Search results for: Gaussian Mixture Models

Authors: S. J. Matlan, M. Mukhlisin, M. R. Taha

Abstract:

Characterization of the engineering behavior of unsaturated soil is dependent on the soil-water characteristic curve (SWCC), a graphical representation of the relationship between water content or degree of saturation and soil suction. A reasonable description of the SWCC is thus important for the accurate prediction of unsaturated soil parameters. The measurement procedures for determining the SWCC, however, are difficult, expensive, and timeconsuming. During the past few decades, researchers have laid a major focus on developing empirical equations for predicting the SWCC, with a large number of empirical models suggested. One of the most crucial questions is how precisely existing equations can represent the SWCC. As different models have different ranges of capability, it is essential to evaluate the precision of the SWCC models used for each particular soil type for better SWCC estimation. It is expected that better estimation of SWCC would be achieved via a thorough statistical analysis of its distribution within a particular soil class. With this in view, a statistical analysis was conducted in order to evaluate the reliability of the SWCC prediction models against laboratory measurement. Optimization techniques were used to obtain the best-fit of the model parameters in four forms of SWCC equation, using laboratory data for relatively coarse-textured (i.e., sandy) soil. The four most prominent SWCCs were evaluated and computed for each sample. The result shows that the Brooks and Corey model is the most consistent in describing the SWCC for sand soil type. The Brooks and Corey model prediction also exhibit compatibility with samples ranging from low to high soil water content in which subjected to the samples that evaluated in this study.

Keywords: Soil-water characteristic curve (SWCC), statistical analysis, unsaturated soil.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2665

Authors: Sinarwati Mohamad Suhaili, Naomie Salim, Mohamad Nazim Jambli

Abstract:

Sequence-to-sequence (seq2seq) models augmented with attention mechanisms are increasingly important in automated customer service. These models, adept at recognizing complex relationships between input and output sequences, are essential for optimizing chatbot responses. Central to these mechanisms are neural attention weights that determine the model’s focus during sequence generation. Despite their widespread use, there remains a gap in the comparative analysis of different attention weighting functions within seq2seq models, particularly in the context of chatbots utilizing the Customer Support Twitter (CST) dataset. This study addresses this gap by evaluating four distinct attention-scoring functions—dot, multiplicative/general, additive, and an extended multiplicative function with a tanh activation parameter — in neural generative seq2seq models. Using the CST dataset, these models were trained and evaluated over 10 epochs with the AdamW optimizer. Evaluation criteria included validation loss and BLEU scores implemented under both greedy and beam search strategies with a beam size of k = 3. Results indicate that the model with the tanh-augmented multiplicative function significantly outperforms its counterparts, achieving the lowest validation loss (1.136484) and the highest BLEU scores (0.438926 under greedy search, 0.443000 under beam search, k = 3). These findings emphasize the crucial influence of selecting an appropriate attention-scoring function to enhance the performance of seq2seq models for chatbots, particularly highlighting the model integrating tanh activation as a promising approach to improving chatbot quality in customer support contexts.

Keywords: Attention weight, chatbot, encoder-decoder, neural generative attention, score function, sequence-to-sequence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 91

Authors: Ml. López-Moreno, Le. Lugo Avilés, Fr. Román, J. Lugo Rosas, Ja. Hernández-Viezcas, Jr. Peralta-Videa, Jl. Gardea-Torresdey

Abstract:

Degradation of agricultural soils has increased rapidly during the last 20 years due to the indiscriminate use of pesticides and other anthropogenic activities. Currently, there is an urgent need of soil restoration to increase agricultural production. Utilization of sewage sludge or municipal solid waste is an important way to recycle nutrient elements and improve soil quality. With these amendments, nutrient availability in the aqueous phase might be increased and production of healthier crops can be accomplished. This research project aimed to achieve sustainable management of tropical agricultural soils, specifically in Puerto Rico, through the amendment of water treatment plant sludge’s. This practice avoids landfill disposal of sewage sludge and at the same time results costeffective practice for recycling solid waste residues. Coriander sativum was cultivated in a compost-soil-sludge mixture at different proportions. Results showed that Coriander grown in a mixture of 25% compost+50% Voladora soi+25% sludge had the best growth and development. High chlorophyll content (33.01 ± 0.8) was observed in Coriander plants cultivated in 25% compost+62.5% Coloso soil+ 12.5% sludge compared to plants grown with no sludge (32.59 ± 0.7). ICP-OES analysis showed variations in mineral element contents (macro and micronutrients) in coriander plant grown I soil amended with sludge and compost.

