International Journal of Modeling, Simulation, and Scientific Computing

Today, artificial intelligence (AI) can use the most powerful edge computing systems in the Internet of Things (IoT) for finding the information extracted from vast sensory data such as cyber effects or models in physical environments for classification, identification, and prediction. Heterogeneous IoT devices produce isolated and dispersed information parts, and knowledge sharing and exchange in IoT intelligent applications with several selfish nodes are necessary for complex tasks. In both academia and business, IoT is driving a digital revolution. However, protection and IoT privacy problems are challenged. It offers comfort for everyday lives. Blockchain, a shared cryptographic database, is a promising IoT encryption solution for several manufacturing, finance, and trade sectors. The IoT-based blockchain architecture is an interesting contrast to the conventional, centralized paradigm that struggles to fulfill specific IoT requirements. New concepts for applying data and resources management protection procedures in distributed networks and cloud computing are introduced. Cloud management services can be linked to the application through blockchain technology and distributed leader, a stable cognitive information system that facilitates management operations and securing data. This document provides many ideas for applying personal and behavioral characteristics to security and cryptography protocols, blockchain based on the cognitive cloud computing (BC-CCC) pattern. The simulation result shows that the proposed strategy can significantly enhance data transmission rate (96.2%), security ratio (94.5%), throughput ratio (92.4%), scalability ratio (91.5%), trust rate (93.8%), data trading ratio (96.2%), and reduce storage cost rate (25.1%) compared to other existing methods.

In recent days, health problems are becoming more prevalent because of changes in lifestyles and inherited factors. Heart disease (HD), in particular, has become increasingly widespread in recent years, putting people’s lives in jeopardy. Blood pressure, cholesterol, and pulse rate are all varied for each person. Normal blood pressure should be 120/90, cholesterol should be 100–129mg/dL, pulse rate should be 72, fasting blood sugar level should be 100mg/dL, heart rate should be 60–100bpm, and ECG should be normal, according to medically established data. The aorta is 25mm (1 inch) wide, whereas capillaries are only 8$\mu$m wide, which signifies HD. This paper is based on a public health dataset that also contains a cardiac dataset. In our previous work, a new conventional neural network (CNN) architecture was used to extract and categorize histopathological images using the $K$-means consensus clustering. We achieved good results with the cardiac dataset compared to the existing results. The outcome of the proposed work achieves a precision rate of 97%. In this paper, a novel conventional neural network (CNN) architecture was utilized to identify and characterize histopathology pictures with the help of using the consensus $K$-nearest neighbor algorithm (CKNN). The usage of a deep neural network, as well as the selection and recovery of functionality, is an essential step until the dataset is classified. As a result, the training process has pre-formed the dataset. The system evaluates the person’s symptoms as input and provides the disease’s possibility as an output. The suggested approach is linked to temporal data modeling and makes use of a prior HD CNN prediction. In comparison to previous outcomes, we had good outcomes with the current cardiac dataset. The proposed model’s conclusion has brought out accuracy of 99.1%.

Placement of thyristor-controlled series compensator (TCSC) devices at appropriate lines reduces the net transmission loss (NTL) through injecting suitable series voltage in the transmission lines. The classical approaches for placing TCSCs in the power network may not provide optimal solution and face intricacies in solving the problem with multifarious constraints and vehemently place all the allotted TCSCs in the network. This paper presents a method employing improved harmony search optimization (MHSO), an evolutionary algorithm, for solving TCSC problem (TCSCP) and places the vital number of SVCs from the allotted ones. This paper presents the solution of TCSCP problem of 14, 30 and 57 bus systems and compares the performances in various aspects with existing TCSCP methods.

In this paper, two different approaches for tumor growth modeling are presented and implemented. In the first part of the paper, a macroscopic approach using a PDE model, where the tumor is viewed as a cell mass, is implemented using the level-set method to track the tumor moving boundary in one hand by using Darcy’s law to compute the normal velocity of the free boundary and on the other hand using the shape optimization to draw the normal velocity. In the second part of the paper, a microscopic approach, which focuses on the cellular scale, is presented. A hybrid model using agent-based modeling for the cell behavior and a PDE for the description of the tumor environment is presented. A sensitivity analysis is performed on the hybrid model for a better understanding of its impact on the tumor growth. Numerical experiments are provided for the proposed approaches.

