Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 26

Search results for: feed-forward

26 Model-Based Control for Piezoelectric-Actuated Systems Using Inverse Prandtl-Ishlinskii Model and Particle Swarm Optimization

Authors: Jin-Wei Liang, Hung-Yi Chen, Lung Lin


In this paper feedforward controller is designed to eliminate nonlinear hysteresis behaviors of a piezoelectric stack actuator (PSA) driven system. The control design is based on inverse Prandtl-Ishlinskii (P-I) hysteresis model identified using particle swarm optimization (PSO) technique. Based on the identified P-I model, both the inverse P-I hysteresis model and feedforward controller can be determined. Experimental results obtained using the inverse P-I feedforward control are compared with their counterparts using hysteresis estimates obtained from the identified Bouc-Wen model. Effectiveness of the proposed feedforward control scheme is demonstrated. To improve control performance feedback compensation using traditional PID scheme is adopted to integrate with the feedforward controller.

Keywords: the Bouc-Wen hysteresis model, particle swarm optimization, Prandtl-Ishlinskii model, automation engineering

Procedia PDF Downloads 396
25 Feedforward Neural Network with Backpropagation for Epilepsy Seizure Detection

Authors: Natalia Espinosa, Arthur Amorim, Rudolf Huebner


Epilepsy is a chronic neural disease and around 50 million people in the world suffer from this disease, however, in many cases, the individual acquires resistance to the medication, which is known as drug-resistant epilepsy, where a detection system is necessary. This paper showed the development of an automatic system for seizure detection based on artificial neural networks (ANN), which are common techniques of machine learning. Discrete Wavelet Transform (DWT) is used for decomposing electroencephalogram (EEG) signal into main brain waves, with these frequency bands is extracted features for training a feedforward neural network with backpropagation, finally made a pattern classification, seizure or non-seizure. Obtaining 95% accuracy in epileptic EEG and 100% in normal EEG.

Keywords: Artificial Neural Network (ANN), Discrete Wavelet Transform (DWT), Epilepsy Detection , Seizure.

Procedia PDF Downloads 26
24 Comparative Analysis of Sigmoidal Feedforward Artificial Neural Networks and Radial Basis Function Networks Approach for Localization in Wireless Sensor Networks

Authors: Ashish Payal, C. S. Rai, B. V. R. Reddy


With the increasing use and application of Wireless Sensor Networks (WSN), need has arisen to explore them in more effective and efficient manner. An important area which can bring efficiency to WSNs is the localization process, which refers to the estimation of the position of wireless sensor nodes in an ad hoc network setting, in reference to a coordinate system that may be internal or external to the network. In this paper, we have done comparison and analysed Sigmoidal Feedforward Artificial Neural Networks (SFFANNs) and Radial Basis Function (RBF) networks for developing localization framework in WSNs. The presented work utilizes the Received Signal Strength Indicator (RSSI), measured by static node on 100 x 100 m2 grid from three anchor nodes. The comprehensive evaluation of these approaches is done using MATLAB software. The simulation results effectively demonstrate that FFANNs based sensor motes will show better localization accuracy as compared to RBF.

Keywords: localization, wireless sensor networks, artificial neural network, radial basis function, multi-layer perceptron, backpropagation, RSSI, GPS

Procedia PDF Downloads 195
23 Comparative Analysis of Control Techniques Based Sliding Mode for Transient Stability Assessment for Synchronous Multicellular Converter

Authors: Rihab Hamdi, Amel Hadri Hamida, Fatiha Khelili, Sakina Zerouali, Ouafae Bennis


This paper features a comparative study performance of sliding mode controller (SMC) for closed-loop voltage control of direct current to direct current (DC-DC) three-cells buck converter connected in parallel, operating in continuous conduction mode (CCM), based on pulse-width modulation (PWM) with SMC based on hysteresis modulation (HM) where an adaptive feedforward technique is adopted. On one hand, for the PWM-based SM, the approach is to incorporate a fixed-frequency PWM scheme which is effectively a variant of SM control. On the other hand, for the HM-based SM, oncoming an adaptive feedforward control that makes the hysteresis band variable in the hysteresis modulator of the SM controller in the aim to restrict the switching frequency variation in the case of any change of the line input voltage or output load variation are introduced. The results obtained under load change, input change and reference change clearly demonstrates a similar dynamic response of both proposed techniques, their effectiveness is fast and smooth tracking of the desired output voltage. The PWM-based SM technique has greatly improved the dynamic behavior with a bit advantageous compared to the HM-based SM technique, as well as provide stability in any operating conditions. Simulation studies in MATLAB/Simulink environment have been performed to verify the concept.

