Search results for: Accidents Prediction Models (APMs)
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 3369

Search results for: Accidents Prediction Models (APMs)

2919 Evaluation of Context Information for Intermittent Networks

Authors: S. Balaji, E. Golden Julie, Y. Harold Robinson

Abstract:

The context aware adaptive routing protocol is presented for unicast communication in intermittently connected mobile ad hoc networks (MANETs). The selection of the node is done by the Kalman filter prediction theory and it also makes use of utility functions. The context aware adaptive routing is defined by spray and wait technique, but the time consumption in delivering the message is too high and also the resource wastage is more. In this paper, we describe the spray and focus routing scheme for avoiding the existing problems.

Keywords: Context aware adaptive routing, Kalman filter prediction, spray and wait, spray and focus, intermittent networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 886
2918 Towards End-To-End Disease Prediction from Raw Metagenomic Data

Authors: Maxence Queyrel, Edi Prifti, Alexandre Templier, Jean-Daniel Zucker

Abstract:

Analysis of the human microbiome using metagenomic sequencing data has demonstrated high ability in discriminating various human diseases. Raw metagenomic sequencing data require multiple complex and computationally heavy bioinformatics steps prior to data analysis. Such data contain millions of short sequences read from the fragmented DNA sequences and stored as fastq files. Conventional processing pipelines consist in multiple steps including quality control, filtering, alignment of sequences against genomic catalogs (genes, species, taxonomic levels, functional pathways, etc.). These pipelines are complex to use, time consuming and rely on a large number of parameters that often provide variability and impact the estimation of the microbiome elements. Training Deep Neural Networks directly from raw sequencing data is a promising approach to bypass some of the challenges associated with mainstream bioinformatics pipelines. Most of these methods use the concept of word and sentence embeddings that create a meaningful and numerical representation of DNA sequences, while extracting features and reducing the dimensionality of the data. In this paper we present an end-to-end approach that classifies patients into disease groups directly from raw metagenomic reads: metagenome2vec. This approach is composed of four steps (i) generating a vocabulary of k-mers and learning their numerical embeddings; (ii) learning DNA sequence (read) embeddings; (iii) identifying the genome from which the sequence is most likely to come and (iv) training a multiple instance learning classifier which predicts the phenotype based on the vector representation of the raw data. An attention mechanism is applied in the network so that the model can be interpreted, assigning a weight to the influence of the prediction for each genome. Using two public real-life data-sets as well a simulated one, we demonstrated that this original approach reaches high performance, comparable with the state-of-the-art methods applied directly on processed data though mainstream bioinformatics workflows. These results are encouraging for this proof of concept work. We believe that with further dedication, the DNN models have the potential to surpass mainstream bioinformatics workflows in disease classification tasks.

Keywords: Metagenomics, phenotype prediction, deep learning, embeddings, multiple instance learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 863
2917 Electricity Price Forecasting: A Comparative Analysis with Shallow-ANN and DNN

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Electricity prices have sophisticated features such as high volatility, nonlinearity and high frequency that make forecasting quite difficult. Electricity price has a volatile and non-random character so that, it is possible to identify the patterns based on the historical data. Intelligent decision-making requires accurate price forecasting for market traders, retailers, and generation companies. So far, many shallow-ANN (artificial neural networks) models have been published in the literature and showed adequate forecasting results. During the last years, neural networks with many hidden layers, which are referred to as DNN (deep neural networks) have been using in the machine learning community. The goal of this study is to investigate electricity price forecasting performance of the shallow-ANN and DNN models for the Turkish day-ahead electricity market. The forecasting accuracy of the models has been evaluated with publicly available data from the Turkish day-ahead electricity market. Both shallow-ANN and DNN approach would give successful result in forecasting problems. Historical load, price and weather temperature data are used as the input variables for the models. The data set includes power consumption measurements gathered between January 2016 and December 2017 with one-hour resolution. In this regard, forecasting studies have been carried out comparatively with shallow-ANN and DNN models for Turkish electricity markets in the related time period. The main contribution of this study is the investigation of different shallow-ANN and DNN models in the field of electricity price forecast. All models are compared regarding their MAE (Mean Absolute Error) and MSE (Mean Square) results. DNN models give better forecasting performance compare to shallow-ANN. Best five MAE results for DNN models are 0.346, 0.372, 0.392, 0,402 and 0.409.

