enzyme‐responsive micelles with tunable fluorescent responses is reported. In the assembled state, the fluorescence of the dyes is quenched or shifted due to intermolecular interactions. Upon enzymatic cleavage of the hydrophobic end‐groups, the labeled polymeric hybrids become hydrophilic, and the micelles disassemble. This supramolecular change is translated into a spectral response as the dye–dye interactions are eliminated and the intrinsic fluorescence is regained. We demonstrate the utilization of this molecular design to generate both Turn‐On and spectral shift responses by adjusting the type of the labeling dye. This approach enables transformation of non‐responsive labeling dyes into smart fluorescent probes.