Search results for: predicting models

Authors: Sadia Munir, Diana White, Aya Albahri, Pratiwi Hastania, Eltahir Mohamed, Mahmood Khan, Fathima Mohamed, Ayat Kadhi, Haila Saleem

Abstract:

Preeclampsia is a major complication of pregnancy. Prediction and management of preeclampsia is a challenge for obstetricians. To our knowledge, no major progress has been achieved in the prevention and early detection of preeclampsia. There is very little known about the clear treatment path of this disorder. Preeclampsia puts both mother and baby at risk of several short term- and long term-health problems later in life. There is huge health service cost burden in the health care system associated with preeclampsia and its complications. Preeclampsia is divided into two different types. Early onset preeclampsia develops before 34 weeks of gestation, and late onset develops at or after 34 weeks of gestation. Different genetic and environmental factors, prognosis, heritability, biochemical and clinical features are associated with early and late onset preeclampsia. Prevalence of preeclampsia greatly varies all over the world and is dependent on ethnicity of the population and geographic region. To authors best knowledge, no published data on preeclampsia exist in Qatar. In this study, we are reporting the incidence of preeclampsia in Qatar. The purpose of this study is to compare the incidence and risk factors of both early onset and late onset preeclampsia in Qatar. This retrospective longitudinal cohort study was conducted using data from the hospital record of Women’s Hospital, Hamad Medical Corporation (HMC), from May 2014-May 2016. Data collection tool, which was approved by HMC, was a researcher made extraction sheet that included information such as blood pressure during admission, socio demographic characteristics, delivery mode, and new born details. A total of 1929 patients’ files were identified by the hospital information management when they apply codes of preeclampsia. Out of 1929 files, 878 had significant gestational hypertension without proteinuria, 365 had preeclampsia, 364 had severe preeclampsia, and 188 had preexisting hypertension with superimposed proteinuria. In this study, 78% of the data was obtained by hospital electronic system (Cerner) and the remaining 22% was from patient’s paper records. We have gone through detail data extraction from 560 files. Initial data analysis has revealed that 15.02% of pregnancies were complicated with preeclampsia from May 2014-May 2016. We have analyzed difference in the two different disease entities in the ethnicity, maternal age, severity of hypertension, mode of delivery and infant birth weight. We have identified promising differences in the risk factors of early onset and late onset preeclampsia. The data from clinical findings of preeclampsia will contribute to increased knowledge about two different disease entities, their etiology, and similarities/differences. The findings of this study can also be used in predicting health challenges, improving health care system, setting up guidelines, and providing the best care for women suffering from preeclampsia.

Keywords: preeclampsia, incidence, risk factors, maternal

Procedia PDF Downloads 120

Authors: Seyyed Hossein Alavi, Soudabeh Mehri Talarposhti

Abstract:

Quick development of urban population need for housing on the one hand and prevention of irregular urban extension for optimum usage of urban land, resolving problems of urban physiognomy, land using, and environmental issues and urban transport, on the other hand, proposed tall building as urban area extension requirement in developing and advanced countries. Beside the tall building, protection, and creation of green architecture is one the most important issues of today's architecture world. This research is about attending tall building with green architecture in Babolsar city 2015. For this, the issues that can make favorite conditions for green architecture has been discussed. The purpose of this discussion is skeleton extension and accessing interactions between architecture and related technologies. This discussion with using of qualitative research methods (Analytical Description) tried to studying designed performance models and also studying and analyzing the inside and foreign articles and books. Hope this research is useful in solving the existing problems in this issue.

Keywords: tall building, green architecture, skeleton extension, Babolsar city

Procedia PDF Downloads 409

Authors: Ameur Abdelkader, Abed Bouarfa Hafida

Abstract:

Since its inception, predictive analysis has revolutionized the IT industry through its robustness and decision-making facilities. It involves the application of a set of data processing techniques and algorithms in order to create predictive models. Its principle is based on finding relationships between explanatory variables and the predicted variables. Past occurrences are exploited to predict and to derive the unknown outcome. With the advent of big data, many studies have suggested the use of predictive analytics in order to process and analyze big data. Nevertheless, they have been curbed by the limits of classical methods of predictive analysis in case of a large amount of data. In fact, because of their volumes, their nature (semi or unstructured) and their variety, it is impossible to analyze efficiently big data via classical methods of predictive analysis. The authors attribute this weakness to the fact that predictive analysis algorithms do not allow the parallelization and distribution of calculation. In this paper, we propose to extend the predictive analysis algorithm, Classification And Regression Trees (CART), in order to adapt it for big data analysis. The major changes of this algorithm are presented and then a version of the extended algorithm is defined in order to make it applicable for a huge quantity of data.

