Search results for: back propagation neural network model.

Authors: Igor Astrov, Mikhail Pikkov, Rein Paluoja

Abstract:

This paper focuses on a critical component of the situational awareness (SA), the control of autonomous vertical flight for vectored thrust aerial vehicle (VTAV). With the SA strategy, we proposed a flight control procedure to address the dynamics variation and performance requirement difference of flight trajectory for an unmanned helicopter model with vectored thrust configuration. This control strategy for chosen model of VTAV has been verified by simulation of take-off and forward maneuvers using software package Simulink and demonstrated good performance for fast stabilization of motors, consequently, fast SA with economy in energy can be asserted during search-and-rescue operations.

Keywords: Neural network predictive controller, situational awareness, vectored thrust aerial vehicle.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1502

Authors: Huan Xiong, Ming Chen

Abstract:

In order to research Internet quantificationally and better model the performance of network, this paper proposes a novel AS level network performance model (MNPM), it takes autonomous system (AS) as basic modeling unit, measures E2E performance between any two outdegrees of an AS and organizes measurement results into matrix form which called performance matrix (PM). Inter-AS performance calculation is defined according to performance information stored in PM. Simulation has been implemented to verify the correctness of MNPM and a practical application of MNPM (network congestion detection) is given.

Keywords: AS, network performance, model, metric, congestion.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1408

Authors: S.I Sulaiman, T.K Abdul Rahman, I. Musirin, S. Shaari

Abstract:

This paper presents performance analysis of the Evolutionary Programming-Artificial Neural Network (EPANN) based technique to optimize the architecture and training parameters of a one-hidden layer feedforward ANN model for the prediction of energy output from a grid connected photovoltaic system. The ANN utilizes solar radiation and ambient temperature as its inputs while the output is the total watt-hour energy produced from the grid-connected PV system. EP is used to optimize the regression performance of the ANN model by determining the optimum values for the number of nodes in the hidden layer as well as the optimal momentum rate and learning rate for the training. The EPANN model is tested using two types of transfer function for the hidden layer, namely the tangent sigmoid and logarithmic sigmoid. The best transfer function, neural topology and learning parameters were selected based on the highest regression performance obtained during the ANN training and testing process. It is observed that the best transfer function configuration for the prediction model is [logarithmic sigmoid, purely linear].

Keywords: Artificial neural network (ANN), Correlation coefficient (R), Evolutionary programming-ANN (EPANN), Photovoltaic (PV), logarithmic sigmoid and tangent sigmoid.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1901

Authors: P. Georgieva, S. Feyo de Azevedo

Abstract:

This paper is focused on issues of process modeling and two model based control strategies of a fed-batch sugar crystallization process applying the concept of artificial neural networks (ANNs). The control objective is to force the operation into following optimal supersaturation trajectory. It is achieved by manipulating the feed flow rate of sugar liquor/syrup, considered as the control input. The control task is rather challenging due to the strong nonlinearity of the process dynamics and variations in the crystallization kinetics. Two control alternatives are considered – model predictive control (MPC) and feedback linearizing control (FLC). Adequate ANN process models are first built as part of the controller structures. MPC algorithm outperforms the FLC approach with respect to satisfactory reference tracking and smooth control action. However, the MPC is computationally much more involved since it requires an online numerical optimization, while for the FLC an analytical control solution was determined.

Keywords: artificial neural networks, nonlinear model control, process identification, crystallization process

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1838

Authors: G. Mokryani, M. R. Haghifam, J. Esmaeilpoor

Abstract:

Happening of Ferroresonance phenomenon is one of the reasons of consuming and ruining transformers, so recognition of Ferroresonance phenomenon has a special importance. A novel method for classification of Ferroresonance presented in this paper. Using this method Ferroresonance can be discriminate from other transients such as capacitor switching, load switching, transformer switching. Wavelet transform is used for decomposition of signals and Competitive Neural Network used for classification. Ferroresonance data and other transients was obtained by simulation using EMTP program. Using Daubechies wavelet transform signals has been decomposed till six levels. The energy of six detailed signals that obtained by wavelet transform are used for training and trailing Competitive Neural Network. Results show that the proposed procedure is efficient in identifying Ferroresonance from other events.

