Search results for: round-off error

Authors: G. Santamato, M. Solazzi, A. Frisoli

Abstract:

Systems for detection of damages in railway pantographs effectively reduce the cost of maintenance and improve time scheduling. In this paper, we present an approach to design a monitoring tool fitting strong customer requirements such as portability and ease of use. Pantograph has been modeled to estimate its dynamical properties, since no data are available. With the aim to focus on suspensions health, a two Degrees of Freedom (DOF) scheme has been adopted. Parameters have been calculated by means of analytical dynamics. A Finite Element Method (FEM) modal analysis verified the former model with an acceptable error. The detection strategy seeks phase-plots topology alteration, induced by defects. In order to test the suitability of the method, leakage in the dashpot was simulated on the lumped model. Results are interesting because changes in phase plots are more appreciable than frequency-shift. Further calculations as well as experimental tests will support future developments of this smart strategy.

Keywords: pantograph models, phase plots, structural health monitoring, damage detection

Procedia PDF Downloads 363

Authors: Hosuk Shin, Young-Hyun Seo, Eunhak Lee, Seung-Young Kho

Abstract:

Currently, in Seoul, users have the privilege to avoid riding crowded buses with the installation of Bus Information System (BIS). BIS has three levels of on-board bus ridership level information (spacious, normal, and crowded). However, there are flaws in the system due to it being real time which could provide incomplete information to the user. For example, a bus comes to the station, and on the BIS it shows that the bus is crowded, but on the stop that the user is waiting many people get off, which would mean that this station the information should show as normal or spacious. To fix this problem, this study predicts the bus ridership level using smart card data to provide more accurate information about the passenger ridership level on the bus. An Artificial Neural Network (ANN) is an interconnected group of nodes, that was created based on the human brain. Forecasting has been one of the major applications of ANN due to the data-driven self-adaptive methods of the algorithm itself. According to the results, the ANN algorithm was stable and robust with somewhat small error ratio, so the results were rational and reasonable.

Keywords: smartcard data, ANN, bus, ridership

Procedia PDF Downloads 167

Authors: Harendra Singh, Rajesh Pandey

Abstract:

The paper presents a numerical method based on operational matrix of integration and Ryleigh method for the solution of a class of non-linear fractional variational problems (NLFVPs). Chebyshev first kind polynomials are used for the construction of operational matrix. Using operational matrix and Ryleigh method the NLFVP is converted into a system of non-linear algebraic equations, and solving these equations we obtained approximate solution for NLFVPs. Convergence analysis of the proposed method is provided. Numerical experiment is done to show the applicability of the proposed numerical method. The obtained numerical results are compared with exact solution and solution obtained from Chebyshev third kind. Further the results are shown graphically for different fractional order involved in the problems.

Keywords: non-linear fractional variational problems, Rayleigh-Ritz method, convergence analysis, error analysis

Procedia PDF Downloads 298

Authors: Yulong Wang, Yuan Yan Tang, Cuiming Zou, Lina Yang

Abstract:

This paper presents a novel sparse representation method for robust pattern classification. Generalized orthogonal matching pursuit (GOMP) is a recently proposed efficient sparse representation technique. However, GOMP adopts the mean square error (MSE) criterion and assign the same weights to all measurements, including both severely and slightly corrupted ones. To reduce the limitation, we propose an information-theoretic GOMP (ITGOMP) method by exploiting the correntropy induced metric. The results show that ITGOMP can adaptively assign small weights on severely contaminated measurements and large weights on clean ones, respectively. An ITGOMP based classifier is further developed for robust pattern classification. The experiments on public real datasets demonstrate the efficacy of the proposed approach.

