Search

Abstract: In this study, the determinability of time related colour changes in prints made using ink that dries on matte coated paper with the offset printing technique and infrared method, has been investigated with artifical neural networks after analysis of the experimental and numerical methods. In the experimental part a ECI 2002 CMYK test scale is printed on a 135g/m2 matte coated. The prints obtained were measured with a spectrophotometer at certain intervals and by converting the reflection data obtained into the CIELAB colour description spectrum, time related changes in printed colours have been determined. In the empirical study however, colour changes in prints made on matte coated paper using inks that dry with the infrared method are modelled numerically. The average deviation has been found to be 0.4%. As a result, artificial neural networks can be used with the aim to digitally calculate time related colour changes in the offset printing system. [Copyright &y& Elsevier]

Abstract: Using advanced machine learning techniques as an alternative to conventional double-entry volume equations, a regression model of the inside-bark volume (dependent variable) for standing Eucalyptus globulus trunks (or main stems) has been built as a function of the following three independent variables: age, height and outside-bark diameter at breast height (DBH). The experimental observed data (age, height, outside-bark DBH and inside-bark volume) for 142 trees (E. globulus) were measured and a nonlinear model was built using a data-mining methodology based on support vector machines (SVM) and multilayer perceptron networks (MLP) for regression problems. Coefficients of determination and Furnival’s indices indicate the superiority of the SVM with a radial kernel over the allometric regression models and the MLP. [Copyright &y& Elsevier]

This paper focuses on training the mathematical models for prediction of optimal livestock feed blend for animal. In this paper, three functions are trained to find the most optimal percentage of price, nutrients and water. For this purpose three objective functions has been prepared using corresponding values of feed ingredients and an algorithm is developed using ANN. The objective functions are trained with 5000 random values to find the optimized results and prediction ability is compared with existing model. Developed algorithm shows superiority over the existing programming models. [ABSTRACT FROM AUTHOR]

Pile foundations are usually used when the conditions of the upper soil layers are weak and unable to support the super-structural loads. Piles carry these super-structural loads deep into the ground. Therefore, the safety and stability of pile-supported structures depends largely on the behavior of the piles. In addition, accurate prediction of pile behavior is necessary to ensure appropriate structural and serviceability performance. In this paper, an ANN model is developed for predicting pile behavior based on the results of cone penetration test (CPT) data. Approximately 500 data sets, obtained from the published literature, are used to develop the ANN model. The paper compares the predictions obtained by the ANN with those given by a number of traditional methods and it is observed that the ANN model significantly outperforms the traditional methods. An important advantage of the ANN model is that the complete load-settlement relationship is captured. Finally, the paper proposes a series of charts for predicting pile behavior that will be useful for pile design. [ABSTRACT FROM AUTHOR]

Context: Data mining (DM) provides the methodology and technology needed to transform huge amounts of data into useful information for decision making. It is a powerful process employed to extract knowledge and discover new patterns embedded in large data sets. Data mining has been increasingly used in medicine, particularly in cardiology. In fact, DM applications can greatly benefit all those involved in cardiology, such as patients, cardiologists and nurses.Objective: The purpose of this paper is to review papers concerning the application of DM techniques in cardiology so as to summarize and analyze evidence regarding: (1) the DM techniques most frequently used in cardiology; (2) the performance of DM models in cardiology; (3) comparisons of the performance of different DM models in cardiology.Method: We performed a systematic literature review of empirical studies on the application of DM techniques in cardiology published in the period between 1 January 2000 and 31 December 2015.Results: A total of 149 articles published between 2000 and 2015 were selected, studied and analyzed according to the following criteria: DM techniques and performance of the approaches developed. The results obtained showed that a significant number of the studies selected used classification and prediction techniques when developing DM models. Neural networks, decision trees and support vector machines were identified as being the techniques most frequently employed when developing DM models in cardiology. Moreover, neural networks and support vector machines achieved the highest accuracy rates and were proved to be more efficient than other techniques. [ABSTRACT FROM AUTHOR]

Entity resolution is an important application in field of data cleaning. Standard approaches like deterministic methods and probabilistic methods are generally used for this purpose. Many new approaches using single layer perceptron, crowdsourcing etc. are developed to improve the efficiency and also to reduce the time of entity resolution. The approaches used for this purpose also depend on the type of dataset, labeled or unlabeled. This paper presents a new method for labeled data which uses single layered convolutional neural network to perform entity resolution. It also describes how crowdsourcing can be used with the output of the convolutional neural network to further improve the accuracy of the approach while minimizing the cost of crowdsourcing. The paper also discusses the data pre-processing steps used for training the convolutional neural network. Finally it describes the airplane sensor dataset which is used for demonstration of this approach and then shows the experimental results achieved using convolutional neural network. [ABSTRACT FROM AUTHOR]

The paper deals with the problem of robust fault detection using recurrent neural networks and chaos engineering. The main part of the proposed approach is a locally recurrent neural network that is composed of complex dynamic neural units for which chaotic behaviour can be obtained. Selected global and local optimization methods are connected to have diphase strategies for training this kind of neural networks. And beyond this, chaos engineering is incorporated into both the evolutionary and simulated annealing algorithm in order to improve the efficiency of the tuning procedure. The problem of selecting the most relevant input variables is solved by means of extended Hellwig׳s method of integral capacity of information. Criteria isolines and a sensitive-based method are used to identify the suitable architecture of a neural network. Moreover, the issue of stability analysis of neural models is also considered in this paper. Recurrence quantification analysis is proposed for residual evaluation in order to have the comprehensive methodology of neural model-based fault detection. The preliminary verification of the elaborated methodology in modelling tasks was carried out for both simulation and industrial data. The fundamental verification was conducted for the data made available within DAMADICS benchmark problem. The achieved results confirm the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Abstract: Knowledge regarding the values of fracture-mechanical parameters is critical for the virtual failure modeling of elements and structures made of concrete. A key parameter in nonlinear fracture mechanics modeling is the specific fracture energy of concrete, and its variability. Three-point bending tests on notched-beam specimens are fundamental experiments for the determination of fracture-mechanical parameters. In the present paper, two basic approaches are applied to determine fracture-mechanical parameter values from these tests: (i) the effective crack model/work-of-fracture method, and (ii) inverse analysis using artificial neural networks and stochastic simulations. First, the paper describes suitable methods for the determination of fracture-mechanical parameters. Second, the FraMePID-3PB software tool, which has been developed in order to automate the whole time consuming process of inverse analysis, is described. Finally, the verification of methodology and software is presented using two illustrative examples. [Copyright &y& Elsevier]

