Publication Date: 2021
Journal of Aerospace Engineering (08931321)34(4)
Despite the many advantages of the design optimization technique, this method is costly for real engineering problems. This cost will increase sharply for issues with a multidisciplinary and uncertain nature and more than one objective function. In this paper, the metamodel concept has been used to overcome this problem. Because of the ability of neural networks to approximate the behavior of complex engineering systems, this tool has been used to create a surrogate model. Because multidisciplinary design optimization and robust design optimization methods have been used in this study and according to the high cost of the multidisciplinary analysis module, a surrogate model of this module has been made to reduce the imposed costs. To show the capability of the considered approach, robust multidisciplinary design optimization of an unmanned aerial vehicle (UAV) has been done. Take-off weight and cruise drag are the considered objective functions in this study, and the nondominated sorting genetic algorithm (NSGA-I) has been used for minimization of them. The optimization results show that the use of the metamodeling concept has reduced computational costs by 94.1%. © 2021 American Society of Civil Engineers.
Publication Date: 2020
Journal of Energy Storage (2352152X)30
In this paper, heat transfer during the melting process of n-octadecane as a phase change material (PCM) is experimentally studied. This study is followed by an artificial neural network (ANN) to predict the melting characteristics of PCM. Experiments are performed in a rectangular enclosure subjected to a uniform heat flux in one vertical side. Melting heat transfer is characterized by observing the solid-liquid interface and recording the temperature distribution in the enclosure. Experimental results indicate that heat transfer during the melting process is dominated by natural convection. A multilayered perceptron feed-forward neural network trained by the Levenberg-Marquardt algorithm is used to predict the Nusselt number and the melted volume fraction. Rayleigh, Fourier and Stefan numbers are set as input parameters of the network. The optimal structure of the ANN to predict the Nusselt number show high accuracy in estimating the heat transfer characteristics during melting by achieving the mean square error and the correlation coefficient of 4.42 × 10−6 and 0.999, respectively. Based on the proposed ANN, the majority of the data falls within ±6.23% and ±6.54% of the Nusselt number and the melted volume fraction, respectively. © 2020 Elsevier Ltd
Publication Date: 2016
Heat and Mass Transfer (09477411)52(8)pp. 1621-1631
In the present study, carbon-based nanomaterials including multiwalled carbon nanotubes (MWCNTs) and vapor-grown carbon nanofibers (CNFs) were dispersed in n-octadecane as a phase change material (PCM) at various mass fractions of 0.5, 1, 2 and 5 wt% by the two-step method. The transient plane source technique was used to measure thermal conductivity of samples at various temperatures in solid (5–25 °C) and liquid (30–55 °C) phases. The experimental results showed that thermal conductivity of the composites increases with increasing the loading of the MWCNTs and CNFs. A maximum thermal conductivity enhancement of 36 % at 5 wt% MWCNTs and 5 °C as well as 50 % at 2 wt% and 55 °C were experimentally obtained for n-octadecane/MWCNTs samples. Dispersing CNFs into n-octadecane raised the thermal conductivity up to 18 % at 5 wt% and 10 °C and 21 % at 5 wt% and 55 °C. However, the average enhancement of 19 and 21 % for solid and liquid phases of MWCNTs composite as well as 33 and 46 % for solid and liquid phase of CNFs promised a better heat transfer characteristics of MWCNTs in n-octadecane. A comparison between results of the present work and available literature revealed a satisfactory enhancement of thermal conductivity. For the investigated n-octadecane/MWCNTs and n-octadecane/CNFs composites, a new correlation was proposed for predicting the thermal conductivity as a function of temperature and nanomaterials loading. © 2015, Springer-Verlag Berlin Heidelberg.