In this research, we are interested in discussing the evolution of the COVID-19 infection cases and predicting the spread of COVID-19 disease in Algeria and India. To this aim, we will approximate the transmission rate in terms of the measures taken by the governments. The least square method is used with an accuracy of 95% for fitting the artificial solution with the real data declared by WHO for the purpose of approximating the density of asymptomatic individuals for COVID-19 disease. As a result, we obtained the different values of the basic reproduction number (BRN) corresponding to each measure taken by the governments. Moreover, we estimate the number of asymptomatic infected persons at the epidemic peak for each country. Further, we will determine the needed ICU beds (intense medical carte beds) and regular treatment beds. Also, we provide the outcome of governmental strategies in reducing the spread of disease. Combining all these components, we offer some suggestions about the necessity of using the recently discovered vaccines as Pfizer/Bioentec and Moderna for limiting the spread of the COVID-19 disease in the studied countries.

The coupled tank system is the most widely used sub-component in chemical process industries. Fluid mixing is a major step in chemical processes that alters the material properties and cost. Fluid flow and its level regulation between several tanks are important control problems. As the first step, this paper addresses the level regulation problem using classical integer order proportional, derivative, integral (PID), fractional order PID controllers. As a second step, model-based robust fractional order controllers are derived using sliding mode approach in order to achieve the desired response, parameters of the proposed controllers are tuned using genetic algorithm. Finally, system performance under all variants of control schemes has been tested using numerical simulations.

Catastrophic forgetting is a well-known characteristic of diverse parameterized supervised learning models. Artificial Neural Networks (ANN) face severe catastrophic forgetting or catastrophic interference in the sequential learning of information that is intolerable to both engineering applications and the human memory model. This problem can be solved through the machine learning community. The main intent of this paper is to implement a novel continuous learning model that could overcome the problem of catastrophic forgetting. The stream data from diverse benchmark sources are used for experimenting. The proposed model adopts the Deep Neural Network (DNN) with testing weight updates. When new data are given, the hybrid meta-heuristic algorithm helps to update the weight that manages to prevent the learning from catastrophic forgetting. The weight update strategy for solving the catastrophic forgetting is done by the hybridization of Shark Smell Optimization (SSO) and Jaya Algorithm (JA) that is named as Hybrid Shark Smell with Jaya Optimization (HSS-JO). A multi-objective function concerning the parameters associated with catastrophic forgetting like accuracy and remembering is used for framing the proposed continuous learning. The proof of the proposed model over conventional models on three publicly available datasets is given for final validation. From the analysis, in Table 3, the accuracy of the proposed HSS-JO-DNN is 38%, 0.5%, 0.55%, 0.14%, 0.98%, and 0.5% superior to DT, NB, KNN, SVM, NN, and RNN, respectively. For dataset 2, the FNR of the proposed HSS-JO-DNN is 90% superior to DT, 89% improved than NB, KNN, and NN, 94% improved than SVM, and 24% improved than RNN. Similarly, the proposed HSS-JO performance is higher in all the results. Thus, the proposed HSS-JO performs better than all the other traditional methods.

In this paper, a new model for count data is introduced by compounding the Poisson distribution with size-biased three-parameter Lindley distribution. Statistical properties, such as reliability, hazard rate, reverse hazard rate, Mills ratio, moments, shewness, kurtosis, moment genrating function, probability generating function and order statistics, have been discussed. Moreover, the collective risk model is discussed by considering the proposed distrubution as the primary distribution and the expoential and Erlang distributions as the secondary ones. Parameter estimation is done using maximum likelihood estimation (MLE). Finally a real dataset is discussed to demonstrate the suitability and applicability of the proposed distribution in modeling count dataset.

The vehicle with tire blowout will have dangerous working conditions such as yaw and tail flick, which will seriously endanger the safety of driving. A tire blowout model was established based on the UniTire model and the change of tire blowout mechanical characteristics. A Carsim/ Simulink joint simulation platform was built to study the dynamic response of the vehicle after the front wheel tire blowout under curve driving. A combined control strategy of outer-loop trajectory control and inner-loop differential braking control based on sliding mode fuzzy control algorithms and fuzzy PID control algorithms was proposed to ensure that the vehicle can still follow the original trajectory stably after tire blowout. The results show that the tire blowout of the front wheel on the same side as the turning direction has a great influence on the instability and yaw of the vehicle, and the designed control strategy can effectively control the running track of the vehicle with tire blowout and the vehicle stability.

