Hybridizing surrogate techniques, rough sets and evolutionary algorithms to efficiently solve multi-objective optimization problems

This article presents a sufficient comparison of two types of advanced non-parametric classifiers implemented in remote sensing for land cover classification. A SPOT-5 HRG image of Yanqing County, Beijing, China, was used, in which agriculture and forest dominate land use. Artificial neural networks (ANNs), including the adaptive backpropagation (ABP) algorithm, Levenberg–Marquardt (LM) algorithm, Quasi-Newton (QN) algorithm and radial basis function (RBF) were carefully tested. The LM–ANN and RBF–ANN, which outperform the other two, were selected to make a detailed comparison with support vector machines (SVMs). The experiments show that those well-trained ANNs and SVMs have no significant difference in classification accuracy, but the SVM usually performs slightly better. Analysis of the effect of the training set size highlights that the SVM classifier has great tolerance on a small training set and avoids the problem of insufficient training of ANN classifiers. The testing also illustrates that the ANNs and SVMs can vary greatly with regard to training time. The LM–ANN can converge very quickly but not in a stable manner. By contrast, the training of RBF–ANN and SVM classifiers is fast and can be repeatable.

Review of <i>Environmental and Hydrological Systems Modeling</i> by A. W. JayawardenaCRC Press Taylor &amp; Francis Group, Boca Raton, FL 33487; 2014; ISBN 978-0-415-46532-8; 516 pp.; $99.95.

Flooding causes several threats with outcomes which include peril to human and animal life, damage to property, and adversity to agricultural fields. Therefore, flood prediction is of prime importance for reducing loss of life and devastation to property. To model complex nature of hydrologic processes artificial neural network (ANN) tool is effectively being utilized for modelling different nonlinear relationships, and has proved to be an appropriate method for flood prediction. Present study investigated relative accuracy of radial basis function neural network (RBFNN) and support vector machine (SVM) models combined with Firefly Algorithm (FA) in predicting river flood discharge and contrasted with that of regular ANN, RBFNN and SVM models. Monthly river flow data of Silchar and Dholai stations located in Cachar district of Assam, India are utilized for the present study. For assessing model performance, coefficient of determination (R2), mean square error (MSE) and root mean square error (RMSE) were measured. Evaluation of outcomes shows that both RBF-FA (radial basis function - firefly algorithm) and SVM-FA (support vector machine - firefly algorithm) hybrid models give more precise forecasting results than RBFNN, FFBPNN (feed forward back propagation neural network) and SVM models. Yet, it can be observed that SVM-FA model give better forecasting outputs with R2 value 0.9818 than RBF-FA model. Results also reveal that simple SVM model performs marginally better than simple ANN model.

