Artificial Neural Network Output Research Articles

Direct Torque Control of Induction Motor with Cascaded Multilevel inverter

3 Abstract: In this Paper, an Intelligent Direct Torque Control (DTC) method is proposed for controlling induction motor using Multilevel inverter with space Vector Modulation (SVM).A stage of Artificial Neural Network (ANN) is utilised for predicting the target parameters with the corresponding input parameters change in motor torque and flux. The change in motor torque and flux parameters are extracted from the behaviour of the system with PI controller. The back propagation learning method is used to learn the ANN. By using the ANN output and PI controller outputs, PWM control signal are generated from the SVM technique and control the multilevel inverter. Then the proposed intelligent control technique is implemented in the MATLAB/Simulink and the effectiveness are analysed with five level cascaded inverter and comparing the results with PI cont roller and the proposed case. The comparison results shows that the proposed method have good speed control response. Keyword: DTC, SVM, ANN, Multilevel inverter, Induction motor.

An Artificial Neural Network Model for Predicting the Pressure Gradient in Horizontal Oil–Water Separated Flow

In this study, a three–layer artificial neural network (ANN) model was developed to predict the pressure gradient in horizontal liquid–liquid separated flow. A total of 455 data points were collected from 13 data sources to develop the ANN model. Superficial velocities, viscosity ratio and density ratio of oil to water, and roughness and inner diameter of pipe were used as input parameters of the network while corresponding pressure gradient was selected as its output. A tansig and a linear function were chosen as transfer functions for hidden and output layers, respectively and Levenberg–Marquardt back–propagation algorithm were applied to train the ANN. The optimal topology of the ANN was achieved with 16 neurons in hidden layer, which made it possible to estimate the pressure gradient with a good accuracy (R2=0.996 &AAPE=7.54%). In addition, the results of the developed ANN model were compared to Al–Wahaibi correlation results (with R2=0.884&AAPE=17.17%) and it is found that the proposed ANN model has higher accuracy. Finally, a sensitivity analysis was carried out to investigate the relative importance of each input parameter on the ANN output. The results revealed that the pipe diameter (D) has the most relative importance (24.43%) on the ANN output, while the importance of the other parameters is nearly the same.

Refrigerant flow through electronic expansion valve: Experiment and neural network modeling

Electronic expansion valve (EEV) plays a crucial role in controlling refrigerant mass flow rate of refrigeration or heat pump systems for energy savings. However, complexities in two-phase throttling process and geometry make accurate modeling of EEV flow characteristics more difficult. This paper developed an artificial neural network (ANN) model using refrigerant inlet and outlet pressures, inlet subcooling, EEV opening as ANN inputs, refrigerant mass flow rate as ANN output. Both linear and nonlinear transfer functions in hidden layer were used and compared to each other. Experimental data from multiple sources including in-house experiments of one EEV with R410A were used for ANN training and test. In addition, literature correlations were compared with ANN as well. Results showed that the ANN model with nonlinear transfer function worked well in all cases and it is much accurate than the literature correlations. In all cases, nonlinear ANN predicted refrigerant mass flow rates within ±0.4% average relative deviation (A.D.) and 2.7% standard deviation (S.D.), meanwhile it predicted the EEV opening at 0.1% A.D. and 2.1% S.D.

Calibration of PARAMICS Model: Application of Artificial Intelligence-Based Approach

The advent and significant improvement in computing technology in the last decades has led to immense popularity of traffic microscopic simulation models in addressing different transportation engineering issues. This paper focuses on the challenges of calibration of microscopic model incorporating the driving behavior for the local traffic conditions in the Kingdom of Saudi Arabia (KSA). One of the state-of-the-art microscopic simulation models, PARAMICS was used for the calibration study. This study proposes machine learning model-based calibration methodology for the PARAMICS model. The developed artificial neural network (ANN) model performs adequately in modeling the queue length as a function of mean target headway and mean reaction time. The selected values of the calibration parameters were finally obtained using the genetic algorithm, which ensures minimum difference with the measured values of queue lengths and the ANN output (i.e., queue lengths). The queue lengths obtained through the ANN- and GA-based approach were used as the input parameters for the PARAMICS model. The conformance of the PARAMICS and the ANN model outputs indicates the validity of the proposed calibration methodology.