Keywords: correntropy induced metric, matching pursuit, pattern classification, sparse representation

Procedia PDF Downloads 355

Authors: Balasaheb Bansode, L. Ladusingh

Abstract:

The public distribution system is an important component of food security. It is a massive welfare program undertaken by Government of India and implemented by state government since India being a federal state; for achieving multiple objectives like eliminating hunger, reduction in malnutrition and making food consumption affordable. This program reaches at the community level through the various agencies of the government. The paper focuses on the accessibility of PDS at household level and how the present policy framework results in exclusion and inclusion errors. It tries to explore the sanctioned food grain quantity received by differentiated ration cards according to income criterion at household level, and also it has highlighted on the type of corruption in food distribution that is generated by the PDS system. The data used is of secondary nature from NSSO 68 round conducted in 2012. Bivariate and multivariate techniques have been used to understand the working and consumption of food for this paper.

Keywords: calories intake, entitle food quantity, poverty aliviation through PDS, target error

Procedia PDF Downloads 332

Authors: Samiah Alammari, Nassim Ammour

Abstract:

When providing a massive number of tasks successively to a deep learning process, a good performance of the model requires preserving the previous tasks data to retrain the model for each upcoming classification. Otherwise, the model performs poorly due to the catastrophic forgetting phenomenon. To overcome this shortcoming, we developed a successful continual learning deep model for remote sensing hyperspectral image regions classification. The proposed neural network architecture encapsulates two trainable subnetworks. The first module adapts its weights by minimizing the discrimination error between the land-cover classes during the new task learning, and the second module tries to learn how to replicate the data of the previous tasks by discovering the latent data structure of the new task dataset. We conduct experiments on HSI dataset Indian Pines. The results confirm the capability of the proposed method.

Keywords: continual learning, data reconstruction, remote sensing, hyperspectral image segmentation

Procedia PDF Downloads 266

Authors: Kamel Al-Khaled

Abstract:

A comparative study of the Sinc-Galerkin and Sinc-Collocation methods for solving the Kuramoto-Sivashinsky equation is given. Both approaches depend on using Sinc basis functions. Firstly, a numerical scheme using Sinc-Galerkin method is developed to approximate the solution of Kuramoto-Sivashinsky equation. Sinc approximations to both derivatives and indefinite integrals reduces the solution to an explicit system of algebraic equations. The error in the solution is shown to converge to the exact solution at an exponential. The convergence proof of the solution for the discrete system is given using fixed-point iteration. Secondly, a combination of a Crank-Nicolson formula in the time direction, with the Sinc-collocation in the space direction is presented, where the derivatives in the space variable are replaced by the necessary matrices to produce a system of algebraic equations. The methods are tested on two examples. The demonstrated results show that both of the presented methods more or less have the same accuracy.

Keywords: Sinc-Collocation, nonlinear PDEs, numerical methods, fixed-point

Procedia PDF Downloads 471

Authors: Keivan Seyyedi, Leila Esmaeilpour, Seyed Jamal Sadeghi

Abstract:

Investigating the effectiveness of explicit focus on form on the written performance of the EFL learners was the aim of this study. To provide empirical support for this study, sixty male English learners were selected and randomly assigned into two groups of explicit focus on form and meaning focused. Narrative writing was employed for data collection. To measure writing performance, participants were required to narrate a story. They were given 20 minutes to finish the task and were asked to write at least 150 words. The participants’ output was coded then analyzed utilizing Independent t-test for grammatical accuracy and fluency of learners’ performance. Results indicated that learners in explicit focus on form group appear to benefit from error correction and rule explanation as two pedagogical techniques of explicit focus on form with respect to accuracy, but regarding fluency they did not yield any significant differences compared to the participants of meaning-focused group.

Keywords: explicit focus on form, rule explanation, accuracy, fluency

Procedia PDF Downloads 511

Authors: Guesh Simretab Gebremedhin, Saumya Rajan Jena

Abstract:

In this work, a septic B-spline scheme has been used to simplify the process of solving an approximate solution of the generalized Rosenau-regularized long-wave equation (GR-RLWE) with initial boundary conditions. The resulting system of first-order ODEs has dealt with Butcher’s fifth order Runge-Kutta (BFRK) approach without using finite difference techniques for discretizing the time-dependent variables at each time level. Here, no transformation or any kind of linearization technique is employed to tackle the nonlinearity of the equation. Two test problems have been selected for numerical justifications and comparisons with other researchers on the basis of efficiency, accuracy, and results of the two invariants Mᵢ (mass) and Eᵢ (energy) of some motion that has been used to test the conservative properties of the proposed scheme.