The main goal of this study was to discover knowledge from data about Porous Asphalt Concrete (PAC) roads to achieve a better understanding of the behavior of them and via this understanding improve pavement quality and enhance its lifespan. The knowledge discovery process includes five steps, being understanding the problem, understanding the data, data preparation, data mining (modeling), and the interpretation/evaluation of the results of the models. At the moment, almost 75% of the Dutch motorways network has a PAC top layer. The main damage of PAC is raveling, which is when the top layer of the road loses stones. The SHRP-NL databases provided ten years of material property data from PAC roads. The data for climate and traffic were obtained from databases of the Royal Dutch Meteorological Institute (KNMI) and the Ministry of Transport and Water Management, respectively. Due to the low number of data points (74 data points), an extensive variable selection was performed using eight different methods to determine the four or five most influential input variables and consequently reduce the input dimension. These methods were decision trees, genetic polynomial, artificial neural network, rough set theory, correlation based variable selection with bidirectional and genetic search, wrappers of neural network with genetic search, and relief ranking filter. The modeling step resulted in 8 intelligent models which were developed using two prediction techniques, being artificial neural networks and support vector machines and two rule-based techniques, being decision trees and rough set theory. Taking the low number of data points into account, the prediction models showed a good performance (R2 = 0.95). The rule based models were transparent and easy to interpret but performed less.KeywordsSupport Vector MachineData MiningArtificial Neural NetworkTest SectionKnowledge DiscoveryThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Stuck pipe incidents are one of the contributors to non-productive time (NPT), where they can result in a higher well cost. This research investigates the feasibility of applying machine learning to predict events of stuck pipes during drilling operations in petroleum fields. The predictive model aims to predict the occurrence of stuck pipes so that relevant drilling operation personnel are warned to enact a mitigation plan to prevent stuck pipes. Two machine learning methodologies were studied in this research, namely, the artificial neural network (ANN) and support vector machine (SVM). A total of 268 data sets were successfully collected through data extraction for the well drilling operation. The data also consist of the parameters with which the stuck pipes occurred during the drilling operations. These drilling parameters include information such as the properties of the drilling fluid, bottom-hole assembly (BHA) specification, state of the bore-hole and operating conditions. The R programming software was used to construct both the ANN and SVM machine learning models. The prediction performance of the machine learning models was evaluated in terms of accuracy, sensitivity and specificity. Sensitivity analysis was conducted on these two machine learning models. For the ANN, two activation functions—namely, the logistic activation function and hyperbolic tangent activation function—were tested. Additionally, all the possible combinations of network structures, from [19, 1, 1, 1, 1] to [19, 10, 10, 10, 1], were tested for each activation function. For the SVM, three kernel functions—namely, linear, Radial Basis Function (RBF) and polynomial—were tested. Apart from that, SVM hyper-parameters such as the regularization factor (C), sigma (σ) and degree (D) were used in sensitivity analysis as well. The results from the sensitivity analysis demonstrate that the best ANN model managed to achieve an 88.89% accuracy, 91.89% sensitivity and 86.36% specificity, whereas the best SVM model managed to achieve an 83.95% accuracy, 86.49% sensitivity and 81.82% specificity. Upon comparison, the ANN model is the better machine learning model in this study because its accuracy, sensitivity and specificity are consistently higher than those of the best SVM model. In conclusion, judging from the promising prediction accurateness as demonstrated in the results of this study, it is suggested that stuck pipe prediction using machine learning is indeed practical.

This paper addresses processing of spectrophotometric array signals based on genetic algorithms (GA) least square support vector machines (LS-SVM) regression to provide a powerful model for machine learning and data mining. The key to complete LS-SVM regression is to choose its optimal parameters. Due to their outstanding ability in solving global optimization problems in complex multidimensional search space, GA are used in this study to obtain the optimal parameter combination of the LS-SVM model. Experimental results showed the GA-LS-SVM method to be successful for simultaneous multicomponent determination even where severe overlap of spectra was present. KeywordsLeast squares support vector machines; Genetic algorithms; Spectrophotometric array signals; Overlapping spectra; Artificial intelligence Nowadays, with the application of photometric diode array detector and computers, rapid scanning commercial spectrophotometers are capable of quickly generating huge data consisting of hundreds and even thousands of absorbance values per spectrum. The array data named fullspectrum contain sufficient information to be able to determine the contents of various compounds. The main drawback of ultraviolet-visible (UV-VIS) is its poor selectivity because in many cases UV-VIS spectra display strong overlaps, especially some less specific and selective chromagenic reagents often give rise to strongly overlapped spectra in many cases. The combination of artificial intelligence methods with the computer-controlled spectrophotometers was proven to be effective in overcoming this difficulty [1-3]. Artificial neural network (ANN) is a form of artificial intelligence that mathematically simulates biological nervous system [4, 5]. However, ANN often has slow convergence, is prone to the existence of many local minima during training, and has a tendency of overfitting. Recently, a promising technology called support vector machines (SVM) has been used for classification and regression problems. SVM pioneered by Vapnik is a kind of machine learning method based on modern statistical learning theory and has notable properties including absence of local minima and high generalization ability [6, 7]. Suykens and his coworkers [8] introduced a modified version of SVM called least square SVM (LS-SVM) , which requires solving a set of linear equations instead of a quadratic programming problem and is much easier and computationally simpler than SVM. SVM and LS-SVM represent relatively recent artificial intelligence method and have found some applications in image analysis, classification and disease diagnosis etc. [9, 10]. It is worth mentioning that the success of LS-SVM model is highly dependent on the optimum choice of two parameters, the relative weight of regression error γ and the kernel width σ of radial basis function (RBF). Genetic algorithms (GA) [11, 12] introduced by John Holland are probabilistic optimization techniques based on natural evolution and genetics and Darwin’s theory of survival of the best. With their efficient and robust global search ability, GA are used to search two optimal parameters for the LS-SVM model simultaneously and automatically. The LS-SVM model then performs the regression task using these optimal parameters.