Keywords: Competitive Neural Network, Ferroresonance, EMTP program, Wavelet transform.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1424

Authors: Ali Reza Tahavvor, Saeed Hosseini, Nazli Jowkar, Afshin Karimzadeh Fard

Abstract:

Experimental & numeral study of temperature distribution during milling process, is important in milling quality and tools life aspects. In the present study the milling cross-section temperature is determined by using Artificial Neural Networks (ANN) according to the temperature of certain points of the work piece and the point specifications and the milling rotational speed of the blade. In the present work, at first three-dimensional model of the work piece is provided and then by using the Computational Heat Transfer (CHT) simulations, temperature in different nods of the work piece are specified in steady-state conditions. Results obtained from CHT are used for training and testing the ANN approach. Using reverse engineering and setting the desired x, y, z and the milling rotational speed of the blade as input data to the network, the milling surface temperature determined by neural network is presented as output data. The desired points temperature for different milling blade rotational speed are obtained experimentally and by extrapolation method for the milling surface temperature is obtained and a comparison is performed among the soft programming ANN, CHT results and experimental data and it is observed that ANN soft programming code can be used more efficiently to determine the temperature in a milling process.

Keywords: Milling process, rotational speed, Artificial Neural Networks, temperature.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2332

Authors: Mounir Frikha, Michael Meincke, Semia Barouni

Abstract:

This paper proposes a vehicle-to-vehicle propagation model implemented with SDL. To estimate the channel characteristics for Inter-Vehicle communication, we first define a predicted propagation pathloss between the moving vehicles under three typical scenarios. A Ray-tracing method is used for the simple gamma model performance.

Keywords: Inter-vehicle communication (IVC), propagationmodel, road traffic, road vicinity, pathloss.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1352

Authors: Muhammad Aqil, Ichiro Kita, Akira Yano, Nishiyama Soichi

Abstract:

This paper presents an alternate approach that uses artificial neural network to simulate the flood level dynamics in a river basin. The algorithm was developed in a decision support system environment in order to enable users to process the data. The decision support system is found to be useful due to its interactive nature, flexibility in approach and evolving graphical feature and can be adopted for any similar situation to predict the flood level. The main data processing includes the gauging station selection, input generation, lead-time selection/generation, and length of prediction. This program enables users to process the flood level data, to train/test the model using various inputs and to visualize results. The program code consists of a set of files, which can as well be modified to match other purposes. This program may also serve as a tool for real-time flood monitoring and process control. The running results indicate that the decision support system applied to the flood level seems to have reached encouraging results for the river basin under examination. The comparison of the model predictions with the observed data was satisfactory, where the model is able to forecast the flood level up to 5 hours in advance with reasonable prediction accuracy. Finally, this program may also serve as a tool for real-time flood monitoring and process control.

Keywords: Decision Support System, Neural Network, Flood Level

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1626

Authors: Diego Ordonez, Carlos Dafonte, Minia Manteiga, Bernardino Arcayy

Abstract:

This work presents a neural network model for the clustering analysis of data based on Self Organizing Maps (SOM). The model evolves during the training stage towards a hierarchical structure according to the input requirements. The hierarchical structure symbolizes a specialization tool that provides refinements of the classification process. The structure behaves like a single map with different resolutions depending on the region to analyze. The benefits and performance of the algorithm are discussed in application to the Iris dataset, a classical example for pattern recognition.

