Search results for: data validation

Authors: Victor Bodell, Lukas Ekstrom, Somayeh Aghanavesi

Abstract:

Fuel consumption (FC) is one of the key factors in determining expenses of operating a heavy-duty vehicle. A customer may therefore request an estimate of the FC of a desired vehicle. The modular design of heavy-duty vehicles allows their construction by specifying the building blocks, such as gear box, engine and chassis type. If the combination of building blocks is unprecedented, it is unfeasible to measure the FC, since this would first r equire the construction of the vehicle. This paper proposes a machine learning approach to predict FC. This study uses around 40,000 vehicles specific and o perational e nvironmental c onditions i nformation, such as road slopes and driver profiles. A ll v ehicles h ave d iesel engines and a mileage of more than 20,000 km. The data is used to investigate the accuracy of machine learning algorithms Linear regression (LR), K-nearest neighbor (KNN) and Artificial n eural n etworks (ANN) in predicting fuel consumption for heavy-duty vehicles. Performance of the algorithms is evaluated by reporting the prediction error on both simulated data and operational measurements. The performance of the algorithms is compared using nested cross-validation and statistical hypothesis testing. The statistical evaluation procedure finds that ANNs have the lowest prediction error compared to LR and KNN in estimating fuel consumption on both simulated and operational data. The models have a mean relative prediction error of 0.3% on simulated data, and 4.2% on operational data.

Keywords: Artificial neural networks, fuel consumption, machine learning, regression, statistical tests.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 754

Authors: Anant Lal, M. Elangovan

Abstract:

A general purpose viscous flow solver Ansys CFX was used to solve the unsteady three-dimensional (3D) Reynolds Averaged Navier-Stokes Equation (RANSE) for simulating a 3D numerical viscous wave tank. A flap-type wave generator was incorporated in the computational domain to generate the desired incident waves. Authors have made effort to study the physical behaviors of Flap type wave maker with governing parameters. Dependency of the water fill depth, Time period of oscillations and amplitude of oscillations of flap were studied. Effort has been made to establish relations between parameters. A validation study was also carried out against CFD methodology with wave maker theory. It has been observed that CFD results are in good agreement with theoretical results. Beaches of different slopes were introduced to damp the wave, so that it should not cause any reflection from boundary. As a conclusion this methodology can simulate the experimental wave-maker for regular wave generation for different wave length and amplitudes.

Keywords: CFD, RANSE, Flap type, wave-maker, VOF, seakeeping, numerical method.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3858

Authors: A. Chebak, N. Barka, A. Menou, J. Brousseau, D. S. Ramdenee

Abstract:

This paper presents the study of hardness profile of spur gear heated by induction heating process in function of the machine parameters, such as the power (kW), the heating time (s) and the generator frequency (kHz). The global work is realized by 3D finite-element simulation applied to the process by coupling and resolving the electromagnetic field and the heat transfer problems, and it was performed in three distinguished steps. First, a Comsol 3D model was built using an adequate formulation and taking into account the material properties and the machine parameters. Second, the convergence study was conducted to optimize the mesh. Then, the surface temperatures and the case depths were deeply analyzed in function of the initial current density and the heating time in medium frequency (MF) and high frequency (HF) heating modes and the edge effect were studied. Finally, the simulations results are validated using experimental tests.

Keywords: Induction heating, simulation, experimental validation, 3D model, hardness profile.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1607

Authors: N. Haghjou, M. J. Abdekhodaie, Y. L. Cheng, M. Saadatmand

Abstract:

Intravitreal injection (IVI) is the most common treatment for eye posterior segment diseases such as endopthalmitis, retinitis, age-related macular degeneration, diabetic retinopathy, uveitis, and retinal detachment. Most of the drugs used to treat vitreoretinal diseases, have a narrow concentration range in which they are effective, and may be toxic at higher concentrations. Therefore, it is critical to know the drug distribution within the eye following intravitreal injection. Having knowledge of drug distribution, ophthalmologists can decide on drug injection frequency while minimizing damage to tissues. The goal of this study was to develop a computer model to predict intraocular concentrations and pharmacokinetics of intravitreally injected drugs. A finite volume model was created to predict distribution of two drugs with different physiochemical properties in the rabbit eye. The model parameters were obtained from literature review. To validate this numeric model, the in vivo data of spatial concentration profile from the lens to the retina were compared with the numeric data. The difference was less than 5% between the numerical and experimental data. This validation provides strong support for the numerical methodology and associated assumptions of the current study.