Keywords: Compost, Coriandrum sativum, nutrients, waste sludge.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2482

Authors: Rafid Saeed Abdulrazak Alshkaki

Abstract:

In this paper, zero-one inflated negative binomial distribution is considered, along with some of its structural properties, then its parameters were estimated using the method of moments. It is found that the method of moments to estimate the parameters of the zero-one inflated negative binomial models is not a proper method and may give incorrect conclusions.

Keywords: Zero one inflated models, negative binomial distribution, moments estimator, non-negative integer sampling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1097

Authors: Antonella Hadzich, Santiago Flores

Abstract:

Alkyds have become essential raw materials in the coating and paint industry, due to their low cost, good application properties and lower environmental impact in comparison with petroleum-based polymers. The properties of these oil-modified materials depend on the type of polyunsaturated vegetable oil used for its manufacturing, since a higher degree of unsaturation provides a better crosslinking of the cured paint. Linum usitatissimum L. (flax) oil is widely used to develop alkyd resins due to its high degree of unsaturation. Although it is intended to find non-traditional sources and increase their commercial value, to authors’ best knowledge a natural source that can replace flaxseed oil has not yet been found. However, Plukenetia volubilis L. oil, of Peruvian origin, contains a similar fatty acid polyunsaturated content to the one reported for Linum usitatissimum L. oil. In this perspective, medium alkyd resins were prepared with a mixture of 50% of Linum usitatissimum L. oil and 50% of Plukenetia volubilis L. oil. Pure Linum usitatissimum L. oil was also used for comparison purposes. Three different resins were obtained by varying the amount of glycerol and pentaerythritol. The synthesized alkyd resins were characterized by FT-IR, and physicochemical properties like acid value, colour, viscosity, density and drying time were evaluated by standard methods. The pencil hardness and chemical resistance behaviour of the cured resins were also studied. Overall, it can be concluded that medium alkyd resins containing Plukenetia volubilis L. oil have an equivalent behaviour compared to those prepared purely with Linum usitatissimum L. oil. Both Plukenetia volubilis L. oil and pentaerythritol have a remarkable influence on certain physicochemical properties of medium alkyd resins.

Keywords: Alkyd resins, flaxseed oil, pentaerythritol, Plukenetia volubilis L. oil, protective coating.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 759

Authors: Ishapathik Das

Abstract:

The purpose of this article is to find a method of comparing designs for ordinal regression models using quantile dispersion graphs in the presence of linear predictor misspecification. The true relationship between response variable and the corresponding control variables are usually unknown. Experimenter assumes certain form of the linear predictor of the ordinal regression models. The assumed form of the linear predictor may not be correct always. Thus, the maximum likelihood estimates (MLE) of the unknown parameters of the model may be biased due to misspecification of the linear predictor. In this article, the uncertainty in the linear predictor is represented by an unknown function. An algorithm is provided to estimate the unknown function at the design points where observations are available. The unknown function is estimated at all points in the design region using multivariate parametric kriging. The comparison of the designs are based on a scalar valued function of the mean squared error of prediction (MSEP) matrix, which incorporates both variance and bias of the prediction caused by the misspecification in the linear predictor. The designs are compared using quantile dispersion graphs approach. The graphs also visually depict the robustness of the designs on the changes in the parameter values. Numerical examples are presented to illustrate the proposed methodology.

