Search results

Recently, the modelling and simulation of switched systems containing new nonlinear components in electronics and power electronics industry have gained importance. In this paper, both feed‐forward artificial neural networks (ANN) and adaptive network‐based fuzzy inference systems (ANFIS) have been applied to switched circuits and systems. Then their performances have been compared in this contribution by developed simulation programs. It has been shown that ANFIS require less training time and offer better performance than those of ANN. In addition, ANFIS using “clustering algorithm” to generate the rules and the numbers of membership functions gives a smaller number of parameters, better performance and less training time than those of ANFIS using “grid partition” to generate the rules. The work not only demonstrates the advantage of the ANFIS architecture using clustering algorithm but also highlights the advantages of the architecture for hardware realizations.

The aim of this study is to propose an efficient rule extraction and integration approach for identifying phishing websites. The proposed approach can elucidate patterns of phishing websites and identify them accurately.

Hyperlink indicators along with URL-based features are used to build the identification model. In the proposed approach, very simple rules are first extracted based on individual features to provide meaningful and easy-to-understand rules. Then, the F-measure score is used to select high-quality rules for identifying phishing websites. To construct a reliable and promising phishing website identification model, the selected rules are integrated using a simple neural network model.

Experiments conducted using self-collected and benchmark data sets show that the proposed approach outperforms 16 commonly used classifiers (including seven non–rule-based and four rule-based classifiers as well as five deep learning models) in terms of interpretability and identification performance.

Investigating patterns of phishing websites based on hyperlink indicators using the efficient rule-based approach is innovative. It is not only helpful for identifying phishing websites, but also beneficial for extracting simple and understandable rules.

This study demonstrates two visual methodologies to support analysts using artificial neural networks (ANNs) in data mining operations. The first part of the paper illustrates the differences and similarities between various learning rules that might be employed by ANN data miners. Since different learning rules lead to different connection weights and stability coefficients, a graphical representation of the data that provides a novel visual means of discerning these similarities and differences is demonstrated. The second part of this research demonstrates a methodology for ANN model variable interpretation that uses network connection weights. It uses empirical marketing data to optimize an ANN and response elasticity graphs are built for each ANN model variable by plotting the derivative of the network output with respect to each variable, while changing network input in equal increments across the range of inputs for each variable. Finally, this paper concludes that such an approach to ANN model interpretation can provide data miners with a rich interpretation of variable importance.

Auditors are required to perform analytical procedures during the planning and concluding phases of the audit. Such procedures typically use data aggregated at a high level. The authors investigate whether artificial neural networks, a more sophisticated technique for analytical review than typically used by auditors, may be effective when using high level data.

Data from companies operating in the dairy industry were used to train an artificial neural network. Data with and without material seeded errors were used to test alternative techniques.

Results suggest that the artificial neural network approach was not significantly more effective (taking into account both Type I and II errors) than traditional ratio and regression analysis, and none of the three approaches provided more overall effectiveness than a purely random procedure. However, the artificial neural network approach did yield considerably fewer Type II errors than the other methods, which suggests artificial neural networks could be a candidate to improve the performance of analytical procedures in circumstances where Type II error rates are the primary concern of the auditor.

The authors extend the work of Coakley and Brown (1983) by investigating the application of artificial neural networks as an analytical procedure using aggregated data. Furthermore, the authors examine multiple companies from one industry and supplement financial information with both exogenous industry and macro-economic data.

The Contingency Outsourcing Relationship (CORE) model originated from the Four Outsourcing Relationship Types (FORT) model and the CORE model is used in the globalized facility management (FM) industry while the FORT model is originally used in the global information technology industry. The purpose of this paper is to analyze the CORE model through the rankings of relationship between a client and a globalized FM service provider from the perspective of the FM service provider in one of the four categories (i.e. in-house, technical expertise, commitment and common goals) and the application of this model with the aid of artificial neural networks (ANNs).

A quantitative methodology using a survey is used to analyze the four types of outsourcing categories. First, the background theory and a set of rules of the CORE is introduced and discussed regarding the proper ways to identify the rankings collected from the survey.

The study reveals that an interesting understanding of the outsourcing categories can be systematically implemented into the FM outsourcing relationships through the methodology of scientific artificial intelligence. FM outsourcing categorization may help to define the appropriate relationship; as either not too aggressive or too passive.

The outcome generated from the ANN can be considered a strong and solid reference to assess and define the existing outsourcing relationships between the stakeholders and the service providers with the goal to assign an outsourcing category to the service provider based on the learnt rules.

To improve the quality of the additive manufacturing (AM) products, it is necessary to estimate surface roughness distribution in advance. Although surface roughness estimation has been previously studied, factors leading to the creation of a rough surface and a comprehensive test for model validation have not been adequately investigated. Therefore, this paper aims to establish a robust model using empirical data based on optimized artificial neural networks (ANNs) to estimate the surface roughness distribution in fused deposition modelling parts. Accordingly, process parameters such as time, cost and quality should be optimized in the process planning stage.