Keywords: Posterior segment, Intravitreal injection (IVI), Pharmacokinetic, Modelling, Finite volume method.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2380

Authors: Abu Bakar Munir, Siti Hajar Mohd Yasin, Firdaus Muhammad-Sukki

Abstract:

This paper seeks to analyse the benefits of big data and more importantly the challenges it pose to the subject of privacy and data protection. First, the nature of big data will be briefly deliberated before presenting the potential of big data in the present days. Afterwards, the issue of privacy and data protection is highlighted before discussing the challenges of implementing this issue in big data. In conclusion, the paper will put forward the debate on the adequacy of the existing legal framework in protecting personal data in the era of big data.

Keywords: Big data, data protection, information, privacy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3857

Authors: Navneet Singh Deora, Aastha Deswal, H. N. Mishra

Abstract:

Pasta is one of the most widely consumed food products around the world. Rapid determination of the moisture content in pasta will assist food processors to provide online quality control of pasta during large scale production. Rapid Fourier transform near-infrared method (FT-NIR) was developed for determining moisture content in pasta. A calibration set of 150 samples, a validation set of 30 samples and a prediction set of 25 samples of pasta were used. The diffuse reflection spectra of different types of pastas were measured by FT-NIR analyzer in the 4,000-12,000cm^-1 spectral range. Calibration and validation sets were designed for the conception and evaluation of the method adequacy in the range of moisture content 10 to 15 percent (w.b) of the pasta. The prediction models based on partial least squares (PLS) regression, were developed in the near-infrared. Conventional criteria such as the R², the root mean square errors of cross validation (RMSECV), root mean square errors of estimation (RMSEE) as well as the number of PLS factors were considered for the selection of three pre-processing (vector normalization, minimum-maximum normalization and multiplicative scatter correction) methods. Spectra of pasta sample were treated with different mathematic pre-treatments before being used to build models between the spectral information and moisture content. The moisture content in pasta predicted by FT-NIR methods had very good correlation with their values determined via traditional methods (R² = 0.983), which clearly indicated that FT-NIR methods could be used as an effective tool for rapid determination of moisture content in pasta. The best calibration model was developed with min-max normalization (MMN) spectral pre-processing (R² = 0.9775). The MMN pre-processing method was found most suitable and the maximum coefficient of determination (R²) value of 0.9875 was obtained for the calibration model developed.

Keywords: FT-NIR, Pasta, moisture determination.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2764

Authors: Basak Oguz Yolcular

Abstract:

A large amount of valuable information is available in plain text clinical reports. New techniques and technologies are applied to extract information from these reports. In this study, we developed a domain based software system to transform 600 Otorhinolaryngology discharge notes to a structured form for extracting clinical data from the discharge notes. In order to decrease the system process time discharge notes were transformed into a data table after preprocessing. Several word lists were constituted to identify common section in the discharge notes, including patient history, age, problems, and diagnosis etc. N-gram method was used for discovering terms co-Occurrences within each section. Using this method a dataset of concept candidates has been generated for the validation step, and then Predictive Apriori algorithm for Association Rule Mining (ARM) was applied to validate candidate concepts.

Keywords: association rule mining, otorhinolaryngology, predictive apriori, text mining

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1572

Authors: Lucie Côté, Martin Lauzier, Guy Beauchamp, France Guertin

Abstract:

Stress causes deleterious effects to the physical, psychological and organizational levels, which highlight the need to use effective coping strategies to deal with it. Several coping models exist, but they don’t integrate the different strategies in a coherent way nor do they take into account the new research on the emotional coping and acceptance of the stressful situation. To fill these gaps, an integrative model incorporating the main coping strategies was developed. This model arises from the review of the scientific literature on coping and from a qualitative study carried out among workers with low or high levels of stress, as well as from an analysis of clinical cases. The model allows one to understand under what circumstances the strategies are effective or ineffective and to learn how one might use them more wisely. It includes Specific Strategies in controllable situations (the Modification of the Situation and the Resignation-Disempowerment), Specific Strategies in non-controllable situations (Acceptance and Stubborn Relentlessness) as well as so-called General Strategies (Wellbeing and Avoidance). This study is intended to undertake and present the process of development and validation of an instrument to measure coping strategies based on this model. An initial pool of items has been generated from the conceptual definitions and three expert judges have validated the content. Of these, 18 items have been selected for a short form questionnaire. A sample of 300 students and employees from a Quebec university was used for the validation of the questionnaire. Concerning the reliability of the instrument, the indices observed following the inter-rater agreement (Krippendorff’s alpha) and the calculation of the coefficients for internal consistency (Cronbach's alpha) are satisfactory. To evaluate the construct validity, a confirmatory factor analysis using MPlus supports the existence of a model with six factors. The results of this analysis suggest also that this configuration is superior to other alternative models. The correlations show that the factors are only loosely related to each other. Overall, the analyses carried out suggest that the instrument has good psychometric qualities and demonstrates the relevance of further work to establish predictive validity and reconfirm its structure. This instrument will help researchers and clinicians better understand and assess coping strategies to cope with stress and thus prevent mental health issues.

Keywords: Acceptance, coping strategies, measurement instrument, questionnaire, stress, validation process.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 852

Authors: Antoaneta Stefanova, Rositsa Gencheva, Pavlin Groudev

Abstract:

This paper presents the modeling approach in SBO sequence for VVER 1000 reactors and describes the reactor core behavior at late in-vessel phase in case of late reflooding by HPIS and gives preliminary results for the ASTECv2 validation. The work is focused on investigation of plant behavior during total loss of power and the operator actions. The main goal of these analyses is to assess the phenomena arising during the Station blackout (SBO) followed by primary side high pressure injection system (HPIS) reflooding of already damaged reactor core at very late “in-vessel” phase. The purpose of the analyses is to define how the later HPIS switching on can delay the time of vessel failure or possibly avoid vessel failure. The times for HPP injection were chosen based on previously performed investigations.

Keywords: VVER, operator action validation, reflooding of overheated reactor core, ASTEC computer code.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1397

Authors: N. Mahendran, R. Madhuranthi

Abstract:

Wireless sensor networks (WSNs), are constantly in demand to process information more rapidly with less energy and area cost. Presently, processor based solutions have difficult to achieve high processing speed with low-power consumption. This paper presents a simple and accurate data processing scheme for low power wireless sensor node, based on reduced number of processing element (PE). The presented model provides a simple recursive structure (SRS) to process the sampled data in the wireless sensor environment and to reduce the power consumption in wireless sensor node. Based on this model, to process the incoming samples and produce a smaller amount of data sufficient to reconstruct the original signal. The ModelSim simulator used to simulate SRS structure. Functional simulation is carried out for the validation of the presented architecture. Xilinx Power Estimator (XPE) tool is used to measure the power consumption. The experimental results show the average power consumption of 91 mW; this is 42% improvement compared to the folded tree architecture.

Keywords: Power consumption, energy efficiency, low power WSN node, recursive structure, sleep/wake scheduling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 965

Authors: Anchana Khemphila, Veera Boonjing

Abstract:

In this study, the Multi-Layer Perceptron (MLP)with Back-Propagation learning algorithm are used to classify to effective diagnosis Parkinsons disease(PD).It-s a challenging problem for medical community.Typically characterized by tremor, PD occurs due to the loss of dopamine in the brains thalamic region that results in involuntary or oscillatory movement in the body. A feature selection algorithm along with biomedical test values to diagnose Parkinson disease.Clinical diagnosis is done mostly by doctor-s expertise and experience.But still cases are reported of wrong diagnosis and treatment. Patients are asked to take number of tests for diagnosis.In many cases,not all the tests contribute towards effective diagnosis of a disease.Our work is to classify the presence of Parkinson disease with reduced number of attributes.Original,22 attributes are involved in classify.We use Information Gain to determine the attributes which reduced the number of attributes which is need to be taken from patients.The Artificial neural networks is used to classify the diagnosis of patients.Twenty-Two attributes are reduced to sixteen attributes.The accuracy is in training data set is 82.051% and in the validation data set is 83.333%.

