Development Of Neural Networks Research Articles

Detection of Oil Chestnuts Infected by Blue Mold Using Near-Infrared Hyperspectral Imaging Combined with Artificial Neural Networks.

Mildew damage is a major reason for chestnut poor quality and yield loss. In this study, a near-infrared hyperspectral imaging system in the 874–1734 nm spectral range was applied to detect the mildew damage to chestnuts caused by blue mold. Principal component analysis (PCA) scored images were firstly employed to qualitatively and intuitively distinguish moldy chestnuts from healthy chestnuts. Spectral data were extracted from the hyperspectral images. A successive projections algorithm (SPA) was used to select 12 optimal wavelengths. Artificial neural networks, including back propagation neural network (BPNN), evolutionary neural network (ENN), extreme learning machine (ELM), general regression neural network (GRNN) and radial basis neural network (RBNN) were used to build models using the full spectra and optimal wavelengths to distinguish moldy chestnuts. BPNN and ENN models using full spectra and optimal wavelengths obtained satisfactory performances, with classification accuracies all surpassing 99%. The results indicate the potential for the rapid and non-destructive detection of moldy chestnuts by hyperspectral imaging, which would help to develop online detection system for healthy and blue mold infected chestnuts.

First Workshop on Developmental Neural Networks

In nature, brains are built through a process of biological development in which many aspects of the network of neurons and connections change are shaped by external information received through sensory organs. Biological development mechanisms such as axon guidance and dendrite pruning have been shown to rely on neural activity. Despite this, most artificial neural network (ANN) models do not include developmental mechanisms and regard learning as the adjustment of connection weights, while some that do use development restrain it to a period before the ANN is used. It is worthwhile to understand the cognitive functions offered by development and to investigate the fundamental questions raised by artificial neural development. In this workshop, we will explore existing and future approaches that aim to incorporate development into ANNs. Invited speakers will present their work with neural networks, both artificial and biological, in the context of development. Accepted submissions on contemporary work in this field will be presented and we will hold an open discussion on the topic.

Efficient fog prediction with multi-objective evolutionary neural networks

This paper proposes the application of novel artificial neural networks with evolutionary training and different basic functions (sigmoidal, product and radial), for a real problem of fog events classification from meteorological input variables. Specifically, a Multiobjective Evolutionary Algorithm is considered as artificial neural network training mechanism in order to obtain a binary classification model for the detection of fog events at Valladolid airport (Spain). The evolutionary neural models developed are based on two-dimensional performance measures: traditional accuracy and the minimum sensitivity, as the lowest percentage of examples correctly predicted as belonging to each class with respect to the total number of examples in the corresponding class. These performance measures are directly related to features associated with any classifier: its global performance and the rate of the worst classified class. These two objectives are usually in conflict when the optimization process tries to construct models with a high classification rate level in the generalization dataset, and also with a good classification level for each class or minimum sensitivity. A sensitivity analysis of the proposed models is carried out, and thus the subjacent relations between the input variables and the output classification target can be better understood.

Evolutionary Data Driven Modeling and Multi Objective Optimization of Noisy Data Set in Blast Furnace Iron Making Process

Data driven models are constructed for the tuyere cooling heat loss, total blast furnace gas flow, tuyere velocity, productivity, and coke rate for an operational blast furnace of an integrated steel plant by using evolutionary computation methods like bi objective genetic programming (BioGP) and evolutionary neural network (EvoNN), which serve as the objectives for their optimization. The models are used to compute the Pareto tradeoff between these conflicting objectives with the help of predator prey genetic algorithm well tasted for computing the Pareto optimality earlier. The results of optimization and the performances of these models are thoroughly analyzed and accessed and a discussion regarding these data driven models and their influence in the ironmaking process are presented. The results are also compared against a similar calculation performed with the commercial software KIMEME.

