International Journal of Modeling, Simulation, and Scientific Computing

The rapid development of computer vision techniques has brought new opportunities for manufacturing industries, accelerating the intelligence of manufacturing systems in terms of product quality assurance, automatic assembly, and industrial robot control. In the electronics manufacturing industry, intensive variability in component shapes and colors, background brightness, and visual contrast between components and background results in difficulties in printed circuit board image classification. In this paper, we apply computer vision techniques to detect diverse electronic components from their background images, which is a challenging problem in electronics manufacturing industries because there are multiple types of components mounted on the same printed circuit board. Specifically, a 13-layer convolutional neural network (ECON) is proposed to detect electronic components either of a single category or of diverse categories. The proposed network consists of five Convolution-MaxPooling blocks, followed by a flattened layer and two fully connected layers. An electronic component image dataset from a real manufacturing company is applied to compare the performance between ECON, Xception, VGG16, and VGG19. In this dataset, there are 11 categories of components as well as their background images. Results show that ECON has higher accuracy in both single-category and diverse component classification than the other networks.

In large-scale social media, sentiment classification is a significant one for connecting gaps among social media contents as well as real-world actions, including public emotional status monitoring, political election prediction, and so on. On the other hand, textual sentiment classification is well studied by various platforms, like Instagram, Twitter, etc. Sentiment classification has many advantages in various fields, like opinion polls, education, and e-commerce. Sentiment classification is an interesting and progressing research area due to its applications in several areas. The information is collected from various people about social, products, and social events by web in sentiment analysis. This review provides a detailed survey of 50 research papers presenting sentiment classification schemes such as active learning-based approach, aspect learning-based method, and machine learning-based approach. The analysis is presented based on the categorization of sentiment classification schemes, the dataset used, software tools utilized, published year, and the performance metrics. Finally, the issues of existing methods considering conventional sentiment classification strategies are elaborated to obtain improved contribution in devising significant sentiment classification strategies. Moreover, the probable future research directions in attaining efficient sentiment classification are provided.

To study the ride comfort of wheel-hub-driven electric vehicles, a simulation and verification method based on a combination of ADAMS and MATLAB modeling is proposed. First, a multibody dynamic simulation model of an in-wheel motor-driven electric vehicle is established using ADAMS/Car. Then, the pavement excitation and electromagnetic force analytical equations are provided based on the specific operating conditions of the vehicle and the in-wheel motor to analyze the impact of the electromagnetic force fluctuation from an unsprung mass increase and motor air gap unevenness on vehicle ride comfort after the introduction of an in-wheel motor. Next, the vibration model and the motion differential equation of the body–wheel dual-mass system of an in-wheel motor-driven electric vehicle are established. The influence of the in-wheel motor on the vibration response index of the dual-mass system is analyzed by using MATLAB/Simulink software. The variation in the vehicle vibration performance index with/without the motor electromagnetic force excitation factor is analyzed and compared with the ADAMS multibody dynamics analysis results. The results show that the method based on a combination of ADAMS and MATLAB modeling can forecast the ride comfort of an in-wheel motor-driven electric vehicle, reducing the cost of physical prototype experiments.

In this work, an attempt has been made for optimization of process parameters in Wire Electric Discharge Machining (WEDM) of Ti–6Al–4V while producing square and circular profiles. The input parameters, namely pulse on time, pulse off time, peak current and servo voltage, were considered to study the responses cutting speed (CS) and surface roughness (SR). Each input parameter was set at three levels. Experiments were conducted as per central composite face (CCF) centered design. Based upon the experimental data, Gray relational analysis (GRA), a multi-objective optimization technique has been employed to find the best level of process parameters to optimize the machining profiles. Analysis of variance (ANOVA) has been conducted for investigating the effect of process parameters on overall machining performance. Finally, it was identified that the process parameters such as pulse on time, current and voltage have more impact on the square and circular profiles.

This article introduces the computational analytical approach to solve the m-dimensional space-time variable Caputo fractional order advection–dispersion equation with the Dirichlet boundary using the two-step Adomian decomposition method and obtain the exact solution in just one iteration. Moreover, with the help of fixed point theory, we study the existence and uniqueness conditions for the positive solution and prove some new results. Also, obtain the Ulam–Hyers stabilities for the proposed problem. Two generalized examples are considered to show the method’s applicability and compared with other existing numerical methods. The present method performs exceptionally well in terms of efficiency and simplicity. Further, we solved both examples using the two most well-known numerical methods and compared them with the TSADM solution.

The main aim of this paper is to propose a kernel-based method for solving the problem of squeezing Cu–Water nanofluid flow between parallel disks. Our method is based on Gaussian Hilbert–Schmidt SVD (HS-SVD), which gives an alternate basis for the data-dependent subspace of “native” Hilbert space without ever forming kernel matrix. The well-conditioning linear system is one of the critical advantages of using the alternate basis obtained from HS-SVD. Numerical simulations are performed to illustrate the efficiency and applicability of the proposed method in the sense of accuracy. Numerical results obtained by the proposed method are assessed by comparing available results in references. The results demonstrate that the proposed method can be recommended as a good option to study the squeezing nanofluid flow in engineering problems.