Keywords: Data mining, classification, Parkinson disease, artificial neural networks, feature selection, information gain.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3710

Authors: N. Lokeshwari, G. Srinikethan, V. S. Hegde

Abstract:

Monitoring is essential to assessing the effectiveness of air pollution control actions. The goal of the air quality information system is through monitoring, to keep authorities, major polluters and the public informed on the short and long-term changes in air quality, thereby helping to raise awareness. Mathematical models are the best tools available for the prediction of the air quality management. The main objective of the work was to apply a Model that predicts the concentration levels of different pollutants at any instant of time. In this study, distribution of air pollutants concentration such as nitrogen dioxides (NO₂), sulphur dioxides (SO₂) and total suspended particulates (TSP) of industries are determined by using Gaussian model. Besides that, the effect of wind speed and its direction on the pollutant concentration within the affected area were evaluated. In order to determine the efficiency and percentage of error in the modeling, validation process of data was done. Sampling of air quality was conducted in getting existing air quality around a factory and the concentrations of pollutants in a plume were inversely proportional to wind velocity. The resultant ground level concentrations were then compared to the quality standards to determine if there could be a negative impact on health. This study concludes that concentration of pollutants can be significantly predicted using Gaussian Model. The data base management is developed for the air data of Hubli-Dharwad region.

Keywords: DBMS, NO2, SO2, Wind rose plots.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1989

Authors: Yogesh Aggarwal

Abstract:

The paper discusses the results obtained to predict reinforcement in singly reinforced beam using Neural Net (NN), Support Vector Machines (SVM-s) and Tree Based Models. Major advantage of SVM-s over NN is of minimizing a bound on the generalization error of model rather than minimizing a bound on mean square error over the data set as done in NN. Tree Based approach divides the problem into a small number of sub problems to reach at a conclusion. Number of data was created for different parameters of beam to calculate the reinforcement using limit state method for creation of models and validation. The results from this study suggest a remarkably good performance of tree based and SVM-s models. Further, this study found that these two techniques work well and even better than Neural Network methods. A comparison of predicted values with actual values suggests a very good correlation coefficient with all four techniques.

Keywords: Linear Regression, M5 Model Tree, Neural Network, Support Vector Machines.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1990

Authors: Manish Gupta

Abstract:

Following the E-Commerce era, M-Commerce is the next big phase in the technology involvement and advancement. This paper intends to explore how Indian consumers are influenced to adopt the M-commerce. In this paper, the revised Technology Acceptance Model (TAM) has been presented on the basis of the most dominant factors that affect the adoption of M-Commerce in Indian scenario. Furthermore, an analytical questionnaire approach was carried out to collect data from Indian consumers. These collected data were further used for the validation of the presented model. Findings indicate that customization, convenience, instant connectivity, compatibility, security, download speed in M-Commerce affect the adoption behavior. Furthermore, the findings suggest that perceived usefulness and attitude towards M-Commerce are positively influenced by number of M-Commerce drivers (i.e. download speed, compatibility, convenience, security, customization, connectivity, and input mechanism).

Keywords: M-Commerce, perceived usefulness, technology acceptance model, perceived ease of use.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1405

Authors: Carlo Bellettini, Alessandro Marchetto, Andrea Trentini

Abstract:

Web applications have become complex and crucial for many firms, especially when combined with areas such as CRM (Customer Relationship Management) and BPR (Business Process Reengineering). The scientific community has focused attention to Web application design, development, analysis, testing, by studying and proposing methodologies and tools. Static and dynamic techniques may be used to analyze existing Web applications. The use of traditional static source code analysis may be very difficult, for the presence of dynamically generated code, and for the multi-language nature of the Web. Dynamic analysis may be useful, but it has an intrinsic limitation, the low number of program executions used to extract information. Our reverse engineering analysis, used into our WAAT (Web Applications Analysis and Testing) project, applies mutational techniques in order to exploit server side execution engines to accomplish part of the dynamic analysis. This paper studies the effects of mutation source code analysis applied to Web software to build application models. Mutation-based generated models may contain more information then necessary, so we need a pruning mechanism.

