Journal of Modeling and Simulation
Volume:54 Issue: 2, Summer-Autumn 2022

Today, in the field of medical science, data collection on various diseases is very important. Baby’s birth and its related issues are the vital subject. Nuchal cord is the term used by medical professionals when baby has their umbilical cord wrapped around their neck. In this article, using data mining methods, the occurrence of nuchal cord is predicted. Also some influence factors in this event are investigated. For achieve this aim, in the first stage, based on the literature review and consultation with gynecologists, the new and comprehensive questionnaire for effective factors on the nuchal cord, was designed. ( 31 features that were completed by 140 samples of pregnant mothers). Then, the questionnaire was evaluated by Cronbach’s Alpha. In the next stage, since the obtained dataset was imbalanced, some techniques are applied to balance it. We compared different classification methods such as SVM, cost-sensitive SVM, Random Forest, KNN, Naïve Base, and neural network for prediction, which bootstrap resampling method in combination with KNN and random forest gain the best accuracy (84%). Also, KNN classifier with smote balance handling method achieves best recall (94%). Finally, to extract effective factors some association rule mining methods such as Predictive Apriori, FP-growth were applied. The results show nutrition, blood pressure, diabetes, fetus number, and Internet usage can have more influence on wrapping the umbilical cord around the fetus.

An iterative tuning method is presented to obtain the multi-input multi-output (MIMO) feedforward controller coefficients to improve disturbance rejection in non-minimum phase (NMP) MIMO systems. In the NMP systems, eliminating the effect of disturbances may cause instability and also can impose extra costs to control the entire system. For this purpose, a simple feedforward controller structure is proposed. The unknown variables of the feedforward controller are calculated using LMIs such that the H∞ norm of the transfer function matrix from disturbance to output is minimized. By taking advantage of the frequency sampling techniques into account and using some iterative algorithms, a new tractable method is constructed to solve the problem. Also, a condition based on the right half plane (RHP) zero direction for the NMP system has been proposed to improve the disturbance rejection property of these systems. To obtain optimal coefficients, the algorithm is repeated several times to reach the best answer. The method employs convex technics and CVX software to perform calculations. The efficiency of the method is shown in various practical examples using different performance indicators such as integral of absolute error (IAE), integral of squared error (ISE), integral of time multiplied by absolute error (ITAE), integral of time multiplied by squared error (ITSE).

Since the Unmanned Underwater Vehicles (UUVs) don’t receive the Global Navigation Satellite System (GNSS) signals under the water, other aided measurements are needed to provide the required accuracy in tilt estimation including roll and pitch angle estimation. Conventional approaches for pressure-based tilt estimation, only consider the relation between the static pressure and the tilt as the measurement model. However, the performance of this approach depends on the dynamic pressure which is caused by the sea waves. This paper improves the accuracy of pressure-based tilt estimation using the more accurate of the measurement model. Also, the proposed approach considers the coupling between the axes of UUV. Due to the cost of the approach and the hardware limitations of installation pressure sensors, the proposed approach is implemented using two pressure sensors. An Extended Kalman Filter (EKF) is used for simultaneous tilt and gyroscopes measurement errors estimation. A Monte-Carlo simulation is developed to evaluate the performance of the proposed approach in comparison with INS only and the conventional static pressure-based tilt estimation. The simulation results show that tilt estimation performance of conventional approach is better than the INS only performance and the performance of proposed approach is better than the both of them.

DT is a quantity that converts universal time (UT; defined by the Earth’s rotation) to terrestrial time (TT; independent of Earth’s rotation). The DT values during the time show the Earth’s rotation variations. Solar activities and the gravitational force of major solar system components are known as astronomical-based factors that can provide these variations. Recently, several models have been proposed to interpolate and forecast the DT values. Structurally, all mentioned methods have just used past DT values for modeling.In this paper, we propose a novel approach for modeling DT based on the brain’s emotional learning with respect to astronomical-origin-based factors effective on the Earth’s rotation as the emotional input signals. This model, which employs memory units in the amygdala and orbitofrontal parts, can be named Memory-Based Brain Emotional Learning (MBBEL). MBBEL was run using the data from 1900 to 2000 and 2000 to 2019 as training and testing stages, respectively. After the modeling process, the mean absolute error (MSE) and maximum absolute error (MaxAE) of the train and test stages were 0.011, 0.051, 0.10, and 0.295, respectively. Comparing the MBBEL results against those of eight prior models revealed that MBBEL results considerably improved compared to those of the previous models.

To successfully complete projects, it is essential to meet all the goals of the criteria that affect the project, such as time, cost, and quality. The time-cost-quality trade-off (TCQT) approach is considered a practical technique when project managers or customers tend to crash the total time of a project and create a balance within these criteria. On the other hand, due to the unique inherent of projects and various risks in the real world, using a certain framework for project management problems does not seem efficient. This paper presents a novel fuzzy Bayesian network-based approach to schedule a project and control real-world uncertainties. This novel approach applies the fuzzy opinions of several experts with regard to their weight. The presented fuzzy Bayesian model can calculate a project’s total cost and duration in various uncertain situations. Consequently, this profound knowledge about the project’s various conditions helps managers be aware of the different probable scenarios. To demonstrate the efficiency and application of the proposed model, a modified project example from the literature review is adopted and solved. A common technique in project management called PERT is applied to verify the proposed approach, and the results are compared. Finally, a comparative analysis with a recent related paper is presented.

With the spread of the Internet and the possibility of online access to articles, a wide range of scientific articles are available to researchers, while finding relevant articles among this substantial number of articles turns out to be a real dilemma. To solve this problem, several scientific paper recommendation algorithms have been proposed. Most of these algorithms suffer from some drawbacks that limit their usability. For example, many of these recommendation methods are designed to recommend papers only to users who had published articles before and can’t support new researchers. Also, they usually do not utilize many important features of articles each of which can have a role in determining the relevance of the articles to users. To address these concerns, in this paper, we present the novel method of Integrated Scientific Paper RECommendation with an edge-weight learning approach, called ISPREC++, as an extended version of ISPREC that focuses on learning the weights of edge types in Heterogeneous Information Networks based on users' preferences. ISPREC++ sets the weights of edges in SPIN using a Bayesian Personalized Ranking (BPR) based method and utilizes Gradient Descent to optimize its objective function. Thereafter, it exploits a limited random-walk algorithm for a Top-N recommendation. Extensive experiments on a real-world dataset demonstrate the significant performance superiority of ISPREC++ compared to the state-of-the-art scientific paper recommendation algorithms.