Publication Date: 2016
International Communications in Heat and Mass Transfer (07351933)73pp. 1-6
In the present paper, the effect of using a heat pipe on the melting and solidification behavior of a phase change material (PCM) in a vertical cylindrical test cell was experimentally studied. The experiments were performed using a constant temperature thermal reservoir to provide constant temperatures above and below the melting point for heating and cooling. The melting and solidification experiments were run in test cells with and without heat pipes. The experimental results indicate that utilizing a heat pipe in PCM test cell dramatically enhance the melting and solidification rate. Heat pipe surface temperature was measured during experiments. It shows heat pipe isothermally transmits heat very well. By applying different reservoir working temperature, it is concluded that a 15 °C increase in reservoir temperature in melting experiment with heat pipe almost decreases the melting time by 53% and a 10 °C decrease in temperature in solidification reduce the solidification time by 49%. The growth of solid layer and solid-liquid interface in PCM during solidification was experimentally investigated. © 2016 Elsevier Ltd.
Publication Date: 2009
International Journal of Hydrogen Energy (03603199)34(5)pp. 2396-2407
This paper presents exergy analysis of a hybrid solid oxide fuel cell and gas turbine (SOFC/GT) system in comparison with retrofitted system with steam injection. It is proposed to use hot gas turbine exhaust gases heat in a heat recovery steam generator to produce steam and inject it into gas turbine. Based on a steady-state model of the processes, exergy flow rates are calculated for all components and a detailed exergy analysis is performed. The components with the highest proportion of irreversibility in the hybrid systems are identified and compared. It is shown that steam injection decreases the wasted exergy from the system exhaust and boosts the exergetic efficiency by 12.11%. Also, 17.87% and 12.31% increase in exergy output and the thermal efficiency, respectively, is demonstrated. A parametric study is also performed for different values of compression pressure ratio, current density and pinch point temperature difference. © 2008 International Association for Hydrogen Energy.
Publication Date: 2014
Simulation Series (07359276)46(1)pp. 77-83
In this paper we propose an agent-based model approach to determining the effects of consumer choice on aggregate demand (CCAD). Our overall goal is to better understand how the availability of information, heuristic decision making, and social norms affect: 1) total aggregate demand and 2) the aggregated demand for disposable vs. more durable goods. In the preliminary model presented here, consumer agents select among baskets of goods with different combinations of quality and disposability. Consumer choices are based on individual agent preferences and subject to a discretionary income constraint. Agents may be either maximizing, which means that they choose the best basket of goods that they can afford, or satisficing, which means that they choose the first affordable basket of goods that they can find with utility greater than their satisfaction threshold. When run at different price levels, the resulting models can be used to generate aggregated demand curves for each group of consumers. We also demonstrate that, satisficers buy more than maximizers overall. Further analysis shows that this is because maximizers focus their trading on more durable products to gain the highest utility, however satisficers purchase more disposable products because they shop for convenience rather than utility maximization.
Publication Date: 2022
AEU - International Journal of Electronics and Communications (16180399)147
Electromagnetic scattering analysis from conducting objects comparable in size with the incident wavelength, using exact numerical approaches, always suffers from high computational complexity, especially when covered with composite penetrable materials. In this paper the asymptotic method of the physical optics (PO) is developed to predict the scattering patterns from conducting objects coated by chiral metamaterials (CMMs) as an absorber. In first stage, the backward ray-tracing is used to determine the lit region on the outer surface of the objects represented by flat elementary facets. Simple closed-form expressions are derived for the co- and cross-polarized reflection coefficients from a metal-backed CMM layer to approximate the equivalent currents on lit facets in terms of the geometrical-optics fields. Then, for stealth applications, a CMM layer with appropriate electromagnetic properties is suggested with reflected power lower than −20 dB in a wide aspect angle of incident ray from 0 to 57 degrees. Finally, the scattering patterns are calculated via the PO approximation and the equivalent currents. In order to check the accuracy of the proposed solutions, the simulation results of several objects will be compared with the experimental data and the results of the exact Mie theory and method of moment (MoM). © 2022
Publication Date: 2017
Electronics (Switzerland) (20799292)6(4)
Metamaterial leaky wave antennas (MTM-LWAs), one kind of frequency scanning antennas, exhibit frequency-space mapping characteristics that can be utilized to obtain a sufficient field of view (FOV) and reconstruct shapes in both remote sensing and microwave imaging. In this article, we utilize MTM-LWAs to conduct a spectrally encoded three-dimensional (3D) microwave tomography and remote sensing that can reconstruct conductive targets with various dimensions. In this novel imaging technique, we employ the linear sampling method (LSM) as a powerful and fast reconstruction approach. Unlike the traditional LSM using only one single frequency to illuminate a fixed direction, the proposed method utilizes a frequency scanning MTM antenna array able to accomplish frequency-space mapping over the targeted 3D background that includes unknown objects. In addition, a novel technique based on a frequency and polarization hybrid method is proposed to improve the shape reconstruction resolution and stability in ill-posed inverse problems. Both simulation and experimental results demonstrate the unique advantages of the proposed LSM using MTM-LWAs with frequency and polarization diversity as an efficient 3D remote sensing and tomography scheme. © 2017 by the authors. Licensee MDPI, Basel, Switzerland.