Keywords: DC-DC converter, hysteresis modulation, parallel multi-cells converter, pulse-width modulation, robustness, sliding mode control

Procedia PDF Downloads 37
22 Decision Support System for Fetus Status Evaluation Using Cardiotocograms

Authors: Oyebade K. Oyedotun


The cardiotocogram is a technical recording of the heartbeat rate and uterine contractions of a fetus during pregnancy. During pregnancy, several complications can occur to both the mother and the fetus; hence it is very crucial that medical experts are able to find technical means to check the healthiness of the mother and especially the fetus. It is very important that the fetus develops as expected in stages during the pregnancy period; however, the task of monitoring the health status of the fetus is not that which is easily achieved as the fetus is not wholly physically available to medical experts for inspection. Hence, doctors have to resort to some other tests that can give an indication of the status of the fetus. One of such diagnostic test is to obtain cardiotocograms of the fetus. From the analysis of the cardiotocograms, medical experts can determine the status of the fetus, and therefore necessary medical interventions. Generally, medical experts classify examined cardiotocograms into ‘normal’, ‘suspect’, or ‘pathological’. This work presents an artificial neural network based decision support system which can filter cardiotocograms data, producing the corresponding statuses of the fetuses. The capability of artificial neural network to explore the cardiotocogram data and learn features that distinguish one class from the others has been exploited in this research. In this research, feedforward and radial basis neural networks were trained on a publicly available database to classify the processed cardiotocogram data into one of the three classes: ‘normal’, ‘suspect’, or ‘pathological’. Classification accuracies of 87.8% and 89.2% were achieved during the test phase of the trained network for the feedforward and radial basis neural networks respectively. It is the hope that while the system described in this work may not be a complete replacement for a medical expert in fetus status evaluation, it can significantly reinforce the confidence in medical diagnosis reached by experts.

Keywords: decision support, cardiotocogram, classification, neural networks

Procedia PDF Downloads 229
21 Artificial Neural Network Based Approach in Prediction of Potential Water Pollution Across Different Land-Use Patterns

Authors: M.Rüştü Karaman, İsmail İşeri, Kadir Saltalı, A.Reşit Brohi, Ayhan Horuz, Mümin Dizman


Considerable relations has recently been given to the environmental hazardous caused by agricultural chemicals such as excess fertilizers. In this study, a neural network approach was investigated in the prediction of potential nitrate pollution across different land-use patterns by using a feedforward multilayered computer model of artificial neural network (ANN) with proper training. Periodical concentrations of some anions, especially nitrate (NO3-), and cations were also detected in drainage waters collected from the drain pipes placed in irrigated tomato field, unirrigated wheat field, fallow and pasture lands. The soil samples were collected from the irrigated tomato field and unirrigated wheat field on a grid system with 20 m x 20 m intervals. Site specific nitrate concentrations in the soil samples were measured for ANN based simulation of nitrate leaching potential from the land profiles. In the application of ANN model, a multi layered feedforward was evaluated, and data sets regarding with training, validation and testing containing the measured soil nitrate values were estimated based on spatial variability. As a result of the testing values, while the optimal structures of 2-15-1 was obtained (R2= 0.96, P < 0.01) for unirrigated field, the optimal structures of 2-10-1 was obtained (R2= 0.96, P < 0.01) for irrigated field. The results showed that the ANN model could be successfully used in prediction of the potential leaching levels of nitrate, based on different land use patterns. However, for the most suitable results, the model should be calibrated by training according to different NN structures depending on site specific soil parameters and varied agricultural managements.

Keywords: artificial intelligence, ANN, drainage water, nitrate pollution

Procedia PDF Downloads 207
20 Orthogonal Basis Extreme Learning Algorithm and Function Approximation

Authors: Ying Li, Yan Li


A new algorithm for single hidden layer feedforward neural networks (SLFN), Orthogonal Basis Extreme Learning (OBEL) algorithm, is proposed and the algorithm derivation is given in the paper. The algorithm can decide both the NNs parameters and the neuron number of hidden layer(s) during training while providing extreme fast learning speed. It will provide a practical way to develop NNs. The simulation results of function approximation showed that the algorithm is effective and feasible with good accuracy and adaptability.

