Anh-Duc Pham

Smart Artificial Firefly Colony Algorithm-Based Support Vector Regression for Enhanced Forecasting in Civil Engineering

Advanced data mining techniques are potential tools for solving civil engineering (CE) problems. This study proposes a novel smart artificial firefly colony algorithm-based support vector regression (SAFCA-SVR) system that integrates firefly algorithm (FA), chaotic maps, adaptive inertia weight, Levy flight, and least squares support vector regression (LS-SVR). First, adaptive approach and randomization methods are incorporated in FA to construct a novel and highly effective metaheuristic algorithm for global optimization. The enhanced FA is then used to optimize parameters in LS-SVR model. The proposed system is validated by comparing its performance with those of empirical methods and previous works via cross-validation algorithm and hypothesis test through the real-world engineering cases. Specifically, high-performance concrete, resilient modulus of subgrade soils, and building cooling load are used as case studies. The SAFCA-SVR achieved 8.8%–91.3% better error rates than those of previous works. Analytical results confirm that using the proposed hybrid system significantly improves the accuracy in solving CE problems.

Optimizing parameters of support vector machine using fast messy genetic algorithm for dispute classification

Hybrid system is a potential tool to deal with construction engineering and management problems. This study proposes an optimized hybrid artificial intelligence model to integrate a fast messy genetic algorithm (fmGA) with a support vector machine (SVM). The fmGA-based SVM (GASVM) is used for early prediction of dispute propensity in the initial phase of public-private partnership projects. Particularly, the SVM mainly provides learning and curve fitting while the fmGA optimizes SVM parameters. Measures in term of accuracy, precision, sensitivity, specificity, and area under the curve and synthesis index are used for performance evaluation of proposed hybrid intelligence classification model. Experimental comparisons indicate that GASVM achieves better cross-fold prediction accuracy compared to other baseline models (i.e., CART, CHAID, QUEST, and C5.0) and previous works. The forecasting results provide the proactive-warning and decision-support information needed to manage potential disputes.

Hybrid artificial intelligence approach based on metaheuristic and machine learning for slope stability assessment

This research proposes an AI approach for slope evaluation.The method is based on the Least Squares Support Vector Classification.The Firefly Algorithm is used to optimize the assessment model.A dataset that contains 168 real slopes is utilized to construct the AI model.Experiments prove that the new method is a superior tool for slope evaluation. Slope stability assessment is a critical research area in civil engineering. Disastrous consequences of slope collapse necessitate better tools for predicting their occurrences. This research proposes a hybrid Artificial Intelligence (AI) for slope stability assessment based on metaheuristic and machine learning. The contribution of this study to the body of knowledge is multifold. First, advantages of the Firefly Algorithm (FA) and the Least Squares Support Vector Classification (LS-SVC) are combined to establish an integrated slope prediction model. Second, an inner cross-validation with the operating characteristic curve computation is embedded in the training process to reliably construct the machine learning model. Third, the FA, an effective and easily implemented metaheuristic, is employed to optimize the model construction process by appropriately selecting the LS-SVMs hyper-parameters. Finally, a dataset that contains 168 real cases of slope evaluation, recorded in various countries, is used to establish and confirm the proposed hybrid approach. Experimental results demonstrate that the new hybrid AI model has achieved roughly 4% improvement in classification accuracy compared with other benchmark methods.

Predicting Compressive Strength of High-Performance Concrete Using Metaheuristic-Optimized Least Squares Support Vector Regression

AbstractThis research establishes a novel model for predicting high-performance concrete (HPC) compressive strength, which hybridizes the firefly algorithm (FA) and the least squares support vector regression (LS-SVR). The LS-SVR is utilized to discover the functional relationship between the compressive strength and HPC components. To achieve the most desirable prediction model that features both modeling accuracy and generalization capability, the FA is employed to optimize the LS-SVR. To construct and verify the proposed model, this study has collected a database consisting of 239 HPC strength tests from an infrastructure development project in central Vietnam. Experimental results have demonstrated that the new model is a promising alternative to predict HPC strength.

Nature-inspired metaheuristic optimization in least squares support vector regression for obtaining bridge scour information

