Showing papers by "Zong Woo Geem published in 2022"

Interpretable Machine Learning Algorithms to Predict the Axial Capacity of FRP-Reinforced Concrete Columns

Abstract: Fiber-reinforced polymer (FRP) rebars are increasingly being used as an alternative to steel rebars in reinforced concrete (RC) members due to their excellent corrosion resistance capability and enhanced mechanical properties. Extensive research works have been performed in the last two decades to develop predictive models, codes, and guidelines to estimate the axial load-carrying capacity of FRP-RC columns. This study utilizes the power of artificial intelligence and develops an alternative approach to predict the axial capacity of FRP-RC columns more accurately using data-driven machine learning (ML) algorithms. A database of 117 tests of axially loaded FRP-RC columns is collected from the literature. The geometric and material properties, column shape and slenderness ratio, reinforcement details, and FRP types are used as the input variables, while the load-carrying capacity is used as the output response to develop the ML models. Furthermore, the input-output relationship of the ML model is explained through feature importance analysis and the SHapely Additive exPlanations (SHAP) approach. Eight ML models, namely, Kernel Ridge Regression, Lasso Regression, Support Vector Machine, Gradient Boosting Machine, Adaptive Boosting, Random Forest, Categorical Gradient Boosting, and Extreme Gradient Boosting, are used in this study for capacity prediction, and their relative performances are compared to identify the best-performing ML model. Finally, predictive equations are proposed using the harmony search optimization and the model interpretations obtained through the SHAP algorithm.

Parameters Optimization of Taguchi Method Integrated Hybrid Harmony Search Algorithm for Engineering Design Problems

Abstract: Performance of convergence to the optimum value is not completely a known process due to characteristics of the considered design problem and floating values of optimization algorithm control parameters. However, increasing robustness and effectiveness of an optimization algorithm may be possible statistically by estimating proper algorithm parameters values. Not only the algorithm which utilizes these estimated-proper algorithm parameter values may enable to find the best fitness in a shorter time, but also it may supply the optimum searching process with a pragmatical manner. This study focuses on the statistical investigation of the optimum values for the control parameters of the harmony search algorithm and their effects on the best solution. For this purpose, the Taguchi method integrated hybrid harmony search algorithm has been presented as an alternative method for optimization analyses instead of sensitivity analyses which are generally used for the investigation of the proper algorithm parameters. The harmony memory size, the harmony memory considering rate, the pitch adjustment rate, the maximum iteration number, and the independent run number of entire iterations have been debated as the algorithm control parameters of the harmony search algorithm. To observe the effects of design problem characteristics on control parameters, the new hybrid method has been applied to different engineering optimization problems including several engineering-optimization examples and a real-size engineering optimization design. End of extensive optimization and statistical analyses to achieve optimum values of control parameters providing rapid convergence to optimum fitness value and handling constraints have been estimated with reasonable relative errors. Employing the Taguchi method integrated hybrid harmony search algorithm in parameter optimization has been demonstrated as it is a reliable and efficient manner to obtain the optimum results with fewer numbers of run and iteration.

Optimal Dimensioning of Retaining Walls Using Explainable Ensemble Learning Algorithms

Abstract: This paper develops predictive models for optimal dimensions that minimize the construction cost associated with reinforced concrete retaining walls. Random Forest, Extreme Gradient Boosting (XGBoost), Categorical Gradient Boosting (CatBoost), and Light Gradient Boosting Machine (LightGBM) algorithms were applied to obtain the predictive models. Predictive models were trained using a comprehensive dataset, which was generated using the Harmony Search (HS) algorithm. Each data sample in this database consists of a unique combination of the soil density, friction angle, ultimate bearing pressure, surcharge, the unit cost of concrete, and six different dimensions that describe an optimal retaining wall geometry. The influence of these design features on the optimal dimensioning and their interdependence are explained and visualized using the SHapley Additive exPlanations (SHAP) algorithm. The prediction accuracy of the used ensemble learning methods is evaluated with different metrics of accuracy such as the coefficient of determination, root mean square error, and mean absolute error. Comparing predicted and actual optimal dimensions on a test set showed that an R2 score of 0.99 could be achieved. In terms of computational speed, the LightGBM algorithm was found to be the fastest, with an average execution speed of 6.17 s for the training and testing of the model. On the other hand, the highest accuracy could be achieved by the CatBoost algorithm. The availability of open-source machine learning algorithms and high-quality datasets makes it possible for designers to supplement traditional design procedures with newly developed machine learning techniques. The novel methodology proposed in this paper aims at producing larger datasets, thereby increasing the applicability and accuracy of machine learning algorithms in relation to optimal dimensioning of structures.