Keywords: Neural networks, Self-organizing feature maps, Hierarchicalsystems, Pattern clustering methods.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1947

Authors: O. S. Ebrahim, M. A. Badr, A. S. Elgendy, K. O. Shawky, P. K. Jain

Abstract:

This paper demonstrates an improved Loss Model Control (LMC) for a 3-phase induction motor (IM) driving pump load. Compared with other power loss reduction algorithms for IM, the presented one has the advantages of fast and smooth flux adaptation, high accuracy, and versatile implementation. The performance of LMC depends mainly on the accuracy of modeling the motor drive and losses. A loss-model for IM drive that considers the surplus power loss caused by inverter voltage harmonics using closed-form equations and also includes the magnetic saturation has been developed. Further, an Artificial Neural Network (ANN) controller is synthesized and trained offline to determine the optimal flux level that achieves maximum drive efficiency. The drive’s voltage and speed control loops are connecting via the stator frequency to avoid the possibility of excessive magnetization. Besides, the resistance change due to temperature is considered by a first-order thermal model. The obtained thermal information enhances motor protection and control. These together have the potential of making the proposed algorithm reliable. Simulation and experimental studies are performed on 5.5 kW test motor using the proposed control method. The test results are provided and compared with the fixed flux operation to validate the effectiveness.

Keywords: Artificial neural network, ANN, efficiency optimization, induction motor, IM, Pulse Width Modulated, PWM, harmonic losses.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 359

Authors: A. Ourici

Abstract:

Rapid progress in process automation and tightening quality standards result in a growing demand being placed on fault detection and diagnostics methods to provide both speed and reliability of motor quality testing. Doubly fed induction generators are used mainly for wind energy conversion in MW power plants. This paper presents a detection of an inter turn stator and an open phase faults, in a doubly fed induction machine whose stator and rotor are supplied by two pulse width modulation (PWM) inverters. The method used in this article to detect these faults, is based on Park-s Vector Approach, using a neural network.

Keywords: Doubly fed induction machine, inter turn stator fault, neural network, open phase fault, Park's vector approach, PWMinverter.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1647

Authors: Seema Chopra, R. Mitra, Vijay Kumar

Abstract:

In this paper, a neural network tuned fuzzy controller is proposed for controlling Multi-Input Multi-Output (MIMO) systems. For the convenience of analysis, the structure of MIMO fuzzy controller is divided into single input single-output (SISO) controllers for controlling each degree of freedom. Secondly, according to the characteristics of the system-s dynamics coupling, an appropriate coupling fuzzy controller is incorporated to improve the performance. The simulation analysis on a two-level mass–spring MIMO vibration system is carried out and results show the effectiveness of the proposed fuzzy controller. The performance though improved, the computational time and memory used is comparatively higher, because it has four fuzzy reasoning blocks and number may increase in case of other MIMO system. Then a fuzzy neural network is designed from a set of input-output training data to reduce the computing burden during implementation. This control strategy can not only simplify the implementation problem of fuzzy control, but also reduce computational time and consume less memory.

Keywords: Fuzzy Control, Neural Network, MIMO System, Optimization of Membership functions.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3210

Authors: O. O. Obe, V. Balanica, E. Neagoe

Abstract:

The effects of hypertension are often lethal thus its early detection and prevention is very important for everybody. In this paper, a neural network (NN) model was developed and trained based on a dataset of hypertension causative parameters in order to forecast the likelihood of occurrence of hypertension in patients. Our research goal was to analyze the potential of the presented NN to predict, for a period of time, the risk of hypertension or the risk of developing this disease for patients that are or not currently hypertensive. The results of the analysis for a given patient can support doctors in taking pro-active measures for averting the occurrence of hypertension such as recommendations regarding the patient behavior in order to lower his hypertension risk. Moreover, the paper envisages a set of three example scenarios in order to determine the age when the patient becomes hypertensive, i.e. determine the threshold for hypertensive age, to analyze what happens if the threshold hypertensive age is set to a certain age and the weight of the patient if being varied, and, to set the ideal weight for the patient and analyze what happens with the threshold of hypertensive age.

Keywords: Neural Network, hypertension, data set, training set, supervised learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1660

Authors: Thejaswi H. Raya, Vineetha Bettaiah, Heggere S. Ranganath

Abstract:

For over a decade, the Pulse Coupled Neural Network (PCNN) based algorithms have been successfully used in image interpretation applications including image segmentation. There are several versions of the PCNN based image segmentation methods, and the segmentation accuracy of all of them is very sensitive to the values of the network parameters. Most methods treat PCNN parameters like linking coefficient and primary firing threshold as global parameters, and determine them by trial-and-error. The automatic determination of appropriate values for linking coefficient, and primary firing threshold is a challenging problem and deserves further research. This paper presents a method for obtaining global as well as local values for the linking coefficient and the primary firing threshold for neurons directly from the image statistics. Extensive simulation results show that the proposed approach achieves excellent segmentation accuracy comparable to the best accuracy obtainable by trial-and-error for a variety of images.

