Soft Computing Methods Research Articles

A novel approach to predict shear strength of tilted angle connectors using artificial intelligence techniques

Shear connectors play a prominent role in the design of steel-concrete composite systems. The behavior of shear connectors is generally determined through conducting push-out tests. However, these tests are costly and require plenty of time. As an alternative approach, soft computing (SC) can be used to eliminate the need for conducting push-out tests. This study aims to investigate the application of artificial intelligence (AI) techniques, as sub-branches of SC methods, in the behavior prediction of an innovative type of C-shaped shear connectors, called Tilted Angle Connectors. For this purpose, several push-out tests are conducted on these connectors and the required data for the AI models are collected. Then, an adaptive neuro-fuzzy inference system (ANFIS) is developed to identify the most influencing parameters on the shear strength of the tilted angle connectors. Totally, six different models are created based on the ANFIS results. Finally, AI techniques such as an artificial neural network (ANN), an extreme learning machine (ELM), and another ANFIS are employed to predict the shear strength of the connectors in each of the six models. The results of the paper show that slip is the most influential factor in the shear strength of tilted connectors and after that, the inclination angle is the most effective one. Moreover, it is deducted that considering only four parameters in the predictive models is enough to have a very accurate prediction. It is also demonstrated that ELM needs less time and it can reach slightly better performance indices than those of ANN and ANFIS.

Photo-voltaic power daily predictions using expanding PDE sum models of polynomial networks based on Operational Calculus

Photo-Voltaic (PV) power production is subject to the current local weather situation which result in the amount of solar radiation components possible to convert by PV modules. Numerical Weather Prediction (NWP) systems are usually run every 6 h to provide course local 24–48-hour forecasts. Statistical models, developed with spatial historical data, can convert or post-process these NWP data to predict PV power for a plant specific situation. Statistical predictions are more precise if rely on the latest weather observations and power measurements as the accuracy of NWP cloudiness is mostly inadequate for PV plant operation and the forecast errors are only magnified. Differential Polynomial Neural Network (D-PNN) is a novel neuro-computing technique based on analogies with brain pulse signal processing. It can model complex patterns without reducing significantly the data dimensionality as regression and soft-computing methods do. D-PNN decomposes the general Partial Differential Equation (PDE), being able to describe the local atmospheric dynamics, into node specific 2nd order sub-PDEs. These are converted using adapted procedures of Operational Calculus to obtain the Laplace images of unknown node functions, which are inverse transformed to obtain the originals. D-PNN can select from dozens of input variables to produce applicable sum PDE components which can extend, step by step, its composite models towards the optima. The PDE models are developed with historical spatial data from the estimated optimal lengths of daily training periods to process the last day input data and predict Clear Sky Index 24-hours ahead. They obtain a better prediction accuracy than simplified statistical solutions which allow to predict in horizon of a few hours only.

Using a soft computing method for impedance modelling of Li-ion battery current

Using the soft computing as a powerful tool for modelling of complex systems is highly regarded. Adaptive neuro fuzzy inference system is one of the best methods of soft computing which identifies and models nonlinear systems. In this paper, complex impedance behaviours of Li-ion batteries are studied by adaptive neuro fuzzy inference system. To present an approach for modelling and identification of electrochemical systems is purposed. This method can be improved to reach the most accurate model of the batteries. In the presented work, complex current is modelled as the main important element of the batteries in impedance state. Modelling results showed that this method can have acceptable output for impedance modelling the batteries.

Soft Computing Methods for Fault Detection in Power Transmission Lines

Communication is a major aspect of our day to day life and for maintaining the transmission of the data; electric power transmission lines play a major role in acting as the medium for this transmission. The transmission lines can further be differentiated as an overhead transmission line and underground transmission line. But the transmission is often hindered by the physical factors or generally known as faults. In the past few years, the implementation of the underground cable has seen an upsurge as these cables are not easily affected by the physical factors as the overhead cables are, as a result, there have been various methods adopted by the engineers for the analysis, detection and control of these faulty lines. Depending on the supply range of a particular nation different materials are used for the transmission lines. Different fault detection methods are used for the exact location of the fault and implementing that in a digitized way is the optimum solution. Whenever there is a fault the entire transmission line is affected, to ensure that the safety of the transmission line a governing system has been implied in our proposed work. Locating a fault requires various detection methods, one such method is the time domain reflectometry (TDR) which we have inculcated in our analysis of fault lines. This technique incorporates the transmission of a pulse down the cable, any change in the characteristics impedance will cause a part of the incident pulse to reflect back, this knowledge is helpful for locating discontinuities in a system.