The results of eutrophication assessment can not only reflect the conditions of water quality and the status of pollution,but also provide some evidence and guidance for eutrophication controls,watershed managements and policy decisions. Essentially,the process of eutrophication assessment could be considered as a multi-index classification problem. However,the relationship between the eco-environmental factors and the eutrophication status is complex,nonlinear and uncertain. In recent years,a variety of artificial intelligent methods have been used for eutrophication assessment,such as fuzzy synthetic evaluation,fuzzy mathematics,grey cluster,grey situation decision,evolutionary algorithm and artificial neural network( ANN). These methods have been playing important roles in eutrophication assessment,but there are still uncertainty and inconsistency in the results. The fuzzy and grey methods have great subjectivity in determining the structures of evaluation functions and the weights of evaluation indexes,the evolutionary algorithm is mainly used for parameter optimization of existing evaluation models; and the ANN has inherent problems such as uncertainty of network structure, potential of local optimum and no guarantee of model generality.As a relatively new machine-learning algorithm,Support Vector Machine( SVM) has shown promising advantages in solving classification problems. The fundamental idea is to use certain kind of kernel functions to map the vectors in lower dimensional space to a higher dimensional space so that these vectors could be linearly classified into two parts,and then conducting a hyperplane that has the largest distance to the nearest vector of any class to make the separation. Although sharing some similarities to ANN in process of model building,SVM has entirely different theoretical basis. Despite its broad applications,the method has been merely used in lake eutrophication assessment. In this study,an eutrophication assessment model has been built by using the classification algorithm of LIBSVM( a simple,easy-to-use,and efficient software for SVM classification and regression),based on the learning data randomly generated from the existing eutrophication assessment standard for lakes and reservoirs. The model was then applied to the Taihu Lake,where data were collected from 33 monitoring sites during July to September in 2012. The results showed that there are 3 types of trophic status in the Taihu Lake with respect to space. The mesotrophic areas were mainly in the east part of the lake,and light eutrophication areas were mostly located in the central and eastern regions,and the moderate eutrophication areas were largely in the northwestern region. The eutrophication status of the entire lake is about light to moderate eutrophication. By comparing to the results from the well-accepted Linear Interpolation Scoring Method,the consistency is about 78.8%,indicating good effectiveness and applicability of the SVM method,owing to its addition feature of high convergence and generalization.