The linear sampling method (LSM) is a powerful and fast reconstruction approach and has shown capabilities of both remote sensing and tomography imaging in the microwave frequency range. In this paper, we report some recent advances in developing a novel kind of LSM by means of metamaterial (MTM) leaky wave antennas (LWAs) to conduct spectrally-encoded three-dimensional (3D) microwave tomography that can reconstruct a conductive target with coaxial multi-layer and various diameter cylinders. The unique frequency-space mapping feature of MTM LWAs enables an efficient 3D microwave imaging with a larger field of view compared with conventional LSM approaches that usually operate at one single frequency. It is shown that the LSM can also be used to conduct remote sensing for radar applications, such as automotive radar sensors, by incorporating frequency mapping antenna array based on MTM-LWAs. The proposed frequency scanning scheme in combination with the LSM in this article serves as an efficient 3D remote sensing scheme without the use of phase shifters. © 2017 IEEE.
In this paper, a target shape reconstruction by using electromagnetic wave in resonance region is proposed. A hybrid level set method and linear sampling method used to reconstruction perfectly electric conducting three dimensional scatterer. The Incident plane wave with frequency 300MHz and uniform directional diversity is exploited to illuminate the corresponding scatterer and the scattered field in the far zone helps to retrieve the scatterer with the largest dimension of 6 meters. The numerical result clearly shows that this inversion algorithm provides an automated process to reconstruct shape of scatterers. © 2014 IEEE.
Publication Date: 2020
Proceedings of the Institution of Mechanical Engineers, Part N: Journal of Nanomaterials, Nanoengineering and Nanosystems (23977922)234(1-2)pp. 3-10
The two-dimensional nanostructures such as graphene, silicene, germanene, and stanene have attracted a lot of attention in recent years. Many studies have been done on graphene, but other two-dimensional structures have not yet been studied extensively. In this work, a molecular dynamics simulation of silicene was done and stress–strain curve of silicene was obtained. Then, the mechanical properties of silicene were investigated using the proposed structural molecular mechanics method. First, using the relations governing the force field and the Lifson–Wershel potential function and structural mechanics relations, the coefficients for the BEAM elements was determined, and a structural mechanics model for silicene was proposed. Then, a silicene sheet with 65 Å × 65 Å was modeled, and Young’s modulus of silicene was obtained. In addition, the natural frequencies and mode shapes of silicene were calculated using finite element method. The results are in good agreement with reports by other papers. © IMechE 2020.