Keywords: Automatic Selection of PCNN Parameters, Image Segmentation, Neural Networks, Pulse Coupled Neural Network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2288

Authors: Guojian Cheng, Tianshi Liu, Jiaxin Han, Zheng Wang

Abstract:

The competitive learning is an adaptive process in which the neurons in a neural network gradually become sensitive to different input pattern clusters. The basic idea behind the Kohonen-s Self-Organizing Feature Maps (SOFM) is competitive learning. SOFM can generate mappings from high-dimensional signal spaces to lower dimensional topological structures. The main features of this kind of mappings are topology preserving, feature mappings and probability distribution approximation of input patterns. To overcome some limitations of SOFM, e.g., a fixed number of neural units and a topology of fixed dimensionality, Growing Self-Organizing Neural Network (GSONN) can be used. GSONN can change its topological structure during learning. It grows by learning and shrinks by forgetting. To speed up the training and convergence, a new variant of GSONN, twin growing cell structures (TGCS) is presented here. This paper first gives an introduction to competitive learning, SOFM and its variants. Then, we discuss some GSONN with fixed dimensionality, which include growing cell structures, its variants and the author-s model: TGCS. It is ended with some testing results comparison and conclusions.

Keywords: Artificial neural networks, Competitive learning, Growing cell structures, Self-organizing feature maps.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1542

Authors: Apidet Booranawong

Abstract:

In an original directed diffusion routing protocol, a sink requests sensing data from a source node by flooding interest messages to the network. Then, the source finds the sink by sending exploratory data messages to all nodes that generate incoming interest messages. This protocol signaling can cause heavy traffic in the network, an interference of the radio signal, collisions, great energy consumption of sensor nodes, etc. According to this research problem, this paper investigates the effect of sending interest and exploratory data messages on the performance of directed diffusion routing protocol. We demonstrate the research problem occurred from employing directed diffusion protocol in mobile wireless environments. For this purpose, we perform a set of experiments by using NS2 (network simulator 2). The radio propagation models; Two-ray ground reflection with and without shadow fading are included to investigate the effect of signaling. The simulation results show that the number of times of sent and received protocol signaling in the case of sending interest and exploratory data messages are larger than the case of sending other protocol signals, especially in the case of shadowing model. Additionally, the number of exploratory data message is largest in one round of the protocol procedure.

Keywords: Directed diffusion, Flooding, Interest message, Exploratory data message, Radio propagation model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1784

Authors: Tienfuan Kerh, Hsienchang Lu, Rob Saunders

Abstract:

Shoreline erosion problems caused by global warming and sea level rising may result in losing of land areas, so it should be examined regularly to reduce possible negative impacts. Initially in this study, three sets of survey images obtained from the years of 1990, 2001, and 2010, respectively, are digitalized by using graphical software to establish the spatial coordinates of six major beaches around the island of Taiwan. Then, by overlaying the known multi-period images, the change of shoreline can be observed from their distribution of coordinates. In addition, the neural network approximation is used to develop a model for predicting shoreline variation in the years of 2015 and 2020. The comparison results show that there is no significant change of total sandy area for all beaches in the three different periods. However, the prediction results show that two beaches may exhibit an increasing of total sandy areas under a statistical 95% confidence interval. The proposed method adopted in this study may be applicable to other shorelines of interest around the world.