Keywords: septic B-spline scheme, Butcher's fifth order Runge-Kutta approach, error norms, generalized Rosenau-RLW equation

Procedia PDF Downloads 66

Authors: Farhia Hassan Mohamed

Abstract:

This study examined the macroeconomic factors that affect the inflation Rate in Somalia using quarterly time series data from 1991q1 to 2017q4 retired from World Development Indicators and SESRIC. It employed the vector error correction model (VECM) and Granger Causality method to measure the long-run and short-run causality of the GDP, inflation exchange rate, and unemployment. The study confirmed that there is one cointegration equation between GDP, exchange rate, inflation, and unemployment in Somalia. However, the VECM model's result indicates a long-run relationship among variables. The VEC Granger causality/Block Exogeneity Wald test result confirmed that all covariates are statistically significant at 5% and are Granger's cause of inflation in the short term. Finally, the impulse response result showed that inflation responds negatively to the shocks from the exchange rate and unemployment rate and positively to GDP and itself. Drawing from the empirical findings, the study makes several policy recommendations for both the monetary and Government sides.

Keywords: CPI, OP, exchange rate, inflation ADF, Johansen, PP, VECM, impulse, ECT

Procedia PDF Downloads 46

Authors: Assaad Ghazouani

Abstract:

Tunisia is ranked among the countries with low energy diversification, but this configuration makes the country too dependent on fossil fuel exporting countries and therefore extremely sensitive to any oil crises, many measures to diversify electricity production must be taken in making use of other forms of renewable and nuclear energy. One of the solutions required to escape this dependence is the liberalization of the electricity industry which can lead to an improvement of supply, energy diversification, and reducing some of the negative effects of the trade balance. This paper examines the issue of renewable electricity and economic growth in Tunisia consumption. The main objective is to study and analyze the causal link between renewable energy consumption and economic growth in Tunisia over the period 1980-2010. To examine the relationship in the short and in the long terms, we used a multidimensional approach to cointegration based on recent advances in time series econometrics (test Zivot - Andrews, Test of Cointegration Johannsen, Granger causality test, error correction model (ECM)).

Keywords: renewable electricity, economic growth, VECM, cointegration, Tunisia

Procedia PDF Downloads 543

Authors: Monika Chuchro

Abstract:

This paper presents a preliminary attempt to apply classification of time series using meta-clusters in order to improve the quality of regression models. In this case, clustering was performed as a method to obtain a subgroups of time series data with normal distribution from inflow into waste water treatment plant data which Composed of several groups differing by mean value. Two simple algorithms: K-mean and EM were chosen as a clustering method. The rand index was used to measure the similarity. After simple meta-clustering, regression model was performed for each subgroups. The final model was a sum of subgroups models. The quality of obtained model was compared with the regression model made using the same explanatory variables but with no clustering of data. Results were compared by determination coefficient (R2), measure of prediction accuracy mean absolute percentage error (MAPE) and comparison on linear chart. Preliminary results allows to foresee the potential of the presented technique.

Keywords: clustering, data analysis, data mining, predictive models

Procedia PDF Downloads 466

Authors: Malki Nadia Fatima Zahra, Kellal Chaimaa, Brahimi Houria

Abstract:

Quality is one of the most important modern management patterns that organizations seek to achieve in all areas and sectors in order to meet the needs and desires of customers and to remain continuity, as they constitute a competitive advantage for the organization, and among the most prominent organizations that must be available on the quality factor are health organizations as they relate to the most valuable component of production It is a person and his health, and that any error in it threatens his life and may lead to death, so she must provide health services of high quality to achieve the highest degree of satisfaction for the patient. This research aims to study the quality of health services and the extent of their impact on patient satisfaction, and this is through an applied study that relied on measuring the level of quality of health services in the university hospital center of Algeria and the extent of their impact on patient satisfaction according to the dimensions of the quality of health services, and we reached a conclusion that the determinants of the quality of health services. It affects patient satisfaction, which necessitates developing health services according to patients' requirements and improving their quality to obtain patient satisfaction.

