Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 419

Search results for: predictions

419 Multivariate Output-Associative RVM for Multi-Dimensional Affect Predictions

Authors: Achut Manandhar, Kenneth D. Morton, Peter A. Torrione, Leslie M. Collins


The current trends in affect recognition research are to consider continuous observations from spontaneous natural interactions in people using multiple feature modalities, and to represent affect in terms of continuous dimensions, incorporate spatio-temporal correlation among affect dimensions, and provide fast affect predictions. These research efforts have been propelled by a growing effort to develop affect recognition system that can be implemented to enable seamless real-time human-computer interaction in a wide variety of applications. Motivated by these desired attributes of an affect recognition system, in this work a multi-dimensional affect prediction approach is proposed by integrating multivariate Relevance Vector Machine (MVRVM) with a recently developed Output-associative Relevance Vector Machine (OARVM) approach. The resulting approach can provide fast continuous affect predictions by jointly modeling the multiple affect dimensions and their correlations. Experiments on the RECOLA database show that the proposed approach performs competitively with the OARVM while providing faster predictions during testing.

Keywords: dimensional affect prediction, output-associative RVM, multivariate regression, fast testing

Procedia PDF Downloads 197
418 On Improving Breast Cancer Prediction Using GRNN-CP

Authors: Kefaya Qaddoum


The aim of this study is to predict breast cancer and to construct a supportive model that will stimulate a more reliable prediction as a factor that is fundamental for public health. In this study, we utilize general regression neural networks (GRNN) to replace the normal predictions with prediction periods to achieve a reasonable percentage of confidence. The mechanism employed here utilises a machine learning system called conformal prediction (CP), in order to assign consistent confidence measures to predictions, which are combined with GRNN. We apply the resulting algorithm to the problem of breast cancer diagnosis. The results show that the prediction constructed by this method is reasonable and could be useful in practice.

Keywords: neural network, conformal prediction, cancer classification, regression

Procedia PDF Downloads 179
417 Predictions for the Anisotropy in Thermal Conductivity in Polymers Subjected to Model Flows by Combination of the eXtended Pom-Pom Model and the Stress-Thermal Rule

Authors: David Nieto Simavilla, Wilco M. H. Verbeeten


The viscoelastic behavior of polymeric flows under isothermal conditions has been extensively researched. However, most of the processing of polymeric materials occurs under non-isothermal conditions and understanding the linkage between the thermo-physical properties and the process state variables remains a challenge. Furthermore, the cost and energy required to manufacture, recycle and dispose polymers is strongly affected by the thermo-physical properties and their dependence on state variables such as temperature and stress. Experiments show that thermal conductivity in flowing polymers is anisotropic (i.e. direction dependent). This phenomenon has been previously omitted in the study and simulation of industrially relevant flows. Our work combines experimental evidence of a universal relationship between thermal conductivity and stress tensors (i.e. the stress-thermal rule) with differential constitutive equations for the viscoelastic behavior of polymers to provide predictions for the anisotropy in thermal conductivity in uniaxial, planar, equibiaxial and shear flow in commercial polymers. A particular focus is placed on the eXtended Pom-Pom model which is able to capture the non-linear behavior in both shear and elongation flows. The predictions provided by this approach are amenable to implementation in finite elements packages, since viscoelastic and thermal behavior can be described by a single equation. Our results include predictions for flow-induced anisotropy in thermal conductivity for low and high density polyethylene as well as confirmation of our method through comparison with a number of thermoplastic systems for which measurements of anisotropy in thermal conductivity are available. Remarkably, this approach allows for universal predictions of anisotropy in thermal conductivity that can be used in simulations of complex flows in which only the most fundamental rheological behavior of the material has been previously characterized (i.e. there is no need for additional adjusting parameters other than those in the constitutive model). Accounting for polymers anisotropy in thermal conductivity in industrially relevant flows benefits the optimization of manufacturing processes as well as the mechanical and thermal performance of finalized plastic products during use.

Keywords: anisotropy, differential constitutive models, flow simulations in polymers, thermal conductivity

Procedia PDF Downloads 96
416 Predictions of Values in a Causticizing Process

Authors: R. Andreola, O. A. A. Santos, L. M. M. Jorge


An industrial system for the production of white liquor of a paper industry, Klabin Paraná Papé is, formed by ten reactors was modeled, simulated, and analyzed. The developed model considered possible water losses by evaporation and reaction, in addition to variations in volumetric flow of lime mud across the reactors due to composition variations. The model predictions agreed well with the process measurements at the plant and the results showed that the slaking reaction is nearly complete at the third causticizing reactor, while causticizing ends by the seventh reactor. Water loss due to slaking reaction and evaporation occurs more pronouncedly in the slaking reaction than in the final causticizing reactors; nevertheless, the lime mud flow remains nearly constant across the reactors.