Keywords: predictive analysis, big data, predictive analysis algorithms, CART algorithm

Procedia PDF Downloads 124

Authors: Aghbalou Nihad, Charki Abderafi, Saida Rahali, Reklaoui Kamal

Abstract:

Maximize the benefit from the wind energy potential is the most interest of the wind power stakeholders. As a result, the wind tower size is radically increasing. Nevertheless, choosing an appropriate wind turbine for a selected site require an accurate estimate of vertical wind profile. It is also imperative from cost and maintenance strategy point of view. Then, installing tall towers or even more expensive devices such as LIDAR or SODAR raises the costs of a wind power project. Various models were developed coming within this framework. However, they suffer from complexity, generalization and lacks accuracy. In this work, we aim to investigate the ability of neural network trained using the Bayesian Regularization technique to estimate wind speed profile up to height of 100 m based on knowledge of wind speed lower heights. Results show that the proposed approach can achieve satisfactory predictions and proof the suitability of the proposed method for generating wind speed profile and probability distributions based on knowledge of wind speed at lower heights.

Keywords: bayesian regularization, neural network, wind shear, accuracy

Procedia PDF Downloads 484

Authors: Liliana Patricia Olivo Arias

Abstract:

The present study focused on the hydrodynamic study in a three-phase fluidized bed reactor and the influence of important aspects, such as volume fractions (Hold up), velocity magnitude of gas, liquid and solid phases (hydrogen, gasoil, and gamma alumina), interactions of phases, through of drag models with the k-epsilon turbulence model. For this purpose was employed a Euler-Euler model and also considers the system is constituted of three phases, gaseous, liquid and solid, characterized by its physical and thermal properties, the transport processes that are developed within the transient regime. The proposed model of the three-phase fluidized bed reactor was solved numerically using the ANSYS-Fluent software with different mesh refinements on bed expansion zone in order to observe the influence of the hydrodynamic parameters and convergence criteria. With this model and the numerical simulations obtained for its resolution, it was possible to predict the results of the volume fractions (Hold ups) and the velocity magnitude for an unsteady system from the initial and boundaries conditions were established.

Keywords: three-phase fluidized bed system, CFD simulation, mesh dependency study, hydrodynamic study

Procedia PDF Downloads 147

Authors: Kyoung-Jae Kim

Abstract:

Collaborative Filtering (CF) is a popular technique for the personalization in the E-commerce domain to reduce information overload. In general, CF provides recommending items list based on other similar users’ preferences from the user-item matrix and predicts the focal user’s preference for particular items by using them. Many recommender systems in real-world use CF techniques because it’s excellent accuracy and robustness. However, it has some limitations including sparsity problems and complex dimensionality in a user-item matrix. In addition, traditional CF does not consider the emotional interaction between users. In this study, we propose recommender systems using social network and singular value decomposition (SVD) to alleviate some limitations. The purpose of this study is to reduce the dimensionality of data set using SVD and to improve the performance of CF by using emotional information from social network data of the focal user. In this study, we test the usability of hybrid CF, SVD and social network information model using the real-world data. The experimental results show that the proposed model outperforms conventional CF models.