Keywords: health service, health quality, quality determinants, patient satisfaction

Procedia PDF Downloads 67

Authors: Charlotte K. Lee, Henrique R. N. Aguiar, Ralph Smith, James Baldock, Sam Botchey

Abstract:

Background: Femoral neck stress fractures (FNSF) are uncommon, making up 1 to 7.2% of stress fractures in healthy subjects. FNSFs are prevalent in young women, military recruits, endurance athletes, and individuals with energy deficiency syndrome or female athlete triad. Presentation is often non-specific and is often misdiagnosed following the initial examination. There is limited research addressing the return–to–activity time after FNSF. Previous studies have demonstrated prognostic time predictions based on various imaging techniques. Here, (1) OxSport clinic FNSF practice standards are retrospectively reviewed, (2) FNSF cohort demographics are examined, (3) Regression models were used to predict return–to–activity prognosis and consequently determine bone stress risk factors. Methods: Patients with a diagnosis of FNSF attending Oxsport clinic between 01/06/2020 and 01/01/2020 were selected from the Rheumatology Assessment Database Innovation in Oxford (RhADiOn) and OxSport Stress Fracture Database (n = 14). (1) Clinical practice was audited against five criteria based on local and National Institute for Health Care Excellence guidance, with a 100% standard. (2) Demographics of the FNSF cohort were examined with Student’s T-Test. (3) Lastly, linear regression and Random Forest regression models were used on this patient cohort to predict return–to–activity time. Consequently, an analysis of feature importance was conducted after fitting each model. Results: OxSport clinical practice met standard (100%) in 3/5 criteria. The criteria not met were patient waiting times and documentation of all bone stress risk factors. Importantly, analysis of patient demographics showed that of the population with complete bone stress risk factor assessments, 53% were positive for modifiable bone stress risk factors. Lastly, linear regression analysis was utilized to identify demographic factors that predicted return–to–activity time [R2 = 79.172%; average error 0.226]. This analysis identified four key variables that predicted return-to-activity time: vitamin D level, total hip DEXA T value, femoral neck DEXA T value, and history of an eating disorder/disordered eating. Furthermore, random forest regression models were employed for this task [R2 = 97.805%; average error 0.024]. Analysis of the importance of each feature again identified a set of 4 variables, 3 of which matched with the linear regression analysis (vitamin D level, total hip DEXA T value, and femoral neck DEXA T value) and the fourth: age. Conclusion: OxSport clinical practice could be improved by more comprehensively evaluating bone stress risk factors. The importance of this evaluation is demonstrated by the population found positive for these risk factors. Using this cohort, potential bone stress risk factors that significantly impacted return-to-activity prognosis were predicted using regression models.

Keywords: eating disorder, bone stress risk factor, femoral neck stress fracture, vitamin D

Procedia PDF Downloads 183

Authors: Marwa Ben Abdessalem, Amin Zribi, Ammar Bouallègue

Abstract:

In this paper, a Joint Source Channel coding scheme based on LDPC codes is investigated. We consider two concatenated LDPC codes, one allows to compress a correlated source and the second to protect it against channel degradations. The original information can be reconstructed at the receiver by a joint decoder, where the source decoder and the channel decoder run in parallel by transferring extrinsic information. We investigate the performance of the JSC LDPC code in terms of Bit-Error Rate (BER) in the case of transmission over an Additive White Gaussian Noise (AWGN) channel, and for different source and channel rate parameters. We emphasize how JSC LDPC presents a performance tradeoff depending on the channel state and on the source correlation. We show that, the JSC LDPC is an efficient solution for a relatively low Signal-to-Noise Ratio (SNR) channel, especially with highly correlated sources. Finally, a source-channel rate optimization has to be applied to guarantee the best JSC LDPC system performance for a given channel.