Optimization of Tuned Liquid Damper Including Different Liquids for Lateral Displacement Control of Single and Multi-Story Structures

Abstract: This study focuses on tuned liquid dampers (TLDs) using liquids with different characteristics optimized with the adaptive harmony search algorithm (AHS). TLDs utilize the characteristic features of the liquid to absorb the dynamic forces entering the structure and benefit from the sloshing movement and the spring stiffness created by the liquid mass. TLDs have been optimized to investigate the effect of liquid characteristics on the control by analyzing various liquids. For optimization, the memory consideration ratio (HMCR) and fret width (FW) values were adapted from the classical harmony search (HS) algorithm parameters. The TLDs were used on three types of structure models, such as single-story, 10, and 40 stories. The contribution of the liquid characteristics to the damping performance was investigated by optimizing the minimum displacement under seismic excitation. According to the results, it was understood that the liquid density and kinematic viscosity do not affect single-story structures alone. However, two characteristic features should be evaluated together. As the structure mass increases, the viscosity and density become more prominent.

Adaptive Harmony Search for Tuned Liquid Damper Optimization under Seismic Excitation

Abstract: In this study, the tuned liquid damper (TLD) device was optimized by the harmony search (HS) and adaptive harmony search algorithms (AHS). Using the harmony search algorithm, seismic excitations were directed at single and ten-story structures, and TLD parameters were optimized to minimize building movement. To improve design parameters, the optimization process was repeated by adapting the design factors of the harmony search algorithm. For this purpose, both the harmony memory consideration ratio (HMCR) and fret width (FW) were gradually reduced by providing an initial value, and optimum algorithm parameters were obtained. As a result of both optimizations, in a critical seismic analysis, the displacements of the adaptive harmony search showed smaller means and standard deviations than those of the classical harmony search.

Optimization of Seismic Base Isolation System Using Adaptive Harmony Search Algorithm

Abstract: In this study, a seismic isolator placed on the base of a structure was optimized under various earthquake records using an adaptive harmony search algorithm (AHS). As known, the base-isolation systems with very low stiffness provide a rigid response of superstructure, so it was assumed that the structure is rigid and the base-isolated structure can be considered as a single-degree of freedom structure. By using this assumption, an optimization method that is independent of structural properties but specific to the chosen earthquake excitation set is proposed. By taking three different damping ratio limits and isolator displacement limits, the isolator period and damping ratio were optimized so that the acceleration of the structure was minimized for nine cases. In the critical seismic analysis performed with optimum isolator parameters, the results obtained for different damping ratios and isolator periods were compared. From the results, it is determined that isolators with low damping ratios require more ductility, and as the damping ratio increases, further restriction of the movement of the isolator increases the control efficiency. Thus, it is revealed that increasing the ductility of the isolator is effective in reducing the total acceleration in the structure.

Optimum Design of Cylindrical Walls Using Ensemble Learning Methods

Abstract: The optimum cost of the structure design is one of the major goals of structural engineers. The availability of large datasets with preoptimized structural configurations can facilitate the process of optimum design significantly. The current study uses a dataset of 7744 optimum design configurations for a cylindrical water tank. Each of them was obtained by using the harmony search algorithm. The database used contains unique combinations of height, radius, total cost, material unit cost, and corresponding wall thickness that minimize the total cost. It was used to create ensemble learning models such as Random Forest, Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Gradient Boosting (CatBoost). Generated machine learning models were able to predict the optimum wall thickness corresponding to new data with high accuracy. Using SHapely Additive exPlanations (SHAP), the height of a cylindrical wall was found to have the greatest impact on the optimum wall thickness followed by radius and the ratio of concrete unit cost to steel unit cost.

A Comprehensive Review of Deep Learning Strategies in Retinal Disease Diagnosis Using Fundus Images

Abstract: In recent years, there has been an unprecedented growth in computer vision and deep learning implementation owing to the exponential rise of computation infrastructure. The same was also reflected in retinal image analysis and successful artificial intelligence models were developed for various retinal disease diagnoses using a wide variety of visual markers obtained from eye fundus images. This article presents a comprehensive study of different deep learning strategies employed in recent times for the diagnosis of five major eye diseases, i.e., Diabetic retinopathy, Glaucoma, age-related macular degeneration, Cataract, and Retinopathy of prematurity. This article is organized according to the deep learning implementation process pipeline, where commonly used datasets, evaluation metrics, image pre-processing techniques, and deep learning backbone models are first illustrated followed by an extensive review of different strategies for each of the five mentioned retinal diseases is presented. Finally, this article summarizes eight major research directions available in the field of retinal disease diagnosis and outlines key challenges and future scope for the present research community.