본 논문에서는 RST(Rough Set Theory)과 SVM(Support Vector Machine) 알고리즘을 이용한 RSIDS (RST and SVM based Intrusion Detection System)를 설계하였다. RSIDS는 PrePro(Preprocessing) 모듈, RRG(RST based Rule Generation) 모듈, 그리고 SAD(SVM based Attack Detection) 모듈로 구성된다. PrePro 모듈은 수집한 정보를 RSIDS의 데이터 형식에 맞게 변경한다. RRG 모듈은 공격 자료를 분석하여 공격 규칙을 생성하고, 그 규칙을 이용하여 대량화된 데이터에서 공격정보를 추출하고, 그리고 추출한 공격정보를 SAD 모듈에 전달한다. SAD 모듈은 추출된 공격 정보를 이용하여 공격을 탐지하여 관리자에게 통보한다. 그 결과, 기존의 SVM과 비교해볼 때, RSIDS는 평균 공격 탐지율 77.71%에서 85.28%로 향상되었으며, 평균 FPR은 13.25%에서 9.87%로 감소하였다. 따라서 RSIDS는 기존의 SVM을 이용한 공격 탐지 기법보다 향상되었다고 할 수 있다. This paper proposes a design of RSIDS(RST and SVM based Intrusion Detection System) using RST(Rough Set Theory) and SVM(Support Vector Machine) algorithm. The RSIDS consists of PrePro(PreProcessing) module, RRG(RST based Rule Generation) module, and SAD(SVM based Attack Detection) module. The PrePro module changes the collected information to the data format of RSIDS. The RRG module analyzes attack data, generates the rules of attacks, extracts attack information from the massive data by using these rules, and transfers the extracted attack information to the SAD module. The SAD module detects the attacks by using it, which the SAD module notifies to a manager. Therefore, compared to the existing SVM, the RSIDS improved average ADR(Attack Detection Ratio) from 77.71% to 85.28%, and reduced average FPR(False Positive ratio) from 13.25% to 9.87%. Thus, the RSIDS is estimated to have been improved, compared to the existing SVM.

Estimating the Technical Deterioration of Large-panel Residential Buildings Using Artificial Neural Networks

Nowadays, the Structural Building Health Damage Monitoring System (SBHDMS) is a crucial technology for predicting the civil building structures' health. SBHDMS contains abnormal changes in the buildings in terms of damage levels. Natural Disasters like Earthquakes, Floods, and cyclones affect the unusual changes in the buildings. If the building undergoes any natural disaster, the sensors capture the vibration data or change the buildings' structure. Due to the vibration data, these unusual changes can be analyzed. Here sensors or Machine Learning based Building Damage Prediction (MLBDP) are used for capturing and collecting the vibration data. This paper proposes a Novel Rough Set based Artificial Neural Network with Support Vector Machine (RAS) metaheuristic method. RAS method is used to predict the damaged building's vibration data levels captured by the sensors. For the feature reduction subset, we use one of the essential pre-processing method called the Rough set theory (RST) strategy. RAS has two contributions. The first one is the Support Vector Machine (SVM) classification method used for identifying the structures of the buildings. The artificial Neural Network (ANN) method used to predict the buildings' damage levels is the second contribution. The proposed method (RAS) is accurately predicting the conditions of the construction building structure and predicting the damage levels, without human intervention. Comparing the results states that the proposed method accuracy is better than SVM's classification methods, ANN. The prediction analysis depicts that the RAS method can effectively detect the damage levels.

Unlike calculation of scour depth around of a single pier, estimation of scour depth around group piers is a complex problem. In this research, four types of artificial neural networks (ANNs) were applied multi layer perceptron (MLP), radial basis function (RBF), neuro fuzzy inference system (ANFIS), and support vector machine (SVM). The inputs of ANNs were coordinates of considered points in the channel (X, Y), size of pier, flow depth, flow discharge, flow velocity, and critical velocity for inception of sediment transport. The trained methods were momentum and Levenberg–Marquardt (LM) training methods. Also, genetic algorithm (GA) was applied for optimization of MLP and RBF. Two group piers were used (three circular piers and three square piers) in a channel with stable flow conditions, scouring of clear water, and uniform bed particles (with D50 = 1.31 mm). Outputs of different ANNs (scour depth) were compared with observed data using of performance criteria correlation coefficient (R), mean square error (MSE), and mean absolute error (MAE). For circular piers, between square piers and behind of gear square pier, the best ANN is RBF-GA, while in front of first square pier, the best ANN is MLP-GA. The best ANNs have two hidden layers, and their training method is the Levenberg–Marquardt (LM). The values of R, MSE, and MAE of RBF-GA are 0.997, 1.66 mm2, and 0.9 mm, and the values of R, MSE, and MAE of MLP-GA are 0.997, 2.55 mm2, and 1.16 mm. Also, the sensitive analysis shows that threshold velocity (Uc) is the most effective factor on scour depth