Keywords: AWGN channel, belief propagation, joint source channel coding, LDPC codes

Procedia PDF Downloads 357

Authors: Samba Raju, Chiluveru, Manoj Tripathy

Abstract:

Intelligibility is an essential characteristic of a speech signal, which is used to help in the understanding of information in speech signal. Background noise in the environment can deteriorate the intelligibility of a recorded speech. In this paper, we presented a simple variance subtracted - variable level discrete wavelet transform, which improve the intelligibility of speech. The proposed algorithm does not require an explicit estimation of noise, i.e., prior knowledge of the noise; hence, it is easy to implement, and it reduces the computational burden. The proposed algorithm decides a separate decomposition level for each frame based on signal dominant and dominant noise criteria. The performance of the proposed algorithm is evaluated with speech intelligibility measure (STOI), and results obtained are compared with Universal Discrete Wavelet Transform (DWT) thresholding and Minimum Mean Square Error (MMSE) methods. The experimental results revealed that the proposed scheme outperformed competing methods

Keywords: discrete wavelet transform, speech intelligibility, STOI, standard deviation

Procedia PDF Downloads 148

Authors: Heng Han, Zhilei Liang, Xiangong Zhou

Abstract:

In this paper, the finite element method is used to study the temperature field of the main cable of the suspension bridge, and the calculation method of the average temperature of the cross-section of the main cable suitable for the construction control of the cable system is proposed; By comparing and analyzing the temperature field of the main cable with five diameters, a reasonable diameter limit for calculating the average temperature of the cross section of the main cable by finite element method is proposed. The results show that the maximum error of this method is less than 1℃, which meets the requirements of construction control accuracy; For the main cable with a diameter greater than 400mm, the surface temperature measuring points combined with the finite element method shall be used to calculate the average cross-section temperature.

Keywords: suspension bridge, main cable, temperature field, finite element

Procedia PDF Downloads 160

Authors: M. I. Youssef, A. E. Emam, M. Abd Elghany

Abstract:

The performance of wireless communication systems is affected mainly by the environment of its associated channel, which is characterized by dynamic and unpredictable behavior. In this paper, different statistical earth-satellite channel models are studied with emphasize on two main models, first is the Rice-Log normal model, due to its representation for the environment including shadowing and multi-path components that affect the propagated signal along its path, and a three-state model that take into account different fading conditions (clear area, moderate shadow and heavy shadowing). The provided models are based on AWGN, Rician, Rayleigh, and log-normal distributions were their Probability Density Functions (PDFs) are presented. The transmission system Bit Error Rate (BER), Peak-Average-Power Ratio (PAPR), and the channel capacity vs. fading models are measured and analyzed. These simulations are implemented using MATLAB tool, and the results had shown the performance of transmission system over different channel models.

Keywords: fading channels, MIMO communication, RNS scheme, statistical modeling

Procedia PDF Downloads 149

Authors: Ravi Kumar, Santhosh Kumar Dubba

Abstract:

This paper presents an experimental study of a diabatic flow of R-600a through a concentric configured capillary tube suction line heat exchanger. The details of experimental facility for testing the diabatic capillary tube with different inlet sub-cooling degree and pressure are discussed. The effect of coil diameter, capillary length, capillary tube diameter, sub-cooling degree and inlet pressure on mass flow rate are presented. The degree of sub-cooling at the inlet of capillary tube is varied from 3-20°C. The refrigerant mass flow rate is scattered up with rising of pressure. A semi-empirical correlation to predict the mass flow rate of R-600a flowing through a diabatic capillary tube is proposed for sub-cooled inlet conditions. The proposed correlation predicts measured data with an error band of ±20 percent.