Keywords: Model misspecification, multivariate kriging, multivariate logistic link, ordinal response models, quantile dispersion graphs.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1002

Authors: Melodi Mbuyi Mata, Blessing Olamide Taiwo, Afolabi Ayodele David

Abstract:

The purpose of this research is to create empirical models for assessing the profitability of granite aggregate production in Akure, Ondo state aggregate quarries. In addition, an Artificial Neural Network (ANN) model and multivariate predicting models for granite profitability were developed in the study. A formal survey questionnaire was used to collect data for the study. The data extracted from the case study mine for this study include granite marketing operations, royalty, production costs, and mine production information. The following methods were used to achieve the goal of this study: descriptive statistics, MATLAB 2017, and SPSS16.0 software in analyzing and modeling the data collected from granite traders in the study areas. The ANN and Multi Variant Regression models' prediction accuracy was compared using a coefficient of determination (R2), Root Mean Square Error (RMSE), and mean square error (MSE). Due to the high prediction error, the model evaluation indices revealed that the ANN model was suitable for predicting generated profit in a typical quarry. More quarries in Nigeria's southwest region and other geopolitical zones should be considered to improve ANN prediction accuracy.

Keywords: National development, granite, profitability assessment, ANN models.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 83

Authors: R. C. J. Mphahlele, K. Bolton, H. Kasaini

Abstract:

Empirical force fields and density functional theory (DFT) was used to study the binding energies and structures of methylamine on the surface of activated carbons (ACs). This is a first step in studying the adsorption of alkyl amines on the surface of functionalized ACs. The force fields used were Dreiding (DFF), Universal (UFF) and Compass (CFF) models. The generalized gradient approximation with Perdew Wang 91 (PW91) functional was used for DFT calculations. In addition to obtaining the aminecarboxylic acid adsorption energies, the results were used to establish reliability of the empirical models for these systems. CFF predicted a binding energy of -9.227 (kcal/mol) which agreed with PW91 at - 13.17 (kcal/mol), compared to DFF 0 (kcal/mol) and UFF -0.72 (kcal/mol). However, the CFF binding energies for the amine to ester and ketone disagreed with PW91 results. The structures obtained from all models agreed with PW91 results.

Keywords: Activated Carbons, Binding energy, DFT, Force fields.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1953

Authors: András Szekrényes

Abstract:

Delamination is one of the major failure modes in laminated composite structures. Delamination tips are mostly captured by spatial numerical models in order to predict crack growth. This paper presents some mechanical models of delaminated composite shells based on shallow shell theories. The mechanical fields are based on a third-order displacement field in terms of the through-thickness coordinate of the laminated shell. The undelaminated and delaminated parts are captured by separate models and the continuity and boundary conditions are also formulated in a general way providing a large size boundary value problem. The system of differential equations is solved by the state space method for an elliptic delaminated shell having simply supported edges. The comparison of the proposed and a numerical model indicates that the primary indicator of the model is the deflection, the secondary is the widthwise distribution of the energy release rate. The model is promising and suitable to determine accurately the J-integral distribution along the delamination front. Based on the proposed model it is also possible to develop finite elements which are able to replace the computationally expensive spatial models of delaminated structures.

Keywords: J-integral, Lévy method, third-order shell theory, state space solution.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 600

Authors: Arash Esmaeili, Zhibang Liu, Yang Xiang, Jimmy Yun, Lei Shao

Abstract:

High pressure carbon dioxide (CO2) absorption from a specific off-gas in a conventional column has been evaluated for the environmental concerns by the Aspen HYSYS simulator using a wide range of single absorbents and piperazine (PZ) blended solutions to estimate the outlet CO2 concentration, CO2 loading, reboiler power supply and regeneration heat duty to choose the most efficient solution in terms of CO2 removal and required heat duty. The property package, which is compatible with all applied solutions for the simulation in this study, estimates the properties based on electrolyte non-random two-liquid (E-NRTL) model for electrolyte thermodynamics and Peng-Robinson equation of state for vapor phase and liquid hydrocarbon phase properties. The results of the simulation indicate that PZ in addition to the mixture of PZ and monoethanolamine (MEA) demand the highest regeneration heat duty compared with other studied single and blended amine solutions respectively. The blended amine solutions with the lowest PZ concentrations (5wt% and 10wt%) were considered and compared to reduce the cost of process, among which the blended solution of 10wt%PZ+35wt%MDEA (methyldiethanolamine) was found as the most appropriate solution in terms of CO2 content in the outlet gas, rich-CO2 loading and regeneration heat duty.

