Search

Artificial neural networks are widely established models of computational intelligence that have been tested for their effectiveness in a variety of real-world applications. These models require a set of parameters to be fitted through the use of an optimization technique. However, an issue that researchers often face is finding an efficient range of values for the parameters of the artificial neural network. This paper proposes an innovative technique for generating a promising range of values for the parameters of the artificial neural network. Finding the value field is conducted by a series of rules for partitioning the original set of values or expanding it, the rules of which are generated using grammatical evolution. After finding a promising interval of values, any optimization technique such as a genetic algorithm can be used to train the artificial neural network on that interval of values. The new technique was tested on a wide range of problems from the relevant literature and the results were extremely promising. [ABSTRACT FROM AUTHOR]

This paper presents and analyzes a programming tool that implements a method for classification and function regression problems. This method builds new features from existing ones with the assistance of a hybrid algorithm that makes use of artificial neural networks and grammatical evolution. The implemented software exploits modern multi-core computing units for faster execution. The method has been applied to a variety of classification and function regression problems, and an extensive comparison with other methods of computational intelligence is made. [ABSTRACT FROM AUTHOR]

Energy consumption has been increasing steadily due to globalization and industrialization. Studies have shown that buildings are responsible for the biggest proportion of energy consumption; for example in European Union countries, energy consumption in buildings represents around 40% of the total energy consumption. In order to control energy consumption in buildings, different policies have been proposed, from utilizing bioclimatic architectures to the use of predictive models within control approaches. There are mainly three groups of predictive models including engineering, statistical and artificial intelligence models. Nowadays, artificial intelligence models such as neural networks and support vector machines have also been proposed because of their high potential capabilities of performing accurate nonlinear mappings between inputs and outputs in real environments which are not free of noise. The main objective of this paper is to compare a neural network model which was designed utilizing statistical and analytical methods, with a group of neural network models designed benefiting from a multi objective genetic algorithm. Moreover, the neural network models were compared to a naïve autoregressive baseline model. The models are intended to predict electric power demand at the Solar Energy Research Center (Centro de Investigación en Energía SOLar or CIESOL in Spanish) bioclimatic building located at the University of Almeria, Spain. Experimental results show that the models obtained from the multi objective genetic algorithm (MOGA) perform comparably to the model obtained through a statistical and analytical approach, but they use only 0.8% of data samples and have lower model complexity. [ABSTRACT FROM AUTHOR]

The paper introduces the artificial intelligence (AI) approach as a general method for the design and optimization study of heat exchangers. Genetic Algorithms (GA) and Artificial Neural Networks (ANN) are applied in the paper. An AGENN model, combining Genetic Algorithms with Artificial Neural Networks, was developed and validated against the desired data on a large falling film evaporator. A broad range of operating conditions and geometric configurations are considered in the study. Four kinds of tubes are deliberated, including plain and enhanced tubes. Different tube pass arrangements, i.e., top-to-bottom, bottom-to-top, and side-by-side, are discussed. Finally, the effects of liquid refrigerant mass flow rate, as well as the number of flooded tubes on the performance of the evaporator, are analyzed. The total heat transfer rate of the evaporator, predicted by the model, is in good agreement with the desired data; the maximum error is lower than ±3%. The highest heat transfer rate of the evaporator is 1140.01 kW and corresponds to Turbo EHP tubes, and bottom-to-top tubes pass arrangements, which guarantee the best thermal energy conversion. The presented approach can be referred to as a complementary technique in heat exchanger design procedures, besides the common rating and sizing tasks. It is an effective and alternative method for the existing approaches, considering the complexity of analytical and numerical techniques as well as the high costs of experiments. [ABSTRACT FROM AUTHOR]

This paper proposes a strain prediction method for wind turbine blades using genetic algorithm back propagation neural networks (GA-BPNNs) with applied loads, loading positions, and displacement as inputs, and the study can be used to provide more data for the wind turbine blades' health assessment and life prediction. Among all parameters to be tested in full-scale static testing of wind turbine blades, strain is very important. The correlation between the blade strain and the applied loads, loading position, displacement, etc., is non-linear, and the number of input variables is too much, thus the calculation and prediction of the blade strain are very complex and difficult. Moreover, the number of measuring points on the blade is limited, so the full-scale blade static test cannot usually provide enough data and information for the improvement of the blade design. As a result of these concerns, this paper studies strain prediction methods for full-scale blade static testing by introducing GA-BPNN. The accuracy and usability of the GA-BPNN prediction model was verified by the comparison with BPNN model and the FEA results. The results show that BPNN can be effectively used to predict the strain of unmeasured points of wind turbine blades. [ABSTRACT FROM AUTHOR]