Keywords: diabatic, capillary tube, concentric, R-600a

Procedia PDF Downloads 204

Authors: James Purnama, Riri Fitri Sari

Abstract:

We investigate the machine learning algorithm selection problem in the term of a depth image based eye gaze estimation, with respect to its essential difficulty in reducing the number of required training samples and duration time of training. Statistics based prediction accuracy are increasingly used to assess and evaluate prediction or estimation in gaze estimation. This article evaluates Root Mean Squared Error (RMSE) and R-Squared statistical analysis to assess machine learning methods on depth camera data for gaze estimation. There are 4 machines learning methods have been evaluated: Random Forest Regression, Regression Tree, Support Vector Machine (SVM), and Linear Regression. The experiment results show that the Random Forest Regression has the lowest RMSE and the highest R-Squared, which means that it is the best among other methods.

Keywords: gaze estimation, gaze tracking, eye tracking, kinect, regression model, orange python

Procedia PDF Downloads 538

Authors: Apolinar Picado, Ronald Solís, Rafael Gamero

Abstract:

The thin-layer drying characteristics of instant coffee solution were investigated in a laboratory tunnel dryer. Drying experiments were carried out at three temperatures (80, 100 and 120 °C) and an air velocity of 1.2 m/s. Drying experimental data obtained are fitted to six (6) thin-layer drying models using the non-linear least squares regression analysis. The acceptability of the thin-layer drying model has been based on a value of the correlation coefficient that should be close to one, and low values for root mean square error (RMSE) and chi-square (x²). According to this evaluation, the most suitable model for describing drying process of thin-layer instant coffee solution is the Page model. Further, the effective moisture diffusivity and the activation energy were computed employing the drying experimental data. The effective moisture diffusivity values varied from 1.6133 × 10⁻⁹ to 1.6224 × 10⁻⁹ m²/s over the temperature range studied and the activation energy was estimated to be 162.62 J/mol.

Keywords: activation energy, diffusivity, instant coffee, thin-layer models

Procedia PDF Downloads 262

Authors: Fernando P. Silva, Valter J. S. Leite, Erivelton G. Nepomuceno

Abstract:

In this paper, a nonlinear controller design for an omnidirectional mobile is presented. The robot controller consists of an inner-loop controller and an outer-loop controller, the first is designed using state feedback (robust allocation) and the second controller is designed based on Robust Multi Inversion (RMI) approach. The objective of RMI controller is rendering the robust inversion of the dynamic, when the model is affected by uncertainties. A model nonlinear MIMO of an omni-directional robot (small-league of Robocup) is used to simulate the RMI approach. The parameters of linear and nonlinear model are varied to cause modelling uncertainties among the model and the real model (real system) generating an error in inner-loop controller signal that must be compensated by RMI controller. The simulation test results show that the RMI is capable of compensating the uncertainties and keep the system stable and controlled under uncertainties.

Keywords: robust multi inversion, omni-directional robot, robocup, nonlinear control

Procedia PDF Downloads 589

Authors: Li Zhang, Yuehong Su

Abstract:

Lightpipe as a mature solar light tube technique has been employed worldwide. Accurately assessing the performance of lightpipe and evaluate daylighting available has been a challenging topic. Previous research had used regression model and computational simulation methods to estimate the performance of lightpipe. However, due to the nonlinear nature of solar light transferring in lightpipe, the methods mentioned above express inaccurate and time-costing issues. In the present study, a neural network model as an alternative method is investigated to predict the transmittance of lightpipe. Four types of commercial lightpipe with bended angle 0°, 30°, 45° and 60° are discussed under clear, intermediate and overcast sky conditions respectively. The neural network is generated in MATLAB by using the outcomes of an optical software Photopia simulations as targets for networks training and testing. The coefficient of determination (R²) for each model is higher than 0.98, and the mean square error (MSE) is less than 0.0019, which indicate the neural network strong predictive ability and the use of the neural network method could be an efficient technique for determining the performance of lightpipe.