Keywords: recommender systems, collaborative filtering, social network information, singular value decomposition

Procedia PDF Downloads 273

Authors: Milad Nooshadi, Alessandro Manzardo

Abstract:

CO₂ emissions in the atmosphere continue to rise, mostly as a result of the combustion of fossil fuels. CO₂ injection into the oceans and geological formation as a process of physical carbon capture are two of the most promising emerging strategies for mitigating climate change and global warming. The purpose of this research is to evaluate the two mentioned methods of CO₂ sequestration and to assess information on previous and current advancements, limitations, and uncertainties associated with carbon sequestration in order to identify possible prospects for ensuring the timely implementation of the technology, such as determining how governments and companies can gain a better understanding of CO₂ storage in terms of which media have the most applicable capacity, which type of injection has the fewer environmental impact, and how much carbon sequestration and storage will cost. The behavior of several forms is characterized as a near field, a far field, and a see-floor in ocean storage, and three medias in geological formations as an oil and gas reservoir, a saline aquifer, and a coal bed. To determine the capacity of various forms of media, an analysis of some models and practical experiments are necessary. Additionally, as a major component of sequestration, the various injection methods into diverse media and their monitoring are associated with a variety of environmental impacts and financial consequences.

Keywords: carbon sequestration, ocean storage, geologic storage, carbon transportation

Procedia PDF Downloads 84

Authors: Mustafa Metin Donma

Abstract:

Metabolic syndrome (MetS) is characterized by a series of biochemical, physiological and anthropometric indicators and is a life-threatening health problem due to its close association with chronic diseases such as diabetes mellitus, hypertension, cancer and cardiovascular diseases. The syndrome deserves great interest both in adults and children. Central obesity is the indispensable component of MetS. Particularly, children, who are morbidly obese have a great tendency to develop the disease, because they are under the threat in their future lives. Preventive measures at this stage should be considered. For this, investigators seek for an informative scale or an index for the purpose. So far, several, but not many suggestions come into the stage. However, the diagnostic decision is not so easy and may not be complete particularly in the pediatric population. The aim of the study was to develop a MetS index capable of predicting MetS, while children are at the morbid obesity stage. This study was performed on morbid obese (MO) children, which were divided into two groups. Morbid obese children, who do not possess MetS criteria comprised the first group (n=44). The second group was composed of children (n=42) with MetS diagnosis. Parents were informed about the signed consent forms, which are required for the participation of their children in the study. The approval of the study protocol was taken from the institutional ethics committee of Tekirdag Namik Kemal University. Helsinki Declaration was accepted prior to and during the study. Anthropometric measurements including weight, height, waist circumference (WC), hip C, head C, neck C, biochemical tests including fasting blood glucose (FBG), insulin (INS), triglycerides (TRG), high density lipoprotein cholesterol (HDL-C) and blood pressure measurements (systolic (SBP) and diastolic (DBP)) were performed. Body fat percentage (BFP) values were determined by TANITA’s Bioelectrical Impedance Analysis technology. Body mass index and MetS indices were calculated. The equations for MetS index (MetSI) and advanced Donma MetS index (ADMI) were [(INS/FBG)/(HDL-C/TRG)]*100 and MetSI*[(SBP+DBP/Height)], respectively. Descriptive statistics including median values, compare means tests, correlation-regression analysis were performed within the scope of data evaluation using the statistical package program, SPSS. Statistically significant mean differences were determined by a p value smaller than 0.05. Median values for MetSI and ADMI in MO (MetS-) and MO (MetS+) groups were calculated as (25.9 and 36.5) and (74.0 and 106.1), respectively. Corresponding mean±SD values for BFPs were 35.9±7.1 and 38.2±7.7 in groups. Correlation analysis of these two indices with corresponding general BFP values exhibited significant association with ADMI, close to significance with MetSI in MO group. Any significant correlation was found with neither of the indices in MetS group. In conclusion, important associations observed with MetS indices in MO group were quite meaningful. The presence of these associations in MO group was important for showing the tendency towards the development of MetS in MO (MetS-) participants. The other index, ADMI, was more helpful for predictive purpose.

Keywords: body fat percentage, child, index, metabolic syndrome, obesity

Procedia PDF Downloads 46

Authors: Sawsan J. Al-husseini, Talib A. Dosa

Abstract:

Educational institutions are today facing increasing pressures due to economic, political and social upheaval. This is only exacerbated by the nature of education as an intangible good which relies upon the intellectual assets of the organisation, its staff. Top management support has been acknowledged as having a positive general influence on knowledge management and creativity. However, there is a lack of models linking top management support, knowledge sharing, and innovation within higher education institutions, in general within developing countries, and particularly in Iraq. This research sought to investigate the impact of top management support on innovation through the mediating role of knowledge sharing in Iraqi private HEIs. A quantitative approach was taken and 262 valid responses were collected to test the causal relationships between top management support, knowledge sharing, and innovation. Employing structural equation modelling with AMOS v.25, the research demonstrated that knowledge sharing plays a pivotal role in the relationship between top management support and innovation. The research has produced some guidelines for researchers as well as leaders, and provided evidence to support the use of knowledge sharing to increase innovation within the higher education environment in developing countries, particularly Iraq.