Keywords: causticizing, lime, prediction, process

Procedia PDF Downloads 198
415 Energy Performance Gaps in Residences: An Analysis of the Variables That Cause Energy Gaps and Their Impact

Authors: Amrutha Kishor


Today, with the rising global warming and depletion of resources every industry is moving toward sustainability and energy efficiency. As part of this movement, it is nowadays obligatory for architects to play their part by creating energy predictions for their designs. But in a lot of cases, these predictions do not reflect the real quantities of energy in newly built buildings when operating. These can be described as ‘Energy Performance Gaps’. This study aims to determine the underlying reasons for these gaps. Seven houses designed by Allan Joyce Architects, UK from 1998 until 2019 were considered for this study. The data from the residents’ energy bills were cross-referenced with the predictions made with the software SefairaPro and from energy reports. Results indicated that the predictions did not match the actual energy usage. An account of how energy was used in these seven houses was made by means of personal interviews. The main factors considered in the study were occupancy patterns, heating systems and usage, lighting profile and usage, and appliances’ profile and usage. The study found that the main reasons for the creation of energy gaps were the discrepancies in occupant usage and patterns of energy consumption that are predicted as opposed to the actual ones. This study is particularly useful for energy-conscious architectural firms to fine-tune the approach to designing houses and analysing their energy performance. As the findings reveal that energy usage in homes varies based on the way residents use the space, it helps deduce the most efficient technological combinations. This information can be used to set guidelines for future policies and regulations related to energy consumption in homes. This study can also be used by the developers of simulation software to understand how architects use their product and drive improvements in its future versions.

Keywords: architectural simulation, energy efficient design, energy performance gaps, environmental design

Procedia PDF Downloads 35
414 Visualization-Based Feature Extraction for Classification in Real-Time Interaction

Authors: Ágoston Nagy


This paper introduces a method of using unsupervised machine learning to visualize the feature space of a dataset in 2D, in order to find most characteristic segments in the set. After dimension reduction, users can select clusters by manual drawing. Selected clusters are recorded into a data model that is used for later predictions, based on realtime data. Predictions are made with supervised learning, using Gesture Recognition Toolkit. The paper introduces two example applications: a semantic audio organizer for analyzing incoming sounds, and a gesture database organizer where gestural data (recorded by a Leap motion) is visualized for further manipulation.

Keywords: gesture recognition, machine learning, real-time interaction, visualization

Procedia PDF Downloads 249
413 D-Wave Quantum Computing Ising Model: A Case Study for Forecasting of Heat Waves

Authors: Dmytro Zubov, Francesco Volponi


In this paper, D-Wave quantum computing Ising model is used for the forecasting of positive extremes of daily mean air temperature. Forecast models are designed with two to five qubits, which represent 2-, 3-, 4-, and 5-day historical data respectively. Ising model’s real-valued weights and dimensionless coefficients are calculated using daily mean air temperatures from 119 places around the world, as well as sea level (Aburatsu, Japan). In comparison with current methods, this approach is better suited to predict heat wave values because it does not require the estimation of a probability distribution from scarce observations. Proposed forecast quantum computing algorithm is simulated based on traditional computer architecture and combinatorial optimization of Ising model parameters for the Ronald Reagan Washington National Airport dataset with 1-day lead-time on learning sample (1975-2010 yr). Analysis of the forecast accuracy (ratio of successful predictions to total number of predictions) on the validation sample (2011-2014 yr) shows that Ising model with three qubits has 100 % accuracy, which is quite significant as compared to other methods. However, number of identified heat waves is small (only one out of nineteen in this case). Other models with 2, 4, and 5 qubits have 20 %, 3.8 %, and 3.8 % accuracy respectively. Presented three-qubit forecast model is applied for prediction of heat waves at other five locations: Aurel Vlaicu, Romania – accuracy is 28.6 %; Bratislava, Slovakia – accuracy is 21.7 %; Brussels, Belgium – accuracy is 33.3 %; Sofia, Bulgaria – accuracy is 50 %; Akhisar, Turkey – accuracy is 21.4 %. These predictions are not ideal, but not zeros. They can be used independently or together with other predictions generated by different method(s). The loss of human life, as well as environmental, economic, and material damage, from extreme air temperatures could be reduced if some of heat waves are predicted. Even a small success rate implies a large socio-economic benefit.

Keywords: heat wave, D-wave, forecast, Ising model, quantum computing

Procedia PDF Downloads 396
412 Partially-Averaged Navier-Stokes for Computations of Flow Around Three-Dimensional Ahmed Bodies

Authors: Maryam Mirzaei, Sinisa Krajnovic´


The paper reports a study about the prediction of flows around simplified vehicles using Partially-Averaged Navier-Stokes (PANS). Numerical simulations are performed for two simplified vehicles: A slanted-back Ahmed body at Re=30 000 and a square back Ahmed body at Re=300 000. A comparison of the resolved and modeled physical flow scales is made with corresponding LES and experimental data for a better understanding of the performance of the PANS model. The PANS model is compared for coarse and fine grid resolutions and it is indicated that even a coarse-grid PANS simulation is able to produce fairly close flow predictions to those from a well-resolved LES simulation. The results indicate the possibility of improvement of the predictions by employing a finer grid resolution.