Keywords: neural network, orthogonal basis extreme learning, function approximation

Procedia PDF Downloads 381
19 Assessment the Quality of Telecommunication Services by Fuzzy Inferences System

Authors: Oktay Nusratov, Ramin Rzaev, Aydin Goyushov


Fuzzy inference method based approach to the forming of modular intellectual system of assessment the quality of communication services is proposed. Developed under this approach the basic fuzzy estimation model takes into account the recommendations of the International Telecommunication Union in respect of the operation of packet switching networks based on IP-protocol. To implement the main features and functions of the fuzzy control system of quality telecommunication services it is used multilayer feedforward neural network.

Keywords: quality of communication, IP-telephony, fuzzy set, fuzzy implication, neural network

Procedia PDF Downloads 329
18 Model Predictive Control of Turbocharged Diesel Engine with Exhaust Gas Recirculation

Authors: U. Yavas, M. Gokasan


Control of diesel engine’s air path has drawn a lot of attention due to its multi input-multi output, closed coupled, non-linear relation. Today, precise control of amount of air to be combusted is a must in order to meet with tight emission limits and performance targets. In this study, passenger car size diesel engine is modeled by AVL Boost RT, and then simulated with standard, industry level PID controllers. Finally, linear model predictive control is designed and simulated. This study shows the importance of modeling and control of diesel engines with flexible algorithm development in computer based systems.

Keywords: predictive control, engine control, engine modeling, PID control, feedforward compensation

Procedia PDF Downloads 436
17 Optimisation of the Input Layer Structure for Feedforward Narx Neural Networks

Authors: Zongyan Li, Matt Best


This paper presents an optimization method for reducing the number of input channels and the complexity of the feed-forward NARX neural network (NN) without compromising the accuracy of the NN model. By utilizing the correlation analysis method, the most significant regressors are selected to form the input layer of the NN structure. An application of vehicle dynamic model identification is also presented in this paper to demonstrate the optimization technique and the optimal input layer structure and the optimal number of neurons for the neural network is investigated.

Keywords: correlation analysis, F-ratio, levenberg-marquardt, MSE, NARX, neural network, optimisation

Procedia PDF Downloads 237
16 Compact Low-Voltage Biomedical Instrumentation Amplifiers

Authors: Phanumas Khumsat, Chalermchai Janmane


Low-voltage instrumentation amplifier has been proposed for 3-lead electrocardiogram measurement system. The circuit’s interference rejection technique is based upon common-mode feed-forwarding where common-mode currents have cancelled each other at the output nodes. The common-mode current for cancellation is generated by means of common-mode sensing and emitter or source followers with resistors employing only one transistor. Simultaneously this particular transistor also provides common-mode feedback to the patient’s right/left leg to further reduce interference entering the amplifier. The proposed designs have been verified with simulations in 0.18-µm CMOS process operating under 1.0-V supply with CMRR greater than 80dB. Moreover ECG signals have experimentally recorded with the proposed instrumentation amplifiers implemented from discrete BJT (BC547, BC558) and MOSFET (ALD1106, ALD1107) transistors working with 1.5-V supply.

Keywords: electrocardiogram, common-mode feedback, common-mode feedforward, communication engineering

Procedia PDF Downloads 261
15 Understanding and Improving Neural Network Weight Initialization

Authors: Diego Aguirre, Olac Fuentes


In this paper, we present a taxonomy of weight initialization schemes used in deep learning. We survey the most representative techniques in each class and compare them in terms of overhead cost, convergence rate, and applicability. We also introduce a new weight initialization scheme. In this technique, we perform an initial feedforward pass through the network using an initialization mini-batch. Using statistics obtained from this pass, we initialize the weights of the network, so the following properties are met: 1) weight matrices are orthogonal; 2) ReLU layers produce a predetermined number of non-zero activations; 3) the output produced by each internal layer has a unit variance; 4) weights in the last layer are chosen to minimize the error in the initial mini-batch. We evaluate our method on three popular architectures, and a faster converge rates are achieved on the MNIST, CIFAR-10/100, and ImageNet datasets when compared to state-of-the-art initialization techniques.