The aim of this paper is to consider the convergence of the numerical methods for stochastic time-fractional evolution equations driven by fractional Brownian motion. The spatial and temporal regularity of the mild solution is given. The numerical scheme approximates the problem in space by the Galerkin finite element method and in time by the backward Euler convolution quadrature formula, and the noise by the $L^2$-projection. The strong convergence error estimates for both semi-discrete and fully discrete schemes are established. A numerical example is presented to verify our theoretical analysis.

Dengue infection affects more than half of the world’s population, with 1 billion symptomatic cases identified per year and several distinct genetic serotypes: DENV 1–4. Transmitted via the mosquito bite, the dengue virus infects Langerhans cells. Monocytes, B lymphocytes, and mast cells infected with dengue virus produce various cytokines although it is not clear which ones are predominant during DHF disease. A mathematical model of the Dengue virus infection is developed according to complex dynamics determined by many factors. Starting from a state of equilibrium that we could define as “virus-free” asymptotically stable with a viral reproduction number lower than one which means a very effective action of the innate immune system: it stops the infectious process, the mathematical analysis of stability in the presence of the virus demonstrates that the proposed model is dynamically influenced. Dengue fever affects more than half of the world’s population, with 1 billion symptomatic cases and multiple genetic serotypes confirmed each year, which simulates a network of interactions between the various populations involved without considering the speeds of the processes in question which are indicated in a separate computation. In this research, a hybrid approach of petri nets is utilized to connect the discrete models of dengue.

The aging population is primarily affected by Alzheimer’s disease (AD) that is an incurable neurodegenerative disorder. There is a need for an automated efficient technique to diagnose Alzheimer’s in its early stage. Various techniques are used to diagnose AD. EEG and neuroimaging methodologies are widely used to highlight changes in the electrical activity of the brain signals that are helpful for early diagnosis. Parkinson’s disease (PD) is a major neurological disease that results in an average of 50,000 new clinical diagnoses worldwide every year. The voice features are majorly used as the main means to diagnose PD. The major symptoms of PD are loss of intensity, the monotony of loudness and pitch, reduction in stress, unidentified silences, and dysphonia. Even though various innovative models are proposed by explorers about Alzheimer’s and Parkinson’s classification diseases, still there is a need for efficient learning methodologies and techniques. This paper provides a review on using machine learning (ML) together with several feature extraction techniques that is helpful in the early detection of AD with Parkinson’s. The novelty and objective of this study are that the CAD technique is used to improve the accuracy of early diagnosis of AD. The proposed technique depends on the nonlinear process for data dimension reduction, feature removal, and classification using kernel-based support vector machine (SVM) classifiers. The dimension of the input space is radically diminished with kernel methods. As the learning set is labeled, it creates sense to utilize this information to make a dependable method of dropping the input space dimension. The different techniques of ML are explained under the major approaches viz. SVM, artificial neural network (ANN), deep learning (DL), and ensemble methods. A comprehensive assessment is presented at SVM, ANN, and DL approaches for better detection of Alzheimer’s with PD highlighting future insights.

In this paper, we propose an image denoising algorithm for compressed sensing based on alternating direction method of multipliers (ADMM). We prove that the objective function of the iterates approaches the optimal value. We also prove the $O(1/N)$ convergence rate of our algorithm in the ergodic sense. At the same time, simulation results show that our algorithm is more efficient in image denoising compared with existing methods.

We investigate through this research the numerical inversion technique for the Laplace transforms cooperated by the integration Boubaker polynomials operational matrix. The efficiency of the presented approach is demonstrated by solving some differential equations. Also, this technique is combined with the standard Laplace Homotopy Perturbation Method. The numerical results highlight that there is a very good agreement between the estimated solutions with exact solutions.

In this research collection, we estimate the existence of the unique solution for the boundary value problem of nonlinear fractional $q$-difference equation having the given form

New atypical pneumonia caused by a virus called Coronavirus (COVID-19) appeared in Wuhan, China in December 2019. Unlike previous epidemics due to the severe acute respiratory syndrome (SARS) and the Middle East respiratory syndrome coronavirus (MERS-CoV), COVID-19 has the particularity that it is more contagious than the other previous ones. In this paper, we try to predict the COVID-19 epidemic peak in Japan with the help of real-time data from January 15 to February 29, 2020 with the uses of fractional derivatives, namely, Caputo derivatives, the Caputo–Fabrizio derivatives, and Atangana–Baleanu derivatives in the Caputo sense. The fixed point theory and Picard–Lindel of approach used in this study provide the proof for the existence and uniqueness analysis of the solutions to the noninteger-order models under the investigations. For each fractional model, we propose a numerical scheme as well as prove its stability. Using parameter values estimated from the Japan COVID-19 epidemic real data, we perform numerical simulations to confirm the effectiveness of used approximation methods by numerical simulations for different values of the fractional-order $\gamma$, and to give the predictions of COVID-19 epidemic peaks in Japan in a specific range of time intervals.