Identification of the elbow motion kinematic parameters by means of artificial neural networks technology

The research objective is to study elbow flexion kinematic parameters using the artificial neural networks (ANN). Parameters of the surface electromyogram (sEMG) are used as ANN inputs. The ANN output is kinematic parameters of motion: direction, angular displacement, and angular velocity. The study has involved DSTU students and staff (11 people without pathologies of the musculoskeletal system). The sEMG signals taken from the biceps of each trial subject during no-load elbow bending are registered. During the experiment, shoulder and elbow joints are fixed by the passive exoskeleton. The feature vector for the neural network is formed using methods of the spectral and statistical analysis. The statistical analysis in the time domain includes the determination of the following parameters: dispersion of sEMG amplitude values, arithmetic mean value and mean-square value of sEMG absolute amplitudes, sEMG signal zero crossing rates. In the frequency domain, sEMG signal spectral analysis is performed by Fast Fourier Transform method. The power spectrum and the mean frequency of the power spectrum are determined. Best results of determining the kinematic parameters are obtained when using the mean frequency of the power spectrum and the total integrated sEMG signal power as inputs to the ANN. The ANN is trained by the method of the direct signal propagation and the back propagation of error. The results obtained can be used in the development of the bioelectric control systems for the mechatronic devices.

Artificial Neural Network Approaches to the Prediction of Eutrophication and Algal Blooms in Aras Dam, Iran

Background and purpose: Eutrophication is one of the major environmental problems in waterways causing substantial adverse impact on domestic, livestock and recreational use of water resources. Aras Dam, Iran which provides Arasful city with drinking water, has chronic algal blooms since 1990. Levels of up to 900,000 cells/mL of toxic cyanobacteria (mainly Anabaena and Microcystis) have been recorded in the dam. Materials and Methods: In this study, artificial neural network (ANN) model was investigated to predict the chlorophyll-a (Chl-a) concentration in water of dam reservoir. Water samples were collected from 5 stations and analyzed for physical quality parameters including; water temperature, total suspended solids, biochemical oxygen demands, orthophosphate, total phosphorous and nitrate concentrations using standard methods. Chl-a was also measured separately in order to investigate the accuracy of the predicted results by ANN. Results: The results showed that a network was highly accurate in predicting the Chl-a concentration. The mean squared error and coefficient of correlation (R) between experimental data and model outputs were calculated. A good agreement between actual data and the ANN outputs for training was observed, indicating the validation of testing data sets. The initial results of the research indicate that the dam is enriched with nutrients (phosphorus and nitrogen) and is on the verge of being eutrophic. Conclusion: The Chl-a concentration that was predicted by the model was beyond the standard levels; indication the possibility of eutrophication especially during fall season. [Rafiee M, *Jahangiri-Rad M. Artificial Neural Network Approaches to the Prediction of Eutrophication and Algal Blooms in Aras Dam, Iran. IJHS 2015; 3(1): 25-32] http://jhs.mazums.ac.ir

Effect of Shorting Wall on Compact 2×4 MSA Array Using Artificial Neural Network

In this paper, a compact 2×4 microstrip antenna (MSA) array is presented and the effect of inserting shorting wall is optimized with the help of artificial neural network (ANN). An ANN model has been developed for predicting the resonant frequencies with the variation of the height of substrate and shorting wall position. For validation of ANN output, a prototype of 2×4 MSA array is physically fabricated and tested. This validation verifies the proposed antenna for which simulated and ANN results are approximately similar. DOI: http://dx.doi.org/10.11591/telkomnika.v13i3.7089

ANN-based modeling of compact impedance-varying transmission lines with applications to ultra-wideband Wilkinson power dividers

