Flow measurement in porous media is a challenging subject, especially when it comes to performing a three-dimensional (3D) velocimetry at the micro scale. Volumetric flow measurement techniques such as defocusing and tomographic imaging generally involve rigorous procedures, complex experimental setups, and multi-part data processing procedures. However, detailed knowledge of the flow pattern at the pore and subpore scales is important in interpreting the phenomena that occur inside the porous media and understanding the macro-scale behaviors. In this work, the flow of an oil inside a porous medium is measured at the pore and subpore scales using refractive index matching (RIM) and shadowgraph imaging techniques. At the macro scale, flow is measured using the particle image velocimetry (PIV) method in two dimensions (2D) to confirm the volumetric nature of the flow and obtain the overall flow pattern in the vicinity of the flow entrance and at the far field. At the micro scale, the three-dimensional (3D) flow within an arbitrary volume of the porous medium was quantified using 2D particle-tracking velocimetry (PTV) utilizing the law of conservation of mass. Using the shadowgraphy method and a single camera makes the flow measurement much less complex than the approaches using laser light sheets or multiple cameras with multiple viewing angles.

The three-dimensional (3D) flow below the interface of an evaporating liquid at a low pressure is visualized and quantified using scanning particle image velocimetry. The technique presented highlights the use of a single camera and a relatively fast moving laser sheet to image the flow for an application where using more than one camera is difficult. The technique allows collection of the full three-dimensional velocity vector map over the whole liquid volume. The out-of-plane component of the velocity has been determined using two different processing approaches: (i) deriving the full vector from a 3D cross-correlation of the particle volumes and (ii) applying the continuity equation to determine out-of-plane velocities from the calculated in-plane velocity vector fields. The results obtained from both methods showed good agreement with each other. The 3D velocity field reveals the existence of a torus shaped vortex below the evaporating meniscus that was induced by the exposure of the cold liquid to the warmer solid walls. The velocity data also shows that the maximum velocity occurs below the interface, not at the interface which highlights that the observed vortex is not driven by thermocapillary forces that usually govern the flow during evaporation at smaller scales.

Undoubtedly, social media are brainstormed by a tremendous volume of stories, feedback, reviews, and reactions expressed in various languages and idioms, even though some are factually incorrect. These motifs make assessing such data challenging, time-consuming, and vulnerable to misinterpretation. This paper describes a classification model for movie reviews founded on deep learning approaches. Almost 500KB pairs of balanced data from the IMDb movie review databases are employed to train the model. People's perspectives regarding movies were classified using both the long short-term memory (LSTM) and convolutional neural network (CNN) strategies. According to the findings, the CNN algorithm's prediction accuracy rate would be almost 97.4%. Furthermore, the model trained by LSTM resulted in accuracies of around and applying 99.2% within the Keras library. The model is investigated more by modification of model parameters. According to the outcomes, LTSM outperforms CNN in assessing IMDb movie reviews and is computationally less costly than LSTM.

This paper presents the application of an adaptive neuro-fuzzy inference system (ANFIS) to predict the generated electrical power in a combined cycle power plant. The ANFIS architecture is implemented in MATLAB through a code that utilizes a hybrid algorithm that combines gradient descent and the least square estimator to train the network. The Model is verified by applying it to approximate a nonlinear equation with three variables, the time series Mackey-Glass equation and the ANFIS toolbox in MATLAB. Once its validity is confirmed, ANFIS is implemented to forecast the generated electrical power by the power plant. The ANFIS has three inputs: temperature, pressure, and relative humidity. Each input is fuzzified by three Gaussian membership functions. The first-order Sugeno type defuzzification approach is utilized to evaluate a crisp output. Proposed ANFIS is cable of successfully predicting power generation with extremely high accuracy and being much faster than Toolbox, which makes it a promising tool for energy generation applications.