Publication Date: 2019
International Journal of Geometric Methods in Modern Physics (17936977)16(6)
Microtubules (MTs), the intracellular structures, are made-up of polar polymers that are composed of α and β tubulins. The functions of MTs are shape the way for vesicles movement and asexual mitosis division. However, one of the main functions of MTs is stability of cells. Fewer geometrical methods are available in the literature to explore the molecular dynamics (MDs) of a MT, which is a difficult task due to its microscopic size and complex structure. A structural mechanics model with rather similar properties to MT can demonstrate the dynamics of MT. The first and most important step for this process is to obtain the interaction force between tubulins, and a mechanical model can be used to simulate the mechanical and dynamical properties of MTs by using meso-and macro-scale simulations. This work reports the interaction properties of β-α tubulin in MT. During this research, with the aid of the MD simulations, the interaction energy in β-α dimer is evaluated. The alpha-beta force-distance diagram is sketched with the aid of force and energy formulae. Thus, the graphical analysis supported the findings of this study. © 2019 World Scientific Publishing Company.
Publication Date: 2023
Journal Of Cellular And Molecular Medicine (15821838)27(5)pp. 714-726
DNA methylation is an early event in tumorigenesis. Here, by integrative analysis of DNA methylation and gene expression and utilizing machine learning approaches, we introduced potential diagnostic and prognostic methylation signatures for stomach cancer. Differentially-methylated positions (DMPs) and differentially-expressed genes (DEGs) were identified using The Cancer Genome Atlas (TCGA) stomach adenocarcinoma (STAD) data. A total of 256 DMPs consisting of 140 and 116 hyper- and hypomethylated positions were identified between 443 tumour and 27 nontumour STAD samples. Gene expression analysis revealed a total of 2821 DEGs with 1247 upregulated and 1574 downregulated genes. By analysing the impact of cis and trans regulation of methylation on gene expression, a dominant negative correlation between methylation and expression was observed, while for trans regulation, in hypermethylated and hypomethylated genes, there was mainly a negative and positive correlation with gene expression, respectively. To find diagnostic biomarkers, we used 28 hypermethylated probes locating in the promoter of 27 downregulated genes. By implementing a feature selection approach, eight probes were selected and then used to build a support vector machine diagnostic model, which had an area under the curve of 0.99 and 0.97 in the training and validation (GSE30601 with 203 tumour and 94 nontumour samples) cohorts, respectively. Using 412 TCGA-STAD samples with both methylation and clinical data, we also identified four prognostic probes by implementing univariate and multivariate Cox regression analysis. In summary, our study introduced potential diagnostic and prognostic biomarkers for STAD, which demands further validation. © 2023 The Authors. Journal of Cellular and Molecular Medicine published by Foundation for Cellular and Molecular Medicine and John Wiley & Sons Ltd.
Publication Date: 2022
Knowledge and Information Systems (02191377)64(12)pp. 3293-3324
Patient similarity assessment, which identifies patients similar to a given patient, is a fundamental component of many secondary uses of medical data. The assessment can be performed using electronic medical records (EMRs). Patient similarity measurement requires converting heterogeneous EMRs into comparable formats to calculate distance. This study presents a new data representation method for EMRs that considers the information in clinical narratives. To address the limitations of previous approaches in handling complex parts of EMR data, an unsupervised manner is proposed for building a patient representation, which integrates unstructured and structured data extracted from patients' EMRs. We employed a tree structure to model the extracted data that capture the temporal relations of multiple medical events from EMR. We processed clinical notes to extract medical concepts using Python libraries such as MedspaCy and ScispaCy and mapped entities to the Unified Medical Language System (UMLS). To capture temporal aspects of the extracted events, we developed two new relabeling methods for the non-leaf nodes of the tree. To create an embedding vector for each patient, we traversed the tree to generate sequences that the Doc2vec algorithm would use. The comprehensive evaluation of the proposed method for patient similarity and mortality prediction tasks demonstrated that our proposed model leads to lower mean-squared error (MSE), higher precision, and normalized discounted cumulative gain (NDCG) relative to baselines. © 2022, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.