Abstract: This paper proposes a novel divide-and-conquer model for CPI predictionwith the existing compilation method of the Consumer Price Index (CPI) in China. Historical national CPI time series is preliminary divided into eight sub-indexes includingfood, articles for smoking and drinking, clothing, household facilities, articles and maintenance services, health care and personal articles, transportation and communication, recreation, education and culture articles and services, and residence. Three models including back propagation neural network (BPNN) model, grey forecasting model (GM (1, 1)) and autoregressive integrated moving average (ARIMA) model are established to predict each sub-index, respectively.Then the best predicting result among the three models’ for each sub-index is identified. To further improve the performance, special modification in predicting method is done to sub-CPIs whose forecasting results are not satisfying enough. After improvement and error adjustment, we get the advanced predicting results of the sub-CPIs.Eventually, the best predicting results of each sub-index are integrated to form the forecasting results of the national CPI. Empirical analysis demonstrates that the accuracy and stability of the introduced method in this paper is better than many commonly adopted forecasting methods, which indicates the proposed method is an effective and alternative one for national CPI prediction in China. [Copyright &y& Elsevier]

Abstract: The application of Artificial Neural Networks (ANNs) in the field of environmental and water resources modelling has become increasingly popular since early 1990s. Despite the recognition of the need for a consistent approach to the development of ANN models and the importance of providing adequate details of the model development process, there is no systematic protocol for the development and documentation of ANN models. In order to address this shortcoming, such a protocol is introduced in this paper. In addition, the protocol is used to critically review the quality of the ANN model development and reporting processes employed in 81 journal papers since 2000 in which ANNs have been used for drinking water quality modelling. The results show that model architecture selection is the best implemented step, while greater focus should be given to input selection considering input independence and model validation considering replicative and structural validity. [Copyright &y& Elsevier]

Abstract: SYCOMORE, a fusion reactor system code based on a modular approach, is under development at CEA. In this framework, this paper describes a methodology developed to build the neutronic module of SYCOMORE. This neutronic module aims to evaluate main neutronic parameters characterising a fusion reactor (tokamak): tritium breeding ratio, multiplication factor, nuclear heating as a function of the reactor main geometrical parameters (major radius, elongation, etc.), of the radial build, Li enrichment, blanket and shield thickness, etc. It is based on calculations carried out with APOLLO2 and TRIPOLI-4 CEA transport code on simplified 1D and 2D neutronic models. These models are validated versus a more detailed 3D Monte-Carlo model (using TRIPOLI-4). To ease the integration of this neutronic module in SYCOMORE and provide results instantly, a surrogate model that replicates the 1D and 2D neutronic model results was used. Among the different surrogate models types (polynomial interpolation, responses functions, interpolating by Kriging, artificial neural network, etc.) the neural networks were selected for their efficiency and flexibility. The methodology described in this paper to build SYCOMORE neutronic module is devoted to HCLL blanket, but it could be applied to any breeder blanket concept provided that appropriate validation could be carried out. [Copyright &y& Elsevier]

Abstract: Objective: An electroencephalogram-based (EEG-based) brain–computer-interface (BCI) provides a new communication channel between the human brain and a computer. Amongst the various available techniques, artificial neural networks (ANNs) are well established in BCI research and have numerous successful applications. However, one of the drawbacks of conventional ANNs is the lack of an explicit input optimization mechanism. In addition, results of ANN learning are usually not easily interpretable. In this paper, we have applied an ANN-based method, the genetic neural mathematic method (GNMM), to two EEG channel selection and classification problems, aiming to address the issues above. Methods and materials: Pre-processing steps include: least-square (LS) approximation to determine the overall signal increase/decrease rate; locally weighted polynomial regression (Loess) and fast Fourier transform (FFT) to smooth the signals to determine the signal strength and variations. The GNMM method consists of three successive steps: (1) a genetic algorithm-based (GA-based) input selection process; (2) multi-layer perceptron-based (MLP-based) modelling; and (3) rule extraction based upon successful training. The fitness function used in the GA is the training error when an MLP is trained for a limited number of epochs. By averaging the appearance of a particular channel in the winning chromosome over several runs, we were able to minimize the error due to randomness and to obtain an energy distribution around the scalp. In the second step, a threshold was used to select a subset of channels to be fed into an MLP, which performed modelling with a large number of iterations, thus fine-tuning the input/output relationship. Upon successful training, neurons in the input layer are divided into four sub-spaces to produce if-then rules (step 3). Two datasets were used as case studies to perform three classifications. The first data were electrocorticography (ECoG) recordings that have been used in the BCI competition III. The data belonged to two categories, imagined movements of either a finger or the tongue. The data were recorded using an 8×8 ECoG platinum electrode grid at a sampling rate of 1000Hz for a total of 378 trials. The second dataset consisted of a 32-channel, 256Hz EEG recording of 960 trials where participants had to execute a left- or right-hand button-press in response to left- or right-pointing arrow stimuli. The data were used to classify correct/incorrect responses and left/right hand movements. Results: For the first dataset, 100 samples were reserved for testing, and those remaining were for training and validation with a ratio of 90%:10% using K-fold cross-validation. Using the top 10 channels selected by GNMM, we achieved a classification accuracy of 0.80±0.04 for the testing dataset, which compares favourably with results reported in the literature. For the second case, we performed multi-time-windows pre-processing over a single trial. By selecting 6 channels out of 32, we were able to achieve a classification accuracy of about 0.86 for the response correctness classification and 0.82 for the actual responding hand classification, respectively. Furthermore, 139 regression rules were identified after training was completed. Conclusions: We demonstrate that GNMM is able to perform effective channel selections/reductions, which not only reduces the difficulty of data collection, but also greatly improves the generalization of the classifier. An important step that affects the effectiveness of GNMM is the pre-processing method. In this paper, we also highlight the importance of choosing an appropriate time window position. [Copyright &y& Elsevier]