Process parameters were selected via a literature review of surface roughness estimation modelling by analytical and empirical methods, and then a specific test part was fabricated to provide a complete evaluation of the proposed model. The ANN structure was optimized by trial and error method and evolutionary algorithms. A novel methodology based on the combination of the intelligent algorithms including the ANN, linked to the particle swarm optimization (PSO) and imperialist competitive algorithm (ICA), was developed. The PSOICA algorithm was implemented to increase the capability of the ANN to perform much faster and converge more precisely to favorable results. The performances of the ANN models were compared to the most well-known analytical models at build angle intervals of equal size. The most effective process variable was found by sensitivity analysis. The validity of proposed model was studied comprehensively where different truncheon parts and medical case studies including molar tooth, skull, femur and a custom-made hip stem were built.

This paper presents several improvements in surface roughness distribution modelling including a more suitable method for process parameter selection according to the design criteria and improvements in the overall surface roughness of parts as compared to analytical methods. The optimized ANN based on the proposed advanced algorithm (PSOICA) represents precise estimation and faster convergence. The validity assessment confirms that the proposed methodology performs better in varied conditions and complex shapes.

This research fills an important gap in surface roughness distribution estimation modelling by using a test part designed for that purpose and optimized ANN models which uses purely empirical data. The novel PSOICA combination enhances the ability of the ANN to perform more accurately and quickly. The advantage in using actual surface roughness values is that all factors resulting in the creation of a rough surface are included, which is impossible if other methods are used.

The purpose of this paper is to develop three methods including artificial bee colony algorithm (ABC-ANN), regression and adaptive neural fuzzy inference system (ANFIS) to predict the environmental indicators for land leveling and to analysis the sensitivity of these parameters.

This paper develops three methods including artificial bee colony algorithm (ABC-ANN), regression and adaptive neural fuzzy inference system (ANFIS) to predict the environmental indicators for land leveling and to analysis the sensitivity of these parameters. So, several soil properties such as soil, cut/fill volume, soil compressibility factor, specific gravity, moisture content, slope, sand per cent and soil swelling index in energy consumption were investigated. A total of 90 samples were collected from three land areas with the selected grid size of (20 m × 20 m). Acquired data were used to develop accurate models for labor, energy (LE), fuel energy (FE), total machinery cost (TMC) and total machinery energy (TM).

By applying the three mentioned analyzing methods, the results of regression showed that, only three parameters of sand per cent, slope and soil, cut/fill volume had significant effects on energy consumption. All developed models (Regression, ANFIS and ABC-ANN) had satisfactory performance in predicting aforementioned parameters in various field conditions. The adaptive neural fuzzy inference system (ANFIS) has the most capability in prediction according to least RMSE and the highest R² value of 0.0143, 0.9990 for LE. The ABC-ANN has the most capability in prediction of the environmental and energy parameters with the least RMSE and the highest R² with the related values for TMC, FE and TME (0.0248, 0.9972), (0.0322, 0.9987) and (0.0161, 0.9994), respectively.

As land leveling with machines requires considerable amount of energy, optimizing energy consumption in land leveling operation is of a great importance. So, three approaches comprising: ABC-ANN, ANFIS as powerful and intensive methods and regression as a fast and simplex model have been tested and surveyed to predict the environmental indicators for land leveling and determine the best method. Hitherto, only a limited number of studies associated with energy consumption in land leveling have been done. In mentioned studies, energy was a function of the volume of excavation (cut/fill volume). Therefore, in this research, energy and cost of land leveling are functions of all the properties of the land including slope, coefficient of swelling, density of the soil, soil moisture, special weight and swelling index which will be thoroughly mentioned and discussed. In fact, predicting minimum cost of land leveling for field irrigation according to the field properties is the main goal of this research which is in direct relation with environment and weather pollution.

This paper aims to provide a predictive framework of customer churn through six stages for accurate prediction and preventing customer churn in the field of business.

The six stages are as follows: first, collection of customer behavioral data and preparation of the data; second, the formation of derived variables and selection of influential variables, using a method of discriminant analysis; third, selection of training and testing data and reviewing their proportion; fourth, the development of prediction models using simple, bagging and boosting versions of supervised machine learning; fifth, comparison of churn prediction models based on different versions of machine-learning methods and selected variables; and sixth, providing appropriate strategies based on the proposed model.

According to the results, five variables, the number of items, reception of returned items, the discount, the distribution time and the prize beside the recency, frequency and monetary (RFM) variables (RFMITSDP), were chosen as the best predictor variables. The proposed model with accuracy of 97.92 per cent, in comparison to RFM, had much better performance in churn prediction and among the supervised machine learning methods, artificial neural network (ANN) had the highest accuracy, and decision trees (DT) was the least accurate one. The results show the substantially superiority of boosting versions in prediction compared with simple and bagging models.