Keywords: partially-averaged Navier-Stokes, large eddy simulation, PANS, LES, Ahmed body

Procedia PDF Downloads 434
411 Patient-Specific Modeling Algorithm for Medical Data Based on AUC

Authors: Guilherme Ribeiro, Alexandre Oliveira, Antonio Ferreira, Shyam Visweswaran, Gregory Cooper


Patient-specific models are instance-based learning algorithms that take advantage of the particular features of the patient case at hand to predict an outcome. We introduce two patient-specific algorithms based on decision tree paradigm that use AUC as a metric to select an attribute. We apply the patient specific algorithms to predict outcomes in several datasets, including medical datasets. Compared to the patient-specific decision path (PSDP) entropy-based and CART methods, the AUC-based patient-specific decision path models performed equivalently on area under the ROC curve (AUC). Our results provide support for patient-specific methods being a promising approach for making clinical predictions.

Keywords: approach instance-based, area under the ROC curve, patient-specific decision path, clinical predictions

Procedia PDF Downloads 372
410 A Non-Linear Eddy Viscosity Model for Turbulent Natural Convection in Geophysical Flows

Authors: J. P. Panda, K. Sasmal, H. V. Warrior


Eddy viscosity models in turbulence modeling can be mainly classified as linear and nonlinear models. Linear formulations are simple and require less computational resources but have the disadvantage that they cannot predict actual flow pattern in complex geophysical flows where streamline curvature and swirling motion are predominant. A constitutive equation of Reynolds stress anisotropy is adopted for the formulation of eddy viscosity including all the possible higher order terms quadratic in the mean velocity gradients, and a simplified model is developed for actual oceanic flows where only the vertical velocity gradients are important. The new model is incorporated into the one dimensional General Ocean Turbulence Model (GOTM). Two realistic oceanic test cases (OWS Papa and FLEX' 76) have been investigated. The new model predictions match well with the observational data and are better in comparison to the predictions of the two equation k-epsilon model. The proposed model can be easily incorporated in the three dimensional Princeton Ocean Model (POM) to simulate a wide range of oceanic processes. Practically, this model can be implemented in the coastal regions where trasverse shear induces higher vorticity, and for prediction of flow in estuaries and lakes, where depth is comparatively less. The model predictions of marine turbulence and other related data (e.g. Sea surface temperature, Surface heat flux and vertical temperature profile) can be utilized in short term ocean and climate forecasting and warning systems.

Keywords: Eddy viscosity, turbulence modeling, GOTM, CFD

Procedia PDF Downloads 108
409 Hourly Solar Radiations Predictions for Anticipatory Control of Electrically Heated Floor: Use of Online Weather Conditions Forecast

Authors: Helene Thieblemont, Fariborz Haghighat


Energy storage systems play a crucial role in decreasing building energy consumption during peak periods and expand the use of renewable energies in buildings. To provide a high building thermal performance, the energy storage system has to be properly controlled to insure a good energy performance while maintaining a satisfactory thermal comfort for building’s occupant. In the case of passive discharge storages, defining in advance the required amount of energy is required to avoid overheating in the building. Consequently, anticipatory supervisory control strategies have been developed forecasting future energy demand and production to coordinate systems. Anticipatory supervisory control strategies are based on some predictions, mainly of the weather forecast. However, if the forecasted hourly outdoor temperature may be found online with a high accuracy, solar radiations predictions are most of the time not available online. To estimate them, this paper proposes an advanced approach based on the forecast of weather conditions. Several methods to correlate hourly weather conditions forecast to real hourly solar radiations are compared. Results show that using weather conditions forecast allows estimating with an acceptable accuracy solar radiations of the next day. Moreover, this technique allows obtaining hourly data that may be used for building models. As a result, this solar radiation prediction model may help to implement model-based controller as Model Predictive Control.

Keywords: anticipatory control, model predictive control, solar radiation forecast, thermal storage

Procedia PDF Downloads 181
408 Stacking Ensemble Approach for Combining Different Methods in Real Estate Prediction

Authors: Sol Girouard, Zona Kostic


A home is often the largest and most expensive purchase a person makes. Whether the decision leads to a successful outcome will be determined by a combination of critical factors. In this paper, we propose a method that efficiently handles all the factors in residential real estate and performs predictions given a feature space with high dimensionality while controlling for overfitting. The proposed method was built on gradient descent and boosting algorithms and uses a mixed optimizing technique to improve the prediction power. Usually, a single model cannot handle all the cases thus our approach builds multiple models based on different subsets of the predictors. The algorithm was tested on 3 million homes across the U.S., and the experimental results demonstrate the efficiency of this approach by outperforming techniques currently used in forecasting prices. With everyday changes on the real estate market, our proposed algorithm capitalizes from new events allowing more efficient predictions.

Keywords: real estate prediction, gradient descent, boosting, ensemble methods, active learning, training

Procedia PDF Downloads 181
407 Road Accidents Bigdata Mining and Visualization Using Support Vector Machines

Authors: Usha Lokala, Srinivas Nowduri, Prabhakar K. Sharma


Useful information has been extracted from the road accident data in United Kingdom (UK), using data analytics method, for avoiding possible accidents in rural and urban areas. This analysis make use of several methodologies such as data integration, support vector machines (SVM), correlation machines and multinomial goodness. The entire datasets have been imported from the traffic department of UK with due permission. The information extracted from these huge datasets forms a basis for several predictions, which in turn avoid unnecessary memory lapses. Since data is expected to grow continuously over a period of time, this work primarily proposes a new framework model which can be trained and adapt itself to new data and make accurate predictions. This work also throws some light on use of SVM’s methodology for text classifiers from the obtained traffic data. Finally, it emphasizes the uniqueness and adaptability of SVMs methodology appropriate for this kind of research work.