Forecasting energy demand, wind generation and carbon dioxide emissions in Ireland using evolutionary neural networks

The ability to accurately predict future power demands, power available from renewable resources and the environmental impact of power generation is vital to the energy sector for the purposes of planning, scheduling and policy making. Machine learning techniques, neural networks in particular, have proven to be very effective methods for addressing these challenging forecasting problems. This research utilizes the powerful evolutionary optimisation algorithm, covariance matrix adaptation evolutionary strategy, as a means of training neural networks to predict short term power demand, wind power generation and carbon dioxide intensity levels in Ireland over a two month period. The network is trained over one month and then tested over the following month. A neural network trained with covariance matrix adaptation evolutionary strategy performs very competitively when compared to other state of the art prediction methods when forecasting Ireland's energy needs, providing fast convergence, more accurate predictions and robust performance. The covariance matrix adaptation evolutionary strategy trained network also gives accurate predictions when predicting multiple time steps into the future.

A novel nature-inspired optimization based neural network simulator to predict coal grindability index

PurposeHardgrove grindability index (HGI) is an important physical parameter used to demonstrate the relative hardness of coal particles. Modeling of HGI based on coal conventional properties is a quite complicated procedure. The paper aims to develop a new accurate model for prediction of HGI that is called optimized evolutionary neural network (OPENN).Design/methodology/approachThe procedure for generation of the proposed OPENN predictive model was performed in two stages. In the first stage, as the high dimensionality involved in the input space, a correlation-based feature selection (CFS) algorithm was used to select the most important influencing variables for HGI prediction. In the second stage, a combination of differential evolution (DE) and biography-based optimization (BBO) algorithms as a global search method were applied to evolve weights of a multi-layer perception neural network.FindingsThe proposed OPENN was examined and compared with other typical models using a wide range of Kentucky coal samples. The testing results showed that the accuracy of the proposed OPENN model is significantly better than the other typical models and can be considered as a promising alternative for HGI prediction.Originality/valueAs HGI test is relatively expensive procedure, there is an economical interest on HGI modeling based on coal conventional properties (proximate, ultimate and petrography); the proposed OPENN model to estimate HGI would be a valuable and practical tool for coal industry.

Predicting host CPU utilization in the cloud using evolutionary neural networks

The Infrastructure as a Service (IaaS) platform in cloud computing provides resources as a service from a pool of compute, network, and storage resources. One of the major challenges facing cloud computing is to predict the usage of these resources in real time. By knowing future demands, cloud data centres can dynamically scale resources to decrease energy consumption while maintaining a high quality of service. However cloud resource consumption is ever changing, making it difficult for accurate predictions to be produced. This motivates the research presented in this paper which aims to predict in advance the level of CPU consumption of a host. This research implements evolutionary Neural Networks (NN), a powerful machine learning method, to make these predictions. A number of state of the art swarm and evolutionary optimization algorithms are implemented to train the neural networks to predict host utilization: Particle Swarm Optimization (PSO), Differential Evolution (DE) and Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES). The results of this research demonstrate that CMA-ES converges faster to a better solution on the training data. However when evaluated on the test data, DE performs statistically equal to CMA-ES. The results also demonstrate that the trained networks are still accurate when applied to CPU utilization data from different hosts with no further training needed. When evaluated to predict multiple steps into the future, the accuracy of the network understandably decreases but still performs well on average.

Application of evolutionary neural networks and support vector machines to model NOx emissions from gas turbines

Evolutionary artificial neural networks and support vector machines were investigated for the modeling of NOx emissions from gas turbines. For ANN’s, a genetic algorithm (GA) with indirect binary encoding was employed to obtain optimal multi-layer perceptron (MLP)-type architectures. The contribution of this research includes the use of an improved GA objective function that takes advantage of the number of effective parameters provided by Bayesian regularization. For SVM’s, a GA is also used with a search space covering all hyperparameters, including the choice of the kernel itself. The objective function took advantage of the number of support vectors to yield models that are more capable of generalization and are less computationally expensive. To test the performance of these models, three datasets describing NOx emissions from three different turbines were used. In previous works, these emissions were modeled using a shallow network architecture obtained by trial and error. When the performance of the models was compared, the optimized ANN’s reduced the mean squared error (MSE) over testing sets by up to 90%, and optimized SVM’s led to a reduction of up to 70%; with the latter’s greatest advantage being computational efficiency and consistency with the different GA runs. The GA converged in a period in the order of minutes, which is more efficient than trial-and-error procedures. This work shows that more attention should be given to the influence of machine learning model architectures on the accuracy of PEMS models, as the computational cost of the GA is well justified by the resulting high accuracy.