Keywords: Deep learning, artificial neural networks, energy price forecasting, Turkey.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1050
2916 Human Pose Estimation using Active Shape Models

Authors: Changhyuk Jang, Keechul Jung

Abstract:

Human pose estimation can be executed using Active Shape Models. The existing techniques for applying to human-body research using Active Shape Models, such as human detection, primarily take the form of silhouette of human body. This technique is not able to estimate accurately for human pose to concern two arms and legs, as the silhouette of human body represents the shape as out of round. To solve this problem, we applied the human body model as stick-figure, “skeleton". The skeleton model of human body can give consideration to various shapes of human pose. To obtain effective estimation result, we applied background subtraction and deformed matching algorithm of primary Active Shape Models in the fitting process. The images which were used to make the model were 600 human bodies, and the model has 17 landmark points which indicate body junction and key features of human pose. The maximum iteration for the fitting process was 30 times and the execution time was less than .03 sec.

Keywords: Active shape models, skeleton, pose estimation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2381
2915 Investigation of Improved Chaotic Signal Tracking by Echo State Neural Networks and Multilayer Perceptron via Training of Extended Kalman Filter Approach

Authors: Farhad Asadi, S. Hossein Sadati

Abstract:

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

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

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 723
2914 Application and Assessment of Artificial Neural Networks for Biodiesel Iodine Value Prediction

Authors: Raquel M. de Sousa, Sofiane Labidi, Allan Kardec D. Barros, Alex O. Barradas Filho, Aldalea L. B. Marques

Abstract:

Several parameters are established in order to measure biodiesel quality. One of them is the iodine value, which is an important parameter that measures the total unsaturation within a mixture of fatty acids. Limitation of unsaturated fatty acids is necessary since warming of higher quantity of these ones ends in either formation of deposits inside the motor or damage of lubricant. Determination of iodine value by official procedure tends to be very laborious, with high costs and toxicity of the reagents, this study uses artificial neural network (ANN) in order to predict the iodine value property as an alternative to these problems. The methodology of development of networks used 13 esters of fatty acids in the input with convergence algorithms of back propagation of back propagation type were optimized in order to get an architecture of prediction of iodine value. This study allowed us to demonstrate the neural networks’ ability to learn the correlation between biodiesel quality properties, in this caseiodine value, and the molecular structures that make it up. The model developed in the study reached a correlation coefficient (R) of 0.99 for both network validation and network simulation, with Levenberg-Maquardt algorithm.

Keywords: Artificial Neural Networks, Biodiesel, Iodine Value, Prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2348
2913 High Capacity Data Hiding based on Predictor and Histogram Modification

Authors: Hui-Yu Huang, Shih-Hsu Chang

Abstract:

In this paper, we propose a high capacity image hiding technology based on pixel prediction and the difference of modified histogram. This approach is used the pixel prediction and the difference of modified histogram to calculate the best embedding point. This approach can improve the predictive accuracy and increase the pixel difference to advance the hiding capacity. We also use the histogram modification to prevent the overflow and underflow. Experimental results demonstrate that our proposed method within the same average hiding capacity can still keep high quality of image and low distortion

Keywords: data hiding, predictor

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1862
2912 The Use of Artificial Neural Network in Option Pricing: The Case of S and P 100 Index Options

Authors: Zeynep İltüzer Samur, Gül Tekin Temur

Abstract:

Due to the increasing and varying risks that economic units face with, derivative instruments gain substantial importance, and trading volumes of derivatives have reached very significant level. Parallel with these high trading volumes, researchers have developed many different models. Some are parametric, some are nonparametric. In this study, the aim is to analyse the success of artificial neural network in pricing of options with S&P 100 index options data. Generally, the previous studies cover the data of European type call options. This study includes not only European call option but also American call and put options and European put options. Three data sets are used to perform three different ANN models. One only includes data that are directly observed from the economic environment, i.e. strike price, spot price, interest rate, maturity, type of the contract. The others include an extra input that is not an observable data but a parameter, i.e. volatility. With these detail data, the performance of ANN in put/call dimension, American/European dimension, moneyness dimension is analyzed and whether the contribution of the volatility in neural network analysis make improvement in prediction performance or not is examined. The most striking results revealed by the study is that ANN shows better performance when pricing call options compared to put options; and the use of volatility parameter as an input does not improve the performance.