Keywords: deep learning, image classification, supervised learning, weight initialization

Procedia PDF Downloads 54
14 A Study on Green Building Certification Systems within the Context of Anticipatory Systems

Authors: Taner Izzet Acarer, Ece Ceylan Baba


This paper examines green building certification systems and their current processes in comparison with anticipatory systems. Rapid growth of human population and depletion of natural resources are causing irreparable damage to urban and natural environment. In this context, the concept of ‘sustainable architecture’ has emerged in the 20th century so as to establish and maintain standards for livable urban spaces, to improve quality of urban life, and to preserve natural resources for future generations. The construction industry is responsible for a large part of the resource consumption and it is believed that the ‘green building’ designs that emerge in construction industry can reduce environmental problems and contribute to sustainable development around the world. A building must meet a specific set of criteria, set forth through various certification systems, in order to be eligible for designation as a green building. It is disputable whether methods used by green building certification systems today truly serve the purposes of creating a sustainable world. Accordingly, this study will investigate the sets of rating systems used by the most popular green building certification programs, including LEED (Leadership in Energy and Environmental Design), BREEAM (Building Research Establishment's Environmental Assessment Methods), DGNB (Deutsche Gesellschaft für Nachhaltiges Bauen System), in terms of ‘Anticipatory Systems’ in accordance with the certification processes and their goals, while discussing their contribution to architecture. The basic methodology of the study is as follows. Firstly analyzes of brief historical and literature review of green buildings and certificate systems will be stated. Secondly, processes of green building certificate systems will be disputed by the help of anticipatory systems. Anticipatory Systems is a set of systems designed to generate action-oriented projections and to forecast potential side effects using the most current data. Anticipatory Systems pull the future into the present and take action based on future predictions. Although they do not have a claim to see into the future, they can provide foresight data. When shaping the foresight data, Anticipatory Systems use feedforward instead of feedback, enabling them to forecast the system’s behavior and potential side effects by establishing a correlation between the system’s present/past behavior and projected results. This study indicates the goals and current status of LEED, BREEAM and DGNB rating systems that created by using the feedback technique will be examined and presented in a chart. In addition, by examining these rating systems with the anticipatory system that using the feedforward method, the negative influences of the potential side effects on the purpose and current status of the rating systems will be shown in another chart. By comparing the two obtained data, the findings will be shown that rating systems are used for different goals than the purposes they are aiming for. In conclusion, the side effects of green building certification systems will be stated by using anticipatory system models.

Keywords: anticipatory systems, BREEAM, certificate systems, DGNB, green buildings, LEED

Procedia PDF Downloads 120
13 Predict Suspended Sediment Concentration Using Artificial Neural Networks Technique: Case Study Oued El Abiod Watershed, Algeria

Authors: Adel Bougamouza, Boualam Remini, Abd El Hadi Ammari, Feteh Sakhraoui


The assessment of sediments being carried by a river is importance for planning and designing of various water resources projects. In this study, Artificial Neural Network Techniques are used to estimate the daily suspended sediment concentration for the corresponding daily discharge flow in the upstream of Foum El Gherza dam, Biskra, Algeria. The FFNN, GRNN, and RBNN models are established for estimating current suspended sediment values. Some statistics involving RMSE and R2 were used to evaluate the performance of applied models. The comparison of three AI models showed that the RBNN model performed better than the FFNN and GRNN models with R2 = 0.967 and RMSE= 5.313 mg/l. Therefore, the ANN model had capability to improve nonlinear relationships between discharge flow and suspended sediment with reasonable precision.

Keywords: artificial neural network, Oued Abiod watershed, feedforward network, generalized regression network, radial basis network, sediment concentration

Procedia PDF Downloads 300
12 Prediction of Structural Response of Reinforced Concrete Buildings Using Artificial Intelligence

Authors: Juan Bojórquez, Henry E. Reyes, Edén Bojórquez, Alfredo Reyes-Salazar


This paper addressed the use of Artificial Intelligence to obtain the structural reliability of reinforced concrete buildings. For this purpose, artificial neuronal networks (ANN) are developed to predict seismic demand hazard curves. In order to have enough input-output data to train the ANN, a set of reinforced concrete buildings (low, mid, and high rise) are designed, then a probabilistic seismic hazard analysis is made to obtain the seismic demand hazard curves. The results are then used as input-output data to train the ANN in a feedforward backpropagation model. The predicted values of the seismic demand hazard curves found by the ANN are then compared. Finally, it is concluded that the computer time analysis is significantly lower and the predictions obtained from the ANN were accurate in comparison to the values obtained from the conventional methods.