Multi-objective Evolutionary Neural Network to Predict Graduation Success at the United States Military Academy

This paper presents an evolutionary neural network approach to classify student graduation status based upon selected academic, demographic, and other indicators. A pareto-based, multi-objective evolutionary algorithm utilizing the Strength Pareto Evolutionary Algorithm (SPEA2) fitness evaluation scheme simultaneously evolves connection weights and identifies the neural network topology using network complexity and classification accuracy as objective functions. A combined vector-matrix representation scheme and differential evolution recombination operators are employed. The model is trained, tested, and validated using 5100 student samples with data compiled from admissions records and institutional research databases. The inputs to the evolutionary neural network model are used to classify students as: graduates, late graduates, or non-graduates. Results of the hybrid method show higher mean classification rates (88%) than the current methodology (80%) with a potential savings of $130M. Additionally, the proposed method is more efficient in that a less complex neural network topology is identified by the algorithm.

An anomaly-based approach for DDoS attack detection in cloud environment

Cloud computing is currently a major focal point for researchers owing to its widespread application and benefits. Cloud computing's complete reliance on the internet for service provision and its distributed nature pose challenges to security, the most serious being insider Distributed Denial of Service (DDoS) which causes a total deactivation of service. Traditional defence mechanisms, such as firewalls, are unable to detect insider attacks. This work proposes an anomaly intrusion detection approach in the hypervisor layer to discourage DDoS activities between virtual machines. The proposed approach is implemented by the evolutionary neural network which integrates the particle swarm optimisation with neural network for detection and classification of the traffic that is exchanged between virtual machines. The performance analysis and results of our proposed approach detect and classify the DDoS attacks in the cloud environment with minimum false alarms and high detection accuracy.

Simultaneous evolutionary neural network based automated video based facial expression analysis

In real life scenario, facial expressions and emotions are nothing but responses to the external and internal events of human being. In Human Computer Interaction (HCI), recognition of end user’s expressions and emotions from the video streaming plays very important role. In such systems it is required to track the dynamic changes in human face movements quickly in order to deliver the required response system. In real time applications, this Facial Expression Recognition (FER) is very helpful like physical fatigue detection based on facial detection and expressions such as driver fatigue detection in order to prevent the accidents on road. Face expression based physical fatigue analysis or detection is out of scope of this work, but this work proposed a Simultaneous Evolutionary Neural Network (SENN) classification scheme is proposed for recognising human emotion or expression. In this work, at first, automatically detects and tracks facial landmarks in videos, and face is detected by using enhanced adaboost algorithm with haar features. Then, in order to describe facial expression modifications, geometric features are taken out and the Local Binary Pattern (LBP) is extracted to improve the detection accuracy and it has a much lower-dimensional size. With the aim of examining the temporal facial expression modifications, we apply SENN probabilistic classifiers, which examine the facial expressions in individual frames, and after that promulgate the likelihoods during the course of the video to take the temporal features of facial expressions such as glad, sad, anger, and fear feelings. The experimental results show that the performance of proposed SENN scheme is attained better results compared than existing recognition schemes like Time-Delay Neural Network with Support Vector Regression (TDNN-SVR) and SVR.