The interaction of prey (small fish) and predator (large fish) in lakes/ ponds at temperate and tropical regions varies when water level fluctuates naturally during seasonal time. We relate the perceptible effect of fear and anti-predator behavior of prey with the water-level fluctuations and describe how these are influenced by the seasonal changing of water level. So, we consider these as time-dependent functions to make the system more realistic. Also, we incorporate the time-dependent delay in the negative growth rate of prey in predator–prey model with Crowley–Martin-type functional response. We clearly provide the basic dynamics of the system such as positiveness, permanence and nonpersistence. The existence of positive periodic solution is studied using Continuation theorem, and suffiecient conditions for globally attractivity of positive periodic solution are also derived. To make the system more comprehensive, we establish numerical simulations, and compare the dynamics of autonomous and nonautonomous systems in the absence as well as the presence of time delay. Our results show that seasonality and time delay create the occurrence of complex behavior such as prevalence of chaotic disorder which can be potentially suppressed by the cost of fear and prey refuge. Also, if time delay increases, then system leads a boundary periodic solution. Our findings assert that the predation, fear of predator and prey refuge are correlated with water-level variations, and give some reasonable biological interpretations for persistence as well as extinction of species due to water-level variations.

The prediction of performance measures is an essential one for manufacturers to increase the service life. This paper deals with the application of Artificial Intelligence (AI) to predict the performance measures like surface roughness, material removal rate, and flank wear during the milling process from the experimental data. The milling experiments were conducted in wet conditions based on the Response Surface Methodology (RSM) design of experiments. The spindle speed, feed rate, and axial depth of cut were considered as process parameters. The experimental data were used to develop the regression model, Mamdani fuzzy inference system, Backpropagation Neural Network (BPNN), and Adaptive Neuro-Fuzzy Inference System (ANFIS) model. The output of regression, fuzzy, neural network, and ANFIS model was compared with the experimental data, and predicted results were found to be in good conformity with the measured data. The prediction capability of the quadratic and Artificial Neural Network (ANN) model was very close to experimentally measured values and the quadratic model had an accuracy of 97.89% for surface roughness, 98.38% for material removal rate (MRR), and 95.72% for flank wear.

At these times, internet of things (IoT) technologies have become ubiquitous in the healthcare sector. Because of the increasing needs of IoT, massive quantity of patient data is being gathered and is utilized for diagnostic purposes. The recent developments of artificial intelligence (AI) and deep learning (DL) models are commonly employed to accurately identify the diseases in real-time scenarios. Despite the benefits, security, energy constraining, insufficient training data are the major issues which need to be resolved in the IoT enabled medical field. To accomplish the security, blockchain technology is recently developed which is a decentralized architecture that is widely utilized. With this motivation, this paper introduces a new blockchain with DL enabled secure medical data transmission and diagnosis (BDL-SMDTD) model. The goal of the BDL-SMDTD model is to securely transmit the medical images and diagnose the disease with maximum detection rate. The BDL-SMDTD model incorporates different stages of operations such as image acquisition, encryption, blockchain, and diagnostic process. Primarily, moth flame optimization (MFO) with elliptic curve cryptography (ECC), called MFO-ECC technique is used for the image encryption process where the optimal keys of ECC are generated using MFO algorithm. Besides, blockchain technology is utilized to store the encrypted images. Then, the diagnostic process involves histogram-based segmentation, Inception with ResNet-v2-based feature extraction, and support vector machine (SVM)-based classification. The experimental performance of the presented BDL-SMDTD technique has been validated using benchmark medical images and the resultant values highlighted the improved performance of the BDL-SMDTD technique. The proposed BDL-SMDTD model accomplished maximum classification performance with sensitivity of 96.94%, specificity of 98.36%, and accuracy of 95.29%, whereas the feature extraction is performed based on ResNet-v2

Technological advancement in a modern environment is approaching universality. The realm and uses of information technology (IT) and Blockchain Security have been extensively broadened. Any business wishing to boost its market prospects would certainly keep records of the perspectives and behaviors of its consumers. The firms employ advanced technological concepts, skills, and methods to comprehend their applicants. Additional information and facts are analyzed to improve judgment. Business analytics and Blockchain Security professionals have a positive opinion. Online shopping behavior analysis (OSBA) is proposed in this research. It addresses a smooth transition from a prediction method to a gradual information strategy that learns the clients’ needs and achieves their electronic trading revenues. Any commercial enterprise must have limitless entry to information. That contains population revenues, industrial patterns, competition and customer information, productivity measurements, computations, and much more. Corporate information has a significant role in this undertaking. Experimental information is collected periodically to evaluate the evidence and provide fresh discoveries and operations that provide fresh perspectives. The major consideration principal element assessment approach is utilized with big data analytics, Blockchain Security, and fuzzy interference system to assess the essential purchasing variables for customers. It achieves an accuracy of 89% and an $F$ score of 87%. Models like support vector machine, convolutional neural network, deep neural network, random forest, fuzzy logic, and decision tree (DT) are compared with the OSBA model’s simulation results (DT). Fuzzy interference, big data, and Blockchain Security analytics improve the OSBA model’s performance.