Keywords: top management support, knowledge sharing, innovation, structural equation modelling

Procedia PDF Downloads 315

Authors: Longqing Li

Abstract:

The paper addresses the inefficiency of the classical model in measuring the Value-at-Risk (VaR) using a normal distribution or a Student’s t distribution. Specifically, the paper focuses on the one day ahead Value-at-Risk (VaR) of major stock market’s daily returns in US, UK, China and Hong Kong in the most recent ten years under 95% confidence level. To improve the predictable power and search for the best performing model, the paper proposes using two leading alternatives, Extreme Value Theory (EVT) and a family of GARCH models, and compares the relative performance. The main contribution could be summarized in two aspects. First, the paper extends the GARCH family model by incorporating EGARCH and TGARCH to shed light on the difference between each in estimating one day ahead Value-at-Risk (VaR). Second, to account for the non-normality in the distribution of financial markets, the paper applies Generalized Error Distribution (GED), instead of the normal distribution, to govern the innovation term. A dynamic back-testing procedure is employed to assess the performance of each model, a family of GARCH and the conditional EVT. The conclusion is that Exponential GARCH yields the best estimate in out-of-sample one day ahead Value-at-Risk (VaR) forecasting. Moreover, the discrepancy of performance between the GARCH and the conditional EVT is indistinguishable.

Keywords: Value-at-Risk, Extreme Value Theory, conditional EVT, backtesting

Procedia PDF Downloads 303

Authors: Abbas Al-Refaie, Nour Bata

Abstract:

A distributor of Apple products' experiences numerous difficulties in developing marketing strategies for new and existing mobile product entries that maximize customer satisfaction and the firm's profitability. This research, therefore, integrates market segmentation in platform-based product family design and conjoint analysis to identify iSystem combinations that increase customer satisfaction and business profits. First, the enhanced market segmentation grid is created. Then, the estimated demand model is formulated. Finally, the profit models are constructed then used to determine the ideal product family design that maximizes profit. Conjoint analysis is used to explore customer preferences with their satisfaction levels. A total of 200 surveys are collected about customer preferences. Then, simulation is used to determine the importance values for each attribute. Finally, sensitivity analysis is conducted to determine the product family design that maximizes both objectives. In conclusion, the results of this research shall provide great support to Apple distributors in determining the best marketing strategies that enhance their market share.

Keywords: market segmentation, conjoint analysis, market strategies, optimization

Procedia PDF Downloads 340

Authors: Shahadut Hossain

Abstract:

Measurement errors in continuous covariates and/or misclassifications in categorical covariates are common in epidemiological studies. Regression analysis ignoring such mismeasurements seriously biases the estimated main and interaction effects of covariates on the outcome of interest. Thus, adjustments for such mismeasurements are necessary. In this research, we propose a Bayesian parametric framework for eliminating deleterious impacts of covariate mismeasurements in logistic regression. The proposed adjustment method is unified and thus can be applied to any generalized linear and non-linear regression models. Furthermore, adjustment for covariate mismeasurements requires validation data usually in the form of either gold standard measurements or replicates of the mismeasured covariates on a subset of the study population. Initial investigation shows that adequacy of such adjustment depends on the sizes of main and validation samples, especially when prevalences of the categorical covariates are low. Thus, we investigate the impact of main and validation sample sizes on the adjusted estimates, and provide a general guideline about these sample sizes based on simulation studies.