Interval-Type 3 Fuzzy Differential Evolution for Designing an Interval-Type 3 Fuzzy Controller of a Unicycle Mobile Robot

Abstract: Recently, interval-type 3 fuzzy systems have begun to appear in different research areas. This article outlines a methodology for the parameterization of interval type-3 membership functions using vertical cuts applied to the dynamic parameter adaptation of the differential evolution algorithm and implemented in an interval-type 3 Sugeno controller. This methodology was applied to the dynamic adaptation of the F (mutation) parameter in differential evolution to improve the performance of this method as the generations occur. To test the type-3 fuzzy differential evolution algorithm, the optimal design of a type-3 Sugeno controller was considered. In this case, the parameterization of the type-3 membership functions of this Sugeno fuzzy controller was performed. The experimentation is based on the application of three different noise levels for validation of the efficacy of the method and performing a comparison study with respect to other articles in the literature. The main idea is to implement the parameterization of interval type-3 membership functions to enhance the ability of differential evolution in designing an optimal interval type-3 system to control a unicycle mobile robot.

DeepPlayer-Track: Player and Referee Tracking with Jersey Color Recognition in Soccer

Abstract: In real-world sports video analysis, identity switching caused by inter-object interactions is still a major difficulty for multi-player tracking. Due to similar appearances of players on the same squad, existing methodologies make it difficult to correlate detections and retain identities. In this paper, a novel approach (DeepPlayer-Track) is proposed to track the players and referees, by representing the deep features to retain the tracking identity. To provide identity-coherent trajectories, a sophisticated multi-player tracker is being developed further, encompassing deep features of player and referee identification. The proposed methodology consists of two parts: (i) the You Only Look Once (YOLOv4) can detect and classify players, soccer balls, referees, and background; (ii) Applying a modified deep feature association with a simple online real-time (SORT) tracking model which connects nodes from frame to frame using cosine distance and deep appearance descriptor to correlate the coefficient of the player identity (ID) which improved tracking performance by distinct identities. The proposed model achieved a tracking accuracy of 96% and 60% on MOTA and GMOTA metrics respectively with a detection speed of 23 frames per second (FPS).

Modified Harmony Search Algorithm-Based Optimization for Eco-Friendly Reinforced Concrete Frames

Abstract: Cost and CO2 are two factors in the optimum design of structures. This study proposes a modified harmony search methodology for optimization of reinforced concrete beams with minimum CO2 emissions. The optimum design was developed in detail by considering all possible combinations of variable loads, including dynamic force resulting from earthquake motion. Moreover, time-history analyses were performed, and requirements of the ACI-318 building code were considered in the reinforced concrete design. The results show that the optimum design based on CO2 emission minimization is greatly different from the optimum cost design results. According to these results, using recycled members provides a sustainable design.

Optimal Planning of Multitype DGs and D-STATCOMs in Power Distribution Network Using an Efficient Parameter Free Metaheuristic Algorithm

Abstract: In a quest to solve the multi-objective optimal planning problem using a simple parameter-free metaheuristic algorithm, this paper establishes the recently proposed student psychology-based optimization (SPBO) algorithm as the most promising one, comparing it with the other two popular nonparametric metaheuristic optimization algorithms, i.e., the symbiotic organisms search (SOS) and Harris hawk optimization (HHO). A novel multi-objective framework (with suitable weights) is proposed with a real power loss minimization index, bus voltage variation minimization index, system voltage stability maximization index, and system annual cost minimization index to cover various technical, economic, and environmental aspects. The performances of these three algorithms are compared extensively for simultaneous allocation of multitype distributed generations (DGs) and D-STACOM in 33-bus and 118-bus test systems considering eight different cases. The detailed analysis also includes the statistical analysis of the results obtained using the three algorithms applied to the two test distribution systems.