Single and Multi-Type Controllers with Soft Computing Methods and Routing in Software Defined Network

The software defined networking topology is enabled for efficient configuration for monitoring and enhance the network performance. The multi-controller placement becomes very critical, and it can be rectified by the proposed approach. The comparison of single type and the multi controllers are discussed in this paper.The first paper is compared with the dragonfly algorithm, in this we have considered only multi POX controllers. So the latency difference depends on the iteration of the algorithm. Thus the latency is reduced in proposed algorithm. Similarly the second paper has compared with the existing algorithm of firefly, which states the multi type of controllers such as POX, NOX, BEACON and FLOODLIGHT, among that latency is calculated and compared. The selection criteria are varied according to its type. Hence the routing is carried out on the two controllers alike POX, and NOX, through ad hoc on demand distance vector routing protocol. Subsequently, the selected controllers specifically are placed and simulated in Pareto-based Optimal Controller placement (POCO) tool for the Internet 2 topology and network simulator(NS2). Finally the comparison results makes the proposed system is better than previous methods.

Single and Multi-Type Controllers with Soft Computing Methods and Routing in Software Defined Network

The software defined networking topology is enabled for efficient configuration for monitoring and enhance the network performance. The multi-controller placement becomes very critical, and it can be rectified by the proposed approach. The comparison of single type and the multi controllers are discussed in this paper.The first paper is compared with the dragonfly algorithm, in this we have considered only multi POX controllers. So the latency difference depends on the iteration of the algorithm. Thus the latency is reduced in proposed algorithm. Similarly the second paper has compared with the existing algorithm of firefly, which states the multi type of controllers such as POX, NOX, BEACON and FLOODLIGHT, among that latency is calculated and compared. The selection criteria are varied according to its type. Hence the routing is carried out on the two controllers alike POX, and NOX, through ad hoc on demand distance vector routing protocol. Subsequently, the selected controllers specifically are placed and simulated in Pareto-based Optimal Controller placement (POCO) tool for the Internet 2 topology and network simulator(NS2). Finally the comparison results makes the proposed system is better than previous methods.

Comparative Assessment Between Statistical and Soft Computing Methods for Accident Severity Classification

Globally traffic scenario has experienced a vast change over the years as volumes of traffic on urban roads have increased by leaps and bounds. This increase has also marked an increase in the number of road accidents, both fatal and non-fatal. Accident prediction has a significant role in the improvement in traffic safety, and urban traffic management. Different statistical methods and various soft computing techniques are being used for developing accident prediction models. In this study, ensemble ranking method, comprising three filter-based ranking methods such as Information Gain, Gain Ratio, and Symmetric Uncertainty, has been employed to select significant features for prediction of accident severity. Through analysis, eight significant features have been selected for accident severity prediction. These are Annual Average Daily Traffic, Road Width, Percentage of Left-Turn Vehicles, Driver’s Age, Percentage of Right-Turn Vehicles, Types of Vehicles Involved, Spot Speed, and Cause of Accidents. Multiple logistic regression (MLGR) and artificial neural network (ANN) have been applied for accident severity prediction in urban roads. This analysis concludes that ANN model gives more accuracy and minimum errors compared with the MLGR method at the time of severity classification of a vehicular accident.

Remaining useful life prediction of crude oil pipeline by means of deterioration curves

AbstractPipelines sometimes generate different kinds of environmental damages which are irreparable and hazardous due to various reasons such as natural hazards, external loads, and corrosion. Many soft computational methods have been introduced to assess the failure rates of pipelines since decades. However, the majority of studies were limited to specific conditions. The aim of this paper is to predict the remaining useful life of the crude oil pipeline by generating the deteriorating curves. The historical inspection data have been used to calculate the metal loss (ML) growth rates. ML anomalies were found to be a major effect on the deterioration rate of a crude oil pipeline. Deterioration curves were developed using ML growth rates on a timely basis. The results may help pipeline technicians in decision making for overhaul planning and to take essential arrangements or to repair when needed, so that produce losses of oil and gas industries can be reduced and hence the lifespan of a pipeline can be increased.