Keywords: Validation, Dynamic Analysis, MutationAnalysis, Reverse Engineering, Web Applications

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1574

Authors: B. Nasri, M. Bensaada

Abstract:

We present a simulation and realization of a battery charge regulator (BCR) in microsatellite earth observation. The tests were performed on battery pack 12volt, capacity 24Ah and the solar array open circuit voltage of 100 volt and optimum power of about 250 watt. The battery charge is made by solar module. The principle is to adapt the output voltage of the solar module to the battery by using the technique of pulse width modulation (PWM). Among the different techniques of charge battery, we opted for the technique of the controller ON/OFF is a standard technique and simple, it-s easy to be board executed validation will be made by simulation "Proteus Isis Professional software ". The circuit and the program of this prototype are based on the PIC16F877 microcontroller, a serial interface connecting a PC is also realized, to view and save data and graphics in real time, for visualization of data and graphs we develop an interface tool “visual basic.net (VB)--.

Keywords: Battery Charge Regulator, Batteries, Buck converter, Power System, Power Conditioning, Power Distribution, Solar arrays.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3168

Authors: Sarah Beaver, Renee Bryce

Abstract:

Audiograms detect hearing impairment, but missing values pose problems. This work explores imputations in an attempt to improve accuracy. This work implements Linear Regression, Lasso, Linear Support Vector Regression, Bayesian Ridge, K Nearest Neighbors (KNN), and Random Forest machine learning techniques to impute audiogram frequencies ranging from 125 Hz to 8000 Hz. The data contain patients who had or were candidates for cochlear implants. Accuracy is compared across two different Nested Cross-Validation k values. Over 4000 audiograms were used from 800 unique patients. Additionally, training on data combines and compares left and right ear audiograms versus single ear side audiograms. The accuracy achieved using Root Mean Square Error (RMSE) values for the best models for Random Forest ranges from 4.74 to 6.37. The R2 values for the best models for Random Forest ranges from .91 to .96. The accuracy achieved using RMSE values for the best models for KNN ranges from 5.00 to 7.72. The R2 values for the best models for KNN ranges from .89 to .95. The best imputation models received R2 between .89 to .96 and RMSE values less than 8dB. We also show that the accuracy of classification predictive models performed better with our imputation models versus constant imputations by a two percent increase.

Keywords: Machine Learning, audiograms, data imputations, single imputations.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 24

Authors: Jawad Makki, Anne-Marie Alquier, Violaine Prince

Abstract:

In this paper we propose an NLP-based method for Ontology Population from texts and apply it to semi automatic instantiate a Generic Knowledge Base (Generic Domain Ontology) in the risk management domain. The approach is semi-automatic and uses a domain expert intervention for validation. The proposed approach relies on a set of Instances Recognition Rules based on syntactic structures, and on the predicative power of verbs in the instantiation process. It is not domain dependent since it heavily relies on linguistic knowledge. A description of an experiment performed on a part of the ontology of the PRIMA1 project (supported by the European community) is given. A first validation of the method is done by populating this ontology with Chemical Fact Sheets from Environmental Protection Agency2. The results of this experiment complete the paper and support the hypothesis that relying on the predicative power of verbs in the instantiation process improves the performance.

Keywords: Information Extraction, Instance Recognition Rules, Ontology Population, Risk Management, Semantic analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1499

Authors: Shaoying Guo, Yanyun Xu, Meng Zhang, Weiqing Huang

Abstract:

The wireless communication network is developing rapidly, thus the wireless security becomes more and more important. Specific emitter identification (SEI) is an vital part of wireless communication security as a technique to identify the unique transmitters. In this paper, a SEI method based on multiscale dispersion entropy (MDE) and refined composite multiscale dispersion entropy (RCMDE) is proposed. The algorithms of MDE and RCMDE are used to extract features for identification of five wireless devices and cross-validation support vector machine (CV-SVM) is used as the classifier. The experimental results show that the total identification accuracy is 99.3%, even at low signal-to-noise ratio(SNR) of 5dB, which proves that MDE and RCMDE can describe the communication signal series well. In addition, compared with other methods, the proposed method is effective and provides better accuracy and stability for SEI.