Keywords: support vector mechanism (SVM), machine learning (ML), support vector machines (SVM), department of transportation (DFT)

Procedia PDF Downloads 195
406 Identification of CLV for Online Shoppers Using RFM Matrix: A Case Based on Features of B2C Architecture

Authors: Riktesh Srivastava


Online Shopping have established an astonishing evolution in the last few years. And it is now apparent that B2C architecture is becoming progressively imperative channel for even traditional brick and mortar type traders as well. In this completion knowing customers and predicting behavior are extremely important. More important, when any customer logs onto the B2C architecture, the traces of their buying patterns can be stored and used for future predictions. Such a prediction is called Customer Lifetime Value (CLV). Earlier, we used Net Present Value to do so, however, it ignores two important aspects of B2C architecture, “market risks” and “big amount of customer data”. Now, we use RFM- Recency, Frequency and Monetary Value to estimate the CLV, and as the term exemplifies, market risks, is well sheltered. Big Data Analysis is also roofed in RFM, which gives real exploration of the Big Data and lead to a better estimation for future cash flow from customers. In the present paper, 6 factors (collected from varied sources) are used to determine as to what attracts the customers to the B2C architecture. For these 6 factors, RFM is computed for 3 years (2013, 2014 and 2015) respectively. CLV and Revenue are the two parameters defined using RFM analysis, which gives the clear picture of the future predictions.

Keywords: CLV, RFM, revenue, recency, frequency, monetary value

Procedia PDF Downloads 140
405 Oil Reservoir Asphalting Precipitation Estimating during CO2 Injection

Authors: I. Alhajri, G. Zahedi, R. Alazmi, A. Akbari


In this paper, an Artificial Neural Network (ANN) was developed to predict Asphaltene Precipitation (AP) during the injection of carbon dioxide into crude oil reservoirs. In this study, the experimental data from six different oil fields were collected. Seventy percent of the data was used to develop the ANN model, and different ANN architectures were examined. A network with the Trainlm training algorithm was found to be the best network to estimate the AP. To check the validity of the proposed model, the model was used to predict the AP for the thirty percent of the data that was unevaluated. The Mean Square Error (MSE) of the prediction was 0.0018, which confirms the excellent prediction capability of the proposed model. In the second part of this study, the ANN model predictions were compared with modified Hirschberg model predictions. The ANN was found to provide more accurate estimates compared to the modified Hirschberg model. Finally, the proposed model was employed to examine the effect of different operating parameters during gas injection on the AP. It was found that the AP is mostly sensitive to the reservoir temperature. Furthermore, the carbon dioxide concentration in liquid phase increases the AP.

Keywords: artificial neural network, asphaltene, CO2 injection, Hirschberg model, oil reservoirs

Procedia PDF Downloads 263
404 Transfer Learning for Protein Structure Classification at Low Resolution

Authors: Alexander Hudson, Shaogang Gong


Structure determination is key to understanding protein function at a molecular level. Whilst significant advances have been made in predicting structure and function from amino acid sequence, researchers must still rely on expensive, time-consuming analytical methods to visualise detailed protein conformation. In this study, we demonstrate that it is possible to make accurate (≥80%) predictions of protein class and architecture from structures determined at low (>3A) resolution, using a deep convolutional neural network trained on high-resolution (≤3A) structures represented as 2D matrices. Thus, we provide proof of concept for high-speed, low-cost protein structure classification at low resolution, and a basis for extension to prediction of function. We investigate the impact of the input representation on classification performance, showing that side-chain information may not be necessary for fine-grained structure predictions. Finally, we confirm that high resolution, low-resolution and NMR-determined structures inhabit a common feature space, and thus provide a theoretical foundation for boosting with single-image super-resolution.

Keywords: transfer learning, protein distance maps, protein structure classification, neural networks

Procedia PDF Downloads 24
403 Verification and Application of Finite Element Model Developed for Flood Routing in Rivers

Authors: A. L. Qureshi, A. A. Mahessar, A. Baloch


Flood wave propagation in river channel flow can be enunciated by nonlinear equations of motion for unsteady flow. However, it is difficult to find analytical solution of these complex non-linear equations. Hence, verification of the numerical model should be carried out against field data and numerical predictions. This paper presents the verification of developed finite element model applying for unsteady flow in the open channels. The results of a proposed model indicate a good matching with both Preissmann scheme and HEC-RAS model for a river reach of 29 km at both sites (15 km from upstream and at downstream end) for discharge hydrographs. It also has an agreeable comparison with the Preissemann scheme for the flow depth (stage) hydrographs. The proposed model has also been applying to forecast daily discharges at 400 km downstream from Sukkur barrage, which demonstrates accurate model predictions with observed daily discharges. Hence, this model may be utilized for predicting and issuing flood warnings about flood hazardous in advance.