Abstract: This paper reports an artificial neural networks (ANN) modelling programme for a light-duty diesel engine powered using blends of various biodiesel fuels with conventional fossil diesel. ANN was used here to predict nine different engine-out responses, namely carbon monoxide (CO), carbon dioxide (CO2), nitrogen monoxide (NO), unburned hydrocarbon (UHC), maximum pressure (P max), location of maximum pressure (CAD P max), maximum heat release rate (HRRmax), location of maximum HRR (CAD HRRmax) and cumulative HRR (CuHRR). Four pertinent engine operating parameters, engine speed, output torque, fuel mass flow rate and biodiesel fuel types and blends, were used as the input parameters for this modelling work. The feasibility of using ANN in predicting the relationships between these inputs and outputs were assessed. Simulated results were first validated against data from parallel engine test-bed study. Key effects of ANN “model” and “model parameter” such as type of transfer function, training algorithm and number of neurons, along with the methods of optimising the network settings were also presented in this paper. [Copyright &y& Elsevier]

Abstract: This paper presents the optimization of chillers operating using artificial neural networks and genetic algorithms. For the needs of generating chiller models, an artificial neural network was used, trained with data collected from an actual chiller. For that purpose the basic characteristics of artificial neural networks are shown as well as the process of making specific chiller models used for testing the results of application of the genetic algorithm in usage optimization. The optimal criteria with the shown steps for the use of the genetic algorithm and optimization results is also displayed in the paper. The results of use of artificial intelligence methods in optimization of chiller operation are verified through an actual office building model created in the simulation software EnergyPlus and through a series of experiments on an actual office building, equipped with a modern integrated BMS. [Copyright &y& Elsevier]

Abstract: In this paper, a new multi-level genetic programming (MLGP) approach is introduced for forecasting transport energy demand (TED) in Iran. It is shown that the result obtained here has smaller error compared with the result obtained using neural network or fuzzy linear regression approach. The forecast uses historical energy data from 1968 to 2002 and it is based on three parameters; gross domestic product (GDP), population (POP), and the number of vehicles (VEH). The approach taken in this paper is based on genetic programming (GP) and the multi-level part of the name comes from the fact that we use GP in two different levels. At the first level, GP is used to obtain the time series model of the three parameters, GDP, POP, and VEH, and forecast those parameters for the time interval that their actual data are not available, and at the second level GP is used one more time to forecast TED based on available data for TED along with the data that are either available or predicted for the three parameters discussed earlier. Actual data from 1968 to 2002 are used for training and the data for years 2003–2005 are used to test the GP model. We have limited ourselves to these data ranges so that we could compare our results with the existing ones in the literature. The estimation GP for the model is formulated as a nonlinear optimization problem and it is solved numerically. [Copyright &y& Elsevier]

Abstract: In-situ stress field is very important in the numerical simulation and stability analysis as well as in the engineering design and construction. So it requests an effective analysis method. The typical in-situ stress analysis method is multivariate regression, which is based on 3-D FEM direct modeling, but it may be not so accurate to obtain the distribution of in-situ stress field of the project, because when the multivariate regression is carried out, the cross influence of the main factors of in-situ stress field is ignored, and the relationship of in-situ stress field and the main factors is too complicated to express by subharmonic multivariate function. This paper presents an improved method back propagation (BP) neural network back analysis of in-situ stress field, based on the calculated results of multivariate linear regression analysis. For in the ANN (Artificial Neural Networks) method, the training samples are difficult to generate, while combining the linear regression method with ANN method this problem can be solved perfectly. Linear elastic multivariate regression is carried out to determine the general bounds of optimized paraments, and uniform design method is carried out to settle different combinations of factor levels. Training samples are gained by FEM analysis. And the visual neural network by using ActiveX technology is realized in this paper, by taking full advantages of strong capability in computing of Matlab and features of friendly interface of VB perfectly. In fact, one needs to know the status of the in-situ stress field at some important location in the engineering, by using neural network method, intelligent expression method of the in-situ stress field is presented, and the developed man-computer interface has the property of easy use in the actual engineering. [Copyright &y& Elsevier]

Abstract: The aim of this paper is to design a neural network based adaptive control scheme for redundant manipulators in the presence of model uncertainties and external disturbances together with multiple self-motion criteria. With reference to the paper (N. Kumar, V. Panwar, N. Sukavanam, S.P. Sharma, J.H. Borm, Neural network based nonlinear tracking control of kinematically redundant robot manipulators, Mathematical and Computer Modelling 53 (2011) 1889–1901), an adaptive mechanism is also developed to estimate the uncertain bound of external disturbances and neural network approximation error etc. without requirement of known bounds. By Lyapunov method asymptotic error convergence can be guaranteed for both task-space and sub-task tracking errors. A comparative simulation study with a robust controller and the proposed controller are included for a 3 link planar robot manipulator. [Copyright &y& Elsevier]

Abstract: This paper studies the vehicle rollover warning based on the vehicle running state parameters which are easy for collecting. By taking advantages of neural network and support vector machine, this paper analyzes the probabilities of the vehicle rollover in the scenario of single lane change and establishes a warning model which could predict the rollover 0.4seconds in advance for a particular type of vehicle. According to the validation experiments on Ve- DYNA which is a vehicle dynamic simulation software, the results validate the warning model''s good performance with the maximum error as 0.04 second and no missing cases which indicates its validity for rollover warning. [Copyright &y& Elsevier]