The intensity non-stationarity is one of the basic characteristics of ground motions, the influences of which on the dynamic responses of structures is a pressing issue in the field of earthquake engineering. The BP neural network modified by the genetic algorithm was adopted in this research to investigate the influence of intensity nonstationary inputs on the structural dynamic responses from a new perspective. Firstly, many training data were generated from the prediction formula of dynamic response. The BP neural network was then pre-trained by sparsely selected data to optimize the initial weights and biases. Finally, the BP neural network was trained by all data, and the mean square error of predicted responses compared with the target response were less than 10−5. The calculation formula of sensitivity was also derived here to quantify the influence of the input change on the output. The presented method combines the advantages of neural networks in nonlinear multi-variable fitting and provides a new perspective for the study of earthquake nonstationary characteristics and their influence on the structural dynamic responses. [ABSTRACT FROM AUTHOR]

Screening and evaluation of developmental disorders include complex and challenging procedures, exhibit uncertainties in the diagnostic fit, and require high clinical expertise. Although typically, clinicians' evaluations rely on diagnostic instrumentation, child observations, and parents' reports, these may occasionally result in subjective evaluation outcomes. Current advances in artificial intelligence offer new opportunities for decision making, classification, and clinical assessment. This study explores the performance of different neural network optimizers in biometric datasets for screening typically and non-typically developed children for speech and language communication deficiencies. The primary motivation was to give clinicians a robust tool to help them identify speech disorders automatically using artificial intelligence methodologies. For this reason, in this study, we use a new dataset from an innovative, recently developed serious game collecting various data on children's speech and language responses. Specifically, we employed different neural network approaches such as Artificial Neural Networks (ANNs), K-Nearest Neighbor (KNN), Support Vector Machines (SVM), along with state-of-the-art Optimizers, namely the Adam, the Broyden–Fletcher–Goldfarb–Shanno (BFGS), Genetic algorithm (GAs), and Particle Swarm Optimization algorithm (PSO). The results were promising, while Integer-bounded Neural Network proved to be the best competitor, opening new inquiries for future work towards automated classification supporting clinicians' decisions on neurodevelopmental disorders. [ABSTRACT FROM AUTHOR]

In the present work, an innovative two-phase method is presented for parameter tuning in radial basis function artificial neural networks. These kinds of machine learning models find application in many scientific fields in classification problems or in function regression. In the first phase, a technique based on particle swarm optimization is performed to locate a promising interval of values for the network parameters. Particle swarm optimization was used as it is a highly reliable method for global optimization problems, and in addition, it is one of the fastest and most-flexible techniques of its class. In the second phase, the network was trained within the optimal interval using a global optimization technique such as a genetic algorithm. Furthermore, in order to speed up the training of the network and due to the use of a two-stage method, parallel programming techniques were utilized. The new method was applied to a number of famous classification and regression datasets, and the results were more than promising. [ABSTRACT FROM AUTHOR]

Forecasting exchange rates is a complex problem that has benefitted from recent advances and research in machine learning. The main goal of this study is to design and implement a method to improve the learning performance of artificial neural networks with large volumes of data using population-based metaheuristics. The micro-genetic training algorithm is thoroughly analyzed using profiling tools to find bottlenecks. We compare the use of a micro-genetic algorithm to predict changes in currency exchange rates on a data set containing more than 500,000 values. To find the best parameters of neural networks, we propose an improved micro-genetic training algorithm by dividing the training data into mini batches. In this case, the improved micro-genetic algorithm proved to be much faster compared to the standard genetic algorithm, while achieving the same prediction accuracy. This allows for the use of this algorithm for just-in-time predictions of high frequency data. Here, neural network models are first created and validated on an existing data set. Then, the new data values can be added to neural network models and retrained in a short time. [ABSTRACT FROM AUTHOR]