Publication Date: 2022
International Journal of Electrical Power and Energy Systems (01420615)134
This paper presents a new mathematical approach for co-planning of transmission expansion planning and battery storage systems placement. An optimal placement of grid-scaled battery storage systems can help transmission systems in congestion managements and improve power system security. In addition, battery storage systems can increase power system reliability in contingency conditions. In this paper a security and reliability viewpoint is implemented for the simultaneous transmission expansion planning and the optimal placement of battery storage systems. The N-1 security constraints are applied to the expansion planning model. The reliability indices evaluated from second order outages are also involved in the decision making process. The Benders’ decomposition approach is used to reduce the computational burden of the proposed model and make it applicable for large scaled power systems. The IEEE 24-bus test system is used to evaluate the applicability of the proposed method. © 2021 Elsevier Ltd
A new risk-constrained bidding curve construction method is presented in this paper. A Day-ahead energy market has been chosen for competition of GenCos and the Information Gap Decision Theory (IGDT) is used for modelling the Day-ahead market price uncertainty and its corresponding risk. The bilateral contracts of the GenCo are also considered in the proposed framework. A Bi-level optimization problem is incorporated in the proposed method to guarantee a pre-specified level of revenue. The proposed IGDT based method constructs the non-decreasing bidding curve while dispatching units based on the uncertain forecasted prices of the next-day market. The verification of the proposed method is demonstrated by simulation of a GenCo with 5 thermal units in various day-ahead markets. © 2013 IEEE.
Publication Date: 2022
Discrete Mathematics, Algorithms and Applications (17938317)14(4)
For a set W of vertices and a vertex v in a graph G, the k-vector r2(v|W) = (aG(v,w1),⋯,aG(v,wk)) is the adjacency representation of v with respect to W, where W = {w1,⋯,wk} and aG(x,y) is the minimum of 2 and the distance between the vertices x and y. The set W is an adjacency resolving set for G if distinct vertices of G have distinct adjacency representations with respect to W. The minimum cardinality of an adjacency resolving set for G is its adjacency dimension. It is clear that the adjacency dimension of an n-vertex graph G is between 1 and n - 1. The graphs with adjacency dimension 1 and n - 1 are known. All graphs with adjacency dimension 2, and all n-vertex graphs with adjacency dimension n - 2 are studied in this paper. In terms of the diameter and order of G, a sharp upper bound is found for adjacency dimension of G. Also, a sharp lower bound for adjacency dimension of G is obtained in terms of order of G. Using these two bounds, all graphs with adjacency dimension 2, and all n-vertex graphs with adjacency dimension n - 2 are characterized. © 2022 World Scientific Publishing Company.
Publication Date: 2011
Applied Mathematics Letters (18735452)24(10)pp. 1625-1629
For an ordered set W=w1,w2,⋯,wk of vertices and a vertex v in a connected graph G, the ordered k-vector r(v|W):=(d(v,w1),d(v,w2),⋯,d(v,wk)) is called the (metric) representation of v with respect to W, where d(x,y) is the distance between the vertices x and y. The set W is called a resolving set for G if distinct vertices of G have distinct representations with respect to W. A resolving set for G with minimum cardinality is called a basis of G and its cardinality is the metric dimension of G. A connected graph G is called a randomly k-dimensional graph if each k-set of vertices of G is a basis of G. In this work, we study randomly k-dimensional graphs and provide some properties of these graphs. © 2011 Elsevier Ltd. All rights reserved.
Publication Date: 2023
Electric Power Systems Research (03787796)219
Power transformer protection performs an essential role in power systems, ensuring a reliable power supply to the customers. One of the main challenges in differential protection of the transformers is to correctly discriminate inrush currents from internal faults and prevent the maloperation of the differential relay. In this regard, a novel differential protection method is proposed, which decomposes the differential current signal to multiple energy levels through the multi-resolution analysis (MRA) and selects the most useful feature to feed to the bidirectional gated recurrent unit (BIGRU) to classify the events. The use of the BIGRU results in the high accuracy and low implementation complexity of the proposed approach. Various simulations carried out on a 70 MVA transformer demonstrate that the proposed approach has an accuracy of 99.70% in discriminating inrush currents from internal faults in less than one-eighth of the power cycle. © 2023 Elsevier B.V.