Keywords: measurement errors, misclassification, mismeasurement, validation sample, Bayesian adjustment

Procedia PDF Downloads 394

Authors: Premrudee Kanchanapiya, Supachai Songngam, Thanapol Tantisattayakul

Abstract:

Perfluorooctanoic acid (PFOA) is one of per- and polyfluoroalkyl substances (PFAS) that have increasingly attracted concerns due to their global distribution in environment, persistence, high bioaccumulation, and toxicity. It is important to study the effective treatment to remove PFOA from contaminated water. The feasibility of using commercial coconut shell activated carbon produced in Thailand to remove PFOA from water was investigated with regard to their adsorption kinetics and isotherms of powder activated carbon (PAC-325) and granular activated carbon (GAC-20x50). Adsorption kinetic results show that the adsorbent size significantly affected the adsorption rate of PFOA, and GAC-20x50 required at least 100 h to achieve the equilibrium, much longer than 3 h for PAC-325. Two kinetic models were fitted to the experimental data, and the pseudo-second-order model well described the adsorption of PFOA on both PAC-325 and GAC-20x50. PAC-325 trended to adsorb PFOA faster than GAC-20x50, and testing with the shortest adsorption times (5 min) still yielded substantial PFOA removal (~80% for PAC-325). The adsorption isotherms show that the adsorption capacity of PAC-325 was 0.80 mmol/g, which is 83 % higher than that for GAC-20x50 (0.13 mmol/g), according to the Langmuir fitting.

Keywords: perfluorooctanoic acid, PFOA, coconut shell activated carbons, adsorption, water treatment

Procedia PDF Downloads 133

Authors: Luana Parisi, Sohrab Donyavi

Abstract:

Cities have become the nodes of global networks, standing at the intersection points of the flows of capital, goods, workers, businesses and travellers, making them the spots where innovation, progress and economic development occur. The primary challenge for them is to create the most fertile ecosystems for triggering innovation activities. Design emerges as an essential feature in this process of laboratorisation of cities. This paper aims at exploring the spatial hubs of transformation within the knowledge economy, providing an overview of the current models of innovation spaces, before focusing on the innovation district of one of the cities that are riding the innovation wave, namely, Boston, USA. Useful lessons will be drawn from the case study of the innovation district in Boston, allowing to define precious tools for policymakers, in the form of a range of factors that define the broad strategy able to implement the model successfully. A mixed methodology is implemented, including information from observations, exploratory interviews to key stakeholders and on-desk data.

Keywords: Innovation District, innovation ecosystem, economic development, urban regeneration

Procedia PDF Downloads 93

Authors: John Pomerat, Aviv Segev

Abstract:

Recently, deep learning has had many theoretical breakthroughs. For deep learning to be successful in the industry, however, there need to be practical algorithms capable of handling many real-world hiccups preventing the immediate application of a learning algorithm. Although AI promises to revolutionize the healthcare industry, getting access to patient data in order to train learning algorithms has not been easy. One proposed solution to this is data- sharing. In this paper, we propose an alternative protocol, based on multi-party computation, to train deep learning models while maintaining both the privacy and security of training data. We examine three methods of training neural networks in this way: Transfer learning, average ensemble learning, and series network learning. We compare these methods to the equivalent model obtained through data-sharing across two different experiments. Additionally, we address the security concerns of this protocol. While the motivating example is healthcare, our findings regarding multi-party computation of neural network training are purely theoretical and have use-cases outside the domain of healthcare.

Keywords: neural network aggregation, multi-party computation, transfer learning, average ensemble learning

Procedia PDF Downloads 141

Authors: Emel Kızılkaya Aydogan, Mihrimah Ozmen, Yılmaz Delice

Abstract:

In recent days, there is a change and the ongoing development of the telecommunications sector in the global market. In this sector, churn analysis techniques are commonly used for analysing why some customers terminate their service subscriptions prematurely. In addition, customer churn is utmost significant in this sector since it causes to important business loss. Many companies make various researches in order to prevent losses while increasing customer loyalty. Although a large quantity of accumulated data is available in this sector, their usefulness is limited by data quality and relevance. In this paper, a cost-sensitive feature selection framework is developed aiming to obtain the feature reducts to predict customer churn. The framework is a cost based optional pre-processing stage to remove redundant features for churn management. In addition, this cost-based feature selection algorithm is applied in a telecommunication company in Turkey and the results obtained with this algorithm.