Keywords: Absorption, amine solutions, Aspen HYSYS, CO2 loading, piperazine, regeneration heat duty.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 615

Authors: Barath Kumar, Oliver Niggemann, Juergen Jasperneite

Abstract:

Model-based approaches have been applied successfully to a wide range of tasks such as specification, simulation, testing, and diagnosis. But one bottleneck often prevents the introduction of these ideas: Manual modeling is a non-trivial, time-consuming task. Automatically deriving models by observing and analyzing running systems is one possible way to amend this bottleneck. To derive a model automatically, some a-priori knowledge about the model structure–i.e. about the system–must exist. Such a model formalism would be used as follows: (i) By observing the network traffic, a model of the long-term system behavior could be generated automatically, (ii) Test vectors can be generated from the model, (iii) While the system is running, the model could be used to diagnose non-normal system behavior. The main contribution of this paper is the introduction of a model formalism called 'probabilistic regression automaton' suitable for the tasks mentioned above.

Keywords: Model-based approach, Probabilistic regression automata, Statistical models and Timed automata.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1540

Authors: T. Y. Liu, C. H Lin., Y. M Ferng

Abstract:

Wind energy is one of the clean renewable energy. However, the low frequency (20-200HZ) noise generated from the wind turbine blades, which bothers the residents, becomes the major problem to be developed. It is useful for predicting the aerodynamic noise by flow field and pressure distribution analysis on the wind turbine blades. Therefore, the main objective of this study is to use different turbulence models to analyze the flow field and pressure distributions of the wing blades.

Three-dimensional Computation Fluid Dynamics (CFD) simulation of the flow field was used to calculate the flow phenomena for the National Renewable Energy Laboratory (NREL) Phase VI horizontal axis wind turbine rotor. Two different flow cases with different wind speeds were investigated: 7m/s with 72rpm and 15m/s with 72rpm.

Four kinds of RANS-based turbulence models, Standard k-ε, Realizable k-ε, SST k-ω, and v2f, were used to predict and analyze the results in the present work. The results show that the predictions on pressure distributions with SST k-ω and v2f turbulence models have good agreements with experimental data.

Keywords: Horizontal Axis Wind Turbine, turbulence model, noise.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2161

Authors: Edlira Kalemi, Sule Yildirim-Yayilgan

Abstract:

Online Social Networks (OSNs) are nowadays being used widely and intensively for crime investigation and prevention activities. As they provide a lot of information they are used by the law enforcement and intelligence. An extensive review on existing solutions and models for collecting intelligence from this source of information and making use of it for solving crimes has been presented in this article. The main focus is on smart solutions and models where ontologies have been used as the main approach for representing criminal domain knowledge. A framework for a prototype ontology named SC-Ont will be described. This defines terms of the criminal domain ontology and the relations between them. The terms and the relations are extracted during both this review and the discussions carried out with domain experts. The development of SC-Ont is still ongoing work, where in this paper, we report mainly on the motivation for using smart ontology models and the possible benefits of using them for solving crimes.