The modeling of the physical and electrical characteristics of microstrip non-uniform transmission lines (NTLs) utilizing artificial neural networks (ANNs) is investigated. The fundamental equations and constraints for designing variable impedance transmission lines are first presented. Then, a proof-of-concept example of a compact non-uniform matching transformer and the counterpart modeled version is elaborated for source and load impedances Zs and Zl, respectively, at 0.5 GHz. For comparison purposes, weights and biases of the proposed ANN are established with three different training techniques; namely: backpropagation (BP), Quasi-Newton (QN), and conjugate gradient (CG); at which the ABCD matrix, impedance variations, input port matching (S11), and transmission parameter (S21) are set as benchmarks to examine the validity of the trained model. The concept is then extended to model a NTL ultrawideband (UWB) Wilkinson power divider (WPD) with three resistors for improved isolation. S-parameters derived from the trained ANN outputs are close to those obtained by the traditional time-consuming optimization procedure, and show input and output ports matching and isolation of below −10 dB, and acceptable values of transmission parameters over the 3.1 GHz to 10.6 GHz band. The resulting models outperform traditional optimizations in terms of simulation time and reserved resources with comparable accuracy. © 2015 Wiley Periodicals, Inc. Int J RF and Microwave CAE 25:563–572, 2015.

Application of artificial neural networks in computer-aided diagnosis.

Computer-aided diagnosis is a diagnostic procedure in which a radiologist uses the outputs of computer analysis of medical images as a second opinion in the interpretation of medical images, either to help with lesion detection or to help determine if the lesion is benign or malignant. Artificial neural networks (ANNs) are usually employed to formulate the statistical models for computer analysis. Receiver operating characteristic curves are used to evaluate the performance of the ANN alone, as well as the diagnostic performance of radiologists who take into account the ANN output as a second opinion. In this chapter, we use mammograms to illustrate how an ANN model is trained, tested, and evaluated, and how a radiologist should use the ANN output as a second opinion in CAD.

Locomotion Learning for an Anguilliform Robotic Fish Using Central Pattern Generator Approach

In this paper, we present locomotion learning for an Anguilliform robotic fish using a central pattern generator (CPG) approach. First, we give the overall structure of the CPG. Different from a traditional CPG that contains only coupled oscillators, our CPG consists of coupled Andronov-Hopf oscillators, an artificial neural network (ANN), and an outer amplitude modulator. Coupled oscillators, which possess a limit-cycle character, are used to generate inputs to excite the ANN. The ANN serves as a learning mechanism, from which we can obtain desired waveforms. By inputting different signals to the ANN, different desired locomotion patterns can be obtained. Outer amplitude modulator resizes the amplitudes of the ANN outputs according to task specifications. The CPG possess temporal scalability, spatial scalability, and phase-shift property; thus, we can obtain desired amplitudes, oscillation frequencies, and phase differences by tuning corresponding parameters. By extracting the swimming pattern from a real fish and using the CPG approach, we successfully generate a new swimming pattern and apply it to the robotic fish. The new pattern reserves the swimming characters of the real fish, and it is more suitable to be applied to the robotic fish. By using the new pattern, the robotic fish can perform both forward locomotion and backward locomotion, which are validated by experiments.

Detecting recalcitrant organic chemicals in water with microbial fuel cells and artificial neural networks

This study integrates artificial neural network (ANN) processing with microbial fuel cell (MFC)-based biosensing in the detection of three organic pollutants: aldicarb, dimethyl-methylphosphonate (DMMP), and bisphenol-A (BPA). Overall, the use of the ANN proved to be more reliable than direct correlations for the determination of both chemical concentration and type. The ANN output matched the appropriate chemical concentration and type for three different concentrations and throughout a wide range of stepwise tests. Additionally, chemicals dissolved in the acetate-based feed medium (FM) were accurately identified by the ANN even though the acetate masked the pollutants' effects on electrical current. The ANN also accurately revealed the identity of chemical mixtures. This study is the first to incorporate ANN modeling with MFC-based biosensing for the detection and quantification of organic pollutants that are not readily biodegradable. Furthermore, this work provides insight into the flexibility of MFC-based biosensing as it pertains to limits of detection and its applicability to scenarios where mixtures of pollutants and unique solvents are involved. This research effort is expected to serve as a guide for future MFC-based biosensing efforts.

A neural network approach to fMRI binocular visual rivalry task analysis.