Keywords: churn prediction, data mining, decision-theoretic rough set, feature selection

Procedia PDF Downloads 427

Authors: Lule Basha, Eralda Gjika

Abstract:

The exchange rate is one of the most important economic variables, especially for a small, open economy such as Albania. Its effect is noticeable in one country's competitiveness, trade and current account, inflation, wages, domestic economic activity, and bank stability. This study investigates the fluctuation of Albania’s exchange rates using monthly average foreign currency, Euro (Eur) to Albanian Lek (ALL) exchange rate with a time span from January 2008 to June 2021, and the macroeconomic factors that have a significant effect on the exchange rate. Initially, the Random Forest Regression algorithm is constructed to understand the impact of economic variables on the behavior of monthly average foreign currencies exchange rates. Then the forecast of macro-economic indicators for 12 months was performed using time series models. The predicted values received are placed in the random forest model in order to obtain the average monthly forecast of the Euro to Albanian Lek (ALL) exchange rate for the period July 2021 to June 2022.

Keywords: exchange rate, random forest, time series, machine learning, prediction

Procedia PDF Downloads 85

Authors: Muna Mitchell, Akshay Parchure, Krishna Singaraju

Abstract:

There is an increasing need for medium- to long-span steel bridges with complex geometry due to site restrictions in developed areas. One of the solutions to grade separations in congested areas is to use longer spans on skewed supports that avoid at-grade obstructions limiting impacts to the foundation. Where vertical clearances are also a constraint, continuous steel girders can be used to reduce superstructure depths. Combining continuous long steel spans on severe skews can resolve the constraints at a cost. The behavior of skewed girders is challenging to analyze and design with subsequent complexity during fabrication and construction. As a part of a corridor improvement project, Walter P Moore designed two 1700-foot side-by-side bridges carrying four lanes of traffic in each direction over a railroad track. The bridges consist of prestressed concrete girder approach spans and three-span continuous steel plate girder units. The roadway design added complex geometry to the bridge with horizontal and vertical curves combined with superelevation transitions within the plate girder units. The substructure at the steel units was skewed approximately 56 degrees to satisfy the existing railroad right-of-way requirements. A horizontal point of curvature (PC) near the end of the steel units required the use flared girders and chorded slab edges. Due to the flared girder geometry, the cross-frame spacing in each bay is unique. Staggered cross frames were provided based on AASHTO LRFD and NCHRP guidelines for high skew steel bridges. Skewed steel bridges develop significant forces in the cross frames and rotation in the girder websdue to differential displacements along the girders under dead and live loads. In addition, under thermal loads, skewed steel bridges expand and contract not along the alignment parallel to the girders but along the diagonal connecting the acute corners, resulting in horizontal displacement both along and perpendicular to the girders. AASHTO LRFD recommends a 95 degree Fahrenheit temperature differential for the design of joints and bearings. The live load and the thermal loads resulted in significant horizontal forces and rotations in the bearings that necessitated the use of HLMR bearings. A unique bearing layout was selected to minimize the effect of thermal forces. The span length, width, skew, and roadway geometry at the bridges also required modular bridge joint systems (MBJS) with inverted-T bent caps to accommodate movement in the steel units. 2D and 3D finite element analysis models were developed to accurately determine the forces and rotations in the girders, cross frames, and bearings and to estimate thermal displacements at the joints. This paper covers the decision-making process for developing the framing plan, bearing configurations, joint type, and analysis models involved in the design of the high-skew three-span continuous steel plate girder bridges.

Keywords: complex geometry, continuous steel plate girders, finite element structural analysis, high skew, HLMR bearings, modular joint

Procedia PDF Downloads 168

Authors: Valentina Zhang

Abstract:

While facial expression is a complex and individualized behavior, all facial emotion recognition (FER) systems known to us rely on a single facial representation and are trained on universal data. We conjecture that: (i) different facial representations can provide different, sometimes complementing views of emotions; (ii) when employed collectively in a discussion group setting, they enable more accurate emotion reading which is highly desirable in autism care and other applications context sensitive to errors. In this paper, we first study FER using pixel-based DL vs semantics-based DL in the context of deepfake videos. Our experiment indicates that while the semantics-trained model performs better with articulated facial feature changes, the pixel-trained model outperforms on subtle or rare facial expressions. Armed with these findings, we have constructed an adaptive FER system learning from both types of models for dyadic or small interacting groups and further leveraging the synthesized group emotions as the ground truth for individualized FER training. Using a collection of group conversation videos, we demonstrate that FER accuracy and personalization can benefit from such an approach.