Machine learning is a very important approach to pattern classification. This paper provides a better insight into Incremental Attribute Learning (IAL) with further analysis as to why it can exhibit better performance than conventional batch training. IAL is a novel supervised machine learning strategy, which gradually trains features in one or more chunks. Previous research showed that IAL can obtain lower classification error rates than a conventional batch training approach. Yet the reason for that is still not very clear. In this study, the feasibility of IAL is verified by mathematical approaches. Moreover, experimental results derived by IAL neural networks on benchmarks also confirm the mathematical validation. [ABSTRACT FROM AUTHOR]

Bio-inspired legged robots have the potential to traverse uneven terrains in a very efficient way. The effectiveness of the robot gait depends on the joint symmetry of the robot; variations in joint symmetries can result in different types of gaits suitable for different scenarios. In the literature, symmetric and asymmetric gaits have been synthesized for legged robots; however, no relation between the gait effectiveness and joint symmetry has been studied. In this research work, the effect of joint symmetry on the robot gait is studied. To test the suggested algorithm, spider-like robot morphology was created in a simulator. The simulation environment was set to a flat surface where the robots could be tested. The simulations were performed on the PyroSim software platform, a physics engine built on top of the Open Dynamics Engine. The quadrupedal robot was created with eight joints, and it is controlled using an artificial neural network. The artificial neural network was optimized using a genetic algorithm. Different robot symmetries were tested, i.e., diagonal joint symmetry, diagonal joint reverse symmetry, adjacent joint symmetry, adjacent joint reverse symmetry and random joint symmetry or joint asymmetry. The robot controllers for each joint symmetry were evolved for a set number of generations and the robot controllers were evaluated using a fitness function that we designed. Our results showed that symmetry in joint movement could help in generating optimal gaits for our test terrain, and joint symmetry produced gaits that were already present in nature. Moreover, our results also showed that certain joint symmetries tended to perform better than others in terms of stability, speed, and distance traveled. [ABSTRACT FROM AUTHOR]

A neuro fuzzy hybrid model (NFHM) is proposed as a new artificial intelligence method to classify blood pressure (BP). The NFHM uses techniques such as neural networks, fuzzy logic and evolutionary computation, and in the last case genetic algorithms (GAs) are used. The main goal is to model the behavior of blood pressure based on monitoring data of 24 h per patient and based on this to obtain the trend, which is classified using a fuzzy system based on rules provided by an expert, and these rules are optimized by a genetic algorithm to obtain the best possible number of rules for the classifier with the lowest classification error. Simulation results are presented to show the advantage of the proposed model. [ABSTRACT FROM AUTHOR]

There are growing demands for condition-based monitoring of gearboxes, and techniques to improve the reliability, effectiveness and accuracy for fault diagnosis are considered valuable contributions. Feature selection is still an important aspect in machine learning-based diagnosis in order to reach good performance in the diagnosis system. The main aim of this research is to propose a multi-stage feature selection mechanism for selecting the best set of condition parameters on the time, frequency and time-frequency domains, which are extracted from vibration signals for fault diagnosis purposes in gearboxes. The selection is based on genetic algorithms, proposing in each stage a new subset of the best features regarding the classifier performance in a supervised environment. The selected features are augmented at each stage and used as input for a neural network classifier in the next step, while a new subset of feature candidates is treated by the selection process. As a result, the inherent exploration and exploitation of the genetic algorithms for finding the best solutions of the selection problem are locally focused. The approach is tested on a dataset from a real test bed with several fault classes under different running conditions of load and velocity. The model performance for diagnosis is over 98%. [ABSTRACT FROM AUTHOR]

Abstract: Accurate measurements of global solar radiation and atmospheric temperature, as well as the availability of the predictions of their evolution over time, are important for different areas of applications, such as agriculture, renewable energy and energy management, or thermal comfort in buildings. For this reason, an intelligent, light-weight and portable sensor was developed, using artificial neural network models as the time-series predictor mechanisms. These have been identified with the aid of a procedure based on the multi-objective genetic algorithm. As cloudiness is the most significant factor affecting the solar radiation reaching a particular location on the Earth surface, it has great impact on the performance of predictive solar radiation models for that location. This work also represents one step towards the improvement of such models by using ground-to-sky hemispherical colour digital images as a means to estimate cloudiness by the fraction of visible sky corresponding to clouds and to clear sky. The implementation of predictive models in the prototype has been validated and the system is able to function reliably, providing measurements and four-hour forecasts of cloudiness, solar radiation and air temperature. [ABSTRACT FROM AUTHOR]