Keywords: Digitalized shoreline coordinates, survey image overlaying, neural network approximation, total beach sandy areas.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2016

Authors: A. Majeed, P. Ali

Abstract:

Before designing an electrical system, the estimation of load is necessary for unit sizing and demand-generation balancing. The system could be a stand-alone system for a village or grid connected or integrated renewable energy to grid connection, especially as there are non–electrified villages in developing countries. In the classical model, the energy demand was found by estimating the household appliances multiplied with the amount of their rating and the duration of their operation, but in this paper, information exists for electrified villages could be used to predict the demand, as villages almost have the same life style. This paper describes a method used to predict the average energy consumed in each two months for every consumer living in a village by Artificial Neural Network (ANN). The input data are collected using a regional survey for samples of consumers representing typical types of different living, household appliances and energy consumption by a list of information, and the output data are collected from administration office of Piramagrun for each corresponding consumer. The result of this study shows that the average demand for different consumers from four villages in different months throughout the year is approximately 12 kWh/day, this model estimates the average demand/day for every consumer with a mean absolute percent error of 11.8%, and MathWorks software package MATLAB version 7.6.0 that contains and facilitate Neural Network Toolbox was used.

Keywords: Artificial neural network, load estimation, regional survey, rural electrification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1359

Authors: Shah Rizam M. S. B., Farah Yasmin A.R., Ahmad Ihsan M. Y., Shazana K.

Abstract:

Agriculture products are being more demanding in market today. To increase its productivity, automation to produce these products will be very helpful. The purpose of this work is to measure and determine the ripeness and quality of watermelon. The textures on watermelon skin will be captured using digital camera. These images will be filtered using image processing technique. All these information gathered will be trained using ANN to determine the watermelon ripeness accuracy. Initial results showed that the best model has produced percentage accuracy of 86.51%, when measured at 32 hidden units with a balanced percentage rate of training dataset.

Keywords: Artificial Neural Network (ANN), Digital ImageProcessing, YCbCr Colour Space, Watermelon Ripeness.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2953

Authors: Farhad Asadi, S. Hossein Sadati

Abstract:

This paper presents a prediction performance of feedforward Multilayer Perceptron (MLP) and Echo State Networks (ESN) trained with extended Kalman filter. Feedforward neural networks and ESN are powerful neural networks which can track and predict nonlinear signals. However, their tracking performance depends on the specific signals or data sets, having the risk of instability accompanied by large error. In this study we explore this process by applying different network size and leaking rate for prediction of nonlinear or chaotic signals in MLP neural networks. Major problems of ESN training such as the problem of initialization of the network and improvement in the prediction performance are tackled. The influence of coefficient of activation function in the hidden layer and other key parameters are investigated by simulation results. Extended Kalman filter is employed in order to improve the sequential and regulation learning rate of the feedforward neural networks. This training approach has vital features in the training of the network when signals have chaotic or non-stationary sequential pattern. Minimization of the variance in each step of the computation and hence smoothing of tracking were obtained by examining the results, indicating satisfactory tracking characteristics for certain conditions. In addition, simulation results confirmed satisfactory performance of both of the two neural networks with modified parameterization in tracking of the nonlinear signals.

Keywords: Feedforward neural networks, nonlinear signal prediction, echo state neural networks approach, leaking rates, capacity of neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 758

Authors: Md. Ashikur Rahman Khan, M. M. Rahman

Abstract:

In electrical discharge machining (EDM), a complete and clear theory has not yet been established. The developed theory (physical models) yields results far from reality due to the complexity of the physics. It is difficult to select proper parameter settings in order to achieve better EDM performance. However, modelling can solve this critical problem concerning the parameter settings. Therefore, the purpose of the present work is to develop mathematical model to predict performance characteristics of EDM on Ti-5Al-2.5Sn titanium alloy. Response surface method (RSM) and artificial neural network (ANN) are employed to develop the mathematical models. The developed models are verified through analysis of variance (ANOVA). The ANN models are trained, tested, and validated utilizing a set of data. It is found that the developed ANN and mathematical model can predict performance of EDM effectively. Thus, the model has found a precise tool that turns EDM process cost-effective and more efficient.