Application of two fuzzy models using knowledge-based and linear aggregation approaches to identifying flooding-prone areas in Tehran

Flooding is one of the most problematic natural events affecting urban areas. In this regard, developing flooding models plays a crucial role in reducing flood-induced losses and assists city managers to determine flooding-prone areas (FPAs). The aim of this study is to investigate on the prediction capability of fuzzy analytical hierarchy process (FAHP) and Mamdani fuzzy inference system (MFIS) methods as two completely and semi-knowledge-based models to identify FPAs in Tehran, Iran. Six flooding conditioning factors including density of channel, distance from channel, land use, elevation, slope, and water discharge were extracted from various geo-spatial datasets. A total of 62 flooding locations were identified in the study area based on the existing reports and field surveys. Of these, 44 (70%) floods were randomly selected as training data and the remaining 18 (30%) cases were used for the validation purposes. After the data preparation step, data were processed by means of two statistical (FAHP) and soft computing (MFIS) methods. Unlike most statistical and soft computing approaches which use flooding inventory data for both training and evaluation of models, only conditioning factor was involved in data processing and inventory data were used in the current study to assess models prediction accuracy. Also, the efficiency of two approaches was evaluated by pixel matching (PM) and area under curve to validate the prediction capability of models. The prediction rate for MFIS and FAHP was 89% and 84%, respectively. Moreover, according to the results obtained from PM, it was found out that about 90% of known flooding locations fell in high-risk areas, whereas it was 83% for FAHP, indicating that flooding susceptibility map of MFIS has higher performance.

Modeling dew point pressure of gas condensate reservoirs: Comparison of hybrid soft computing approaches, correlations, and thermodynamic models

Optimal future management of gas condensate reservoirs requires reliable estimation of the dew point pressure (Pd). Due to the limitations of the available Pd determination methods, such as cost and the prohibitive time for experimental approaches, and inaccuracies and lack of generalization for predictive approaches, it is still necessary to establish more accurate and user friendly Pd paradigms. In this study, various methodologies based on soft computing (SC) techniques, optimization algorithms, and generalized reduced gradient (GRG) method were implemented to develop Pd models based on a widespread databank. Two types of artificial neural networks, namely radial basis function (RBF) neural networks and Multilayer perceptron (MLP) are the employed SC methods. To improve the prediction capability of the latter, Levenberg-Marquardt (LM), Bayesian Regularization (BR), and Scaled Conjugate Gradient (SCG) algorithms were used in the training phase of MLP, while three nature-inspired algorithms, namely Genetic Algorithm (GA), Bat Algorithm (BA), and Salp Swarm Algorithm (SSA) were first considered in the RBF learning phase. Then, the four best-found models were assembled beneath a unified paradigm utilizing a committee machine intelligent system (CMIS). Also, a correlation was developed using GRG. The developed CMIS and GRG correlation were compared with four empirical correlations as well as seven equations of state (EOSs). Based on the results obtained, CMIS model exhibits very satisfactory Pd predictions with an overall average absolute percent relative error (AAPRE) of 5.28%, and outperforms largely the other existing predictive approaches. Furthermore, the developed correlation provided more accurate results compared to existing correlations and EOSs.

Soft Computing Methods with Phase Space Reconstruction for Wind Speed Forecasting—A Performance Comparison

This article presents a comparison of wind speed forecasting techniques, starting with the Auto-regressive Integrated Moving Average, followed by Artificial Intelligence-based techniques. The objective of this article is to compare these methods and provide readers with an idea of what method(s) to apply to solve their forecasting needs. The Artificial Intelligence-based techniques included in the comparison are Nearest Neighbors (the original method, and a version tuned by Differential Evolution), Fuzzy Forecasting, Artificial Neural Networks (designed and tuned by Genetic Algorithms), and Genetic Programming. These techniques were tested against twenty wind speed time series, obtained from Russian and Mexican weather stations, predicting the wind speed for 10 days, one day at a time. The results show that Nearest Neighbors using Differential Evolution outperforms the other methods. An idea this article delivers to the reader is: what part of the history of the time series to use as input to a forecaster? This question is answered by the reconstruction of phase space. Reconstruction methods approximate the phase space from the available data, yielding m (the system’s dimension) and τ (the sub-sampling constant), which can be used to determine the input for the different forecasting methods.

Potential impacts of climate change on groundwater level through hybrid soft-computing methods: a case study-Shabestar Plain, Iran.