Power System Stability Enhancement Using Robust FACTS-Based Stabilizer Designed by a Hybrid Optimization Algorithm

Abstract: Improving the stability of power systems using FACT devices is an important and effective method. This paper uses a static synchronous series compensator (SSSC) installed in a power system to smooth out inter-area oscillations. A meta-heuristic optimization method is proposed to design the supplementary damping controller and its installation control channel within the SSSC. In this method, two control channels, phase and magnitude have been investigated for installing a damping controller to improve maximum stability and resistance in different operating conditions. An effective control channel has been selected. The objective function considered in this optimization method is multi-objective, using the sum of weighted coefficients method. The first function aims to minimize the control gain of the damping controller to the reduction of control cost, and the second objective function moves the critical modes to improve stability. It is defined as the minimum phase within the design constraints of the controller. A hybrid of two well-known meta-heuristic methods, the genetic algorithm (GA) and grey wolf optimizer (GWO) algorithm have been used to design this controller. The proposed method in this paper has been applied to develop a robust damping controller with an optimal control channel based on SSSC for two standard test systems of 4 and 50 IEEE machines. The results obtained from the analysis of eigenvalues and nonlinear simulation of the power system study show the improvement in the stability of the power system as well as the robust performance of the damping in the phase control channel.

Optimal Placement of Renewable Energy Generators Using Grid-Oriented Genetic Algorithm for Loss Reduction and Flexibility Improvement

Abstract: Optimal planning of renewable energy generator (REG) units helps to meet future power demand with improved flexibility. Hence, this paper proposes a grid-oriented genetic algorithm (GOGA) based on a hybrid combination of a genetic algorithm (GA) and a solution using analytical power flow equations for optimal sizing and placement of REG units in a power system network. The objective of the GOGA is system loss minimization and flexibility improvement. The objective function expresses the system losses as a function of the power generated by different generators, using the Kron equation. A flexibility index (FI) is proposed to evaluate the improvement in the flexibility, based on the voltage deviations and system losses. A power flow run is performed after placement of REGs at various buses of the test system, and system losses are computed, which are considered as chromosome fitness values. The GOGA searches for the lowest value of the fitness function by changing the location of REG units. Crossover, mutation, and replacement operators are used by the GOGA to generate new chromosomes until the optimal solution is obtained in terms of size and location of REGs. A study is performed on a part of the practical transmission network of Rajasthan Rajya Vidyut Prasaran Nigam Ltd. (RVPN), India for the base year 2021 and the projected year 2031. Load forecasting for the 10-year time horizon is computed using a linear fit mathematical model. A cost–benefit analysis is performed, and it is established that the proposed GOGA provides a financially viable solution with improved flexibility. It is established that GOGA ensures high convergence speed and good solution accuracy. Further, the performance of the GOGA is superior compared to a conventional GA.

MTHSA-DHEI: multitasking harmony search algorithm for detecting high-order SNP epistatic interactions

Abstract: Abstract Genome-wide association studies have succeeded in identifying genetic variants associated with complex diseases, but the findings have not been well interpreted biologically. Although it is widely accepted that epistatic interactions of high- order single nucleotide polymorphisms (SNPs) [(1) Single nucleotide polymorphisms (SNP) are mainly deoxyribonucleic acid (DNA) sequence polymorphisms caused by variants at a single nucleotide at the genome level. They are the most common type of heritable variation in humans.] are important causes of complex diseases, the combinatorial explosion of millions of SNPs and multiple tests impose a large computational burden. Moreover, it is extremely challenging to correctly distinguish high- order SNP epistatic interactions from other high- order SNP combinations due to small sample sizes. In this study, a multitasking harmony search algorithm (MTHSA-DHEI) is proposed for detecting high- order epistatic interactions [(2) In classical genetics, if genes X1 and X2 are mutated and each mutation by itself produces a unique disease status (phenotype) but the mutations together cause the same disease status as the gene X1 mutation, gene X1 is epistatic and gene X2 is hypostatic, and gene X1 has an epistatic effect (main effect) on disease status. In this work, a high-order epistatic interaction occurs when two or more SNP loci have a joint influence on disease status.], with the goal of simultaneously detecting multiple types of high- order ( k 1 - order , k 2 - order , …, k n - order ) SNP epistatic interactions. Unified coding is adopted for multiple tasks, and four complementary association evaluation functions are employed to improve the capability of discriminating the high- order SNP epistatic interactions. We compare the proposed MTHSA-DHEI method with four excellent methods for detecting high- order SNP interactions for 8 high- order e pistatic i nteraction models with n o m arginal e ffect (EINMEs) and 12 e pistatic i nteraction models with m arginal e ffects (EIMEs) (*) and implement the MTHSA-DHEI algorithm with a real dataset: age-related macular degeneration (AMD). The experimental results indicate that MTHSA-DHEI has power and an F1-score exceeding 90% for all EIMEs and five EINMEs and reduces the computational time by more than 90%. It can efficiently perform multiple high- order detection tasks for high- order epistatic interactions and improve the discrimination ability for diverse epistasis models.