Keywords: Option Pricing, Neural Network, S&P 100 Index, American/European options

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3049
2911 Determining the Width and Depths of Cut in Milling on the Basis of a Multi-Dexel Model

Authors: Jens Friedrich, Matthias A. Gebele, Armin Lechler, Alexander Verl

Abstract:

Chatter vibrations and process instabilities are the most important factors limiting the productivity of the milling process. Chatter can leads to damage of the tool, the part or the machine tool. Therefore, the estimation and prediction of the process stability is very important. The process stability depends on the spindle speed, the depth of cut and the width of cut. In milling, the process conditions are defined in the NC-program. While the spindle speed is directly coded in the NC-program, the depth and width of cut are unknown. This paper presents a new simulation based approach for the prediction of the depth and width of cut of a milling process. The prediction is based on a material removal simulation with an analytically represented tool shape and a multi-dexel approach for the workpiece. The new calculation method allows the direct estimation of the depth and width of cut, which are the influencing parameters of the process stability, instead of the removed volume as existing approaches do. The knowledge can be used to predict the stability of new, unknown parts. Moreover with an additional vibration sensor, the stability lobe diagram of a milling process can be estimated and improved based on the estimated depth and width of cut.

Keywords: Dexel, process stability, material removal, milling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2230
2910 Investigation of Some Technical Indexes inStock Forecasting Using Neural Networks

Authors: Myungsook Klassen

Abstract:

Training neural networks to capture an intrinsic property of a large volume of high dimensional data is a difficult task, as the training process is computationally expensive. Input attributes should be carefully selected to keep the dimensionality of input vectors relatively small. Technical indexes commonly used for stock market prediction using neural networks are investigated to determine its effectiveness as inputs. The feed forward neural network of Levenberg-Marquardt algorithm is applied to perform one step ahead forecasting of NASDAQ and Dow stock prices.

Keywords: Stock Market Prediction, Neural Networks, Levenberg-Marquadt Algorithm, Technical Indexes

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1921
2909 Simulation of Reactive Distillation: Comparison of Equilibrium and Nonequilibrium Stage Models

Authors: Asfaw Gezae Daful

Abstract:

In the present study, two distinctly different approaches are followed for modeling of reactive distillation column, the equilibrium stage model and the nonequilibrium stage model. These models are simulated with a computer code developed in the present study using MATLAB programming. In the equilibrium stage models, the vapor and liquid phases are assumed to be in equilibrium and allowance is made for finite reaction rates, where as in the nonequilibrium stage models simultaneous mass transfer and reaction rates are considered. These simulated model results are validated from the experimental data reported in the literature. The simulated results of equilibrium and nonequilibrium models are compared for concentration, temperature and reaction rate profiles in a reactive distillation column for Methyl Tert Butyle Ether (MTBE) production. Both the models show similar trend for the concentration, temperature and reaction rate profiles but the nonequilibrium model predictions are higher and closer to the experimental values reported in the literature.

Keywords: Reactive Distillation, Equilibrium model, Nonequilibrium model, Methyl Tert-Butyl Ether

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4175
2908 CFD Study of Subcooled Boiling Flow at Elevated Pressure Using a Mechanistic Wall Heat Partitioning Model

Authors: Machimontorn Promtong, Sherman C. P. Cheung, Guan H. Yeoh, Sara Vahaji, Jiyuan Tu

Abstract:

The wide range of industrial applications involved with boiling flows promotes the necessity of establishing fundamental knowledge in boiling flow phenomena. For this purpose, a number of experimental and numerical researches have been performed to elucidate the underlying physics of this flow. In this paper, the improved wall boiling models, implemented on ANSYS CFX 14.5, were introduced to study subcooled boiling flow at elevated pressure. At the heated wall boundary, the Fractal model, Force balance approach and Mechanistic frequency model are given for predicting the nucleation site density, bubble departure diameter, and bubble departure frequency. The presented wall heat flux partitioning closures were modified to consider the influence of bubble sliding along the wall before the lift-off, which usually happens in the flow boiling. The simulation was performed based on the Two-fluid model, where the standard k-ω SST model was selected for turbulence modelling. Existing experimental data at around 5 bars were chosen to evaluate the accuracy of the presented mechanistic approach. The void fraction and Interfacial Area Concentration (IAC) are in good agreement with the experimental data. However, the predicted bubble velocity and Sauter Mean Diameter (SMD) are over-predicted. This over-prediction may be caused by consideration of only dispersed and spherical bubbles in the simulations. In the future work, the important physical mechanisms of bubbles, such as merging and shrinking during sliding on the heated wall will be incorporated into this mechanistic model to enhance its capability for a wider range of flow prediction.

Keywords: CFD, mechanistic model, subcooled boiling flow, two-fluid model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1231
2907 Classification of Business Models of Italian Bancassurance by Balance Sheet Indicators

Authors: Andrea Bellucci, Martina Tofi

Abstract:

The aim of paper is to analyze business models of bancassurance in Italy for life business. The life insurance business is very developed in the Italian market and banks branches have 80% of the market share. Given its maturity, the life insurance market needs to consolidate its organizational form to allow for the development of non-life business, which nowadays collects few premiums but represents a great opportunity to enlarge the market share of bancassurance using its strength in the distribution channel while the market share of independent agents is decreasing. Starting with the main business model of bancassurance for life business, this paper will analyze the performances of life companies in the Italian market by balance sheet indicators and by main discriminant variables of business models. The study will observe trends from 2013 to 2015 for the Italian market by exploiting a database managed by Associazione Nazionale delle Imprese di Assicurazione (ANIA). The applied approach is based on a bottom-up analysis starting with variables and indicators to define business models’ classification. The statistical classification algorithm proposed by Ward is employed to design business models’ profiles. Results from the analysis will be a representation of the main business models built by their profile related to indicators. In that way, an unsupervised analysis is developed that has the limit of its judgmental dimension based on research opinion, but it is possible to obtain a design of effective business models.

Keywords: Balance sheet indicators, Bancassurance, business models, ward algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1233
2906 The Strengths and Limitations of the Statistical Modeling of Complex Social Phenomenon: Focusing on SEM, Path Analysis, or Multiple Regression Models

Authors: Jihye Jeon

Abstract:

This paper analyzes the conceptual framework of three statistical methods, multiple regression, path analysis, and structural equation models. When establishing research model of the statistical modeling of complex social phenomenon, it is important to know the strengths and limitations of three statistical models. This study explored the character, strength, and limitation of each modeling and suggested some strategies for accurate explaining or predicting the causal relationships among variables. Especially, on the studying of depression or mental health, the common mistakes of research modeling were discussed.

Keywords: Multiple regression, path analysis, structural equation models, statistical modeling, social and psychological phenomenon.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 9161
2905 Mathematical Rescheduling Models for Railway Services

Authors: Zuraida Alwadood, Adibah Shuib, Norlida Abd Hamid

Abstract:

This paper presents the review of past studies concerning mathematical models for rescheduling passenger railway services, as part of delay management in the occurrence of railway disruption. Many past mathematical models highlighted were aimed at minimizing the service delays experienced by passengers during service disruptions. Integer programming (IP) and mixed-integer programming (MIP) models are critically discussed, focusing on the model approach, decision variables, sets and parameters. Some of them have been tested on real-life data of railway companies worldwide, while a few have been validated on fictive data. Based on selected literatures on train rescheduling, this paper is able to assist researchers in the model formulation by providing comprehensive analyses towards the model building. These analyses would be able to help in the development of new approaches in rescheduling strategies or perhaps to enhance the existing rescheduling models and make them more powerful or more applicable with shorter computing time.