Keywords: Cross-validation support vector machine, refined composite multiscale dispersion entropy, specific emitter identification, transient signal, wireless communication device.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 787

Authors: K. Kamalanand, P. Mannar Jawahar

Abstract:

Many systems in the natural world exhibit chaos or non-linear behavior, the complexity of which is so great that they appear to be random. Identification of chaos in experimental data is essential for characterizing the system and for analyzing the predictability of the data under analysis. The Lyapunov exponents provide a quantitative measure of the sensitivity to initial conditions and are the most useful dynamical diagnostic for chaotic systems. However, it is difficult to accurately estimate the Lyapunov exponents of chaotic signals which are corrupted by a random noise. In this work, a method for estimation of Lyapunov exponents from noisy time series using unscented transformation is proposed. The proposed methodology was validated using time series obtained from known chaotic maps. In this paper, the objective of the work, the proposed methodology and validation results are discussed in detail.

Keywords: Lyapunov exponents, unscented transformation, chaos theory, neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1941

Authors: Fred Lacy

Abstract:

Electrical resistivity is a fundamental parameter of metals or electrical conductors. Since resistivity is a function of temperature, in order to completely understand the behavior of metals, a temperature dependent theoretical model is needed. A model based on physics principles has recently been developed to obtain an equation that relates electrical resistivity to temperature. This equation is dependent upon a parameter associated with the electron travel time before being scattered, and a parameter that relates the energy of the atoms and their separation distance. Analysis of the energy parameter reveals that the equation is optimized if the proportionality term in the equation is not constant but varies over the temperature range. Additional analysis reveals that the theoretical equation can be used to determine the mean free path of conduction electrons, the number of defects in the atomic lattice, and the ‘equivalent’ charge associated with the metallic bonding of the atoms. All of this analysis provides validation for the theoretical model and provides insight into the behavior of metals where performance is affected by temperatures (e.g., integrated circuits and temperature sensors).

Keywords: Callendar–van Dusen, conductivity, mean free path, resistance temperature detector, temperature sensor.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2143

Authors: Murat Ayyıldız, Oya Kalıpsız, Sırma Yavuz

Abstract:

Software project effort estimation is frequently seen as complex and expensive for individual software engineers. Software production is in a crisis. It suffers from excessive costs. Software production is often out of control. It has been suggested that software production is out of control because we do not measure. You cannot control what you cannot measure. During last decade, a number of researches on cost estimation have been conducted. The metric-set selection has a vital role in software cost estimation studies; its importance has been ignored especially in neural network based studies. In this study we have explored the reasons of those disappointing results and implemented different neural network models using augmented new metrics. The results obtained are compared with previous studies using traditional metrics. To be able to make comparisons, two types of data have been used. The first part of the data is taken from the Constructive Cost Model (COCOMO'81) which is commonly used in previous studies and the second part is collected according to new metrics in a leading international company in Turkey. The accuracy of the selected metrics and the data samples are verified using statistical techniques. The model presented here is based on Multi-Layer Perceptron (MLP). Another difficulty associated with the cost estimation studies is the fact that the data collection requires time and care. To make a more thorough use of the samples collected, k-fold, cross validation method is also implemented. It is concluded that, as long as an accurate and quantifiable set of metrics are defined and measured correctly, neural networks can be applied in software cost estimation studies with success

Keywords: Software Metrics, Software Cost Estimation, Neural Network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1912

Authors: Mohd Tariq

Abstract:

The three phase system drives produce the problem of more torque pulsations and harmonics. This issue prevents the smooth operation of the drives and it also induces the amount of heat generated thus resulting in an increase in power loss. Higher phase system offers smooth operation of the machines with greater power capacity. Five phase variable-speed induction motor drives are commonly used in various industrial and commercial applications like tractions, electrical vehicles, ship propulsions and conveyor belt drive system. In this work, a comparative analysis of the different modulation schemes applied on the five-level five-phase Packed U Cell (PUC) inverter fed induction motor drives is presented. The performance of the inverter is greatly affected with the modulation schemes applied. The system is modeled, designed, and implemented in MATLAB^®/Simulink environment. Experimental validation is done for the prototype of single phase, whereas five phase experimental validation is proposed in the future works.