Abstract: The computation of Global Climate Models (GCMs) presents significant numerical challenges. This paper presents new algorithms based on sparse occupancy trees for learning and emulating the long wave radiation parameterization in the NCAR CAM climate model. This emulation occupies by far the most significant portion of the computational time in the implementation of the model. From the mathematical point of view this parameterization can be considered as a mapping which is to be learned from scattered data samples , . Hence, the problem represents a typical application of high-dimensional statistical learning. The goal is to develop learning schemes that are not only accurate and reliable but also computationally efficient and capable of adapting to time-varying environmental states. The algorithms developed in this paper are compared with other approaches such as neural networks, nearest neighbor methods, and regression trees as to how these various goals are met. [Copyright &y& Elsevier]

Abstract: This paper presents a modeling method of the operation process of repairable technical objects of various classes. A particular attention was paid to the model of the process which includes a service expert system with an artificial neural network. The manner was described of the characterization (description) of the operation processes of repairable objects for the purpose of their simulative examination with the use of computer technology. The present paper also includes theoretical grounds of the modeling process of the operation of objects in the form of the following models: mathematical (analytical), graphical and descriptive. For the purpose of the research, an organization model was developed of the servicing system of those technical objects which require short shutdown time (aircrafts, radiolocation systems, etc.). [ABSTRACT FROM AUTHOR]

Abstract: The suitability of the project delivery system (PDS) selected for a project greatly influences the efficiency to conduct a project. It is not an easy task to select an appropriate PDS as a large amount of ambiguous information exists. The paper aims to develop a PDS selection model to help owners to make a decision. The similar projects are identified through the similarity metrics between the target project to be predicted and those in the database. In addition, some of the indicator values are examined and modified through DEA-BND model, and then they are trained by ANN model to predict an appropriate PDS for the target project. A survey was conducted by postal questionnaire to empirically validate the reliability of the model in China. The indicator system for the selection of an appropriate PDS is established. Through the comparison of results predicted by different models, it is found that the PDS selection model developed in this paper can predict PDS precisely, and shows higher reliability than the ANN model. A PDS selection model is developed by inputting project-specific data, which proves to be more accurate and less dependent on experts’ judgment. Its practical application will benefit the owner’s decision making in the selection of the PDS. [ABSTRACT FROM AUTHOR]

Abstract: This paper studies the H ∞ performance for the uncertain recurrent neural networks with both nonlinear external disturbance and Markovian jump parameters, in which the time delay is varying. Our objective is to design robust controllers, that are independent of the time delay, such that the uncertain system is stochastic stable with a generalized H ∞ disturbance attenuation level γ. For the given uncertain stochastic system, new controllers which are composed of a linear controller and an adaptive controller are proposed to realize H ∞ control by introducing a switching function and using the idea of completing square. Based on It’s differential formula and Lyapunov stability theory, new sufficient conditions are obtained in terms of linear matrices inequalities. A numerical example is constructed to show effectiveness of the designed controller in this paper. [Copyright &y& Elsevier]

Abstract: This paper presents some unpublished aspects and ongoing developments of the recently elaborated generator approach to the evolutionary optimization of catalytic materials, the purpose of which is to obtain evolutionary algorithms precisely tailored to the problem being solved. It briefly recalls the principles of the approach, and then it describes how the employed evolutionary operations reflect the specificity of the involved mixed constrained optimization tasks, and how the approach tackles checking the feasibility of large polytope systems, frequently resulting from the optimization constraints. Finally, the paper discusses the integration of the approach with surrogate modeling, paying particular attention to surrogate models enhanced with boosting. The usefulness of surrogate modeling in general and of boosted surrogate models in particular is documented on a case study with data from a high-temperature synthesis of hydrocyanic acid. [Copyright &y& Elsevier]

Abstract: This paper describes the development of neural network models for automatic incident detection on arterial roads, using simulated data derived from inductive loop detectors and probe vehicles. The work reported in this paper extends previous research by comparing the performance of various data fusion neural network architectures and assessing model performance for various probe vehicle penetration rates and loop detector configurations. Data from 108 incidents was collected from loop detectors and probe vehicles using a calibrated and validated traffic simulation model. The best performance was obtained for detector configurations found on most existing road networks, with a detection rate of 86%, false alarm rate of 0.36% and probe vehicle penetration rate of 20%. Fusion of speed data further improved performance, resulting in an incident detection rate of 90% and a false alarm rate of 0.5%. The results reported in this paper demonstrate the feasibility of developing advanced data fusion neural network architectures for detection of incidents on urban arterials using data from existing loop detector configurations and probe vehicles. [ABSTRACT FROM AUTHOR]

Abstract This paper provides a starting point for the development of metacognition in a common model of cognition. It identifies significant theoretical work on metacognition from multiple disciplines that the authors believe worthy of consideration. After first defining cognition and metacognition, we outline three general categories of metacognition, provide an initial list of its main components, consider the more difficult problem of consciousness, and present examples of prominent artificial systems that have implemented metacognitive components. Finally, we identify pressing design issues for the future. [ABSTRACT FROM AUTHOR]