Iris double recognition based on modified evolutionary neural network

Aiming at multicategory iris recognition under illumination and noise interference, this paper proposes a method of iris double recognition based on a modified evolutionary neural network. An equalization histogram and Laplace of Gaussian operator are used to process the iris to suppress illumination and noise interference and Haar wavelet to convert the iris feature to binary feature encoding. Calculate the Hamming distance for the test iris and template iris , and compare with classification threshold, determine the type of iris. If the iris cannot be identified as a different type, there needs to be a secondary recognition. The connection weights in back-propagation (BP) neural network use modified evolutionary neural network to adaptively train. The modified neural network is composed of particle swarm optimization with mutation operator and BP neural network. According to different iris libraries in different circumstances of experimental results, under illumination and noise interference, the correct recognition rate of this algorithm is higher, the ROC curve is closer to the coordinate axis, the training and recognition time is shorter, and the stability and the robustness are better.

Cotton Yarn Quality Prediction Based on Mind Evolutionary Neural Network

In order to forecast the quality of cotton yarn based on the cotton fiber indexes more accurately, a yarn quality forecasting model based on Mind Evolutionary Algorithm (MEA) was used to optimize the BP neural network prediction of yarn strength and yarn evenness. The model adopts the Mind Evolutionary Algorithm to complete the BP network weights and threshold optimization, giving full play to the advantages of this method in the field of global optimization. The results show that the BP neural network prediction model based on Mind Evolutionary Algorithm to optimize is superior to the single BP neural network prediction model.

A new evolutionary neural networks based on intrusion detection systems using multiverse optimization

Building an intrusion detection system (IDS) has become an increasingly urgent issue for detecting network security breaches in computer and network systems. However, an effective and flexible IDS is imperative. In this paper, a new natural evolutionary algorithm (EA) called multiverse optimizer (MVO) is investigated and combined with an artificial neural network (ANN) to develop advanced detection approaches for an IDS. Under this context, the combination of ANN and EA produce evolutionary neural network (ENN). ENN makes this combination a new improved system for solving problems encountered by ANNs. The main idea of this work is to use an MVO to train a feed forward multilayer artificial neural network (MVO-ANN) to identify new attacks. This approach is applied to NSL-KDD and the new benchmark dataset called UNSW-NB15. In this manner, the effectiveness of our approach on detecting various forms of attack is demonstrated. Our results using UNSW-NB15 is better than those that were obtained using NSL-KDD. Furthermore, the efficacy of our proposed method is confirmed by performing better when compared to other well-known heuristic-based approaches such as practical swarm optimizer and artificial neural network (PSO-ANN).

Displacement prediction in geotechnical engineering based on evolutionary neural network

It is very important to study displacement prediction in geotechnical engineering. Nowadays, the grey system method, time series analysis method and artificial neural network method are three main methods. Based on the brief introduction, the three methods are analyzed comprehensively. Their merits and demerits, applied ranges are revealed. To solve the shortcomings of the artificial neural network method, a new prediction method based on new evolutionary neural network is proposed. Finally, through two real engineering applications, the analysis of three main methods and the new evolutionary neural network method all have been verified. The results show that, the grey system method is a kind of exponential approximation to displacement sequence, and time series analysis is linear autoregression approximation, while artificial neural network is nonlinear autoregression approximation. Thus, the grey system method can suitably analyze the sequence, which has the exponential law, the time series method can suitably analyze the random sequence and the neural network method almostly can be applied in any sequences. Moreover, the prediction results of new evolutionary neural network method is the best, and its approximation sequence and the generalization prediction sequence are all coincided with the real displacement sequence well. Thus, the new evolutionary neural network method is an acceptable method to predict the measurement displacements of geotechnical engineering.