Optimization and Predictive Modeling of Reinforced Concrete Circular Columns

Abstract: Metaheuristic optimization techniques are widely applied in the optimal design of structural members. This paper presents the application of the harmony search algorithm to the optimal dimensioning of reinforced concrete circular columns. For the objective of optimization, the total cost of steel and concrete associated with the construction process were selected. The selected variables of optimization include the diameter of the column, the total cross-sectional area of steel, the unit costs of steel and concrete used in the construction, the total length of the column, and applied axial force and the bending moment acting on the column. By using the minimum allowable dimensions as the constraints of optimization, 3125 different data samples were generated where each data sample is an optimal design configuration. Based on the generated dataset, the SHapley Additive exPlanations (SHAP) algorithm was applied in combination with ensemble learning predictive models to determine the impact of each design variable on the model predictions. The relationships between the design variables and the objective function were visualized using the design of experiments methodology. Applying state-of-the-art statistical accuracy measures such as the coefficient of determination, the predictive models were demonstrated to be highly accurate. The current study demonstrates a novel technique for generating large datasets for the development of data-driven machine learning models. This new methodology can enhance the availability of large datasets, thereby facilitating the application of high-performance machine learning predictive models for optimal structural design.

A Fully-Self-Adaptive Harmony Search GMDH-Type Neural Network Algorithm to Estimate Shear-Wave Velocity in Porous Media

Abstract: Shear wave velocity (VS) is one of the most important parameters in deep and surface studies and the estimation of geotechnical design parameters. This parameter is widely utilized to determine permeability and porosity, lithology, rock mechanical parameters, and fracture assessment. However, measuring this important parameter is either impossible or difficult due to the challenges related to horizontal and deviation wells or the difficulty in reaching cores. Artificial Intelligence (AI) techniques, especially Machine Learning (ML), have emerged as efficient approaches for dealing with such challenges. Therefore, considering the advantage of the ML, the current research proposes a novel Fully-Self-Adaptive Harmony Search—Group Method of Data Handling (GMDH)-type neural network, named FSHS-GMDH, to estimate the VS parameter. In this way, the Harmony Memory Consideration Rate (HMCR) and Pitch Adjustment Rate (PAR) parameters are calculated automatically. A novel method is also introduced to adjust the value of the Bandwidth (BW) parameter based on the cosine wave and each decision variable values. In addition, a variable-size harmony memory is proposed to enhance both the diversification and intensification. Our proposed FSHS-GMDH algorithm quickly explores the problem space and exploits the best regions at the late iterations. This algorithm allows for the training of the prediction model based on the P-wave velocity (VP) and the bulk density of rock (RHOB). Applying the proposed algorithm to a carbonate petroleum reservoir in the Persian Gulf demonstrates that it is capable of accurately estimating the VS parameter better than state-of-the-art machine learning methods in terms of the coefficient of determination (R2), Mean Square Error (MSE), and Root Mean Square Error (RMSE).

Evaluation of Dimension Stone According to Resistance to Freeze–Thaw Cycling to Use in Cold Regions

Abstract: 1. Associate Professor, Department of Mining Engineering, Faculty of Environment, Urmia University of Technology, Urmia, Iran 2. Assistant Professor, Department of Mining Engineering, Faculty of Environment, Urmia University of Technology, Urmia, Iran 3. Ph.D. Candidate, Department of Civil Engineering, University of Calabria, 87036 Rende, Italy 4. Professor, Department of Mining, Petroleum & Geophysics Engineering, Shahrood University of Technology, Shahrood, Iran 5. M.S., Department of Civil Engineering, Faculty of Environment, Urmia University of Technology, Urmia, Iran 6. Ph.D. Candidate, Department of Mining and Metallurgical Engineering, Yazd University, Yazd, Iran 7. Professor, Department of Civil Engineering, Korea Maritime and Ocean University, Pusan 49112, Korea 8. Associate Professor, College of IT Convergence, Gachon University, Seongnam 13120, Korea Corresponding author: geem@gachon.ac.kr