Keywords: structural reliability, seismic design, machine learning, artificial neural network, probabilistic seismic hazard analysis, seismic demand hazard curves

Procedia PDF Downloads 35
11 Simulation of Flow through Dam Foundation by FEM and ANN Methods Case Study: Shahid Abbaspour Dam

Authors: Mehrdad Shahrbanozadeh, Gholam Abbas Barani, Saeed Shojaee


In this study, a finite element (Seep3D model) and an artificial neural network (ANN) model were developed to simulate flow through dam foundation. Seep3D model is capable of simulating three-dimensional flow through a heterogeneous and anisotropic, saturated and unsaturated porous media. Flow through the Shahid Abbaspour dam foundation has been used as a case study. The FEM with 24960 triangular elements and 28707 nodes applied to model flow through foundation of this dam. The FEM being made denser in the neighborhood of the curtain screen. The ANN model developed for Shahid Abbaspour dam is a feedforward four layer network employing the sigmoid function as an activator and the back-propagation algorithm for the network learning. The water level elevations of the upstream and downstream of the dam have been used as input variables and the piezometric heads as the target outputs in the ANN model. The two models are calibrated and verified using the Shahid Abbaspour’s dam piezometric data. Results of the models were compared with those measured by the piezometers which are in good agreement. The model results also revealed that the ANN model performed as good as and in some cases better than the FEM.

Keywords: seepage, dam foundation, finite element method, neural network, seep 3D model

Procedia PDF Downloads 351
10 Modeling and Dynamics Analysis for Intelligent Skid-Steering Vehicle Based on Trucksim-Simulink

Authors: Yansong Zhang, Xueyuan Li, Junjie Zhou, Xufeng Yin, Shihua Yuan, Shuxian Liu


Aiming at the verification of control algorithms for skid-steering vehicles, a vehicle simulation model of 6×6 electric skid-steering unmanned vehicle was established based on Trucksim and Simulink. The original transmission and steering mechanism of Trucksim are removed, and the electric skid-steering model and a closed-loop controller for the vehicle speed and yaw rate are built in Simulink. The simulation results are compared with the ones got by theoretical formulas. The results show that the predicted tire mechanics and vehicle kinematics of Trucksim-Simulink simulation model are closed to the theoretical results. Therefore, it can be used as an effective approach to study the dynamic performance and control algorithm of skid-steering vehicle. In this paper, a method of motion control based on feed forward control is also designed. The simulation results show that the feed forward control strategy can make the vehicle follow the target yaw rate more quickly and accurately, which makes the vehicle have more maneuverability.

Keywords: skid-steering, Trucksim-Simulink, feedforward control, dynamics

Procedia PDF Downloads 207
9 Identification System for Grading Banana in Food Processing Industry

Authors: Ebenezer O. Olaniyi, Oyebade K. Oyedotun, Khashman Adnan


In the food industry high quality production is required within a limited time to meet up with the demand in the society. In this research work, we have developed a model which can be used to replace the human operator due to their low output in production and slow in making decisions as a result of an individual differences in deciding the defective and healthy banana. This model can perform the vision attributes of human operators in deciding if the banana is defective or healthy for food production based. This research work is divided into two phase, the first phase is the image processing where several image processing techniques such as colour conversion, edge detection, thresholding and morphological operation were employed to extract features for training and testing the network in the second phase. These features extracted in the first phase were used in the second phase; the classification system phase where the multilayer perceptron using backpropagation neural network was employed to train the network. After the network has learned and converges, the network was tested with feedforward neural network to determine the performance of the network. From this experiment, a recognition rate of 97% was obtained and the time taken for this experiment was limited which makes the system accurate for use in the food industry.

Keywords: banana, food processing, identification system, neural network

Procedia PDF Downloads 360
8 Data Mining of Students' Performance Using Artificial Neural Network: Turkish Students as a Case Study

Authors: Samuel Nii Tackie, Oyebade K. Oyedotun, Ebenezer O. Olaniyi, Adnan Khashman


Artificial neural networks have been used in different fields of artificial intelligence, and more specifically in machine learning. Although, other machine learning options are feasible in most situations, but the ease with which neural networks lend themselves to different problems which include pattern recognition, image compression, classification, computer vision, regression etc. has earned it a remarkable place in the machine learning field. This research exploits neural networks as a data mining tool in predicting the number of times a student repeats a course, considering some attributes relating to the course itself, the teacher, and the particular student. Neural networks were used in this work to map the relationship between some attributes related to students’ course assessment and the number of times a student will possibly repeat a course before he passes. It is the hope that the possibility to predict students’ performance from such complex relationships can help facilitate the fine-tuning of academic systems and policies implemented in learning environments. To validate the power of neural networks in data mining, Turkish students’ performance database has been used; feedforward and radial basis function networks were trained for this task; and the performances obtained from these networks evaluated in consideration of achieved recognition rates and training time.