Keywords: neural network, bended lightpipe, transmittance, Photopia

Procedia PDF Downloads 152

Authors: Wayan Widhiada, Cok Indra Partha, Gusti Ngurah Nitya Santhiarsa

Abstract:

The purpose of this paper is to investigate the sophistication of the use of Proportional Integral and Derivative Control to control the kinematic motion of the mobile robot manipulator. Simulation and experimental methods will be used to investigate the sophistication of PID control to control the mobile robot arm in the collection and placement of several kinds of objects quickly, accurately and correctly. Mathematical modeling will be done by utilizing the integration of Solidworks and MATLAB / Simmechanics software. This method works by converting the physical model file into the xml file. This method is easy, fast and accurate done in modeling and design robotics. The automatic control design of this robot manipulator will be validated in simulations and experimental in control labs as evidence that the mobile robot manipulator gripper control design can achieve the best performance such as the error signal is lower than 5%, small overshoot and get steady signal response as quickly.

Keywords: control analysis, kinematics motion, mobile robot manipulator, performance

Procedia PDF Downloads 410

Authors: Piotr A. Kowalski, Kasper Sapala, Wiktor Warchalowski

Abstract:

PM10 is a suspended dust that primarily has a negative effect on the respiratory system. PM10 is responsible for attacks of coughing and wheezing, asthma or acute, violent bronchitis. Indirectly, PM10 also negatively affects the rest of the body, including increasing the risk of heart attack and stroke. Unfortunately, Poland is a country that cannot boast of good air quality, in particular, due to large PM concentration levels. Therefore, based on the dense network of Airly sensors, it was decided to deal with the problem of prediction of suspended particulate matter concentration. Due to the very complicated nature of this issue, the Machine Learning approach was used. For this purpose, Convolution Neural Network (CNN) neural networks have been adopted, these currently being the leading information processing methods in the field of computational intelligence. The aim of this research is to show the influence of particular CNN network parameters on the quality of the obtained forecast. The forecast itself is made on the basis of parameters measured by Airly sensors and is carried out for the subsequent day, hour after hour. The evaluation of learning process for the investigated models was mostly based upon the mean square error criterion; however, during the model validation, a number of other methods of quantitative evaluation were taken into account. The presented model of pollution prediction has been verified by way of real weather and air pollution data taken from the Airly sensor network. The dense and distributed network of Airly measurement devices enables access to current and archival data on air pollution, temperature, suspended particulate matter PM1.0, PM2.5, and PM10, CAQI levels, as well as atmospheric pressure and air humidity. In this investigation, PM2.5, and PM10, temperature and wind information, as well as external forecasts of temperature and wind for next 24h served as inputted data. Due to the specificity of the CNN type network, this data is transformed into tensors and then processed. This network consists of an input layer, an output layer, and many hidden layers. In the hidden layers, convolutional and pooling operations are performed. The output of this system is a vector containing 24 elements that contain prediction of PM10 concentration for the upcoming 24 hour period. Over 1000 models based on CNN methodology were tested during the study. During the research, several were selected out that give the best results, and then a comparison was made with the other models based on linear regression. The numerical tests carried out fully confirmed the positive properties of the presented method. These were carried out using real ‘big’ data. Models based on the CNN technique allow prediction of PM10 dust concentration with a much smaller mean square error than currently used methods based on linear regression. What's more, the use of neural networks increased Pearson's correlation coefficient (R²) by about 5 percent compared to the linear model. During the simulation, the R² coefficient was 0.92, 0.76, 0.75, 0.73, and 0.73 for 1st, 6th, 12th, 18th, and 24th hour of prediction respectively.

Keywords: air pollution prediction (forecasting), machine learning, regression task, convolution neural networks

Procedia PDF Downloads 149

Authors: Haniye Dehestani, Yadollah Ordokhani

Abstract:

In this work, we present an efficient approach for solving variable-order time-fractional partial differential equations, which are based on Legendre and Laguerre polynomials. First, we introduced the pseudo-operational matrices of integer and variable fractional order of integration by use of some properties of Riemann-Liouville fractional integral. Then, applied together with collocation method and Legendre-Laguerre functions for solving variable-order time-fractional partial differential equations. Also, an estimation of the error is presented. At last, we investigate numerical examples which arise in physics to demonstrate the accuracy of the present method. In comparison results obtained by the present method with the exact solution and the other methods reveals that the method is very effective.