Keywords: Mathematical modelling, Mixed-integer programming, Railway rescheduling, Service delays.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3205
2904 The Classification Model for Hard Disk Drive Functional Tests under Sparse Data Conditions

Authors: S. Pattanapairoj, D. Chetchotsak

Abstract:

This paper proposed classification models that would be used as a proxy for hard disk drive (HDD) functional test equitant which required approximately more than two weeks to perform the HDD status classification in either “Pass" or “Fail". These models were constructed by using committee network which consisted of a number of single neural networks. This paper also included the method to solve the problem of sparseness data in failed part, which was called “enforce learning method". Our results reveal that the constructed classification models with the proposed method could perform well in the sparse data conditions and thus the models, which used a few seconds for HDD classification, could be used to substitute the HDD functional tests.

Keywords: Sparse data, Classifications, Committee network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1708
2903 Forecasting the Volatility of Geophysical Time Series with Stochastic Volatility Models

Authors: Maria C. Mariani, Md Al Masum Bhuiyan, Osei K. Tweneboah, Hector G. Huizar

Abstract:

This work is devoted to the study of modeling geophysical time series. A stochastic technique with time-varying parameters is used to forecast the volatility of data arising in geophysics. In this study, the volatility is defined as a logarithmic first-order autoregressive process. We observe that the inclusion of log-volatility into the time-varying parameter estimation significantly improves forecasting which is facilitated via maximum likelihood estimation. This allows us to conclude that the estimation algorithm for the corresponding one-step-ahead suggested volatility (with ±2 standard prediction errors) is very feasible since it possesses good convergence properties.

Keywords: Augmented Dickey Fuller Test, geophysical time series, maximum likelihood estimation, stochastic volatility model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 836
2902 An Integrative Bayesian Approach to Supporting the Prediction of Protein-Protein Interactions: A Case Study in Human Heart Failure

Authors: Fiona Browne, Huiru Zheng, Haiying Wang, Francisco Azuaje

Abstract:

Recent years have seen a growing trend towards the integration of multiple information sources to support large-scale prediction of protein-protein interaction (PPI) networks in model organisms. Despite advances in computational approaches, the combination of multiple “omic" datasets representing the same type of data, e.g. different gene expression datasets, has not been rigorously studied. Furthermore, there is a need to further investigate the inference capability of powerful approaches, such as fullyconnected Bayesian networks, in the context of the prediction of PPI networks. This paper addresses these limitations by proposing a Bayesian approach to integrate multiple datasets, some of which encode the same type of “omic" data to support the identification of PPI networks. The case study reported involved the combination of three gene expression datasets relevant to human heart failure (HF). In comparison with two traditional methods, Naive Bayesian and maximum likelihood ratio approaches, the proposed technique can accurately identify known PPI and can be applied to infer potentially novel interactions.

Keywords: Bayesian network, Classification, Data integration, Protein interaction networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1592
2901 Imputing Missing Data in Electronic Health Records: A Comparison of Linear and Non-Linear Imputation Models

Authors: Alireza Vafaei Sadr, Vida Abedi, Jiang Li, Ramin Zand

Abstract:

Missing data is a common challenge in medical research and can lead to biased or incomplete results. When the data bias leaks into models, it further exacerbates health disparities; biased algorithms can lead to misclassification and reduced resource allocation and monitoring as part of prevention strategies for certain minorities and vulnerable segments of patient populations, which in turn further reduce data footprint from the same population – thus, a vicious cycle. This study compares the performance of six imputation techniques grouped into Linear and Non-Linear models, on two different real-world electronic health records (EHRs) datasets, representing 17864 patient records. The mean absolute percentage error (MAPE) and root mean squared error (RMSE) are used as performance metrics, and the results show that the Linear models outperformed the Non-Linear models in terms of both metrics. These results suggest that sometimes Linear models might be an optimal choice for imputation in laboratory variables in terms of imputation efficiency and uncertainty of predicted values.