Groundwater aquifers have always been confronted with significant challenges around the world such as climate change, over-extraction, pollution by wastewaters, and saltwater intrusion in coastal areas. Prediction of groundwater level under the effects of climate change is more important in water resource management. This study has therefore been evaluated the effects of two climate parameters (i.e., precipitation and temperature) in groundwater level for the Shabestar Plain, Iran. For this end, four models from General Circulation Models (GCM) were then used to evaluate future climate change scenarios of the Representative Concentration Pathway (i.e., RCP2.6, RCP4.5, RCP8.5). In the next phase, to reduce the spatial complexity of observation wells, clustering analysis was used. In case of groundwater level modeling, time series in the base period, Least Square Support Vector Machine (LSSVM), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Nonlinear Autoregressive Network with Exogenous inputs (NARX) were also used. To improve the prediction accuracy, time series preprocessing made by wavelet-based de-noising approach was used. Analysis of the results illustrates an increase in temperature and a decrease in precipitation for study region in the future period times. The results also reveal that hybrid techniques of the wavelet-NARX give best results in comparison with the other models. A simulation result illustrates that the groundwater level declines in RCP2.6, 4.5, and 8.5, which gives average levels of 0.61, 0.81, and 1.53m, respectively, for the future period years (i.e., 2020-2024). These results would lead to continuous groundwater depletion. These findings emphasize the necessity of the importance of extraction policies in water resource management.

Soft Computing Methods based on Fuzzy, Evolutionary and Swarm Intelligence for Analysis of Digital Mammography Images for Diagnosis of Breast Tumors

Soft Computing Methods based on Fuzzy, Evolutionary and Swarm Intelligence for Analysis of Digital Mammography Images for Diagnosis of Breast Tumors

Feature Selection using Hybrid Dragonfly Algorithm in a Heart Disease Predication System

The heart disease considers as one of the fatal disease in many countries. The main reason is due to the approved methods of diagnostic are not available to the ordinary people. Many studies have been done to handle this case with the use of both methods of soft computing and machine learning. In this study, a hybrid binary dragonfly algorithm and mutual information proposed for feature selection, support vector machine and multilayer perceptron employed for classification. The Statlog dataset used for experiments. Out of a total of 270 instances of patient data, 216 employees for the purpose of practicing, 54 of them used for the purpose of examining. Maximum classification accuracy of 94.44% achieved with support vector machine and 92.59% with multilayer perceptron on features selected with binary dragonfly algorithm, whereas with features obtained from mutual information combined with binary dragonfly (MI_BDA) algorithm support vector machine and multilayer perceptron attained an accuracy of 96.29%. The time algorithm takes reduced from 15.4 with binary dragonfly algorithm to 6.95 seconds with MI_BDA.

Evaluating the Performance of CHIRPS Satellite Rainfall Data for Streamflow Forecasting

Streamflow forecasting can offer valuable information for optimal management of water resources, flood mitigation, and drought warning. This research aims in evaluating the effectiveness of CHIRPS satellite rainfall data in comparison with IMD gridded Rainfall Data and development of various flow forecasting models. Daily rainfall data for three decades (1983–2012) over the Nethravathi Basin, Karnataka, India is used for analysis. The analysis is carried out for the monsoon season (June–September), out of which 70% data considered for training the model and remaining for testing. Different input combinations are developed, and soft-computing methods like ANFIS, GRNN, PSO-ANN, and ELM are applied for flow forecasting on a temporal scale. The model performance is evaluated using various statistical indices like NNSE, RRMSE, and MAE. The results indicate that CHIRPS rainfall showed better performance in comparison with IMD data. ELM expressed an enhanced effect when compared to all other methods. The usefulness and effectiveness of CHIRPS data compared to IMD data has been explored.

Vibration-based diagnostics of epicyclic gearboxes – From classical to soft-computing methods

The paper presents up-to-date multidisciplinary review of scientific knowledge and industrial guidelines concerning the issue of technical assessment of epicyclic gearboxes on the basis of vibrational measurement. The paper covers norms, patents, signal processing methods, technical features, diagnostic methodologies, and high-level soft computing. The review classifies recognized papers according to different aspects, like case difficulty, applied methods or studied objects. Moreover, the paper discusses recent development of diagnostic techniques taking into account changing operational conditions and requiring powerful data processing units not available hitherto. Since in recent years many partial review papers have been published in different journals, the current paper presents their individual scope. Because diagnostics of epicyclic gearboxes generally covers and extends the classical signal processing techniques and classical machine condition monitoring functionality, the current paper might serve as a descriptive database of sources of information and bibliography or as a reference to individual techniques.