Keywords: finite element method, Preissmann scheme, HEC-RAS, flood forecasting, Indus river

Procedia PDF Downloads 409
402 A Trend Based Forecasting Framework of the ATA Method and Its Performance on the M3-Competition Data

Authors: H. Taylan Selamlar, I. Yavuz, G. Yapar


It is difficult to make predictions especially about the future and making accurate predictions is not always easy. However, better predictions remain the foundation of all science therefore the development of accurate, robust and reliable forecasting methods is very important. Numerous number of forecasting methods have been proposed and studied in the literature. There are still two dominant major forecasting methods: Box-Jenkins ARIMA and Exponential Smoothing (ES), and still new methods are derived or inspired from them. After more than 50 years of widespread use, exponential smoothing is still one of the most practically relevant forecasting methods available due to their simplicity, robustness and accuracy as automatic forecasting procedures especially in the famous M-Competitions. Despite its success and widespread use in many areas, ES models have some shortcomings that negatively affect the accuracy of forecasts. Therefore, a new forecasting method in this study will be proposed to cope with these shortcomings and it will be called ATA method. This new method is obtained from traditional ES models by modifying the smoothing parameters therefore both methods have similar structural forms and ATA can be easily adapted to all of the individual ES models however ATA has many advantages due to its innovative new weighting scheme. In this paper, the focus is on modeling the trend component and handling seasonality patterns by utilizing classical decomposition. Therefore, ATA method is expanded to higher order ES methods for additive, multiplicative, additive damped and multiplicative damped trend components. The proposed models are called ATA trended models and their predictive performances are compared to their counter ES models on the M3 competition data set since it is still the most recent and comprehensive time-series data collection available. It is shown that the models outperform their counters on almost all settings and when a model selection is carried out amongst these trended models ATA outperforms all of the competitors in the M3- competition for both short term and long term forecasting horizons when the models’ forecasting accuracies are compared based on popular error metrics.

Keywords: accuracy, exponential smoothing, forecasting, initial value

Procedia PDF Downloads 86
401 Creep Analysis and Rupture Evaluation of High Temperature Materials

Authors: Yuexi Xiong, Jingwu He


The structural components in an energy facility such as steam turbine machines are operated under high stress and elevated temperature in an endured time period and thus the creep deformation and creep rupture failure are important issues that need to be addressed in the design of such components. There are numerous creep models being used for creep analysis that have both advantages and disadvantages in terms of accuracy and efficiency. The Isochronous Creep Analysis is one of the simplified approaches in which a full-time dependent creep analysis is avoided and instead an elastic-plastic analysis is conducted at each time point. This approach has been established based on the rupture dependent creep equations using the well-known Larson-Miller parameter. In this paper, some fundamental aspects of creep deformation and the rupture dependent creep models are reviewed and the analysis procedures using isochronous creep curves are discussed. Four rupture failure criteria are examined from creep fundamental perspectives including criteria of Stress Damage, Strain Damage, Strain Rate Damage, and Strain Capability. The accuracy of these criteria in predicting creep life is discussed and applications of the creep analysis procedures and failure predictions of simple models will be presented. In addition, a new failure criterion is proposed to improve the accuracy and effectiveness of the existing criteria. Comparisons are made between the existing criteria and the new one using several examples materials. Both strain increase and stress relaxation form a full picture of the creep behaviour of a material under high temperature in an endured time period. It is important to bear this in mind when dealing with creep problems. Accordingly there are two sets of rupture dependent creep equations. While the rupture strength vs LMP equation shows how the rupture time depends on the stress level under load controlled condition, the strain rate vs rupture time equation reflects how the rupture time behaves under strain-controlled condition. Among the four existing failure criteria for rupture life predictions, the Stress Damage and Strain Damage Criteria provide the most conservative and non-conservative predictions, respectively. The Strain Rate and Strain Capability Criteria provide predictions in between that are believed to be more accurate because the strain rate and strain capability are more determined quantities than stress to reflect the creep rupture behaviour. A modified Strain Capability Criterion is proposed making use of the two sets of creep equations and therefore is considered to be more accurate than the original Strain Capability Criterion.

Keywords: creep analysis, high temperature mateials, rapture evalution, steam turbine machines

Procedia PDF Downloads 180
400 Working Title: Estimating the Power Output of Photovoltaics in Kuwait Using a Monte Carlo Approach

Authors: Mohammad Alshawaf, Rahmat Poudineh, Nawaf Alhajeri


The power generated from photovoltaic (PV) modules is non-dispatchable on demand due to the stochastic nature of solar radiation. The random variations in the measured intensity of solar irradiance are due to clouds and, in the case of arid regions, dust storms which decrease the intensity of intensity of solar irradiance. Therefore, modeling PV power output using average, maximum, or minimum solar irradiance values is inefficient to predict power generation reliably. The overall objective of this paper is to predict the power output of PV modules using Monte Carlo approach based the weather and solar conditions measured in Kuwait. Given the 250 Wp PV module used in study, the average daily power output is 1021 Wh/day. The maximum power was generated in April and the minimum power was generated in January 1187 Wh/day and 823 Wh/day respectively. The certainty of the daily predictions varies seasonally and according to the weather conditions. The output predictions were far more certain in the summer months, for example, the 80% certainty range for August is 89 Wh/day, whereas the 80% certainty range for April is 250 Wh/day.