The period of the available data was limited to two years. The research data were limited to only one grocery store whereby it may not be applicable to other industries; therefore, generalizing the results to other business centers should be used with caution.

Business owners must try to enforce a clear rule to provide a prize for a certain number of purchased items. Of course, the prize can be something other than the purchased item. Business owners must accept the items returned by the customers for any reasons, and the conditions for accepting returned items and the deadline for accepting the returned items must be clearly communicated to the customers. Store owners must consider a discount for a certain amount of purchase from the store. They have to use an exponential rule to increase the discount when the amount of purchase is increased to encourage customers for more purchase. The managers of large stores must try to quickly deliver the ordered items, and they should use equipped and new transporting vehicles and skilled and friendly workforce for delivering the items. It is recommended that the types of services, the rules for prizes, the discount, the rules for accepting the returned items and the method of distributing the items must be prepared and shown in the store for all the customers to see. The special services and reward rules of the store must be communicated to the customers using new media such as social networks. To predict the customer behaviors based on the data, the future researchers should use the boosting method because it increases efficiency and accuracy of prediction. It is recommended that for predicting the customer behaviors, particularly their churning status, the ANN method be used. To extract and select the important and effective variables influencing customer behaviors, the discriminant analysis method can be used which is a very accurate and powerful method for predicting the classes of the customers.

The current study tries to fill this gap by considering five basic and important variables besides RFM in stores, i.e. prize, discount, accepting returns, delay in distribution and the number of items, so that the business owners can understand the role services such as prizes, discount, distribution and accepting returns play in retraining the customers and preventing them from churning. Another innovation of the current study is the comparison of machine-learning methods with their boosting and bagging versions, especially considering the fact that previous studies do not consider the bagging method. The other reason for the study is the conflicting results regarding the superiority of machine-learning methods in a more accurate prediction of customer behaviors, including churning. For example, some studies introduce ANN (Huang et al., 2010; Hung and Wang, 2004; Keramati et al., 2014; Runge et al., 2014), some introduce support vector machine ( Guo-en and Wei-dong, 2008; Vafeiadis et al., 2015; Yu et al., 2011) and some introduce DT (Freund and Schapire, 1996; Qureshi et al., 2013; Umayaparvathi and Iyakutti, 2012) as the best predictor, confusing the users of the results of these studies regarding the best prediction method. The current study identifies the best prediction method specifically in the field of store businesses for researchers and the owners. Moreover, another innovation of the current study is using discriminant analysis for selecting and filtering variables which are important and effective in predicting churners and non-churners, which is not used in previous studies. Therefore, the current study is unique considering the used variables, the method of comparing their accuracy and the method of selecting effective variables.

Process mining is a research area used to discover, monitor and improve real business processes by extracting knowledge from event logs available in process-aware information systems. The purpose of this paper is to evaluate the application of artificial neural networks (ANNs) and support vector machines (SVMs) in data mining tasks in the process mining context. The goal was to understand how these computational intelligence techniques are currently being applied in process mining.

The authors conducted a systematic literature review with three research questions formulated to evaluate the use of ANNs and SVMs in process mining.

The authors identified 11 papers as primary studies according to the criteria established in the review protocol. Most of them deal with process mining enhancement, mainly using ANNs. Regarding the data mining task, the authors identified three types of tasks used: categorical prediction (or classification); numeric prediction, considering the “regression” type, and clustering analysis.

Although there is scientific interest in process mining, little attention has been specifically given to ANNs and SVM. This scenario does not reflect the general context of data mining, where these two techniques are widely used. This low use may be possibly due to a relative lack of knowledge about their potential for this type of problem, which the authors seek to reverse with the completion of this study.

The purpose of the paper is to model the relationship between the yield strength of austenitic stainless steel and its chemical composition through the employment of artificial neural network (ANN). The effect of annealing temperature is also taken into consideration.

The influence of network parameters, total number of neurons, number of neurons in a hidden layer, number of hidden layers and the interlayer distribution of neurons with a constant total neuron number, on the achievable training error is studied. Different learning rules available in MATLAB are used to assess the learning efficiencies of various networks.

It is found that increasing neuron number leads to a lowering of achievable training error up to a certain value beyond which training error remains constant. Increasing number of layers at constant total number of neurons causes a rise in the achievable training error. It is noted that if there is a sudden restriction of data flow in an ANN architecture, the achievable training error becomes higher. Interlayer distribution of neurons in ANNs used with different algorithms is found to have significant influence on the predictive performance of the networks.

From the study on metallurgical validation of the output of various ANNs, it appears that mere attainment of a lower training error is not sufficient to achieve better generalization. A convergent network topology is found to be better than a divergent one in respect of effectively describing the input‐output relationship in austenitic stainless steel.