Keywords: artificial neural network, data mining, classification, students’ evaluation

Procedia PDF Downloads 474
7 Nelder-Mead Parametric Optimization of Elastic Metamaterials with Artificial Neural Network Surrogate Model

Authors: Jiaqi Dong, Qing-Hua Qin, Yi Xiao


Some of the most fundamental challenges of elastic metamaterials (EMMs) optimization can be attributed to the high consumption of computational power resulted from finite element analysis (FEA) simulations that render the optimization process inefficient. Furthermore, due to the inherent mesh dependence of FEA, minuscule geometry features, which often emerge during the later stages of optimization, induce very fine elements, resulting in enormously high time consumption, particularly when repetitive solutions are needed for computing the objective function. In this study, a surrogate modelling algorithm is developed to reduce computational time in structural optimization of EMMs. The surrogate model is constructed based on a multilayer feedforward artificial neural network (ANN) architecture, trained with prepopulated eigenfrequency data prepopulated from FEA simulation and optimized through regime selection with genetic algorithm (GA) to improve its accuracy in predicting the location and width of the primary elastic band gap. With the optimized ANN surrogate at the core, a Nelder-Mead (NM) algorithm is established and its performance inspected in comparison to the FEA solution. The ANNNM model shows remarkable accuracy in predicting the band gap width and a reduction of time consumption by 47%.

Keywords: artificial neural network, machine learning, mechanical metamaterials, Nelder-Mead optimization

Procedia PDF Downloads 26
6 Non-Linear Assessment of Chromatographic Lipophilicity and Model Ranking of Newly Synthesized Steroid Derivatives

Authors: Milica Karadzic, Lidija Jevric, Sanja Podunavac-Kuzmanovic, Strahinja Kovacevic, Anamarija Mandic, Katarina Penov Gasi, Marija Sakac, Aleksandar Okljesa, Andrea Nikolic


The present paper deals with chromatographic lipophilicity prediction of newly synthesized steroid derivatives. The prediction was achieved using in silico generated molecular descriptors and quantitative structure-retention relationship (QSRR) methodology with the artificial neural networks (ANN) approach. Chromatographic lipophilicity of the investigated compounds was expressed as retention factor value logk. For QSRR modeling, a feedforward back-propagation ANN with gradient descent learning algorithm was applied. Using the novel sum of ranking differences (SRD) method generated ANN models were ranked. The aim was to distinguish the most consistent QSRR model that can be found, and similarity or dissimilarity between the models that could be noticed. In this study, SRD was performed with average values of retention factor value logk as reference values. An excellent correlation between experimentally observed retention factor value logk and values predicted by the ANN was obtained with a correlation coefficient higher than 0.9890. Statistical results show that the established ANN models can be applied for required purpose. This article is based upon work from COST Action (TD1305), supported by COST (European Cooperation in Science and Technology).

Keywords: artificial neural networks, liquid chromatography, molecular descriptors, steroids, sum of ranking differences

Procedia PDF Downloads 205
5 Setting Uncertainty Conditions Using Singular Values for Repetitive Control in State Feedback

Authors: Muhammad A. Alsubaie, Mubarak K. H. Alhajri, Tarek S. Altowaim


A repetitive controller designed to accommodate periodic disturbances via state feedback is discussed. Periodic disturbances can be represented by a time delay model in a positive feedback loop acting on system output. A direct use of the small gain theorem solves the periodic disturbances problem via 1) isolating the delay model, 2) finding the overall system representation around the delay model and 3) designing a feedback controller that assures overall system stability and tracking error convergence. This paper addresses uncertainty conditions for the repetitive controller designed in state feedback in either past error feedforward or current error feedback using singular values. The uncertainty investigation is based on the overall system found and the stability condition associated with it; depending on the scheme used, to set an upper/lower limit weighting parameter. This creates a region that should not be exceeded in selecting the weighting parameter which in turns assures performance improvement against system uncertainty. Repetitive control problem can be described in lifted form. This allows the usage of singular values principle in setting the range for the weighting parameter selection. The Simulation results obtained show a tracking error convergence against dynamic system perturbation if the weighting parameter chosen is within the range obtained. Simulation results also show the advantage of weighting parameter usage compared to the case where it is omitted.