Keywords: Monte Carlo, solar energy, variable renewable energy, Kuwait

Procedia PDF Downloads 56
399 An Analytical Wall Function for 2-D Shock Wave/Turbulent Boundary Layer Interactions

Authors: X. Wang, T. J. Craft, H. Iacovides


When handling the near-wall regions of turbulent flows, it is necessary to account for the viscous effects which are important over the thin near-wall layers. Low-Reynolds- number turbulence models do this by including explicit viscous and also damping terms which become active in the near-wall regions, and using very fine near-wall grids to properly resolve the steep gradients present. In order to overcome the cost associated with the low-Re turbulence models, a more advanced wall function approach has been implemented within OpenFoam and tested together with a standard log-law based wall function in the prediction of flows which involve 2-D shock wave/turbulent boundary layer interactions (SWTBLIs). On the whole, from the calculation of the impinging shock interaction, the three turbulence modelling strategies, the Lauder-Sharma k-ε model with Yap correction (LS), the high-Re k-ε model with standard wall function (SWF) and analytical wall function (AWF), display good predictions of wall-pressure. However, the SWF approach tends to underestimate the tendency of the flow to separate as a result of the SWTBLI. The analytical wall function, on the other hand, is able to reproduce the shock-induced flow separation and returns predictions similar to those of the low-Re model, using a much coarser mesh.

Keywords: SWTBLIs, skin-friction, turbulence modeling, wall function

Procedia PDF Downloads 240
398 Uncertainty in Building Energy Performance Analysis at Different Stages of the Building’s Lifecycle

Authors: Elham Delzendeh, Song Wu, Mustafa Al-Adhami, Rima Alaaeddine


Over the last 15 years, prediction of energy consumption has become a common practice and necessity at different stages of the building’s lifecycle, particularly, at the design and post-occupancy stages for planning and maintenance purposes. This is due to the ever-growing response of governments to address sustainability and reduction of CO₂ emission in the building sector. However, there is a level of uncertainty in the estimation of energy consumption in buildings. The accuracy of energy consumption predictions is directly related to the precision of the initial inputs used in the energy assessment process. In this study, multiple cases of large non-residential buildings at design, construction, and post-occupancy stages are investigated. The energy consumption process and inputs, and the actual and predicted energy consumption of the cases are analysed. The findings of this study have pointed out and evidenced various parameters that cause uncertainty in the prediction of energy consumption in buildings such as modelling, location data, and occupant behaviour. In addition, unavailability and insufficiency of energy-consumption-related inputs at different stages of the building’s lifecycle are classified and categorized. Understanding the roots of uncertainty in building energy analysis will help energy modellers and energy simulation software developers reach more accurate energy consumption predictions in buildings.

Keywords: building lifecycle, efficiency, energy analysis, energy performance, uncertainty

Procedia PDF Downloads 38
397 Data Refinement Enhances The Accuracy of Short-Term Traffic Latency Prediction

Authors: Man Fung Ho, Lap So, Jiaqi Zhang, Yuheng Zhao, Huiyang Lu, Tat Shing Choi, K. Y. Michael Wong


Nowadays, a tremendous amount of data is available in the transportation system, enabling the development of various machine learning approaches to make short-term latency predictions. A natural question is then the choice of relevant information to enable accurate predictions. Using traffic data collected from the Taiwan Freeway System, we consider the prediction of short-term latency of a freeway segment with a length of 17 km covering 5 measurement points, each collecting vehicle-by-vehicle data through the electronic toll collection system. The processed data include the past latencies of the freeway segment with different time lags, the traffic conditions of the individual segments (the accumulations, the traffic fluxes, the entrance and exit rates), the total accumulations, and the weekday latency profiles obtained by Gaussian process regression of past data. We arrive at several important conclusions about how data should be refined to obtain accurate predictions, which have implications for future system-wide latency predictions. (1) We find that the prediction of median latency is much more accurate and meaningful than the prediction of average latency, as the latter is plagued by outliers. This is verified by machine-learning prediction using XGBoost that yields a 35% improvement in the mean square error of the 5-minute averaged latencies. (2) We find that the median latency of the segment 15 minutes ago is a very good baseline for performance comparison, and we have evidence that further improvement is achieved by machine learning approaches such as XGBoost and Long Short-Term Memory (LSTM). (3) By analyzing the feature importance score in XGBoost and calculating the mutual information between the inputs and the latencies to be predicted, we identify a sequence of inputs ranked in importance. It confirms that the past latencies are most informative of the predicted latencies, followed by the total accumulation, whereas inputs such as the entrance and exit rates are uninformative. It also confirms that the inputs are much less informative of the average latencies than the median latencies. (4) For predicting the latencies of segments composed of two or three sub-segments, summing up the predicted latencies of each sub-segment is more accurate than the one-step prediction of the whole segment, especially with the latency prediction of the downstream sub-segments trained to anticipate latencies several minutes ahead. The duration of the anticipation time is an increasing function of the traveling time of the upstream segment. The above findings have important implications to predicting the full set of latencies among the various locations in the freeway system.