Keywords: Criminal digital evidence, social media, ontologies, reasoning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2378

Authors: Guang Zou, Kian Banisoleiman, Arturo González

Abstract:

Crack initiation and propagation threatens structural integrity of welded joints and normally inspections are assigned based on crack propagation models. However, the approach based on crack propagation models may not be applicable for some high-quality welded joints, because the initial flaws in them may be so small that it may take long time for the flaws to develop into a detectable size. This raises a concern regarding the inspection planning of high-quality welded joins, as there is no generally acceptable approach for modeling the whole fatigue process that includes the crack initiation period. In order to address the issue, this paper reviews treatment methods for crack initiation period and initial crack size in crack propagation models applied to inspection planning. Generally, there are four approaches, by: 1) Neglecting the crack initiation period and fitting a probabilistic distribution for initial crack size based on statistical data; 2) Extrapolating the crack propagation stage to a very small fictitious initial crack size, so that the whole fatigue process can be modeled by crack propagation models; 3) Assuming a fixed detectable initial crack size and fitting a probabilistic distribution for crack initiation time based on specimen tests; and, 4) Modeling the crack initiation and propagation stage separately using small crack growth theories and Paris law or similar models. The conclusion is that in view of trade-off between accuracy and computation efforts, calibration of a small fictitious initial crack size to S-N curves is the most efficient approach.

Keywords: Crack initiation, fatigue reliability, inspection planning, welded joints.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1398

Authors: Mohammad H. Fattahi

Abstract:

Chaotic analysis has been performed on the river flow time series before and after applying the wavelet based de-noising techniques in order to investigate the noise content effects on chaotic nature of flow series. In this study, 38 years of monthly runoff data of three gauging stations were used. Gauging stations were located in Ghar-e-Aghaj river basin, Fars province, Iran. Noise level of time series was estimated with the aid of Gaussian kernel algorithm. This step was found to be crucial in preventing removal of the vital data such as memory, correlation and trend from the time series in addition to the noise during de-noising process.

Keywords: Chaotic behavior, wavelet, noise reduction, river flow.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2095

Authors: Fatih Tosunoğlu, İbrahim Can

Abstract:

The flow duration curve (FDC) is an informative method that represents the flow regime’s properties for a river basin. Therefore, the FDC is widely used for water resource projects such as hydropower, water supply, irrigation and water quality management. The primary purpose of this study is to obtain synthetic daily flow duration curves for Çoruh Basin, Turkey. For this aim, we firstly developed univariate auto-regressive moving average (ARMA) models for daily flows of 9 stations located in Çoruh basin and then these models were used to generate 100 synthetic flow series each having same size as historical series. Secondly, flow duration curves of each synthetic series were drawn and the flow values exceeded 10, 50 and 95% of the time and 95% confidence limit of these flows were calculated. As a result, flood, mean and low flows potential of Çoruh basin will comprehensively be represented.

Keywords: ARMA models, Çoruh basin, flow duration curve, Turkey.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3791

Authors: Eakong Atiptamvaree, Twittie Senivongse

Abstract:

A new paradigm for software design and development models software by its business process, translates the model into a process execution language, and has it run by a supporting execution engine. This process-oriented paradigm promotes modeling of software by less technical users or business analysts as well as rapid development. Since business process models may be shared by different organizations and sometimes even by different business domains, it is interesting to apply a technique used in traditional software component technology to design reusable business processes. This paper discusses an approach to apply a technique for software component fabrication to the design of process-oriented software units, called process components. These process components result from decomposing a business process of a particular application domain into subprocesses with an aim that the process components can be reusable in different process-based software models. The approach is quantitative because the quality of process component design is measured from technical features of the process components. The approach is also strategic because the measured quality is determined against business-oriented component management goals. A software tool has been developed to measure how good a process component design is, according to the required managerial goals and comparing to other designs. We also discuss how we benefit from reusable process components.

Keywords: Business process model, process component, component management goals, measurement

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1676

Authors: Ahmet Kayabasi, Ali Akdagli

Abstract:

In this study, three robust predicting methods, namely artificial neural network (ANN), adaptive neuro fuzzy inference system (ANFIS) and support vector machine (SVM) were used for computing the resonant frequency of A-shaped compact microstrip antennas (ACMAs) operating at UHF band. Firstly, the resonant frequencies of 144 ACMAs with various dimensions and electrical parameters were simulated with the help of IE3D™ based on method of moment (MoM). The ANN, ANFIS and SVM models for computing the resonant frequency were then built by considering the simulation data. 124 simulated ACMAs were utilized for training and the remaining 20 ACMAs were used for testing the ANN, ANFIS and SVM models. The performance of the ANN, ANFIS and SVM models are compared in the training and test process. The average percentage errors (APE) regarding the computed resonant frequencies for training of the ANN, ANFIS and SVM were obtained as 0.457%, 0.399% and 0.600%, respectively. The constructed models were then tested and APE values as 0.601% for ANN, 0.744% for ANFIS and 0.623% for SVM were achieved. The results obtained here show that ANN, ANFIS and SVM methods can be successfully applied to compute the resonant frequency of ACMAs, since they are useful and versatile methods that yield accurate results.

Keywords: A-shaped compact microstrip antenna, Artificial Neural Network (ANN), adaptive Neuro-Fuzzy Inference System (ANFIS), Support Vector Machine (SVM).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2215

Authors: Fariba Esfandiary, Ghafoor Aghaie, Ali Dolati Mehr

Abstract:

Wheat prediction was carried out using different meteorological variables together with agro meteorological indices in Ardebil district for the years 2004-2005 & 2005–2006. On the basis of correlation coefficients, standard error of estimate as well as relative deviation of predicted yield from actual yield using different statistical models, the best subset of agro meteorological indices were selected including daily minimum temperature (Tmin), accumulated difference of maximum & minimum temperatures (TD), growing degree days (GDD), accumulated water vapor pressure deficit (VPD), sunshine hours (SH) & potential evapotranspiration (PET). Yield prediction was done two months in advance before harvesting time which was coincide with commencement of reproductive stage of wheat (5th of June). It revealed that in the final statistical models, 83% of wheat yield variability was accounted for variation in above agro meteorological indices.

Keywords: Wheat yields prediction, agro meteorological indices, statistical models

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2145

Authors: Daniel Morariu, Lucian N. Vintan, Volker Tresp

Abstract:

Text categorization is the problem of classifying text documents into a set of predefined classes. After a preprocessing step, the documents are typically represented as large sparse vectors. When training classifiers on large collections of documents, both the time and memory restrictions can be quite prohibitive. This justifies the application of feature selection methods to reduce the dimensionality of the document-representation vector. In this paper, three feature selection methods are evaluated: Random Selection, Information Gain (IG) and Support Vector Machine feature selection (called SVM_FS). We show that the best results were obtained with SVM_FS method for a relatively small dimension of the feature vector. Also we present a novel method to better correlate SVM kernel-s parameters (Polynomial or Gaussian kernel).

Keywords: Feature Selection, Learning with Kernels, SupportVector Machine, and Classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1829

Authors: A. Falsafain, S. M. Taheri, M. Mashinchi

Abstract:

Using a set of confidence intervals, we develop a common approach, to construct a fuzzy set as an estimator for unknown parameters in statistical models. We investigate a method to derive the explicit and unique membership function of such fuzzy estimators. The proposed method has been used to derive the fuzzy estimators of the parameters of a Normal distribution and some functions of parameters of two Normal distributions, as well as the parameters of the Exponential and Poisson distributions.

Keywords: Confidence interval. Fuzzy number. Fuzzy estimation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2273

Authors: D. Hişam, S. İkizoğlu

Abstract:

Identifying the problem behind balance disorder is one of the most interesting topics in medical literature. This study has considerably enhanced the development of artificial intelligence (AI) algorithms applying multiple machine learning (ML) models to sensory data on gait collected from humans to classify between normal people and those suffering from Vestibular System (VS) problems. Although AI is widely utilized as a diagnostic tool in medicine, AI models have not been used to perform feature extraction and identify VS disorders through training on raw data. In this study, three ML models, the Random Forest Classifier (RF), Extreme Gradient Boosting (XGB), and K-Nearest Neighbor (KNN), have been trained to detect VS disorder, and the performance comparison of the algorithms has been made using accuracy, recall, precision, and f1-score. With an accuracy of 95.28 %, Random Forest (RF) Classifier was the most accurate model.