In this paper, a hybrid model using modular neural networks and fuzzy logic was designed to provide the hypertension risk diagnosis of a person. This model considers age, risk factors and behavior of the blood pressure in a period of 24 h, using as a basis the Framingham Heart Study. Records of blood pressure are collected with the ambulatory blood pressure monitoring (ABPM), a device which takes readings for a period of time of 24 h. A modular neural network was designed, with three modules, of which the first and second modules correspond to the systolic and diastolic pressures and the last one to the heart rate. Each module is trained with the data obtained by the ABPM of different patients, this in order that the neural network learns the different behaviors that the blood pressure may have. Also, different architectures and learning methods are considered to obtain the best possible architecture. In addition, two fuzzy inference systems (FISs) for classification purpose are proposed, the first one for the heart rate level and the second one for the night profile of the patient. These were tested with different types of membership functions and then selecting the FIS that obtained the best results. Furthermore, a third FIS as a blood pressure classifier is also used. The different proposed methodologies were tested, in the case of the modular neural network to find the architecture that produces better results and in the fuzzy inference systems to find which membership functions were the ideal ones for the case study, in this way obtaining overall good results. For the case of the modular neural network, the learning accuracy in the first module is 98%, in the second module is 97.62% and the third module is 97.83% respectively. For the night profile, the fuzzy system is compared to a traditional system of production rules, and it is noted that the first one gives all correct outputs and the second one just gives 53% of the outputs, this is due to the uncertainty handling that fuzzy systems can provide, which the traditional system cannot because its rules are very strict. Hybrid intelligent systems for the solution of this kind of complex problems have excellent performance, due to the good learning in each module of the neural network and the classification uncertainty that is well managed by the fuzzy systems, obtaining with this a hybrid combination for achieving good results. [ABSTRACT FROM AUTHOR]

Graphical abstract Highlights • An improved LM, incorporating an adaptive learning rate strategy into the learning process, is developed to improve the modeling performance. • The structure of RRBFNN can be self-organized by using the efficient information-oriented algorithm during the learning process. • The convergence of IOA-RRBFNN has been demonstrated theoretically and experimentally. Abstract In this paper, an efficient self-organizing recurrent radial basis function neural network (RRBFNN), is developed for nonlinear system modeling. In RRBFNN, a two-steps learning approach is introduced during the learning process. In the first step, the objective is to find the optimal set of parameters using an improved Levenberg-Marquardt (LM) algorithm. In the second step, an efficient information-oriented algorithm (IOA), without any thresholds, is developed to optimize the structure of RRBFNN. The hidden neurons in this IOA-based RRBFNN (IOA-RRBFNN) are generated or pruned automatically to reduce the computational complexity and improve the generalization power. Meanwhile, a theoretical analysis on the learning convergence of IOA-RRBFNN is given in details. To demonstrate the merits of IOA-RRBFNN for modeling nonlinear systems, several benchmark problems and a real world application are present with comparisons against other existing methods. Some promising results are reported in this study, indicating that the proposed IOA-RRBFNN performs prediction accuracy in the case of fast learning speed and compact structure. [ABSTRACT FROM AUTHOR]

Abstract: This paper comments on a series of papers using artificial neural networks published in materials journals. The issues discussed include the size of the database for training a neural network, database enlargement for training a neural network, and extrapolation based on modelling results. The paper includes criticisms of other mistakes in those previously published papers. [ABSTRACT FROM AUTHOR]

Abstract: The probability of occurrence of spread-F can be modeled and predicted using neural networks (NNs). This paper presents a feasibility study into the development of a NN based model for the prediction of the probability of occurrence of spread-F over selected equatorial stations within the Brazilian sector. The input space included the day number (seasonal variation), hour (diurnal variation), sunspot number (measure of the solar activity), magnetic index (measure of the magnetic activity) and magnetic position. Twelve years of spread-F data from Brazil (covering the period 1978–1989) measured at the equatorial site Fortaleza (3.9°S, 38.45°W) and low latitude site Cachoeira Paulista (22.6°S, 45.0°W) are used in the development of an input space and NN architecture for the model. Spread-F data that is believed to be related to plasma bubble developments (range spread-F) was used in the development of the model. The model results show the probability of spread-F occurrence as a function of local time, season and latitude. Results from the Brazilian Sector NN (BSNN) based model are presented in this paper, as well as a comparative analysis with a Brazilian model developed for the same purpose. [Copyright &y& Elsevier]

Abstract: A new neural network (NN) based global empirical model for the foF2 parameter, which represents the peak ionospheric electron density, has been developed using extended temporal and spatial geophysical relevant inputs. It has been proposed that this new model be considered as a suitable replacement for the International Union of Radio Science (URSI) and International Radio Consultative Committee (CCIR) model options currently used within the International Reference Ionosphere (IRI) model for the purpose of F2 peak electron density predictions. The most recent version of the model has incorporated data from 135 global ionospheric stations including a number of equatorial stations. This paper concentrates on the ability of this new model to predict foF2 for the equatorial sector, an area that has been identified as problematic within the current IRI peak prediction setup. The improvement in the predictions of the foF2 parameter by the new model as compared to the URSI and CCIR model options of the IRI is demonstrated and the requirement for additional foF2 data from the equatorial zone for the purpose of global modeling of foF2 is highlighted in this paper. [Copyright &y& Elsevier]

Abstract: Landslide-susceptibility mapping is one of the most critical issues in Malaysia. These landslides can be systematically assessed and mapped through a traditional mapping framework that uses geoinformation technologies (GIT). The main purpose of this paper is to investigate the possible application of an artificial neural network model and its cross-application of weights at three study areas in Malaysia, Penang Island, Cameron Highland and Selangor. Landslide locations were identified in the study areas from the interpretation of aerial photographs, field surveys and inventory reports. A landslide-related spatial database was constructed from topographic, soil, geology, and land-cover maps. For the calculation of the relative weight and importance of each factor to a particular landslide occurrence, an artificial neural network (ANN) method was applied. Landslide susceptibility was analyzed using the landslide occurrence factors provided by the artificial neural network model. Then, the landslide-susceptibility analysis results were validated and cross-validated using the landslide locations as study areas. Different training sites were randomly selected to train the neural network, and nine sets of landslide-susceptibility maps were prepared. The paper then illustrates the verification of those maps using an “area under the curve” (AUC) method. The verification results show that the case of the weight using the same test area showed slightly higher accuracy than the weight used for the cross-applied area. Among the three studied areas, the verification results showed similar accuracy trends while using the weight for the study area itself. Cameron showed the best accuracy and Penang showed the worst accuracy. Generally, the verification results showed satisfactory agreement between the susceptibility map and the existing data on the landslide location. [Copyright &y& Elsevier]