Keywords: model mismatch, repetitive control, singular values, state feedback

Procedia PDF Downloads 57
4 Implications of Optimisation Algorithm on the Forecast Performance of Artificial Neural Network for Streamflow Modelling

Authors: Martins Y. Otache, John J. Musa, Abayomi I. Kuti, Mustapha Mohammed


The performance of an artificial neural network (ANN) is contingent on a host of factors, for instance, the network optimisation scheme. In view of this, the study examined the general implications of the ANN training optimisation algorithm on its forecast performance. To this end, the Bayesian regularisation (Br), Levenberg-Marquardt (LM), and the adaptive learning gradient descent: GDM (with momentum) algorithms were employed under different ANN structural configurations: (1) single-hidden layer, and (2) double-hidden layer feedforward back propagation network. Results obtained revealed generally that the gradient descent with momentum (GDM) optimisation algorithm, with its adaptive learning capability, used a relatively shorter time in both training and validation phases as compared to the Levenberg- Marquardt (LM) and Bayesian Regularisation (Br) algorithms though learning may not be consummated; i.e., in all instances considering also the prediction of extreme flow conditions for 1-day and 5-day ahead, respectively especially using the ANN model. In specific statistical terms on the average, model performance efficiency using the coefficient of efficiency (CE) statistic were Br: 98%, 94%; LM: 98 %, 95 %, and GDM: 96 %, 96% respectively for training and validation phases. However, on the basis of relative error distribution statistics (MAE, MAPE, and MSRE), GDM performed better than the others overall. Based on the findings, it is imperative to state that the adoption of ANN for real-time forecasting should employ training algorithms that do not have computational overhead like the case of LM that requires the computation of the Hessian matrix, protracted time, and sensitivity to initial conditions; to this end, Br and other forms of the gradient descent with momentum should be adopted considering overall time expenditure and quality of the forecast as well as mitigation of network overfitting. On the whole, it is recommended that evaluation should consider implications of (i) data quality and quantity and (ii) transfer functions on the overall network forecast performance.

Keywords: streamflow, neural network, optimisation, algorithm

Procedia PDF Downloads 26
3 A Hybrid Model of Structural Equation Modelling-Artificial Neural Networks: Prediction of Influential Factors on Eating Behaviors

Authors: Maryam Kheirollahpour, Mahmoud Danaee, Amir Faisal Merican, Asma Ahmad Shariff


Background: The presence of nonlinearity among the risk factors of eating behavior causes a bias in the prediction models. The accuracy of estimation of eating behaviors risk factors in the primary prevention of obesity has been established. Objective: The aim of this study was to explore the potential of a hybrid model of structural equation modeling (SEM) and Artificial Neural Networks (ANN) to predict eating behaviors. Methods: The Partial Least Square-SEM (PLS-SEM) and a hybrid model (SEM-Artificial Neural Networks (SEM-ANN)) were applied to evaluate the factors affecting eating behavior patterns among university students. 340 university students participated in this study. The PLS-SEM analysis was used to check the effect of emotional eating scale (EES), body shape concern (BSC), and body appreciation scale (BAS) on different categories of eating behavior patterns (EBP). Then, the hybrid model was conducted using multilayer perceptron (MLP) with feedforward network topology. Moreover, Levenberg-Marquardt, which is a supervised learning model, was applied as a learning method for MLP training. The Tangent/sigmoid function was used for the input layer while the linear function applied for the output layer. The coefficient of determination (R²) and mean square error (MSE) was calculated. Results: It was proved that the hybrid model was superior to PLS-SEM methods. Using hybrid model, the optimal network happened at MPLP 3-17-8, while the R² of the model was increased by 27%, while, the MSE was decreased by 9.6%. Moreover, it was found that which one of these factors have significantly affected on healthy and unhealthy eating behavior patterns. The p-value was reported to be less than 0.01 for most of the paths. Conclusion/Importance: Thus, a hybrid approach could be suggested as a significant methodological contribution from a statistical standpoint, and it can be implemented as software to be able to predict models with the highest accuracy.

Keywords: hybrid model, structural equation modeling, artificial neural networks, eating behavior patterns

Procedia PDF Downloads 31
2 Dimensionality Reduction in Modal Analysis for Structural Health Monitoring