Modern power systems are prone to widespread failures. With the increase in power demand, operation and planning of large interconnected power system are becoming more and more complex, so power system will become less secure. Operating environment, conventional planning and operating methods can leave power system exposed to instabilities. Voltage instability is one of the phenomena which have result in a major blackout. Moreover, with the fast development of restructuring, the problem of voltage stability has become a major concern in deregulated power systems. To maintain security of such systems, it is desirable to plan suitable measures to improve power system security and increase voltage stability margins. FACTS devices can regulate the active and reactive power control as well as adaptive to voltage-magnitude control simultaneously because of their flexibility and fast control characteristics. Placement of these devices in suitable location can lead to control in line flow and maintain bus voltages in desired level and so improve voltage stability margins. This paper presents a Genetic Algorithm (GA) based allocation algorithm for FACTS devices considering Cost function of FACTS devices and power system losses. Proposed algorithm is tested on IEEE 30 bus power system for optimal allocation of multi-type FACTS devices and results are presented.
Publication Date: 2018
IEEE Transactions on Power Systems (0885-8950)33(4)pp. 4275-4284
This paper presents a microgrid (MG) proactive management framework to cope with adverse impacts of extreme windstorms. Upon receiving alerts for the forecasted windstorm, the framework finds a conservative schedule of MG with the minimum number of vulnerable branches in service while total load is served. The schedule ensures the MG normal operation prior to the windstorm while reducing the MG vulnerability at the event onset. The proposed method makes benefit of network reconfiguration, generation reschedule, conservation voltage regulation, optimal parameter settings of droop-controlled units, demand-side resources, and backup generation capacity. A vulnerability index is defined to assess the effectiveness of the proposed proactive management in reducing the MG vulnerability at the event onset. The proposed model is linearized that guarantees simplicity, robustness, and computational efficiency of the solution. The effectiveness of the proposed method is tested on a real-scale MG against a windstorm. © 1969-2012 IEEE.
Publication Date: 2016
Journal of Algebra (00218693)460pp. 128-142
A famous theorem of algebra due to Osofsky states that "if every cyclic left R-module is injective, then R is semisimple". Therefore, a natural question of this sort is: "What is the class of rings R for which every cyclic left R-module is pure-injective or pure-projective?" The goal of this paper is to answer this question. For instance, we show that if every cyclic left R-module is pure-injective, then R is a left perfect ring. As a consequence, a commutative coherent ring R is Artinian if and only if every cyclic R-module is pure-injective. Also, a commutative ring R is pure-semisimple (i.e., every R-module is pure-injective) if and only if all cyclic R-modules and all indecomposable R-modules are pure-injective. We obtain some generalizations of Osofsky's theorem in the cases R is semiprimitive or commutative coherent or a commutative semiprime Goldie ring. Finally, we show that a ring R is left Noetherian if and only if every cyclic left R-module is pure-projective. As a corollary of this result we obtain: if every cyclic left R-module is pure-injective and pure-projective, then R is a left Artinian ring. The converse is also true when R is commutative. © 2016 Elsevier Inc.
Publication Date: 2016
Applied Thermal Engineering (13594311)102pp. 1462-1472
Piston bowl geometries are crucial to the combustion and emission characteristics of reactivity controlled compression ignition (RCCI) engines. The present numerical study explores the effects of piston bowl geometry on natural gas/diesel RCCI performance and emissions at medium engine load. Three different piston bowl geometries including stock, bathtub and cylindrical with constant compression ratio 16.1:1 are selected using double injection strategy and influences of engine speed, piston bowl depth and chamfered ring-land are investigated. It is found that the bowl profile does not affect combustion of RCCI engine at low engine speeds, but it has much considerable effect at higher engine speeds. The results obtained also show that bathtub design yields the best performance and emissions at higher speeds. It is also reported that both piston bowl depth and chamfered ring-land can also affect engine-out emissions specially UHC and CO emissions. © 2016 Elsevier Ltd. All rights reserved.