The purpose of this study was to investigate whether artificial neural networks (ANN) are able to decode participants’ conscious experience perception from brain activity alone, using complex and ecological stimuli. To reach the aim we conducted pattern recognition data analysis on fMRI data acquired during the execution of a binocular visual rivalry paradigm (BR). Twelve healthy participants were submitted to fMRI during the execution of a binocular non-rivalry (BNR) and a BR paradigm in which two classes of stimuli (faces and houses) were presented. During the binocular rivalry paradigm, behavioral responses related to the switching between consciously perceived stimuli were also collected. First, we used the BNR paradigm as a functional localizer to identify the brain areas involved the processing of the stimuli. Second, we trained the ANN on the BNR fMRI data restricted to these regions of interest. Third, we applied the trained ANN to the BR data as a ‘brain reading’ tool to discriminate the pattern of neural activity between the two stimuli. Fourth, we verified the consistency of the ANN outputs with the collected behavioral indicators of which stimulus was consciously perceived by the participants. Our main results showed that the trained ANN was able to generalize across the two different tasks (i.e. BNR and BR) and to identify with high accuracy the cognitive state of the participants (i.e. which stimulus was consciously perceived) during the BR condition. The behavioral response, employed as control parameter, was compared with the network output and a statistically significant percentage of correspondences (p-value <0.05) were obtained for all subjects. In conclusion the present study provides a method based on multivariate pattern analysis to investigate the neural basis of visual consciousness during the BR phenomenon when behavioral indicators lack or are inconsistent, like in disorders of consciousness or sedated patients.

Electricity Load Forecasting using Hybrid of Multiplicative Double Seasonal Exponential Smoothing Model with Artificial Neural Network

Electricity load forecasting often has many properties such as the nonlinearity, double seasonal cycles, and others those may be obstacles for the accuracy of forecasting using some classical statistical models. Many papers in this field have proposed using double seasonal (DS) exponential smoothing model to forecast. These papers indicated that electricity load forecasting using DS exponential smoothing model has better fit. Using artificial neural network (ANN) as a modern approach may be used for superior fitted forecasting, since this approach can deal with the non-linearity components of load data. The purpose of this paper is to improve the electricity load forecasting by building the hybrid model that includes a double seasonal exponential smoothing with an artificial neural network. This hybrid model will study the double seasonal effects and non-linearity components together based on the electricity load data. The strategy of building this hybrid model is by entering ANN output as an input in double seasonal exponential smoothing model. The data sets are taken from three stations with different electricity load characteristics such as a residential, industrial and city center. The electricity load testing forecast of DS exponential smoothing-ANN hybrid model gave the most minimum mean absolute percentage error (MAPE) measurement comparing with the electricity load testing forecasts of DS exponential smoothing and ANN for all electricity load data sets. In conclusion, DS exponential smoothing-ANN hybrid model are the most fitted for every electricity load data which contains the double seasonal effects and non-linearity components.

SU-E-T-206: Improving Radiotherapy Toxicity Based On Artificial Neural Network (ANN) for Head and Neck Cancer Patients

Purpose/Objective(s): The aim of this study is to build the estimator of toxicity using artificial neural network (ANN) for head and neck cancer patients Materials/Methods: An ANN can combine variables into a predictive model during training and considered all possible correlations of variables. We constructed an ANN based on the data from 73 patients with advanced H and N cancer treated with external beam radiotherapy and/or chemotherapy at our institution. For the toxicity estimator we defined input data including age, sex, site, stage, pathology, status of chemo, technique of external beam radiation therapy (EBRT), length of treatment, dose of EBRT, status of post operation, length of follow-up, the status of local recurrences and distant metastasis. These data were digitized based on the significance and fed to the ANN as input nodes. We used 20 hidden nodes (for the 13 input nodes) to take care of the correlations of input nodes. For training ANN, we divided data into three subsets such as training set, validation set and test set. Finally, we built the estimator for the toxicity from ANN output. Results: We used 13 input variables including the status of local recurrences and distant metastasis and 20 hidden nodes for correlations.more » 59 patients for training set, 7 patients for validation set and 7 patients for test set and fed the inputs to Matlab neural network fitting tool. We trained the data within 15% of errors of outcome. In the end we have the toxicity estimation with 74% of accuracy. Conclusion: We proved in principle that ANN can be a very useful tool for predicting the RT outcomes for high risk H and N patients. Currently we are improving the results using cross validation.« less

Aeronautical Study for Flight Time Estimation Applying Artificial Neural Network and Genetic Algorithm