Keywords: Packed U-Cell inverter, pulse width modulation, five-phase system, induction motor.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 666

Authors: M.H. Ahmad Fadzil, Esa Prakasa, Hurriyatul Fitriyah, Hermawan Nugroho, Azura Mohd Affandi, S.H. Hussein

Abstract:

Psoriasis is a widespread skin disease affecting up to 2% population with plaque psoriasis accounting to about 80%. It can be identified as a red lesion and for the higher severity the lesion is usually covered with rough scale. Psoriasis Area Severity Index (PASI) scoring is the gold standard method for measuring psoriasis severity. Scaliness is one of PASI parameter that needs to be quantified in PASI scoring. Surface roughness of lesion can be used as a scaliness feature, since existing scale on lesion surface makes the lesion rougher. The dermatologist usually assesses the severity through their tactile sense, therefore direct contact between doctor and patient is required. The problem is the doctor may not assess the lesion objectively. In this paper, a digital image analysis technique is developed to objectively determine the scaliness of the psoriasis lesion and provide the PASI scaliness score. Psoriasis lesion is modelled by a rough surface. The rough surface is created by superimposing a smooth average (curve) surface with a triangular waveform. For roughness determination, a polynomial surface fitting is used to estimate average surface followed by a subtraction between rough and average surface to give elevation surface (surface deviations). Roughness index is calculated by using average roughness equation to the height map matrix. The roughness algorithm has been tested to 444 lesion models. From roughness validation result, only 6 models can not be accepted (percentage error is greater than 10%). These errors occur due the scanned image quality. Roughness algorithm is validated for roughness measurement on abrasive papers at flat surface. The Pearson-s correlation coefficient of grade value (G) of abrasive paper and Ra is -0.9488, its shows there is a strong relation between G and Ra. The algorithm needs to be improved by surface filtering, especially to overcome a problem with noisy data.

Keywords: psoriasis, roughness algorithm, polynomial surfacefitting.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2446

Authors: Sin Yin Teh, Abdul Rahman Othman, Michael Boon Chong Khoo

Abstract:

In this paper, the concepts of dichotomous logistic regression (DLR) with leave-one-out (L-O-O) were discussed. To illustrate this, the L-O-O was run to determine the importance of the simulation conditions for robust test of spread procedures with good Type I error rates. The resultant model was then evaluated. The discussions included 1) assessment of the accuracy of the model, and 2) parameter estimates. These were presented and illustrated by modeling the relationship between the dichotomous dependent variable (Type I error rates) with a set of independent variables (the simulation conditions). The base SAS software containing PROC LOGISTIC and DATA step functions can be making used to do the DLR analysis.

Keywords: Dichotomous logistic regression, leave-one-out, testof spread.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2022

Authors: S. Ben Saad, F. Ayad, H. Damotte

Abstract:

This study deals with Computational Fluid Dynamics (CFD) studies of the interactions between the air flow and louvered fins which equipped the automotive heat exchangers. 3D numerical simulation results are obtained by using the ANSYS Fluent 13.0 code and compared to experimental data. The paper studies the effect of louver angle and louver pitch geometrical parameters, on overall thermal hydraulic performances of louvered fins. The comparison between CFD simulations and experimental data show that established 3-D CFD model gives a good agreement. The validation agrees, with about 7% of deviation respectively of friction and Colburn factors to experimental results. As first, it is found that the louver angle has a strong influence on the heat transfer rate. Then, louver angle and louver pitch variation of the louvers and their effects on thermal hydraulic performances are studied. In addition to this study, it is shown that the second half of the fin takes has a significant contribution on pressure drop increase without any increase in heat transfer.

Keywords: CFD simulations, automotive heat exchanger, performances.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2943

Authors: Pascal Mwenge, Tumisang Seodigeng

Abstract:

The combination of world population and the third industrial revolution led to high demand for fuels. On the other hand, the decrease of global fossil 8fuels deposits and the environmental air pollution caused by these fuels has compounded the challenges the world faces due to its need for energy. Therefore, new forms of environmentally friendly and renewable fuels such as biodiesel are needed. The primary analytical techniques for methanolysis yield monitoring have been chromatography and spectroscopy, these methods have been proven reliable but are more demanding, costly and do not provide real-time monitoring. In this work, the in situ monitoring of biodiesel from sunflower oil using FTIR (Fourier Transform Infrared) has been studied; the study was performed using EasyMax Mettler Toledo reactor equipped with a DiComp (Diamond) probe. The quantitative monitoring of methanolysis was performed by building a quantitative model with multivariate calibration using iC Quant module from iC IR 7.0 software. 15 samples of known concentrations were used for the modelling which were taken in duplicate for model calibration and cross-validation, data were pre-processed using mean centering and variance scale, spectrum math square root and solvent subtraction. These pre-processing methods improved the performance indexes from 7.98 to 0.0096, 11.2 to 3.41, 6.32 to 2.72, 0.9416 to 0.9999, RMSEC, RMSECV, RMSEP and R2Cum, respectively. The R² value of 1 (training), 0.9918 (test), 0.9946 (cross-validation) indicated the fitness of the model built. The model was tested against univariate model; small discrepancies were observed at low concentration due to unmodelled intermediates but were quite close at concentrations above 18%. The software eliminated the complexity of the Partial Least Square (PLS) chemometrics. It was concluded that the model obtained could be used to monitor methanol of sunflower oil at industrial and lab scale.

Keywords: Biodiesel, calibration, chemometrics, FTIR, methanolysis, multivariate analysis, transesterification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 853

Authors: Khaled E. A. Negm

Abstract:

A neuron can emit spikes in an irregular time basis and by averaging over a certain time window one would ignore a lot of information. It is known that in the context of fast information processing there is no sufficient time to sample an average firing rate of the spiking neurons. The present work shows that the spiking neurons are capable of computing the radial basis functions by storing the relevant information in the neurons' delays. One of the fundamental findings of the this research also is that when using overlapping receptive fields to encode the data patterns it increases the network-s clustering capacity. The clustering algorithm that is discussed here is interesting from computer science and neuroscience point of view as well as from a perspective.

Keywords: Temporal Neurons, RBF Recognition, Perturbation, On Line Recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1436

Authors: S. O. Adeosun, E. I. Akpan, S. A. Balogun, O. O. Taiwo

Abstract:

A model to predict the plastic zone size for material under plane stress condition has been developed and verified experimentally. The developed model is a function of crack size, crack angle and material property (dislocation density). Simulation and validation results show that the model developed show good agreement with experimental results. Samples of low carbon steel (0.035%C) with included surface crack angles of 45o, 50o, 60o, 70o and 90o and crack depths of 2mm and 4mm were subjected to low strain rate between 0.48 x 10-3 s-1 – 2.38 x 10-3 s-1. The mechanical properties studied were ductility, tensile strength, modulus of elasticity, yield strength, yield strain, stress at fracture and fracture toughness. The experimental study shows that strain rate has no appreciable effect on the size of plastic zone while crack depth and crack angle plays an imperative role in determining the size of the plastic zone of mild steel materials.

Keywords: Applied stress, crack angle, crack size, material property, plastic zone size, strain rate.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1570

Authors: M. Khosravy-el-Hossani, Q. Dorosti

Abstract:

One of the important applications of gas turbines is their utilization for heat recovery steam generator in combine-cycle technology. Exhaust flow and energy are two key parameters for determining heat recovery steam generator performance which are mainly determined by the main gas turbine components performance data. For this reason a method was developed for determining the exhaust energy in the new edition of ASME PTC22. The result of this investigation shows that the method of standard has considerable error. Therefore in this paper a new method is presented for modifying of the performance calculation. The modified method is based on exhaust gas constituent analysis and combustion calculations. The case study presented here by two kind of General Electric gas turbine design data for validation of methodologies. The result shows that the modified method is more precise than the ASME PTC22 method. The exhaust flow calculation deviation from design data is 1.5-2 % by ASME PTC22 method so that the deviation regarding with modified method is 0.3-0.5%. Based on precision of analyzer instruments, the method can be suitable alternative for gas turbine standard performance test. In advance two methods are proposed based on known and unknown fuel in modified method procedure. The result of this paper shows that the difference between the two methods is below than %0.02. In according to reasonable esult of the second procedure (unknown fuel composition), the method can be applied to performance evaluation of gas turbine, so that the measuring cost and data gathering should be reduced.

Keywords: Gas turbine, Performance test code, Combined cycle.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2944