Keywords: Vestibular disorder, machine learning, random forest classifier, k-nearest neighbor, extreme gradient boosting.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 169

Authors: Alireza Ansariyar, Safieh Laaly

Abstract:

Over the last decades, the vehicle industry has shown increased interest in integrating autonomous, connected, and electrical technologies in vehicle design with the primary hope of improving mobility and road safety while reducing transportation’s environmental impact. Using the State of Maryland (M.D.) in the United States as a pilot study, this research investigates Connected and Autonomous Vehicles (CAVs) fuel consumption and air pollutants including Carbon Monoxide (CO), Particulate Matter (PM), and Nitrogen Oxides (NOx) and utilizes meaningful linear regression models to predict CAV’s environmental effects. Maryland transportation network was simulated in VISUM software, and data on a set of variables were collected through a comprehensive survey. The number of pollutants and fuel consumption were obtained for the time interval 2010 to 2021 from the macro simulation. Eventually, four linear regression models were proposed to predict the amount of C.O., NOx, PM pollutants, and fuel consumption in the future. The results highlighted that CAVs’ pollutants and fuel consumption have a significant correlation with the income, age, and race of the CAV customers. Furthermore, the reliability of four statistical models was compared with the reliability of macro simulation model outputs in the year 2030. The error of three pollutants and fuel consumption was obtained at less than 9% by statistical models in SPSS. This study is expected to assist researchers and policymakers with planning decisions to reduce CAV environmental impacts in M.D.

Keywords: Connected and autonomous vehicles, statistical model, environmental effects, pollutants and fuel consumption, VISUM, linear regression models.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 462

Authors: Ching-I Chen

Abstract:

The continued rise of e-commerce is the main driver of the rapid growth of global online purchase. Consumers can nearly buy everything they want at one occasion through online shopping. The purchase behavior models which focus on single product category are insufficient to describe online shopping behavior. Therefore, analysis of multi-category purchase gets more and more popular. For example, market basket analysis explores customers’ buying tendency of the association between product categories. The information derived from market basket analysis facilitates to make cross-selling strategies and product recommendation system.

To detect the association between different product categories, we use the market basket analysis with the multidimensional scaling technique to build an associated map which describes how likely multiple product categories are bought at the same time. Besides, we also build an inter-purchase time model for associated products to describe how likely a product will be bought after its associated product is bought. We classify inter-purchase time behaviors of multi-category products into nine types, and use a mixture regression model to integrate those behaviors under our assumptions of purchase sequences. Our sample data is from comScore which provides a panelist-label database that captures detailed browsing and buying behavior of internet users across the United States. Finding the inter-purchase time from books to movie is shorter than the inter-purchase time from movies to books. According to the model analysis and empirical results, this research finally proposes the applications and recommendations in the management.

Keywords: Multiple-category purchase behavior, inter-purchase time, market basket analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1871

Authors: Catherine Maware, Olufemi Adetunji

Abstract:

The paper is aimed at developing a model to measure the impact of Lean manufacturing deployment on organizational performance. The model will help industry practitioners to assess the impact of implementing Lean constructs on organizational performance. It will also harmonize the measurement models of Lean performance with the house of Lean that seems to have become the industry standard. The sheer number of measurement models for impact assessment of Lean implementation makes it difficult for new adopters to select an appropriate assessment model or deployment methodology. A literature review is conducted to classify the Lean performance model. Pareto analysis is used to select the Lean constructs for the development of the model. The model is further formalized through the use of Structural Equation Modeling (SEM) in defining the underlying latent structure of a Lean system. An impact assessment measurement model developed can be used to measure Lean performance and can be adopted by different industries.

Keywords: Impact measurement model, lean bundles, lean manufacturing, organizational performance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1225

Authors: [email protected]

Abstract:

Breast cancer is one of the most common types in women. Early prediction of breast cancer helps physicians detect cancer in its early stages. Big cancer data need a very powerful tool to analyze and extract predictions. Machine learning and deep learning are two of the most efficient tools for predicting cancer based on textual data. In this study, we developed a fusion model of two machine learning and deep learning models. To obtain the final prediction, Long-Short Term Memory (LSTM), ensemble learning with hyper parameters optimization, and score-level fusion is used. Experiments are done on the Breast Cancer Surveillance Consortium (BCSC) dataset after balancing and grouping the class categories. Five different training scenarios are used, and the tests show that the designed fusion model improved the performance by 3.3% compared to the individual models.