Since the adoption of open-air policy, people make more frequent use of air travel to do various business or tourism activities. The volume of air traffic has greatly increased, along with the occurrences of traffic jam in the air. Delays of landings or take-offs and the congestions in the approach air space have become commonplace, exacerbating the already heavy workload of air-traffic controllers and the inadequacies of ATC system. Therefore, a study of flight time in ATC operation to help alleviate airspace congestions has become more and more urgent and important. Taking international airway A1 as an example, this study makes use of the known entry time, flight altitude, speed, penetrating and descending as the input of artificial neural networks; the time between departure and transfer point as the output of Artificial Neural Networks, to establish artificial neural network. Applying artificial neural networks and genetic algorithm to the study to simulate the result of actual flight, one can precisely estimate the flight time, thereby making it an efficient air-traffic-control instrument. It can help controllers handle different time segments of air traffic, thus upgrading the quality of air traffic control service.

A retrospective analysis of the utility of an artificial neural network to predict ED volume

ObjectiveThe objectives of this study are to design an artificial neural network (ANN) and to test it retrospectively to determine if it may be used to predict emergency department (ED) volume. MethodsWe conducted a retrospective review of patient registry data from February 4, 2007, to December 31, 2009, from an inner city, tertiary care hospital. We harvested data regarding weather, days of week, air quality, and special events to train the ANN. The ANN belongs to a class of neural networks called multilayer perceptrons. We designed an ANN composed of 37 input neurons, 22 hidden neurons, and 1 output neuron designed to predict the daily number of ED visits. The training method is a supervised backpropagation algorithm that uses mean squared error to minimize the average squared error between the ANN's output and the number of ED visits over all the example pairs. ResultsA linear regression between the predicted and actual ED visits demonstrated an R2 of 0.957 with a slope of 0.997. Ninety-five percent of the time, the ANN was within 20 visits. ConclusionThe results of this study show that a properly designed ANN is an effective tool that may be used to predict ED volume. The scatterplot demonstrates that the ANN is least predictive at the extreme ends of the spectrum suggesting that the ANN may be missing important variables. A properly calibrated ANN may have the potential to allow ED administrators to staff their units more appropriately in an effort to reduce patient wait times, decrease ED physician burnout rates, and increase the ability of caregivers to provide quality patient care. A prospective is needed to validate the utility of the ANN.

Technoeconomic Projections with Artificial Neural Networks using an Ensemble of Sparsely-Sampled Bootstrapped Data

Aims: The present study refers to developing an artificial neural network (ANN) that can be designed exclusively for ex ante forecasting in technoeconomic contexts using an ensemble set of sparse and insufficient sampled-data availed ex post. Study Design: In general, the samples in a data set of technoeconomic structures would largely be limited in number due to sparse-sampling; also, availability of number of such sets is mostly inadequate for robust training of an ANN so as to obtain realistic inferences subsequently in the prediction phase. Hence, a sparsity-recovery strategy is advocated via a cardinality enhancement procedure (through Nyquist sampling) performed on the sparse data set in order to augment the number of samples in its sampled-data space. Further, the concept of statistical bootstrapping technique of resampling is invoked and applied on the cardinality-improved subset so as to obtain an enhanced number of data sets. This ensemble of data set is then adopted to facilitate robust training of the test Original Research Article British Journal of Economics, Management & Trade, 4(2): 228-263, 2014 229 ANN. Place and Duration of Study: The studies were conducted (2012-2013) at: Department of Computer and Electrical Engineering and Computer Science, College of Engineering & Computer Science, Florida Atlantic University, Boca Raton, Florida 33431, USA. Methodology: The study governs technoeconomic ex ante projections pertinent to a wind-power generation business complex elucidated via ANN-based forecasting. Relevant test ANN is designed to accommodate training with an ensemble of sampled set available ex post but, in limited numbers. The associated scarcity is recovered by artificially enhancing the data space to an adequate extent via Nyquist sampling and bootstrapping techniques. Further, the test ANN designed corresponds to a multilayer perceptron (MLP) supporting backpropagation of the perceived error at the output with respect to a supervisory value. It accommodates the bootstrapped data space at its input relevant to technoeconomic details on a practical wind-power system performance reported in the literature. The training and prediction exercises on the test ANN corresponds to optimally elucidating output predictions in the context of the technoeconomics framework of the power generation considered. Results: Using the test ANN trained with bootstrap-enhanced, scarcity-recovered sparse data on wind-power generation statistics and associated plant economics, reliable inference (in the prediction phase) is achieved on the system performance. That is, the ANN output obtained depicts forecast projections on the productivity of electric power generation in the ex ante regime. Simulation studies thereof and results obtained demonstrate the efficacy of the method proposed, bootstrapping algorithm developed and the use of MLP in the technoeconomic contexts.