Keywords: data refinement, machine learning, mutual information, short-term latency prediction

Procedia PDF Downloads 73
396 Using Soil Texture Field Observations as Ordinal Qualitative Variables for Digital Soil Mapping

Authors: Anne C. Richer-De-Forges, Dominique Arrouays, Songchao Chen, Mercedes Roman Dobarco


Most of the digital soil mapping (DSM) products rely on machine learning (ML) prediction models and/or the use or pedotransfer functions (PTF) in which calibration data come from soil analyses performed in labs. However, many other observations (often qualitative, nominal, or ordinal) could be used as proxies of lab measurements or as input data for ML of PTF predictions. DSM and ML are briefly described with some examples taken from the literature. Then, we explore the potential of an ordinal qualitative variable, i.e., the hand-feel soil texture (HFST) estimating the mineral particle distribution (PSD): % of clay (0-2µm), silt (2-50µm) and sand (50-2000µm) in 15 classes. The PSD can also be measured by lab measurements (LAST) to determine the exact proportion of these particle-sizes. However, due to cost constraints, HFST are much more numerous and spatially dense than LAST. Soil texture (ST) is a very important soil parameter to map as it is controlling many of the soil properties and functions. Therefore, comes an essential question: is it possible to use HFST as a proxy of LAST for calibration and/or validation of DSM predictions of ST? To answer this question, the first step is to compare HFST with LAST on a representative set where both information are available. This comparison was made on ca 17,400 samples representative of a French region (34,000 km2). The accuracy of HFST was assessed, and each HFST class was characterized by a probability distribution function (PDF) of its LAST values. This enables to randomly replace HFST observations by LAST values while respecting the PDF previously calculated and results in a very large increase of observations available for the calibration or validation of PTF and ML predictions. Some preliminary results are shown. First, the comparison between HFST classes and LAST analyses showed that accuracies could be considered very good when compared to other studies. The causes of some inconsistencies were explored and most of them were well explained by other soil characteristics. Then we show some examples applying these relationships and the increase of data to several issues related to DSM. The first issue is: do the PDF functions that were established enable to use HSFT class observations to improve the LAST soil texture prediction? For this objective, we replaced all HFST for topsoil by values from the PDF 100 time replicates). Results were promising for the PTF we tested (a PTF predicting soil water holding capacity). For the question related to the ML prediction of LAST soil texture on the region, we did the same kind of replacement, but we implemented a 10-fold cross-validation using points where we had LAST values. We obtained only preliminary results but they were rather promising. Then we show another example illustrating the potential of using HFST as validation data. As in numerous countries, the HFST observations are very numerous; these promising results pave the way to an important improvement of DSM products in all the countries of the world.

Keywords: digital soil mapping, improvement of digital soil mapping predictions, potential of using hand-feel soil texture, soil texture prediction

Procedia PDF Downloads 72
395 Numerical Predictions of Trajectory Stability of a High-Speed Water-Entry and Water-Exit Projectile

Authors: Lin Lu, Qiang Li, Tao Cai, Pengjun Zhang


In this study, a detailed analysis of trajectory stability and flow characteristics of a high-speed projectile during the water-entry and water-exit process has been investigated numerically. The Zwart-Gerber-Belamri (Z-G-B) cavitation model and the SST k-ω turbulence model based on the Reynolds Averaged Navier-Stokes (RANS) method are employed. The numerical methodology is validated by comparing the experimental photograph of cavitation shape and the experimental underwater velocity with the numerical simulation results. Based on the numerical methodology, the influences of rotational speed, water-entry and water-exit angle of the projectile on the trajectory stability and flow characteristics have been carried out in detail. The variation features of projectile trajectory and total resistance have been conducted, respectively. In addition, the cavitation characteristics of water-entry and water-exit have been presented and analyzed. Results show that it may not be applicable for the water-entry and water-exit to achieve the projectile stability through the rotation of projectile. Furthermore, there ought to be a critical water-entry angle for the water-entry stability of practical projectile. The impact of water-exit angle on the trajectory stability and cavity phenomenon is not as remarkable as that of the water-entry angle.

Keywords: cavitation characteristics, high-speed projectile, numerical predictions, trajectory stability, water-entry, water-exit

Procedia PDF Downloads 37
394 Comparisons of Co-Seismic Gravity Changes between GRACE Observations and the Predictions from the Finite-Fault Models for the 2012 Mw = 8.6 Indian Ocean Earthquake Off-Sumatra

Authors: Armin Rahimi


The Gravity Recovery and Climate Experiment (GRACE) has been a very successful project in determining math redistribution within the Earth system. Large deformations caused by earthquakes are in the high frequency band. Unfortunately, GRACE is only capable to provide reliable estimate at the low-to-medium frequency band for the gravitational changes. In this study, we computed the gravity changes after the 2012 Mw8.6 Indian Ocean earthquake off-Sumatra using the GRACE Level-2 monthly spherical harmonic (SH) solutions released by the University of Texas Center for Space Research (UTCSR). Moreover, we calculated gravity changes using different fault models derived from teleseismic data. The model predictions showed non-negligible discrepancies in gravity changes. However, after removing high-frequency signals, using Gaussian filtering 350 km commensurable GRACE spatial resolution, the discrepancies vanished, and the spatial patterns of total gravity changes predicted from all slip models became similar at the spatial resolution attainable by GRACE observations, and predicted-gravity changes were consistent with the GRACE-detected gravity changes. Nevertheless, the fault models, in which give different slip amplitudes, proportionally lead to different amplitude in the predicted gravity changes.