Keywords: EHR, Machine Learning, imputation, laboratory variables, algorithmic bias.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 85
2900 Interaction Effect of Feed Rate and Cutting Speed in CNC-Turning on Chip Micro-Hardness of 304- Austenitic Stainless Steel

Authors: G. H. Senussi

Abstract:

The present work is concerned with the effect of turning process parameters (cutting speed, feed rate, and depth of cut) and distance from the center of work piece as input variables on the chip micro-hardness as response or output. Three experiments were conducted; they were used to investigate the chip micro-hardness behavior at diameter of work piece for 30[mm], 40[mm], and 50[mm]. Response surface methodology (R.S.M) is used to determine and present the cause and effect of the relationship between true mean response and input control variables influencing the response as a two or three dimensional hyper surface. R.S.M has been used for designing a three factor with five level central composite rotatable factors design in order to construct statistical models capable of accurate prediction of responses. The results obtained showed that the application of R.S.M can predict the effect of machining parameters on chip micro-hardness. The five level factorial designs can be employed easily for developing statistical models to predict chip micro-hardness by controllable machining parameters. Results obtained showed that the combined effect of cutting speed at it?s lower level, feed rate and depth of cut at their higher values, and larger work piece diameter can result increasing chi micro-hardness.

Keywords: Machining Parameters, Chip Micro-Hardness, CNCMachining, 304-Austenic Stainless Steel.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3256
2899 Using Fractional Factorial Designs for Variable Importance in Random Forest Models

Authors: Ewa. M. Sztendur, Neil T. Diamond

Abstract:

Random Forests are a powerful classification technique, consisting of a collection of decision trees. One useful feature of Random Forests is the ability to determine the importance of each variable in predicting the outcome. This is done by permuting each variable and computing the change in prediction accuracy before and after the permutation. This variable importance calculation is similar to a one-factor-at a time experiment and therefore is inefficient. In this paper, we use a regular fractional factorial design to determine which variables to permute. Based on the results of the trials in the experiment, we calculate the individual importance of the variables, with improved precision over the standard method. The method is illustrated with a study of student attrition at Monash University.

Keywords: Random Forests, Variable Importance, Fractional Factorial Designs, Student Attrition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1966
2898 An Improved Model for Prediction of the Effective Thermal Conductivity of Nanofluids

Authors: K. Abbaspoursani, M. Allahyari, M. Rahmani

Abstract:

Thermal conductivity is an important characteristic of a nanofluid in laminar flow heat transfer. This paper presents an improved model for the prediction of the effective thermal conductivity of nanofluids based on dimensionless groups. The model expresses the thermal conductivity of a nanofluid as a function of the thermal conductivity of the solid and liquid, their volume fractions and particle size. The proposed model includes a parameter which accounts for the interfacial shell, brownian motion, and aggregation of particle. The validation of the model is verified by applying the results obtained by the experiments of Tio2-water and Al2o3-water nanofluids.

Keywords: Critical particle size, nanofluid, model, and thermal conductivity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2020
2897 A Hybrid System of Hidden Markov Models and Recurrent Neural Networks for Learning Deterministic Finite State Automata

Authors: Pavan K. Rallabandi, Kailash C. Patidar

Abstract:

In this paper, we present an optimization technique or a learning algorithm using the hybrid architecture by combining the most popular sequence recognition models such as Recurrent Neural Networks (RNNs) and Hidden Markov models (HMMs). In order to improve the sequence/pattern recognition/classification performance by applying a hybrid/neural symbolic approach, a gradient descent learning algorithm is developed using the Real Time Recurrent Learning of Recurrent Neural Network for processing the knowledge represented in trained Hidden Markov Models. The developed hybrid algorithm is implemented on automata theory as a sample test beds and the performance of the designed algorithm is demonstrated and evaluated on learning the deterministic finite state automata.

Keywords: Hybrid systems, Hidden Markov Models, Recurrent neural networks, Deterministic finite state automata.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2850
2896 Transformation Method CIM to PIM: From Business Processes Models Defined in BPMN to Use Case and Class Models Defined in UML

Authors: Y. Rhazali, Y. Hadi, A. Mouloudi

Abstract:

This paper proposes a method to automatic transformation of CIM level to PIM level respecting the MDA approach. Our proposal is based on creating a good CIM level through well-defined rules allowing as achieving rich models that contain relevant information to facilitate the task of the transformation to the PIM level. We define, thereafter, an appropriate PIM level through various UML diagram. Next, we propose set rules to move from CIM to PIM. Our method follows the MDA approach by considering the business dimension in the CIM level through the use BPMN, standard modeling business of OMG, and the use of UML in PIM advocated by MDA in this level.