Estimating Passive Microwave Brightness Temperature Over Snow-Covered Land in North America Using a Land Surface Model and an Artificial Neural Network

An artificial neural network (ANN) is presented for the purpose of estimating passive microwave (PMW) brightness temperatures over snow covered land in North America. The NASA Catchment Land Surface Model (Catchment) is used to define snowpack properties; the Catchment-based ANN is then trained with PMW measurements acquired by the Advanced Microwave Scanning Radiometer (AMSR-E). A comparison of ANN output against AMSR-E measurements not used during training activities as well as a comparison against independent PMW measurements collected during airborne surveys demonstrates the predictive skill of the ANN. When averaged over the study domain for the 9-year study period, computed statistics (relative to AMSR-E measurements not used during training) for multiple frequencies and polarizations yielded a near-zero bias, a root mean squared error less than 10 K, and a time series anomaly correlation coefficient of approximately 0.5. The ANN demonstrates skill during the accumulation phase when the snowpack is relatively dry as well as during the ablation phase when the snowpack is ripe and relatively wet. Overall, the results suggest the ANN could serve as a computationally efficient measurement operator for data assimilation at the continental scale.

Risk prediction models for biochemical recurrence after radical prostatectomy using prostate-specific antigen and Gleason score.

Many computer models for predicting the risk of prostate cancer have been developed including for prediction of biochemical recurrence (BCR). However, models for individual BCR free probability at individual time-points after a BCR free period are rare. Follow-up data from 1656 patients who underwent laparoscopic radical prostatectomy (LRP) were used to develop an artificial neural network (ANN) to predict BCR and to compare it with a logistic regression (LR) model using clinical and pathologic parameters, prostate-specific antigen (PSA), margin status (R0/1), pathological stage (pT), and Gleason Score (GS). For individual BCR prediction at any given time after operation, additional ANN, and LR models were calculated every 6 months for up to 7.5 years of follow-up. The areas under the receiver operating characteristic (ROC) curve (AUC) for the ANN (0.754) and LR models (0.755) calculated immediately following LRP, were larger than that for GS (AUC: 0.715; P = 0.0015 and 0.001), pT or PSA (AUC: 0.619; P always <0.0001) alone. The GS predicted the BCR better than PSA (P = 0.0001), but there was no difference between the ANN and LR models (P = 0.39). Our ANN and LR models predicted individual BCR risk from radical prostatectomy for up to 10 years postoperative. ANN and LR models equally and significantly improved the prediction of BCR compared with PSA and GS alone. When the GS and ANN output values are combined, a more accurate BCR prediction is possible, especially in high-risk patients with GS ≥7.

An Optimization of Wind Turbine Airfoil Possessing Good Stall Characteristics by Genetic Algorithm Utilizing CFD and Neural Network

In this research, an optimization of a wind turbine airfoil is performed by Genetic Algorithm (GA) as optimization method, coupled with CFD (Computational Fluid Dynamics) and Artificial Neural Network (ANN). A pressure-based implicit procedure is applied to solve the Navier-Stokes equations on a nonorthogonal mesh with collocated finite volume formulation to calculate the aerodynamic coefficients. The boundedness criteria for the numerical procedure are determined by Normalized Variable Diagram (NVD) scheme and the k-e eddy-viscosity turbulence model is utilized. ANN has been used as surrogate model to reduce computational cost and time. Single objective and multi objective optimization of wind turbine airfoil have been performed and the results of optimization are presented. To decrease the number of design variables and producing a smooth shaped airfoil, modified Hicks-Henne functions are applied. In this process, the Eppler E387 airfoil has been applied as the base airfoil. The angle of attack varies from 0 to 20 degrees and Reynolds number of the flow is 460000. The presented technique decreases the time of optimization by 99.5%. Moreover, the results manifest the good agreement of trained ANN outputs and CFD simulation. In addition, the Multi-objective optimization can attain the better solutions than single objective to design a wind turbine airfoil with good stall characteristics.