Abstract: Electronic commerce (EC) has become a trend in the world nowadays. However, most researches neglect a fundamental issue – the user’s product-specific knowledge on which the useful intelligent systems are based. This research employs the user’s product-specific knowledge and mine his/her interior desire on appropriate target products as a part of personalization process to construct the overall EC strategy for businesses. This paper illustrates a novel web usage mining approach, based on the sequence mining technique applied to user’s navigation behaviour, to discover patterns in the navigation of websites. Three critical contributions are made in this paper: (1) using the footstep graph to visualize the user’s click-stream data and any interesting pattern can be detected more easily and quickly; (2) illustrating a novel sequence mining approach to identify pre-designated user navigation patterns automatically and integrates back-propagation network (BPN) model smoothly; and (3) applying the empirical research to indicate that the proposed approach can predict and categorize the users’ navigation behaviour with high accuracy. [Copyright &y& Elsevier]

Abstract: Wind energy evaluation is an important goal in the conversion of energy systems to more environmentally friendly solutions. In this paper, we present a novel approach to wind speed spatial estimation on the isle of Sicily (Italy): an incremental self-organizing neural network (Generalized Mapping Regressor – GMR) is coupled with exploratory data analysis techniques in order to obtain a map of the spatial distribution of the average wind speed over the entire region. First, the topographic surface of the island was modelled using two different neural techniques and by exploiting the information extracted from a digital elevation model of the region. Then, GMR was used for automatic modelling of the terrain roughness. Afterwards, a statistical analysis of the wind data allowed for the estimation of the parameters of the Weibull wind probability distribution function. In the last sections of the paper, the expected values of the Weibull distributions were regionalized using the GMR neural network. [Copyright &y& Elsevier]

Abstract: In this paper, we investigate the statistical properties of the fluctuations of the Chinese Stock Index, and we study the statistical properties of HSI, DJI, IXIC and SP500 by comparison. According to the theory of artificial neural networks, a stochastic time effective function is introduced in the forecasting model of the indices in the present paper, which gives an improved neural network – the stochastic time effective neural network model. In this model, a promising data mining technique in machine learning has been proposed to uncover the predictive relationships of numerous financial and economic variables. We suppose that the investors decide their investment positions by analyzing the historical data on the stock market, and the historical data are given weights depending on their time, in detail, the nearer the time of the historical data is to the present, the stronger impact the data have on the predictive model, and we also introduce the Brownian motion in order to make the model have the effect of random movement while maintaining the original trend. In the last part of the paper, we test the forecasting performance of the model by using different volatility parameters and we show some results of the analysis for the fluctuations of the global stock indices using the model. [Copyright &y& Elsevier]

Abstract: The paper reports on work concerned with the development of artificial neural network approaches to modeling the propagation of bomb blast waves in a built-up environment. A review of current methods of modeling blast wave propagation identifies a need for a modeling system that is both fast and versatile in its scope of application. This is followed by a description of a preliminary study that used artificial neural networks to estimate peak pressures on buildings protected by simple blast barriers, using data generated from, first, an existing empirical model and, second, miniature bomb-barrier-building experiments. The first of these studies demonstrates the viability of the approach in terms of producing accurate results very rapidly. However, the study using data from live miniature bomb-barrier-building experiments was inconclusive due to a poor distribution of the sample data. The paper then describes on-going research refining this artificial neural network approach to allow the modeling of the time-wise progress of the blast wave over the surfaces of critical structures, facilitating a three-dimensional visualization of the problem. Finally, the paper outlines a proposed novel method of modeling blast wave propagation that uses a coarse-grain simulation approach combined with artificial neural networks, which has the goal of extending modeling to complicated geometries while maintaining rapid processing. [Copyright &y& Elsevier]

Abstract: In this paper, we investigate bidirectional associative memory Cohen–Grossberg neural networks with time delays. By applying the Young inequality technique, Dini derivative, and introducing many real parameters, a series of new and useful criteria on the existence and uniqueness of an equilibrium point and its global asymptotical stability are established. It is shown that in some special cases of the results, the stability criteria can be easily checked. Finally, an example is given to illustrate the result obtained in this paper. [Copyright &y& Elsevier]

Modelling of material behaviour generally involves the development of a mathematical model derived from observations and experimental data. An alternative way discussed in this paper is Artificial Neural Network (ANN)-based modelling which is a subfield of artificial intelligence. The main benefit in using an ANN approach is that the network is built directly from experimental data using the self-organising capabilities of the ANN. In this paper the Two-Parameter Model (TPM) in the fracture of cementitious materials is modelled with a back-propagation ANN. The results of an ANN-based TPM look viable and very promising. [Copyright &y& Elsevier]

This paper describes the mathematical modeling and control of the tension and the speed of moving web in a web-fed machine. In this paper the web control system is structured as a two-input and two-output system. To lessen the effects of system uncertainties, such as system parameters, unmodeled errors, and external disturbance uncertainties in the web control system, a sliding mode control (SMC) is proposed, with an estimator based on a recurrent neural network, which is applied to estimate system uncertainties. Some simulation results are presented to show that the proposed control scheme is feasible for a web-fed machine. [Copyright &y& Elsevier]

Neuromorphic computing was originally referred to as the hardware that mimics neuro-biological architectures to implement models of neural systems. The concept was then extended to the computing systems that can run bio-inspired computing models, e.g., neural networks and deep learning networks. In recent years, the rapid growth of cognitive applications and the limited processing capability of conventional von Neumann architecture on these applications motivated worldwide research on neuromorphic computing systems. In this paper, we review the evolution of neuromorphic computing technique in both computing model and hardware implementation from a historical perspective. Various implementation methods and practices are also discussed. Finally, we present some emerging technologies that may potentially change the landscape of neuromorphic computing in the future, e.g., new devices and interdisciplinary computing architectures. [ABSTRACT FROM AUTHOR]