Keywords: Model transformation, MDA, CIM, PIM.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3640
2895 Modeling the Saltatory Conduction in Myelinated Axons by Order Reduction

Authors: Ruxandra Barbulescu, Daniel Ioan, Gabriela Ciuprina

Abstract:

The saltatory conduction is the way the action potential is transmitted along a myelinated axon. The potential diffuses along the myelinated compartments and it is regenerated in the Ranvier nodes due to the ion channels allowing the flow across the membrane. For an efficient simulation of populations of neurons, it is important to use reduced order models both for myelinated compartments and for Ranvier nodes and to have control over their accuracy and inner parameters. The paper presents a reduced order model of this neural system which allows an efficient simulation method for the saltatory conduction in myelinated axons. This model is obtained by concatenating reduced order linear models of 1D myelinated compartments and nonlinear 0D models of Ranvier nodes. The models for the myelinated compartments are selected from a series of spatially distributed models developed and hierarchized according to their modeling errors. The extracted model described by a nonlinear PDE of hyperbolic type is able to reproduce the saltatory conduction with acceptable accuracy and takes into account the finite propagation speed of potential. Finally, this model is again reduced in order to make it suitable for the inclusion in large-scale neural circuits.

Keywords: Saltatory conduction, action potential, myelinated compartments, nonlinear, Ranvier nodes, reduced order models, POD.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 800
2894 Comparison of Stochastic Point Process Models of Rainfall in Singapore

Authors: Y. Lu, X. S. Qin

Abstract:

Extensive rainfall disaggregation approaches have been developed and applied in climate change impact studies such as flood risk assessment and urban storm water management.In this study, five rainfall models that were capable ofdisaggregating daily rainfall data into hourly one were investigated for the rainfall record in theChangi Airport, Singapore. The objectives of this study were (i) to study the temporal characteristics of hourly rainfall in Singapore, and (ii) to evaluate the performance of variousdisaggregation models. The used models included: (i) Rectangular pulse Poisson model (RPPM), (ii) Bartlett-Lewis Rectangular pulse model (BLRPM), (iii) Bartlett-Lewis model with 2 cell types (BL2C), (iv) Bartlett-Lewis Rectangular with cell depth distribution dependent on duration (BLRD), and (v) Neyman-Scott Rectangular pulse model (NSRPM). All of these models werefitted using hourly rainfall data ranging from 1980 to 2005 (which was obtained from Changimeteorological station).The study results indicated that the weight scheme of inversely proportional variance could deliver more accurateoutputs for fitting rainfall patterns in tropical areas, and BLRPM performedrelatively better than other disaggregation models.

Keywords: Rainfall disaggregation, statistical properties, poisson processed, Bartlett-Lewis model, Neyman-Scott model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2257
2893 Applications of Prediction and Identification Using Adaptive DCMAC Neural Networks

Authors: Yu-Lin Liao, Ya-Fu Peng

Abstract:

An adaptive dynamic cerebellar model articulation controller (DCMAC) neural network used for solving the prediction and identification problem is proposed in this paper. The proposed DCMAC has superior capability to the conventional cerebellar model articulation controller (CMAC) neural network in efficient learning mechanism, guaranteed system stability and dynamic response. The recurrent network is embedded in the DCMAC by adding feedback connections in the association memory space so that the DCMAC captures the dynamic response, where the feedback units act as memory elements. The dynamic gradient descent method is adopted to adjust DCMAC parameters on-line. Moreover, the analytical method based on a Lyapunov function is proposed to determine the learning-rates of DCMAC so that the variable optimal learning-rates are derived to achieve most rapid convergence of identifying error. Finally, the adaptive DCMAC is applied in two computer simulations. Simulation results show that accurate identifying response and superior dynamic performance can be obtained because of the powerful on-line learning capability of the proposed DCMAC.