Keywords: collocation method, fractional partial differential equations, legendre-laguerre functions, pseudo-operational matrix of integration

Procedia PDF Downloads 166

Authors: Belkacem Laimouche

Abstract:

With the field of artificial intelligence (AI) experiencing exponential growth, fueled by technological advancements that pave the way for increasingly innovative and promising applications, there is an escalating need to develop rigorous methods for assessing their performance in pursuit of transparency and equity. This article proposes a metrology-inspired statistical framework for evaluating bias and explainability in AI systems. Drawing from the principles of metrology, we propose a pioneering approach, using a concrete example, to evaluate the accuracy and precision of AI models, as well as to quantify the sources of measurement uncertainty that can lead to bias in their predictions. Furthermore, we explore a statistical approach for evaluating the explainability of AI systems based on their ability to provide interpretable and transparent explanations of their predictions.

Keywords: artificial intelligence, metrology, measurement uncertainty, prediction error, bias, machine learning algorithms, probabilistic models, interlaboratory comparison, data analysis, data reliability, measurement of bias impact on predictions, improvement of model accuracy and reliability

Procedia PDF Downloads 105

Authors: Osarobo Omorogieva Ighodaro, Josephus Otejere

Abstract:

This paper contains the modelling and simulation of GT13E2 combined cycle gas turbine with the aid of the software EBSILON PROFESSIONAL. The design mode was modeled using guaranteed performance data from the power plant, in the off design, temperature variation of ambient air and fogging (spray water at inlet to compressor) was simulated. The fogging was simulated under two different modes; constant fuel consumption and constant turbine exhaust temperature .The model results were validated using actual operating data by applying error percentage analysis. The validation results obtained ranged from -0.0038% to 0% in design condition while the results varied from -0.9202% to 10.24% The model shows that fogging decreases compressor inlet temperature which in turn decreases the power required to drive the compressor hence improving the simple cycle efficiency and hence increasing power generated.

Keywords: inlet fogging, off design, combined cycle, modelling

Procedia PDF Downloads 39

Authors: H. Barati, M. Wu, A. Kharicha, A. Ludwig

Abstract:

A transient model for nozzle clogging has been developed and successfully validated against a laboratory experiment. Key steps of clogging are considered: transport of particles by turbulent flow towards the nozzle wall; interactions between fluid flow and nozzle wall, and the adhesion of the particle on the wall; the growth of the clog layer and its interaction with the flow. The current paper is to investigate the mesh (size and type) sensitivity of the model in both two and three dimensions. It is found that the algorithm for clog growth alone excluding the flow effect is insensitive to the mesh type and size, but the calculation including flow becomes sensitive to the mesh quality. The use of 2D meshes leads to overestimation of the clog growth because the 3D nature of flow in the boundary layer cannot be properly solved by 2D calculation. 3D simulation with tetrahedron mesh can also lead to an error estimation of the clog growth. A mesh-independent result can be achieved with hexahedral mesh, or at least with triangular prism (inflation layer) for near-wall regions.

Keywords: clogging, continuous casting, inclusion, simulation, submerged entry nozzle

Procedia PDF Downloads 283

Authors: A. Ejah Umraeni Salam, M. Tola, M. Selintung, F. Maricar

Abstract:

Clean water is an essential and fundamental human need. Therefore, its supply must be assured by maintaining the quality, quantity and water pressure. However the fact is, on its distribution system, leakage happens and becomes a common world issue. One of the technical causes of the leakage is a leaking pipe. The purpose of the research is how to use the Radial Basis Function Neural (RBFNN) model to detect the location and the magnitude of the pipeline leakage rapidly and efficiently. In this study the RBFNN are trained and tested on data from EPANET hydraulic modeling system. Method of Radial Basis Function Neural Network is proved capable to detect location and magnitude of pipeline leakage with of the accuracy of the prediction results based on the value of RMSE (Root Meant Square Error), comparison prediction and actual measurement approaches 0.000049 for the whole pipeline system.

Keywords: radial basis function neural network, leakage pipeline, EPANET, RMSE

Procedia PDF Downloads 358