Online Performance Monitoring of Grid-Connected Photovoltaic System using Hybrid Improved Fast Evolutionary Programming and Artificial Neural Network

<p>This paper presents the development of online performance monitoring methods for grid-connected photovoltaic (GCPV) system based on hybrid Improved Fast Evolutionary Programming and Artificial Neural Network (IFEP-ANN). The approach has been developed and validated using previous predicted data measurement. Solar radiation (SR), module temperature (MT) and ambient temperature (AT) has been employed as the inputs, and AC output power (PAC) as the sole output to the neural network model. The actual data from the server has been called and uploaded every five minute interval into Matlab by using FTP (File Transfer Protocol) and the predicted AC output power has been produced based on the prediction developed in the training stages. It is then compared with the actual AC output power by using Average Test Ratio, AR. Any predicted AC output power less than the threshold set up, indicates an error has been occurred in the system. The obtained results show that the hybrid IFEP-ANN gives good performance by producing a sufficiently high correlation coefficient, R value of 0.9885. Besides, the proposed technique can analyse and monitor the system in online mode. </p>

Integrated Intelligent Method for Displacement Prediction in Underground Engineering

Considering the complicated monotonously increasing character of the displacement series in underground engineering, the original displacement sequence is divided into two components: the displacement trend sequence and the displacement deviation sequence. This study proposes a new, integrated intelligent method for displacement prediction in underground engineering which is the combining of the grey system method and the evolutionary neural network. The architecture and algorithmic parameters of the neural network simultaneously evolve by immunized evolutionary programming and MBP algorithm. In this method, the grey system method is used to predict the displacement trend sequence, which is one simple monotonous sequence; the evolutionary neural network is used to predict the displacement deviation sequence, which is one very complicated time series. The applications in various real underground engineering examples prove that the approximation sequence and the generalization predication sequence of the integrated intelligent method all coincide well with the measurement displacement sequence. The robustness, performance and applicability of the newly integrated intelligent method are far superior to those of the traditional method. Therefore, this method is an excellent means to predict the measurement displacements of underground engineering.

A Constrained Multi-Objective Learning Algorithm for Feed-Forward Neural Network Classifiers

This paper proposes a new approach to address the optimal design of a Feed-forward Neural Network (FNN) based classifier. The originality of the proposed methodology, called CMOA, lie in the use of a new constraint handling technique based on a self-adaptive penalty procedure in order to direct the entire search effort towards finding only Pareto optimal solutions that are acceptable. Neurons and connections of the FNN Classifier are dynamically built during the learning process. The approach includes differential evolution to create new individuals and then keeps only the non-dominated ones as the basis for the next generation. The designed FNN Classifier is applied to six binary classification benchmark problems, obtained from the UCI repository, and results indicated the advantages of the proposed approach over other existing multi-objective evolutionary neural networks classifiers reported recently in the literature.

Based on SARIMA-BP hybrid model and SSVM model of international crude oil price prediction research