Keywords: undersea earthquake, GRACE observation, gravity change, dislocation model, slip distribution

Procedia PDF Downloads 272
393 Some Accuracy Related Aspects in Two-Fluid Hydrodynamic Sub-Grid Modeling of Gas-Solid Riser Flows

Authors: Joseph Mouallem, Seyed Reza Amini Niaki, Norman Chavez-Cussy, Christian Costa Milioli, Fernando Eduardo Milioli


Sub-grid closures for filtered two-fluid models (fTFM) useful in large scale simulations (LSS) of riser flows can be derived from highly resolved simulations (HRS) with microscopic two-fluid modeling (mTFM). Accurate sub-grid closures require accurate mTFM formulations as well as accurate correlation of relevant filtered parameters to suitable independent variables. This article deals with both of those issues. The accuracy of mTFM is touched by assessing the impact of gas sub-grid turbulence over HRS filtered predictions. A gas turbulence alike effect is artificially inserted by means of a stochastic forcing procedure implemented in the physical space over the momentum conservation equation of the gas phase. The correlation issue is touched by introducing a three-filtered variable correlation analysis (three-marker analysis) performed under a variety of different macro-scale conditions typical or risers. While the more elaborated correlation procedure clearly improved accuracy, accounting for gas sub-grid turbulence had no significant impact over predictions.

Keywords: fluidization, gas-particle flow, two-fluid model, sub-grid models, filtered closures

Procedia PDF Downloads 43
392 A Predictive Analytics Approach to Project Management: Reducing Project Failures in Web and Software Development Projects

Authors: Tazeen Fatima


Use of project management in web & software development projects is very significant. It has been observed that even with the application of effective project management, projects usually do not complete their lifecycle and fail. To minimize these failures, key performance indicators have been introduced in previous studies to counter project failures. However, there are always gaps and problems in the KPIs identified. Despite of incessant efforts at technical and managerial levels, projects still fail. There is no substantial approach to identify and avoid these failures in the very beginning of the project lifecycle. In this study, we aim to answer these research problems by analyzing the concept of predictive analytics which is a specialized technology and is very easy to use in this era of computation. Project organizations can use data gathering, compute power, and modern tools to render efficient Predictions. The research aims to identify such a predictive analytics approach. The core objective of the study was to reduce failures and introduce effective implementation of project management principles. Existing predictive analytics methodologies, tools and solution providers were also analyzed. Relevant data was gathered from projects and was analyzed via predictive techniques to make predictions well advance in time to render effective project management in web & software development industry.

Keywords: project management, predictive analytics, predictive analytics methodology, project failures

Procedia PDF Downloads 210
391 An Application for Risk of Crime Prediction Using Machine Learning

Authors: Luis Fonseca, Filipe Cabral Pinto, Susana Sargento


The increase of the world population, especially in large urban centers, has resulted in new challenges particularly with the control and optimization of public safety. Thus, in the present work, a solution is proposed for the prediction of criminal occurrences in a city based on historical data of incidents and demographic information. The entire research and implementation will be presented start with the data collection from its original source, the treatment and transformations applied to them, choice and the evaluation and implementation of the Machine Learning model up to the application layer. Classification models will be implemented to predict criminal risk for a given time interval and location. Machine Learning algorithms such as Random Forest, Neural Networks, K-Nearest Neighbors and Logistic Regression will be used to predict occurrences, and their performance will be compared according to the data processing and transformation used. The results show that the use of Machine Learning techniques helps to anticipate criminal occurrences, which contributed to the reinforcement of public security. Finally, the models were implemented on a platform that will provide an API to enable other entities to make requests for predictions in real-time. An application will also be presented where it is possible to show criminal predictions visually.

Keywords: crime prediction, machine learning, public safety, smart city

Procedia PDF Downloads 27
390 Solar Radiation Time Series Prediction

Authors: Cameron Hamilton, Walter Potter, Gerrit Hoogenboom, Ronald McClendon, Will Hobbs


A model was constructed to predict the amount of solar radiation that will make contact with the surface of the earth in a given location an hour into the future. This project was supported by the Southern Company to determine at what specific times during a given day of the year solar panels could be relied upon to produce energy in sufficient quantities. Due to their ability as universal function approximators, an artificial neural network was used to estimate the nonlinear pattern of solar radiation, which utilized measurements of weather conditions collected at the Griffin, Georgia weather station as inputs. A number of network configurations and training strategies were utilized, though a multilayer perceptron with a variety of hidden nodes trained with the resilient propagation algorithm consistently yielded the most accurate predictions. In addition, a modeled DNI field and adjacent weather station data were used to bolster prediction accuracy. In later trials, the solar radiation field was preprocessed with a discrete wavelet transform with the aim of removing noise from the measurements. The current model provides predictions of solar radiation with a mean square error of 0.0042, though ongoing efforts are being made to further improve the model’s accuracy.

Keywords: artificial neural networks, resilient propagation, solar radiation, time series forecasting

Procedia PDF Downloads 234