Assessment of solar potential over a location of interest is an important step towards the successful planning of renewable energy projects. However, solar data are not available for every point of interest due to the absence of meteorological stations and sophisticated solar sensors, so solar radiation has to be estimated using models. This paper presents a hybrid technique to improve the performance of a widely used modeling technique i.e. artificial neural network (ANN). Four different architectures of ANN, namely: multilayer perceptron (MLP), Adaptive neuro-fuzzy inference system (ANFIS), Nonlinear autoregressive recurrent exogenous neural network (NARX), and generalized regression neural networks (GRNN), are used in this study. A wavelet multiresolution analysis is applied to decompose the complex meteorological signals into relatively simple parts, wavelet sub-series, using discrete wavelet transformation (DWT) algorithm. The wavelet sub-series are modeled by the ANN models and reconstructed to estimate the original signal. Hence, enhancing the learning process of these models. Four meteorological parameters, namely: temperature (T), relative humidity (RH), wind speed (WS), and sunshine duration (SSD), are used to mode the global horizontal irradiation (GHI) over Abu Dhabi, the United Arab Emirates. The proposed approach is compared to standalone ANN models and validated using well-known statistical validation metrics including coefficient of determination (R 2 ), root mean square error (RMSE), mean bias error (MBE), mean absolute percentage error (MAPE), and t -statistics. In addition, wavelet cross spectrum (WCS) is used as a visual indicator of the model performance in time, frequency, and phase domains. The results show that using the proposed strategy considerably improves the modeling performance of the ANN with a maximum improvement of 6.84% in R 2 for MLP. In addition, minimum RMSE of 2.78% is observed for GRNN. [ABSTRACT FROM AUTHOR]

Nowadays, more and more object recognition tasks are being solved with Convolutional Neural Networks (CNN). Due to its high recognition rate and fast execution, the convolutional neural networks have enhanced most of computer vision tasks, both existing and new ones. In this article, we propose an implementation of traffic signs recognition algorithm using a convolution neural network. The paper also shows several CNN architectures, which are compared to each other. Training of the neural network is implemented using the TensorFlow library and massively parallel architecture for multithreaded programming CUDA. The entire procedure for traffic sign detection and recognition is executed in real time on a mobile GPU. The experimental results confirmed high efficiency of the developed computer vision system. [ABSTRACT FROM AUTHOR]

In the present world of ‘Big Data,’ the communication channels are always remaining busy and overloaded to transfer quintillion bytes of information. To design an effective equalizer to prevent the inter-symbol interference in such scenario is a challenging task. In this paper, we develop equalizers based on a nonlinear neural structure (wavelet neural network (WNN)) and train it's weighted by a recently developed meta-heuristic (symbiotic organisms search algorithm). The performance of the proposed equalizer is compared with WNN trained by cat swarm optimization (CSO) and clonal selection algorithm (CLONAL), particle swarm optimization (PSO) and least mean square algorithm (LMS). The performance is also compared with other equalizers with structure based on functional link artificial neural network (trigonometric FLANN), radial basis function network (RBF) and finite impulse response filter (FIR). The superior performance is demonstrated on equalization of two non-linear three taps channels and a linear twenty-three taps telephonic channel. It is observed that the performance of the gradient algorithm based equalizers fails in the presence of burst error. The robustness in the performance of the proposed equalizers to handle the burst error conditions is also demonstrated. [ABSTRACT FROM AUTHOR]

Significant variance exists in the nominal capacity of lithium ion (Li-ion) pouch cells used for commercial electric vehicle battery packs. Accurate estimation of heat generation in such cells is critical for designing battery thermal management system. However, multi-physics models describing thermal behaviour of these cells are too complex whereas other numerical models discount the effect of cell capacity on heat generation. This paper proposes a new computational model based on artificial neural network (ANN) for estimating battery heat generation rate with cell nominal capacity as one of its key inputs along with ambient temperature, discharge rate and depth of discharge. A custom-designed calorimeter is utilised for experimentally generating the training dataset for the ANN. Problem of data scarcity is addressed analytically and virtual samples are produced via enthalpy formulation for battery heat generation. Subsequently, the model is trained using Levenberg–Marquardt algorithm. Results disclose that a three-layered feedforward ANN with one hidden layer having six neurons is optimum for this application. The architecture of the trained ANN for accurately simulating thermal behaviour of LiFePO 4 pouch cells of the nominal capacities from 8 to 20 Ah under varied conditions is exemplified. [ABSTRACT FROM AUTHOR]

Validation is a critical component of any modelling process. In artificial neural network (ANN) modelling, validation generally consists of the assessment of model predictive performance on an independent validation set (predictive validity). However, this ignores other aspects of model validation considered to be good practice in other areas of environmental modelling, such as residual analysis (replicative validity) and checking the plausibility of the model in relation to a priori system understanding (structural validity). In order to address this shortcoming, a validation framework for ANNs is introduced in this paper that covers all of the above aspects of validation. In addition, the validann R-package is introduced that enables these validation methods to be implemented in a user-friendly and consistent fashion. The benefits of the framework and R-package are demonstrated for two environmental modelling case studies, highlighting the importance of considering replicative and structural validity in addition to predictive validity. [ABSTRACT FROM AUTHOR]

The study presented in this paper uses a mathematical model to measure the degree in which a product will be perceived as environmentally friendly from its physical attributes. A model based on genetic algorithms and neural networks was developed to predict the judgement of the users about environmental friendliness of different tables. Opinions of real users about a large set of tables were used to train the model. The results of the study suggest that, using this procedure in advanced stages of product design process, designers can determine the set of product's physical attributes that best convey the idea of “environmentally sustainable” to the customer. The analysis of the obtained model allows establishing how different product's attributes influence users' perception. From these results, the utilization of users' affective response models to design the appearance of environmentally sustainable products is discussed. [ABSTRACT FROM AUTHOR]