Authors: Elia Favarelli, Enrico Testi, Andrea Giorgetti


Autonomous structural health monitoring (SHM) of many structures and bridges became a topic of paramount importance for maintenance purposes and safety reasons. This paper proposes a set of machine learning (ML) tools to perform automatic feature selection and detection of anomalies in a bridge from vibrational data and compare different feature extraction schemes to increase the accuracy and reduce the amount of data collected. As a case study, the Z-24 bridge is considered because of the extensive database of accelerometric data in both standard and damaged conditions. The proposed framework starts from the first four fundamental frequencies extracted through operational modal analysis (OMA) and clustering, followed by density-based time-domain filtering (tracking). The fundamental frequencies extracted are then fed to a dimensionality reduction block implemented through two different approaches: feature selection (intelligent multiplexer) that tries to estimate the most reliable frequencies based on the evaluation of some statistical features (i.e., mean value, variance, kurtosis), and feature extraction (auto-associative neural network (ANN)) that combine the fundamental frequencies to extract new damage sensitive features in a low dimensional feature space. Finally, one class classifier (OCC) algorithms perform anomaly detection, trained with standard condition points, and tested with normal and anomaly ones. In particular, a new anomaly detector strategy is proposed, namely one class classifier neural network two (OCCNN2), which exploit the classification capability of standard classifiers in an anomaly detection problem, finding the standard class (the boundary of the features space in normal operating conditions) through a two-step approach: coarse and fine boundary estimation. The coarse estimation uses classics OCC techniques, while the fine estimation is performed through a feedforward neural network (NN) trained that exploits the boundaries estimated in the coarse step. The detection algorithms vare then compared with known methods based on principal component analysis (PCA), kernel principal component analysis (KPCA), and auto-associative neural network (ANN). In many cases, the proposed solution increases the performance with respect to the standard OCC algorithms in terms of F1 score and accuracy. In particular, by evaluating the correct features, the anomaly can be detected with accuracy and an F1 score greater than 96% with the proposed method.

Keywords: anomaly detection, frequencies selection, modal analysis, neural network, sensor network, structural health monitoring, vibration measurement

Procedia PDF Downloads 16
1 Ensemble Machine Learning Approach for Estimating Missing Data from CO₂ Time Series

Authors: Atbin Mahabbati, Jason Beringer, Matthias Leopold


To address the global challenges of climate and environmental changes, there is a need for quantifying and reducing uncertainties in environmental data, including observations of carbon, water, and energy. Global eddy covariance flux tower networks (FLUXNET), and their regional counterparts (i.e., OzFlux, AmeriFlux, China Flux, etc.) were established in the late 1990s and early 2000s to address the demand. Despite the capability of eddy covariance in validating process modelling analyses, field surveys and remote sensing assessments, there are some serious concerns regarding the challenges associated with the technique, e.g. data gaps and uncertainties. To address these concerns, this research has developed an ensemble model to fill the data gaps of CO₂ flux to avoid the limitations of using a single algorithm, and therefore, provide less error and decline the uncertainties associated with the gap-filling process. In this study, the data of five towers in the OzFlux Network (Alice Springs Mulga, Calperum, Gingin, Howard Springs and Tumbarumba) during 2013 were used to develop an ensemble machine learning model, using five feedforward neural networks (FFNN) with different structures combined with an eXtreme Gradient Boosting (XGB) algorithm. The former methods, FFNN, provided the primary estimations in the first layer, while the later, XGB, used the outputs of the first layer as its input to provide the final estimations of CO₂ flux. The introduced model showed slight superiority over each single FFNN and the XGB, while each of these two methods was used individually, overall RMSE: 2.64, 2.91, and 3.54 g C m⁻² yr⁻¹ respectively (3.54 provided by the best FFNN). The most significant improvement happened to the estimation of the extreme diurnal values (during midday and sunrise), as well as nocturnal estimations, which is generally considered as one of the most challenging parts of CO₂ flux gap-filling. The towers, as well as seasonality, showed different levels of sensitivity to improvements provided by the ensemble model. For instance, Tumbarumba showed more sensitivity compared to Calperum, where the differences between the Ensemble model on the one hand and the FFNNs and XGB, on the other hand, were the least of all 5 sites. Besides, the performance difference between the ensemble model and its components individually were more significant during the warm season (Jan, Feb, Mar, Oct, Nov, and Dec) compared to the cold season (Apr, May, Jun, Jul, Aug, and Sep) due to the higher amount of photosynthesis of plants, which led to a larger range of CO₂ exchange. In conclusion, the introduced ensemble model slightly improved the accuracy of CO₂ flux gap-filling and robustness of the model. Therefore, using ensemble machine learning models is potentially capable of improving data estimation and regression outcome when it seems to be no more room for improvement while using a single algorithm.

Keywords: carbon flux, Eddy covariance, extreme gradient boosting, gap-filling comparison, hybrid model, OzFlux network

Procedia PDF Downloads 34