Publication Date: 2025
Ain Shams Engineering Journal (20904479)16(11)
High-Impedance Arcing Faults (HIAFs) in electrical microgrids are among the abnormal conditions that are difficult to detect by conventional protective devices due to low current and non-linear behavior. In addition, the behavioral similarity of HIAFs to other transient events (TEs) in microgrids leads to classification challenges. This study addresses this issue by proposing a new protective algorithm for the fast and accurate detection of HIAFs and their differentiation from other TEs. The proposed method uses the third harmonic angle of the residual current (THARC) as a key identification feature, which is extracted using a fast, accurate two-layer Master-Slave ADALINE (MS-ADALINE) architecture. The THARC is then smoothed using the Moving Average (MWA) technique, and a new index is introduced for fault detection. Simulations conducted in the EMTP-RV software environment demonstrate that the proposed algorithm can distinguish HIAFs from other TEs under noisy and complex conditions with an accuracy of 99.17% and a detection time of 20 msec. Low computational cost and simple, practical implementation are additional significant advantages of the proposed method. © 2025 The Author(s)
Currently, the majority of installed renewable energy systems operate in their maximum power point tracking (MPPT) mode to optimize power output. Therefore, the output power generated by these resources is fluctuating. When the producing capacity of renewable energy resources increases, the output power fluctuation influence on the power system stability becomes more significant. In this situation, employment of energy storage resources like batteries, despite their high cost, is inevitable in mitigation of power fluctuations. Electric vehicle parkings, as one of the smart grid components, can contribute to enhance the integration of renewable energy resources with centralized power systems. These electric vehicle parkings can optimize the cost of batteries required in the distribution network. Modeling of electric vehicle parkings is a very important issue in smoothing the power fluctuation of renewable energy resources. In this paper, existing methods for electric vehicle parking modeling are reviewed and then a behavioral model is proposed. As a case study, all the vehicle parkings in Tehran city are studied and thus, the extracted pattern is based on real statistic data. The proposed model demonstrates that the capacity of electric vehicle parkings is variable and depends on different factors. Therefore, two daily and weekly patterns are presented for this model. The proposed behavioral model in this paper can be used in the studies of power fluctuation smoothing in renewable energy resources for modeling and simulation of electric vehicle parkings. © 2025 IEEE.
Publication Date: 2025
Machine Learning with Applications (26668270)22
Road traffic injuries continue to pose a significant public health challenge in Australia, with pedestrians representing one of the most vulnerable road user groups. Accurate prediction of injury severity, particularly fatal outcomes, is essential for improving road safety interventions and resource allocation. This study applies advanced machine learning techniques to predict pedestrian crash severity using national hospitalization and mortality data collected from 2011 to 2021. The analysis focuses on addressing class imbalance, a common issue in injury data by evaluating the impact of several data balancing methods, including SMOTE, ADASYN, Random Oversampling (ROS), and Threshold Moving. We implement and compare four supervised learning algorithms: Logistic Regression, Support Vector Machine (SVM), Decision Tree, and XGBoost. Model performance is assessed using F1-score and macro-accuracy, with a focus on the minority (fatality) class. Results show that XGBoost combined with Threshold Moving achieves the highest performance, yielding an F1-score of 72% for fatality classification and a macro-accuracy of 84%. Additionally, feature importance analysis using SHAP values reveals age, gender, road user type, and crash location as key predictors of injury severity. The study highlights the critical role of data balancing strategies in enhancing predictive accuracy for rare but high-impact outcomes. These findings provide actionable insights for transport authorities and policymakers seeking to develop data-driven, targeted safety measures to protect pedestrians and reduce the severity of crash outcomes. © 2025 The Author(s).