Cogeneration is the simultaneous generation of electricity and useful heat with the aim of exploiting more efficiently the energy stored in the fuel. Cogeneration is, however, a complex process that encompasses a great amount of sub-systems and variables. This fact makes it very difficult to obtain an analytical model of the whole plant, and therefore providing a mechanism or a methodology able to optimize the global behavior. This paper proposes a neuro-genetic strategy for modeling and optimizing a cogeneration process of a real industrial plant. Firstly, the modeling of the process is carried out by means of several interconnected neural networks where, each neural network deals with a particular sub-system of the plant. Next, the obtained models are used by a genetic algorithm, which solves a multiobjective optimization problem of the plant, where the goal is to minimize the fuel consumption and maximize both the generated electricity and the use of the heat. The proposed approach is evaluated with data of a real cogeneration plant collected over a one-year period. Obtained results show not only that the modeling of the plant is correct but also that the optimization increases significantly the efficiency of the cogeneration plant. [ABSTRACT FROM AUTHOR]

The time-consuming experimental method for handling qualities assessment cannot meet the increasing fast design requirements for the manned space flight. As a tool for the aircraft handling qualities research, the model-predictive-control structured inverse simulation (MPC-IS) has potential applications in the aerospace field to guide the astronauts’ operations and evaluate the handling qualities more effectively. Therefore, this paper establishes MPC-IS for the manual-controlled rendezvous and docking (RVD) and proposes a novel artificial neural network inverse simulation system (ANN-IS) to further decrease the computational cost. The novel system was obtained by replacing the inverse model of MPC-IS with the artificial neural network. The optimal neural network was trained by the genetic Levenberg–Marquardt algorithm, and finally determined by the Levenberg–Marquardt algorithm. In order to validate MPC-IS and ANN-IS, the manual-controlled RVD experiments on the simulator were carried out. The comparisons between simulation results and experimental data demonstrated the validity of two systems and the high computational efficiency of ANN-IS. [ABSTRACT FROM AUTHOR]

The popularity of realized measures and various linear models for volatility forecasting has been the focus of attention in the literature addressing energy markets’ price variability over the past decade. However, there are no studies to help practitioners achieve optimal forecasting accuracy by guiding them to a specific estimator and model. This paper contributes to this literature in two ways. First, to capture the complex patterns hidden in linear models commonly used to forecast realized volatility, we propose a novel framework that couples realized measures with generalized regression based on artificial neural networks. Our second contribution is to comprehensively evaluate multiple-step-ahead volatility forecasts of energy markets using several popular high frequency measures and forecasting models. We compare forecasting performance across models and across realized measures of crude oil, heating oil, and natural gas volatility during three qualitatively distinct periods: the pre-crisis period, the 2008 global financial crisis, and the post-crisis period. We conclude that the newly proposed approach yields both statistical and economic gains, while reducing the tendency to over-predict volatility uniformly during all the tested periods. In addition, the proposed methodology is robust to a substantial structural break induced by the recent financial crisis. Our analysis favors median realized volatility because it delivers the best performance and is a computationally simple alternative for practitioners. [ABSTRACT FROM AUTHOR]

Since the air monitoring stations do not provide the relation between other toxic gas and meteorological parameters with the particulate matter up to 10 micrometer or PM-10. The influence of meteorological as well as correlation with other toxic gas is investigated and used them to forecast PM-10 in the case of Chiang Mai province of Thailand. In this paper an attempt to develop hybrid models of an Autoregressive Integrated Moving Average (ARIMA) model with other exogenous variables (ARIMAX) and Neural Networks (NNs), the two hybrid models, i.e. hybrid ARIMAX-NNs model and hybrid NNs-ARIMAX model were implemented to forecast PM-10 for highly season during January-April of Chiang Mai Province. Simulation results of hybrid model are compared with the results of ARIMA, ARIMAX and NNs model. The experimental results demonstrated that the hybrid NNs-ARIMAX model outperformed best over the hybrid ARIMAX-NNs model, ARIMAX model, NNs model, and ARIMA model respectively. In this case study and maybe other cases, it has proved that the NNs model should be priori captured and filtered the non-stationary non-linear component while the fully linearly stationary residuals were accurately predicted by ARIMAX model later. [ABSTRACT FROM AUTHOR]

Research involving artificial neural networks has tended to be driven towards efficient computation, especially in the domain of pattern recognition, or towards elucidating biological processes in the brain. Models have become more detailed as our understanding of the biology of the brain has increased, incorporating real-time behaviour of individual neurons interacting within complex system structures and dynamics. There are few examples of abstract and fully formal models of biologically plausible neural networks: in the neural networks literature models are often presented as a mixture of mathematical equations and natural language, supported by simulation code and associated experimental results. The informality often hides or obscures important aspects of a particular model, and leaves a large conceptual gap between the model descriptions and the usually low-level programming code used to simulate them. The main contribution of this paper is formally modelling and analysing a biologically plausible neural network model from the literature that exhibits complex neuron-level behaviour and network-level structure. To achieve this a modelling language ‘Pann’ is developed, based on the process algebras CSP and Hybrid χ . It is designed to be convenient for mixing the behaviour of discrete events (such as a neuron spike) with mutable continuous and discrete variables (representing chemical properties of a neuron, for instance). Its behaviour is defined using an operational semantics, from which a set of general properties of the language is proved. The groundwork for the biological model is laid by first formalising some well-known concepts from the artificial neural networks domain, such as feedforward behaviour, backpropagation, and recurrent neural networks. The Pann model of a feedforward network, comprising a set of communicating processes representing individual neurons, is proved equivalent to the standard one-line calculation of feedforward behaviour. [ABSTRACT FROM AUTHOR]