Neural Network and Principle Component Analysis Based Numerical Data Analysis for Stock Market Prediction with Machine Learning Techniques

Financial market prediction is gaining attention throughout the market phenomena since various applicable techniques within soft-computational methods have been analyzed to define the optimization. The study of this experimental research focused on two benchmark numerical stock market dataset (S&P 500 index dataset and OHLCV dataset). This structural dataset is analyzed through two main applicable techniques such as Feed-forward Neural Network and Principle Component Analysis for stock market prediction where the remarkable Machine Learning technique hold a variant of features. The architectural neural network is rebuilt based on four layers with neurons that influence on high-dimensional dataset with the performance of popular ReUL activation function. Model specification also embodies the result of precision, recall and “F-score” within the number of twenty epochs. An overall picture of this developing model approaches the maximum level of accuracy which impacts on the academical research philosophy for financial market prediction.

Automatic Selection of Optimal Parameters Based on Simple Soft-Computing Methods: A Case Study of Micromilling Processes

Nowadays, the application of novel soft-computing methods to new industrial processes is often limited by the actual capacity of the industry to assimilate state-of-the-art computational methods. The selection of optimal parameters for efficient operation is very challenging in microscale manufacturing processes, because of intrinsic nonlinear behavior and reduced dimensions. In this paper, a decision-making system for selecting optimal parameters in micromilling operations is designed and implemented using simple and efficient soft-computing techniques. The procedure primarily consists of four steps: an experimental characterization; the modeling of cutting force and surface roughness by means of a multilayer perceptron; multiobjective optimization using the cross-entropy method, taking into account productivity and surface quality; and a decision-making procedure for selecting the most appropriate parameters using a fuzzy inference system. Finally, two different alloys for micromilling processes are considered, in order to evaluate the proposed system: a titanium-based alloy and a tungsten-copper alloy. The experimental study demonstrated the effectiveness of the proposed solution for automated decision-making, based on simple soft-computing methods, and its successful application to a real-life industrial challenge.

Saxena-Easo Fuzzy Time Series on Indonesia’s Inflation Rate Forecasting

Saxena-Easo Fuzzy Time Series (FTS) is a softcomputing method for forecasting using fuzzy concept. It doesn’t need any assumption like conventional forecasting method. Generally it’s focused on three important steps like percentage change as the universe of discourse, interval partition, and defuzzification. In this research, this method is applied to Indonesia’s inflation rate data. The aim of this research is to forecast Indonesia’s inflation rate in 2017 by using input from Autoregressive Integrated Moving Average (ARIMA) process, Saxena-Easo FTS, and actual data from 1970-2016. ARIMA is focused on four steps like identifying, parameter estimation, diagnostic checking, and forecasting. The result for Indonesia’s inflation rate forecasting in 2017 is about 5.9182 using Saxena-Easo FTS. Root Mean Square Error (RMSE) is also computed to compare the accuracy rate from each method between Saxena-Easo FTS and ARIMA. RMSE from Saxena-Easo FTS is about 0.9743 while ARIMA is about 6.3046. Keywords: saxena-easo fuzzy time series, ARIMA, inflation rate, RMSE.

Application of AHP-VIKOR and GMDH framework to develop an indicator to identify utilisation potential of wave energy converter with respect to location

The potential of analytical hierarchy process (AHP)-rough number based compromise ranking method (also known as VIKOR) multi-criteria decision-making (MCDM) and group method of data handling (GMDH) multimodal predictive method was analysed for smart representation of 'utilisation potential' of wave energy converters from specific locations. The significant parameters were identified by considering different case studies and their influence on converter efficiency. The soft-computation methods like AHP-VIKOR and GMDH were used for the first time to find the relative priority values of the parameters. The results from the multi-method estimation model were validated with the help of multi linear regression equation and certain real-time case analysis. With an accuracy of above, 99% the ensemble MCDM-ANN model depicted reliability, which ensures the author of its wide application for real benefits like cost reduction and efficiency maximisation of converters in the utilisation of the potential wave energy of locations.