A novel model is proposed for enhancing prediction accuracy in engineering design.A nature-inspired metaheuristic information model is constructed for use in global optimization.The parameters of LS-SVR are optimized using an enhanced firefly algorithm.The proposed hybrid model outperforms other predictive methods through cross-fold validation and hypothesis testing.The approach can be effectively applied to prediction of scour depth around bridge piers. The scouring of stream and river channels is a complicated phenomenon; it is a function of flow energy, sediment transport, and bridge substructure characteristics that challenges bridge engineers worldwide. Scour is also a major cause of bridge failure, thus contributing substantially to the total construction and maintenance costs of a typical bridge. Accurately estimating local scour depth near bridge piers is vital in engineering design and management. Thus, an effective technique is necessary to estimate the safety and economy of bridge design and management projects. This study developed a novel hybrid smart artificial firefly colony algorithm (SAFCA)-based support vector regression (SAFCAS) model for predicting bridge scour depth near piers. The SAFCAS integrates a firefly algorithm (FA), chaotic maps, adaptive inertia weight, Lvy flight, and support vector regression (SVR). First, adaptive approaches and randomization methods were incorporated into the FA to construct a novel metaheuristic algorithm for global optimization. An SVR model was then optimized through SAFCA to maximize its generalization performance. Laboratory and field data reported in the literature were applied to evaluate the proposed hybrid model. The effectiveness of the proposed intelligence fusion system was evaluated by comparing the SAFCAS modeling results with those of numerical predictive models and with the results of empirical methods. For the bridge scour depth problem, the proposed hybrid model achieved 3.99%87.12% better error rates compared with other predictive methods, as measured through cross-fold validation algorithms and hypothesis testing. The resulting SAFCAS model can infer decisive information to assist civil engineers in designing safe and cost-effective bridge substructures.

A novel time series prediction approach based on a hybridization of least squares support vector regression and swarm intelligence

This research aims at establishing a novel hybrid artificial intelligence (AI) approach, named as firefly-tuned least squares support vector regression for time series prediction (FLSVRTSP). The proposed model utilizes the least squares support vector regression (LS-SVR) as a supervised learning technique to generalize the mapping function between input and output of time series data. In order to optimize the LS-SVRs tuning parameters, the FLSVRTSP incorporates the firefly algorithm (FA) as the search engine. Consequently, the newly construction model can learn from historical data and carry out prediction autonomously without any prior knowledge in parameter setting. Experimental results and comparison have demonstrated that the FLSVRTSP has achieved a significant improvement in forecasting accuracy when predicting both artificial and real-world time series data. Hence, the proposed hybrid approach is a promising alternative for assisting decision-makers to better cope with time series prediction.

Estimating Compressive Strength of High Performance Concrete with Gaussian Process Regression Model

This research carries out a comparative study to investigate a machine learning solution that employs the Gaussian Process Regression (GPR) for modeling compressive strength of high-performance concrete (HPC). This machine learning approach is utilized to establish the nonlinear functional mapping between the compressive strength and HPC ingredients. To train and verify the aforementioned prediction model, a data set containing 239 HPC experimental tests, recorded from an overpass construction project in Danang City (Vietnam), has been collected for this study. Based on experimental outcomes, prediction results of the GPR model are superior to those of the Least Squares Support Vector Machine and the Artificial Neural Network. Furthermore, GPR model is strongly recommended for estimating HPC strength because this method demonstrates good learning performance and can inherently express prediction outputs coupled with prediction intervals.

Opposition Multiple Objective Symbiotic Organisms Search (OMOSOS) for Time, Cost, Quality and Work Continuity Tradeoff in Repetitive Projects

Abstract Construction managers often face with projects containing multiple units wherein activities repeat from unit to unit. Therefore effective resource management is crucial in terms of project duration, cost and quality. Accordingly, researchers have developed several models to aid planners in developing practical and near-optimal schedules for repetitive projects. Despite their undeniable benefits, such models lack the ability of pure simultaneous optimization because existing methodologies optimize the schedule with respect to a single factor, to achieve minimum duration, total cost, resource work breaks or various combinations, respectively. This study introduces a novel approach called “opposition multiple objective symbiotic organisms search” (OMOSOS) for scheduling repetitive projects. The proposed algorithm used an opposition-based learning technique for population initialization and for generation jumping. Further, this study integrated a scheduling module (M1) to determine all project objectives including time, cost, quality and interruption. The proposed algorithm was implemented on two application examples in order to demonstrate its capabilities in optimizing the scheduling of repetitive construction projects. The results indicate that the OMOSOS approach is a powerful optimization technique and can assist project managers in selecting appropriate plan for project.

Estimating Concrete Workability Based on Slump Test with Least Squares Support Vector Regression

Concrete workability, quantified by concrete slump, is an important property of a concrete mixture. Concrete slump is generally known to affect the consistency, flowability, pumpability, compactibility, and harshness of a concrete mix. Hence, an accurate prediction of this property is a practical need of construction engineers. This research proposes a machine learning model for predicting concrete slump based on the Least Squares Support Vector Regression (LS-SVR). LS-SVR is employed to model the nonlinear mapping between the mix components and slump values. Since the learning process of the LS-SVR necessitates two hyperparameters, the regularization and the kernel parameters, the grid search method is employed search for the most desirable set of hyperparameters. Furthermore, to construct the hybrid model, this research collected a dataset including actual concrete slump tests from a hydroelectric dam construction project in Vietnam. Experimental results show that the proposed model is capable of predicting concrete slump accurately.