Rough set theory (RST) can mine useful information from a large number of data and generate decision rules without prior knowledge. Support vector machines (SVMs) have good classification performances and good capabilities of fault-tolerance and generalization. To inherit the merits of both RST and SVMs, a hybrid classifier called rough set support vector machines (RS-SVMs) is proposed to recognize radar emitter signals in this paper. RST is used as preprocessing step to improve the performances of SVMs. A large number of experimental results show that RS-SVMs achieve lower recognition error rates than SVMs and RS-SVMs have stronger capabilities of classification and generalization than SVMs, especially when the number of training samples is small. RS-SVMs are superior to SVMs greatly.

Load forecasting is key for the optimal control of heating, ventilating, and air-conditioning. However, accurate forecasting modeling requires the ability of selecting relevant factors so that the influences of the irrelevant factors can be reduced substantially. This paper presents a novel hybrid method combining rough set theory and support vector machine network (RSSV). Rough set (RS) theory is applied to find the relevant factors of the load, which are used as the inputs of support vector machine (SVM) to predict cooling load. To improve the accuracy and enhance the robustness of load forecasting results, a general load prediction model synthesizing multi-RSSV (MRSSV) is presented so as to make full use of redundant information. Optimum principle is employed to deduce the weights of each RSSV model. Actual prediction results for a real HVAC system show that the MRSSV forecasting model, whose relative error turned out to be within 4%, may be better than those models using individual RSSV, recursive least squares (RLS), and autoregressive integrated moving average (ARIMA). In addition, individual RSSV forecasting results are also better than that of ARIMA.

This article aims to provide a concise review on the state-of-the-art application of soft computing techniques to predict various parameters in tunnelling and underground excavations. Various soft computing techniques involving data mining and machine learning have found their application in the tunnelling-related problems. This article explores the application of artificial neural networks (ANNs), radial basis functions (RBFs), decision trees (DTs), random forest (RF) method, support vector machines (SVMs), nonlinear regression methods such as multi-adaptive regression splines (MARS), and hybrid intelligent models in the prediction of engineering response of tunnels and underground excavations. They help in predicting crucial parameters that decide the serviceability of tunnels and associated structures lying above the tunnel cavity. The researchers working in this domain have utilized the real-time data available from the construction projects in creating various machine learning models. It is observed that there are no proper guidelines to obtain optimal network architecture in ANN for assessing the parameters of the stated problem. RBFs and wavelet neural networks, which evolved from ANN, showed improvement in prediction accuracy. SVM and MARS methods are ornamented with improved computational efficiency and robustness of the algorithm. DT and RF methods are interpretable and computationally less expensive compared to neural networks. Hybrid intelligent models provided globally optimal solutions for nonlinear complex problems than simple neural network models. The limitations of the adopted soft computing methods are also emphasized. Overall, this article provides an intricate insight on the various soft computing techniques used by researchers to improve the performance of the machine learning models.

In this paper, a classifier based on a combination of Rough Set and 1-v-1 (one-versus-one) Support Vector Machine for Content Based Image Retrieval system is presented. Some problems of 1-v-1 Support Vector Machine can be reduced using Rough Set. With Rough Set, a 1-v-1 Support Vector Machine can provide good results when dealing with incomplete and uncertain data and features. In addition, boundary region in Rough Set can reduce the error rate. Storage requirements are reduced when compared to the conventional 1-v-1 Support Vector Machine. This classifier has better semantic interpretation of the classification process. We compare our Content Based Image Retrieval system with other image retrieval systems that uses neural network, K-nearest neighbour and Support Vector Machine as the classifier in their methodology. Experiments are carried out using a standard Corel dataset to test the accuracy and robustness of the proposed system. The experiment results show the proposed method can retrieve images more efficiently than other methods in comparison.