SinLU: Sinu-Sigmoidal Linear Unit

Abstract: Non-linear activation functions are integral parts of deep neural architectures. Given the large and complex dataset of a neural network, its computational complexity and approximation capability can differ significantly based on what activation function is used. Parameterizing an activation function with the introduction of learnable parameters generally improves the performance. Herein, a novel activation function called Sinu-sigmoidal Linear Unit (or SinLU) is proposed. SinLU is formulated as SinLU(x)=(x+asinbx)·σ(x), where σ(x) is the sigmoid function. The proposed function incorporates the sine wave, allowing new functionalities over traditional linear unit activations. Two trainable parameters of this function control the participation of the sinusoidal nature in the function, and help to achieve an easily trainable, and fast converging function. The performance of the proposed SinLU is compared against widely used activation functions, such as ReLU, GELU and SiLU. We showed the robustness of the proposed activation function by conducting experiments in a wide array of domains, using multiple types of neural network-based models on some standard datasets. The use of sine wave with trainable parameters results in a better performance of SinLU than commonly used activation functions.

Explainable Ensemble Learning Models for the Rheological Properties of Self-Compacting Concrete

Abstract: Self-compacting concrete (SCC) has been developed as a type of concrete capable of filling narrow gaps in highly reinforced areas of a mold without internal or external vibration. Bleeding and segregation in SCC can be prevented by the addition of superplasticizers. Due to these favorable properties, SCC has been adopted worldwide. The workability of SCC is closely related to its yield stress and plastic viscosity levels. Therefore, the accurate prediction of yield stress and plastic viscosity of SCC has certain advantages. Predictions of the shear stress and plastic viscosity of SCC is presented in the current study using four different ensemble machine learning techniques: Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), random forest, and Categorical Gradient Boosting (CatBoost). A new database containing the results of slump flow, V-funnel, and L-Box tests with the corresponding shear stress and plastic viscosity values was curated from the literature to develop these ensemble learning models. The performances of these algorithms were compared using state-of-the-art statistical measures of accuracy. Afterward, the output of these ensemble learning algorithms was interpreted with the help of SHapley Additive exPlanations (SHAP) analysis and individual conditional expectation (ICE) plots. Each input variable’s effect on the predictions of the model and their interdependencies have been illustrated. Highly accurate predictions could be achieved with a coefficient of determination greater than 0.96 for both shear stress and plastic viscosity.

Performance Enhancement of Radial Power Distribution Networks Using Network Reconfiguration and Optimal Planning of Solar Photovoltaic-Based Distributed Generation and Shunt Capacitors

Abstract: In this work, an efficient hybrid optimization approach entitled harmony search and particle artificial bee colony algorithm is proposed to deal with the distribution network reconfiguration and solar photovoltaic-based distributed generation and shunt capacitor deployment in power distribution networks to improve the operating performance of power distribution networks. The proposed hybrid algorithm combines the exploration and exploitation capability of both algorithms to achieve optimal results. The optimization problem is formalized which includes distributed generation and shunt capacitor locations, open/close state of switches as discrete decision variables, and the optimum operating point of compensation devices as continuous variables. An efficient spanning tree approach is utilized to track the optimal topology of the network. The validity of the proposed hybrid algorithm in handling the optimal planning problem of the distribution network is assured through eight different operating scenarios at three discrete load levels. The efficiency of the proposed performance enhancement approaches was validated using 69 node and 118 node distribution networks. The obtained results are compared against similar techniques presented in the literature.

An Overview of the Application of Harmony Search for Chemical Engineering Optimization

Abstract: Harmony search algorithm and its variants have been used in several applications in medicine, telecommunications, computer science, and engineering. This article reviews the global and multi-objective optimization for chemical engineering using harmony search. The main features of the HS method and several of its popular variants and hybrid versions including their relevant algorithm characteristics are described and discussed. A variety of global and multi-objective optimization problems from chemical engineering and their resolution using HS-based methods are also included. These problems involve thermodynamic calculations (phase stability analysis, phase equilibrium calculations, parameter estimation, and azeotrope calculation), heat exchanger design, distillation simulation, life cycle analysis, and water distribution systems, among others. Remarks on future developments of HS and its related algorithms for global and multi-objective optimization in chemical engineering are also provided in this review. HS is a reliable and promising stochastic optimizer to resolve challenging global and multi-objective optimization problems for process systems engineering.