Keywords: Analysis of variance, artificial neural network, material removal rate, modelling, response surface method, surface finish.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 731

Authors: Hidehiko Okada

Abstract:

The author proposes an extension of genetic algorithm (GA) for solving fuzzy-valued optimization problems. In the proposed GA, values in the genotypes are not real numbers but fuzzy numbers. Evolutionary processes in GA are extended so that GA can handle genotype instances with fuzzy numbers. The proposed method is applied to evolving neural networks with fuzzy weights and biases. Experimental results showed that fuzzy neural networks evolved by the fuzzy GA could model hidden target fuzzy functions well despite the fact that no training data was explicitly provided.

Keywords: Evolutionary algorithm, genetic algorithm, fuzzy number, neural network, neuroevolution.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2303

Authors: Zulkiflee M., Robiah Y., Nur Azman Abu, Shahrin S.

Abstract:

Malware is software which was invented and meant for doing harms on computers. Malware is becoming a significant threat in computer network nowadays. Malware attack is not just only involving financial lost but it can also cause fatal errors which may cost lives in some cases. As new Internet Protocol version 6 (IPv6) emerged, many people believe this protocol could solve most malware propagation issues due to its broader addressing scheme. As IPv6 is still new compares to native IPv4, some transition mechanisms have been introduced to promote smoother migration. Unfortunately, these transition mechanisms allow some malwares to propagate its attack from IPv4 to IPv6 network environment. In this paper, a proof of concept shall be presented in order to show that some existing IPv4 malware detection technique need to be improvised in order to detect malware attack in dual-stack network more efficiently. A testbed of dual-stack network environment has been deployed and some genuine malware have been released to observe their behaviors. The results between these different scenarios will be analyzed and discussed further in term of their behaviors and propagation methods. The results show that malware behave differently on IPv6 from the IPv4 network protocol on the dual-stack network environment. A new detection technique is called for in order to cater this problem in the near future.

Keywords: Dual-Stack, Malware, Worm, IPv6;IDS

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2005

Authors: El Mahdi Barrah, Said Safi, Abdessamad Malaoui

Abstract:

In this paper, we present an algorithm for reconstruction from incomplete 2D scans for tifinagh characters. This algorithm is based on using correlation between the lost block and its neighbors. This system proposed contains three main parts: pre-processing, features extraction and recognition. In the first step, we construct a database of tifinagh characters. In the second step, we will apply “shape analysis algorithm”. In classification part, we will use Neural Network. The simulation results demonstrate that the proposed method give good results.

Keywords: Tifinagh character recognition, Neural networks, Local cost computation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1286

Authors: Chia-Ling Chang, Chung-Sheng Liao

Abstract:

The present study focuses on the discussion over the parameter of Artificial Neural Network (ANN). Sensitivity analysis is applied to assess the effect of the parameters of ANN on the prediction of turbidity of raw water in the water treatment plant. The result shows that transfer function of hidden layer is a critical parameter of ANN. When the transfer function changes, the reliability of prediction of water turbidity is greatly different. Moreover, the estimated water turbidity is less sensitive to training times and learning velocity than the number of neurons in the hidden layer. Therefore, it is important to select an appropriate transfer function and suitable number of neurons in the hidden layer in the process of parameter training and validation.

Keywords: Artificial Neural Network (ANN), sensitivity analysis, turbidity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2814

Authors: Jimeng Shi, Mahek Jain, Giri Narasimhan

Abstract:

Time Series Forecasting (TSF) is used to predict the target variables at a future time point based on the learning from previous time points. To keep the problem tractable, learning methods use data from a fixed length window in the past as an explicit input. In this paper, we study how the performance of predictive models change as a function of different look-back window sizes and different amounts of time to predict into the future. We also consider the performance of the recent attention-based transformer models, which had good success in the image processing and natural language processing domains. In all, we compare four different deep learning methods (Recurrent Neural Network (RNN), Long Short-term Memory (LSTM), Gated Recurrent Units (GRU), and Transformer) along with a baseline method. The dataset (hourly) we used is the Beijing Air Quality Dataset from the website of University of California, Irvine (UCI), which includes a multivariate time series of many factors measured on an hourly basis for a period of 5 years (2010-14). For each model, we also report on the relationship between the performance and the look-back window sizes and the number of predicted time points into the future. Our experiments suggest that Transformer models have the best performance with the lowest Mean   Absolute Errors (MAE = 14.599, 23.273) and Root Mean Square Errors (RSME = 23.573, 38.131) for most of our single-step and multi-steps predictions. The best size for the look-back window to predict 1 hour into the future appears to be one day, while 2 or 4 days perform the best to predict 3 hours into the future.