Keywords: Machine learning, Deep learning, cancer prediction, breast cancer, LSTM, Score-Level Fusion.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 404

Authors: Ugur Akyol, Dinçer Akal, Ahmet Cihan, Kamil Kahveci

Abstract:

This study is concerned with the investigation of the suitability of several empirical and semi-empirical drying models available in the literature to define drying behavior of viscose yarn bobbins. For this purpose, firstly, experimental drying behaviour of viscose bobbins was determined on an experimental dryer setup which was designed and manufactured based on hot-air bobbin dryers used in textile industry. Afterwards, drying models considered were fitted to the experimentally obtained moisture ratios. Drying parameters were drying temperature and bobbin diameter. The fit was performed by selecting the values for constants in the models in such a way that these values make the sum of the squared differences between the experimental and the model results for moisture ratio minimum. Suitability of fitting was specified as comparing the correlation coefficient, standard error and mean square deviation. The results show that the most appropriate model in describing the drying curves of viscose bobbins is the Page model.

Keywords: Drying, moisture ratio, Page model, viscose

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1751

Authors: Ceren Kaya, Okan Erkaymaz, Orhan Ayar, Mahmut Özer

Abstract:

Diabetes Mellitus (Diabetes) is a disease based on insulin hormone disorders and causes high blood glucose. Clinical findings determine that diabetes can be diagnosed by electrophysiological signals obtained from the vital organs. 'Diabetic Retinopathy' is one of the most common eye diseases resulting on diabetes and it is the leading cause of vision loss due to structural alteration of the retinal layer vessels. In this study, features of horizontal and vertical Video-Oculography (VOG) signals have been used to classify non-proliferative and proliferative diabetic retinopathy disease. Twenty-five features are acquired by using discrete wavelet transform with VOG signals which are taken from 21 subjects. Two models, based on multi-layer perceptron and radial basis function, are recommended in the diagnosis of Diabetic Retinopathy. The proposed models also can detect level of the disease. We show comparative classification performance of the proposed models. Our results show that proposed the RBF model (100%) results in better classification performance than the MLP model (94%).

Keywords: Diabetic retinopathy, discrete wavelet transform, multi-layer perceptron, radial basis function, video-oculography.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1346

Authors: Joshua Prakash, Chin Jeng Feng

Abstract:

The paper describes the workings for four models of CONWIP systems used till date; the basic CONWIP system, the hybrid CONWIP system, the multi-product CONWIP system, and the parallel CONWIP system. The final novel model is introduced in this paper in a general form. These models may be adopted for analysis for both simulation studies and implementation on the shop floor. For each model, input parameters of interest are highlighted and their impacts on several system performance measures are addressed.

Keywords: CONWIP, hybrid CONWIP, mixed CONWIP, multi-product CONWIP.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2327

Authors: Panudet Saengseedam, Nanthachai Kantanantha

Abstract:

This paper proposes a linear mixed model (LMM) with spatial effects to forecast rice and cassava yields in Thailand at the same time. A multivariate conditional autoregressive (MCAR) model is assumed to present the spatial effects. A Bayesian method is used for parameter estimation via Gibbs sampling Markov Chain Monte Carlo (MCMC). The model is applied to the rice and cassava yields monthly data which have been extracted from the Office of Agricultural Economics, Ministry of Agriculture and Cooperatives of Thailand. The results show that the proposed model has better performance in most provinces in both fitting part and validation part compared to the simple exponential smoothing and conditional auto regressive models (CAR) from our previous study.

Keywords: Bayesian method, Linear mixed model, Multivariate conditional autoregressive model, Spatial time series.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2247