Optimum Design of Reinforced Concrete Folded Plate Structures to ACI 318-11 Using Soft Computing Algorithm

Abstract: In this paper, an optimum design algorithm is presented for reinforced concrete folded plate structures. The design provisions are implemented by ACI 318-11 and ACI 318.2-14, which are quite complex to apply. The design variables are divided into three classes. The first class refers to the variables involving the plates, which are the number of supports, thicknesses of the plates, configurations of longitudinal and transverse reinforcement, span length of each plate, and angle of inclination of the inclined plates. The second class consists of the variables involving the auxiliary members’ (beams and diaphragms) depth and breadth and the configurations of longitudinal and shear reinforcement. The third class of variables can be the supporting columns, which involve the dimensions of the column along each axis and the configurations of longitudinal and shear reinforcement. The objective function is considered as the total cost of the folded plate structure, which consists of the cost of concrete, reinforcement, and formwork that is required to construct the building. With such formulation, the design problem becomes a discrete nonlinear programming problem. Its solution is obtained by using three different soft computing techniques, which are artificial bee colony, differential evolution, and enhanced beetle antennae search. The enhancement suggested makes use of the population of beetles instead of one, as is the case in the standard algorithm. With this novel improvement, the beetle antennae search algorithm became very efficient. Two folded plate structures are designed by the proposed optimum design algorithm. It is observed that the differential evolution algorithm performed better than the other two metaheuristics and achieved the cheapest solution.

Cantilever Soldier Pile Design: The Multiobjective Optimization of Cost and CO2 Emission via Pareto Front Analysis

Abstract: In the context of this study, it is focused on the design of cantilever soldier piles under the concept of Pareto optimality with multiobjective analyses of cost and CO2 emission considering the change in the excavation depth, the shear strength parameters of the foundation soil strata, and the unit costs and unit emission amounts of structural materials. Considering this aim, the harmony search algorithm was used as a tool to achieve the integrated effects of the solution variants. The lateral response of the soil mass was determined based on the active Rankine earth pressure theory and the design process was shaped according to the beams on the elastic foundation soil assumption. Moreover, the specification envisaged by the American Concrete Institute (ACI 318-11) was used to control the structural requirements of the design. Pareto front graphs and also design charts were created to achieve the eco- and cost optimization, simultaneously, for the design with arbitrarily selected cases to compare the results of the multiobjective analysis to minimize both the cost and the CO2 emission.

Quantitative and Qualitative Analysis of Harmony Search Algorithm in Geomechanics and Its Applications

Abstract: The harmony search (HS) algorithm is one of the meta-heuristic algorithms that was inspired by the concept of the musical process with the aim of harmony, to achieve the best solution. In comparison with other meta-heuristic algorithms, one of the most significant characteristics of this algorithm that has increased the flexibility of the algorithm in search of solution spaces is the use of all the solutions in its memory. The literature review shows that, according to the high efficiency of the harmony search algorithm, it has been widely used in various sciences in recent years. Hence, the main purpose of this study is to review the applications of the harmony search algorithm in geomechanics which is a significant research topic in the engineering and academic sectors. For this purpose, articles of geomechanics including the two main disciplines, namely soil mechanics and rock mechanics, are evaluated from 2011 to 2021. Also, two qualitative and quantitative investigations are applied to review articles based on the Web of Science (WOS) platform. This study indicates that the harmony search algorithm can be applied as a powerful tool for modeling some problems involved in geomechanics.

Harmony Search Algorithm with Reduction of Variable Value Range

Abstract: 본 논문에서는 확률적으로 해 공간을 탐색하는 하모니서치 알고리즘의 탐색 효율 향상을 위해서, 알고리즘 파라미터값을 조절하던 기존 연구들과는 달리, 결정 변수들의 값범위를 특정 조건을 만족하거나 시간의 흐름에 따라 축소 시켜가면서 해 공간의 크기를 줄여 확률적으로 최적해에 도달할 확률을 높여보고자 하였다. 그 결과 너무 급격하게 작은 범위까지 축소시킬 경우, 전역 최적 해를 찾지 못할 확률이 더 높아진다는 사실을 확인 할 수 있었으며, 비교적 큰 범위로만 축소시킨 경우에는 조건에 따라 기존의 고정된 변수 범위 방식보다 좋은 결과를 보임으로써, 알고리즘 성능 개선에 대한 가능성을 볼 수 있었다.