We propose two hybrid prediction models for the international crude oil price: SARIMA-BP hybrid model; and SSVM model. The SARIMA-BP hybrid model combines seasonality analysis and autoregressive integrated moving average with back propagation neural network model. The SSVM model combines seasonality analysis with support vector machines. New York Mercantile Exchange (NYMEX) crude oil's monthly closing price, which ranges from January 2002 to April 2016, is selected as the experimental data sets. Experimental results are compared among the SARIMA-BP hybrid model, SSVM model and single SARIMA model. Empirical analysis shows that the SSVM model has highest prediction accuracy, and the single SARIMA model has lowest prediction accuracy. Thus, the SSVM model displays a better performance in oil price prediction. Further, the SSVM model predicts NYMEX crude oil's closing price will approach 50 dollars per barrel in May 2016. References Z. B. Zhou, X. C. Dong, Analysis about the seasonality of china's crude oil import based on x-12-arima, Energy 42 (42) (2012) 281–288. P. F. Pai, C. S. Lin, A hybrid arima and support vector machines model in stock price forecasting, Omega 33 (6) (2005) 497–505. T. Kriechbaumer, A. Angus, D. Parsons, M. R. Casado, An improved waveletcarima approach for forecasting metal prices, Resources Policy 39 (1) (2014) 32–41. T. Koutroumanidis, K. Ioannou, G. Arabatzis, Predicting fuelwood prices in greece with the use of arima models, artificial neural networks and a hybrid arimacann model, Energy Policy 37 (9) (2009) 3627–3634. H. Mohammadi, L. Su, International evidence on crude oil price dynamics: Applications of arima-garch models, Energy Economics 32 (5) (2010) 1001–1008. H. Chiroma, S. Abdulkareem, T. Herawan, Evolutionary neural network model for west texas intermediate crude oil price prediction, Applied Energy 142 (2015) 266–273. L. A. Laboissiere, R. A. S. Fernandes, G. G. Lage, Maximum and minimum stock price forecasting of brazilian power distribution companies based on artificial neural networks, Applied Soft Computing 35 (2015) 66–74. H. Al-Askar, A. J. Hussain, D. Al-Jumeily, N. Radi, Regularized dynamic self organized neural network inspired by the immune algorithm for financial time series prediction, Lecture Notes in Computer Science 8590 (2014) 56–62. V. Sampathkumar, M. H. Santhi, J. Vanjinathan, Forecasting the land price using statistical and neural network software, Procedia Computer Science 57 (2015) 112–121. J. P. Maran, B. Priya, Modeling of ultrasound assisted intensification of biodiesel production from neem ( azadirachta indica ) oil using response surface methodology and artificial neural network, Fuel 143 (2015) 262–267. D. Singhal, K. S. Swarup, Electricity price forecasting using artificial neural networks, International Journal of Electrical Power and Energy Systems 33 (44) (2008) 111–118. X. Y. Zeng, L. Shu, G. M. Huang, J. Jiang, Triangular fuzzy series forecasting based on grey model and neural network, Applied Mathematical Modelling 40 (3) (2015) 1717–1727. L. Fan, S. Pan, Z. Li, H. Li, An ica-based support vector regression scheme for forecasting crude oil prices, Technological Forecasting and Social Change. F. Wen, J. Xiao, H. E. Zhifang, X. Gong, Stock price prediction based on ssa and svm , Procedia Computer Science 31 (2014) 625–631. X. Guo, D. C. Li, A. Zhang, Improved support vector machine oil price forecast model based on genetic algorithm optimization parameters, Aasri Procedia 1 (4) (2012) 525–530. J. L. Zhang, Y. J. Zhang, L. Zhang, A novel hybrid method for crude oil price forecasting, Energy Economics 49 (2015) 649–659. C. C. Chang, C. J. Lin, Libsvm: A library for support vector machines, Acm Transactions on Intelligent Systems \(and\) Technology 2 (3, article 27) (2007) 389–396. S. E. Yang, L. Huang, Financial crisis warning model based on bp neural network, Systems Engineering-theory and Practice 25 (1) (2005) 12–19.

Modeling groundwater fluctuations by three different evolutionary neural network techniques using hydroclimatic data

The accuracies of three different evolutionary artificial neural network (ANN) approaches, ANN with genetic algorithm (ANN-GA), ANN with particle swarm optimization (ANN-PSO) and ANN with imperialist competitive algorithm (ANN-ICA), were compared in estimating groundwater levels (GWL) based on precipitation, evaporation and previous GWL data. The input combinations determined using auto-, partial auto- and cross-correlation analyses and tried for each model are: (i) GWL t−1 and GWL t−2; (ii) GWL t−1, GWL t−2 and P t ; (iii) GWL t−1, GWL t−2 and E t ; (iv) GWL t−1, GWL t−2, P t and E t ; (v) GWL t−1, GWL t−2 and P t−1 where GWL t , P t and E t indicate the GWL, precipitation and evaporation at time t, individually. The optimal ANN-GA, ANN-PSO and ANN-ICA models were obtained by trying various control parameters. The best accuracies of the ANN-GA, ANN-PSO and ANN-ICA models were obtained from input combination (i). The mean square error accuracies of the ANN-GA and ANN-ICA models were increased by 165 and 124% using ANN-PSO model. The results indicated that the ANN-PSO model performed better than the other models in modeling monthly groundwater levels.