Keywords: adaptive, cerebellar model articulation controller, CMAC, prediction, identification

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1380
2892 Modeling and Simulation for Physical Vapor Deposition: Multiscale Model

Authors: Jürgen Geiser, Robert Röhle

Abstract:

In this paper we present modeling and simulation for physical vapor deposition for metallic bipolar plates. In the models we discuss the application of different models to simulate the transport of chemical reactions of the gas species in the gas chamber. The so called sputter process is an extremely sensitive process to deposit thin layers to metallic plates. We have taken into account lower order models to obtain first results with respect to the gas fluxes and the kinetics in the chamber. The model equations can be treated analytically in some circumstances and complicated multi-dimensional models are solved numerically with a software-package (UG unstructed grids, see [1]). Because of multi-scaling and multi-physical behavior of the models, we discuss adapted schemes to solve more accurate in the different domains and scales. The results are discussed with physical experiments to give a valid model for the assumed growth of thin layers.

Keywords: Convection-diffusion equations, multi-scale problem, physical vapor deposition, reaction equations, splitting methods.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1713
2891 Safety Climate Assessment and Its Impact on the Productivity of Construction Enterprises

Authors: Krzysztof J. Czarnocki, F. Silveira, E. Czarnocka, K. Szaniawska

Abstract:

Research background: Problems related to the occupational health and decreasing level of safety occur commonly in the construction industry. Important factor in the occupational safety in construction industry is scaffold use. All scaffolds used in construction, renovation, and demolition shall be erected, dismantled and maintained in accordance with safety procedure. Increasing demand for new construction projects unfortunately still is linked to high level of occupational accidents. Therefore, it is crucial to implement concrete actions while dealing with scaffolds and risk assessment in construction industry, the way on doing assessment and liability of assessment is critical for both construction workers and regulatory framework. Unfortunately, professionals, who tend to rely heavily on their own experience and knowledge when taking decisions regarding risk assessment, may show lack of reliability in checking the results of decisions taken. Purpose of the article: The aim was to indicate crucial parameters that could be modeling with Risk Assessment Model (RAM) use for improving both building enterprise productivity and/or developing potential and safety climate. The developed RAM could be a benefit for predicting high-risk construction activities and thus preventing accidents occurred based on a set of historical accident data. Methodology/Methods: A RAM has been developed for assessing risk levels as various construction process stages with various work trades impacting different spheres of enterprise activity. This project includes research carried out by teams of researchers on over 60 construction sites in Poland and Portugal, under which over 450 individual research cycles were carried out. The conducted research trials included variable conditions of employee exposure to harmful physical and chemical factors, variable levels of stress of employees and differences in behaviors and habits of staff. Genetic modeling tool has been used for developing the RAM. Findings and value added: Common types of trades, accidents, and accident causes have been explored, in addition to suitable risk assessment methods and criteria. We have found that the initial worker stress level is more direct predictor for developing the unsafe chain leading to the accident rather than the workload, or concentration of harmful factors at the workplace or even training frequency and management involvement.

Keywords: Civil engineering, occupational health, productivity, safety climate.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1064
2890 Prediction of Compressive Strength of Concrete from Early Age Test Result Using Design of Experiments (RSM)

Authors: Salem Alsanusi, Loubna Bentaher

Abstract:

Response Surface Methods (RSM) provide statistically validated predictive models that can then be manipulated for finding optimal process configurations. Variation transmitted to responses from poorly controlled process factors can be accounted for by the mathematical technique of propagation of error (POE), which facilitates ‘finding the flats’ on the surfaces generated by RSM. The dual response approach to RSM captures the standard deviation of the output as well as the average. It accounts for unknown sources of variation. Dual response plus propagation of error (POE) provides a more useful model of overall response variation. In our case, we implemented this technique in predicting compressive strength of concrete of 28 days in age. Since 28 days is quite time consuming, while it is important to ensure the quality control process. This paper investigates the potential of using design of experiments (DOE-RSM) to predict the compressive strength of concrete at 28th day. Data used for this study was carried out from experiment schemes at university of Benghazi, civil engineering department. A total of 114 sets of data were implemented. ACI mix design method was utilized for the mix design. No admixtures were used, only the main concrete mix constituents such as cement, coarseaggregate, fine aggregate and water were utilized in all mixes. Different mix proportions of the ingredients and different water cement ratio were used. The proposed mathematical models are capable of predicting the required concrete compressive strength of concrete from early ages.

Keywords: Mix proportioning, response surface methodology, compressive strength, optimal design.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2176