A Case Study on Renewable Energy Sources, Power Demand, and Policies in the States of South India—Development of a Thermoelectric Model

Abstract: This work aims to perform a holistic review regarding renewable energy mix, power production approaches, demand scenarios, power policies, and investments with respect to clean energy production in the southern states of India. Further, a thermoelectric-generator model is proposed to meet rural demands using a proposed solar dish collector technology. The proposed model is based on the idea of employing a parabolic concentrator and a thermoelectric (TE) module to generate electricity directly from the sun’s energy. A parabolic dish collector with an aperture of 1.11 m is used to collect sunlight and concentrate it onto a receiver plate with an area of 1.56 m in the proposed TE solar concentrator. The concentrated solar thermal energy is converted directly into electrical energy by using a bismuth telluride (BiTe)-based TE module mounted on the receiver plate. A rectangular fin heatsink, coupled with a fan, is employed to remove heat from the TE module’s cool side, and a tracking device is used to track the sun continuously. The experimental results show considerable agreement with the mathematical model as well as its potential applications. Solar thermal power generation plays a crucial part in bridging the demand–supply gap for electricity, and it can be achieved through rural electrification using the proposed solar dish collector technology, which typically has a 10 to 25 kW capacity per dish and uses a Stirling engine to generate power. Here the experimentation work generates a voltage of 11.6 V, a current of 0.7 A, and a power of 10.5 W that can be used for rural electrification, especially for domestic loads.

The Development of a Suicidal Ideation Predictive Model for Community-Dwelling Elderly Aged >55 Years

Abstract: Purpose Suicide is an important health and social concern worldwide. Both suicidal ideation and suicide rates are higher in the elderly population than in other age groups; thus, more careful attention and targeted interventions are required. Therefore, we have developed a model to predict suicidal ideation in the community-dwelling elderly aged of >55 years. Patients and Methods A random forest algorithm was applied to those who participated in the Korea Welfare Panel. We used a total of 26 variables as potential predictors. To resolve the imbalance in the dataset resulting from the low frequency of suicidal ideation, training was performed by applying the synthetic minority oversampling technique. The performance index was calculated by applying the predictive model to the test set, which was not included in the training process. Results A total of 6410 elderly Korean aged of >55 (mean, 71.48; standard deviation, 9.56) years were included in the analysis, of which 2.7% had suicidal ideation. The results for predicting suicidal ideation using the 26 chosen variables showed an AUC of 0.879, accuracy of 0.871, sensitivity of 0.750, and specificity of 0.874. The most significant variable in the predictive model was the severity of depression, followed by life satisfaction and self-esteem factors. Basic demographic variables such as age and gender demonstrated a relatively small effect. Conclusion Machine learning can be used to create algorithms for predicting suicidal ideation in community-dwelling elderly. However, there are limitations to predicting future suicidal ideation. A predictive model that includes both biological and cognitive indicators should be created in the future.

Review on Theory and Applications of Harmony Search Algorithm based on Korea Citation Index

Abstract: 세계적으로 연구의 영향력이 있는 과학기술논문들을 모아 SCI (Science Citation Index) 데이터베이스에서 관리한다. 비슷하게 국내에서도 KCI (Korea Citation Index)를 만들어 논문을 관리하고 있다. 본 연구에서는 그동안 KCI에 등재된 하모니 서치 관련 국문 논문에 대한 광범위한 리뷰를 하였다. 하모니 서치는 음악에서 영감을 받은 지능형 최적화 알고리즘으로 그동안 다양한 문제에 적용되었는데 본 리뷰에서는 이론분야 (알고리즘 구조개선, 알고리즘간의 융합)나 응용분야 (토목공학, 전기/전자/통신공학, 컴퓨터학, 기타공학 및 의사결정분야)의 주요한 60여편의 논문을 선정하여 요약정리 하였다. 이를 통해 그동안 알고리즘이 국내에 적용된 분야를 확인 할 수 있었고 또 추후 나아가야할 연구의 방향을 제시하였다.

Prediction of Photovoltaic Generation Using Machine Learning Models with Various Weight Optimization Techniques

Abstract: 본 논문에서는 충남 홍성지역의 상업운전 중인 1MW급 태양광 발전소와 주변지역의 기상조건을 근거로 태양광 발전량을 머신러닝 기법과 통계기법으로 예측하고 비교해보았다. 모형의 입력자료는 홍성지역의 약 9개월간 시간대별 실제발전량과 주변지역의 시간별 습도, 일조시간, 일사량을 사용하였으며, 각 방법별로 학습과 평가를 수행하였다. 계산결과 기존의 통계기법보다는 하모니 서치기법과 결합된 신경망 모형이 오차는 더 줄이고 결정계수는 더 높였다. 이를 통해 태양광발전원의 간헐적인 전력품질을 개선하고 분산형 전원확대에 큰 도움이 될 것으로 기대된다.