Keywords: Air quality prediction, deep learning algorithms, time series forecasting, look-back window.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1171

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

In this paper, an approach to reduce the computation steps required by fast neural networksfor the searching process is presented. The principle ofdivide and conquer strategy is applied through imagedecomposition. Each image is divided into small in sizesub-images and then each one is tested separately usinga fast neural network. The operation of fast neuralnetworks based on applying cross correlation in thefrequency domain between the input image and theweights of the hidden neurons. Compared toconventional and fast neural networks, experimentalresults show that a speed up ratio is achieved whenapplying this technique to locate human facesautomatically in cluttered scenes. Furthermore, fasterface detection is obtained by using parallel processingtechniques to test the resulting sub-images at the sametime using the same number of fast neural networks. Incontrast to using only fast neural networks, the speed upratio is increased with the size of the input image whenusing fast neural networks and image decomposition.

Keywords: Fast Neural Networks, 2D-FFT, CrossCorrelation, Image decomposition, Parallel Processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2179

Authors: J. K. Alhassan, B. Attah, S. Misra

Abstract:

Human beings have the ability to make logical decisions. Although human decision - making is often optimal, it is insufficient when huge amount of data is to be classified. Medical dataset is a vital ingredient used in predicting patient’s health condition. In other to have the best prediction, there calls for most suitable machine learning algorithms. This work compared the performance of Artificial Neural Network (ANN) and Decision Tree Algorithms (DTA) as regards to some performance metrics using diabetes data. WEKA software was used for the implementation of the algorithms. Multilayer Perceptron (MLP) and Radial Basis Function (RBF) were the two algorithms used for ANN, while RegTree and LADTree algorithms were the DTA models used. From the results obtained, DTA performed better than ANN. The Root Mean Squared Error (RMSE) of MLP is 0.3913 that of RBF is 0.3625, that of RepTree is 0.3174 and that of LADTree is 0.3206 respectively.

Keywords: Artificial neural network, classification, decision tree, diabetes mellitus.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2417

Authors: Hamid Reza Boveiri

Abstract:

Classification of Persian printed numeral characters has been considered and a proposed system has been introduced. In representation stage, for the first time in Persian optical character recognition, extended moment invariants has been utilized as characters image descriptor. In classification stage, four different classifiers namely minimum mean distance, nearest neighbor rule, multi layer perceptron, and fuzzy min-max neural network has been used, which first and second are traditional nonparametric statistical classifier. Third is a well-known neural network and forth is a kind of fuzzy neural network that is based on utilizing hyperbox fuzzy sets. Set of different experiments has been done and variety of results has been presented. The results showed that extended moment invariants are qualified as features to classify Persian printed numeral characters.

Keywords: Extended moment invariants, optical characterrecognition, Persian numerals classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1919

Authors: Najam Aziz, Nasru Minallah, Ahmad Junaid, Kashaf Gul

Abstract:

Landcover classification using automated classification techniques, while employing remotely sensed multi-spectral imagery, is one of the promising areas of research. Different land conditions at different time are captured through satellite and monitored by applying different classification algorithms in specific environment. In this paper, a SPOT-5 image provided by SUPARCO has been studied and classified in Environment for Visual Interpretation (ENVI), a tool widely used in remote sensing. Then, Artificial Neural Network (ANN) classification technique is used to detect the land cover changes in Abbottabad district. Obtained results are compared with a pixel based Distance classifier. The results show that ANN gives the better overall accuracy of 99.20% and Kappa coefficient value of 0.98 over the Mahalanobis Distance Classifier.

Keywords: Landcover classification, artificial neural network, remote sensing, SPOT-5.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1607