Keywords: neurodivergence care, facial emotion recognition, deep learning, ground truth for supervised learning

Procedia PDF Downloads 125

Authors: Nadia Masood Khan, Muhammad Salman Khan, Gul Muhammad Khan

Abstract:

Cardiologists perform cardiac auscultation to detect abnormalities in heart sounds. Since accurate auscultation is a crucial first step in screening patients with heart diseases, there is a need to develop computer-aided detection/diagnosis (CAD) systems to assist cardiologists in interpreting heart sounds and provide second opinions. In this paper different algorithms are implemented for automated heart sound classification using unsegmented phonocardiogram (PCG) signals. Support vector machine (SVM), artificial neural network (ANN) and cartesian genetic programming evolved artificial neural network (CGPANN) without the application of any segmentation algorithm has been explored in this study. The signals are first pre-processed to remove any unwanted frequencies. Both time and frequency domain features are then extracted for training the different models. The different algorithms are tested in multiple scenarios and their strengths and weaknesses are discussed. Results indicate that SVM outperforms the rest with an accuracy of 73.64%.

Keywords: pattern recognition, machine learning, computer aided diagnosis, heart sound classification, and feature extraction

Procedia PDF Downloads 237

Authors: Samira Hamiditehrani

Abstract:

Automated vehicles (AVs) are emerging technologies that could potentially offer a wide range of opportunities and challenges for the transportation sector. The advent of AV technology has also resulted in new business models in shared mobility services where many ride hailing and car sharing companies are developing on-demand AVs including shared automated vehicles (SAVs) and pooled automated vehicles (Pooled AVs). SAVs and Pooled AVs could provide alternative shared mobility services which encourage sustainable transport systems, mitigate traffic congestion, and reduce automobile dependency. However, the success of on-demand AVs in addressing major transportation policy issues depends on whether and how the public adopts them as regular travel modes. To identify conditions under which individuals may adopt on-demand AVs, previous studies have applied human behavior and technology acceptance theories, where Theory of Planned Behavior (TPB) has been validated and is among the most tested in on-demand AV research. In this respect, this study has three objectives: (a) to propose and validate a theoretical model for behavioral intention to use SAVs and Pooled AVs by extending the original TPB model; (b) to identify the characteristics of early adopters of SAVs, who prefer to have a shorter and private ride, versus prospective users of Pooled AVs, who choose more affordable but longer and shared trips; and (c) to investigate Canadians’ intentions to adopt on-demand AVs for regular trips. Toward this end, this study uses data from an online survey (n = 3,622) of workers or adult students (18 to 75 years old) conducted in October and November 2021 for six major Canadian metropolitan areas: Toronto, Vancouver, Ottawa, Montreal, Calgary, and Hamilton. To accomplish the goals of this study, a base bivariate ordered probit model, in which both SAV and Pooled AV adoptions are estimated as ordered dependent variables, alongside a full structural equation modeling (SEM) system are estimated. The findings of this study indicate that affective motivations such as attitude towards AV technology, perceived privacy, and subjective norms, matter more than sociodemographic and travel behavior characteristic in adopting on-demand AVs. Also, the results of second objective provide evidence that although there are a few affective motivations, such as subjective norms and having ample knowledge, that are common between early adopters of SAVs and PooledAVs, many examined motivations differ among SAV and Pooled AV adoption factors. In other words, motivations influencing intention to use on-demand AVs differ among the service types. Likewise, depending on the types of on-demand AVs, the sociodemographic characteristics of early adopters differ significantly. In general, findings paint a complex picture with respect to the application of constructs from common technology adoption models to the study of on-demand AVs. Findings from the final objective suggest that policymakers, planners, the vehicle and technology industries, and the public at large should moderate their expectations that on-demand AVs may suddenly transform the entire transportation sector. Instead, this study suggests that SAVs and Pooled AVs (when they entire the Canadian market) are likely to be adopted as supplementary mobility tools rather than substitutions for current travel modes

Keywords: automated vehicles, Canadian perception, theory of planned behavior, on-demand AVs

Procedia PDF Downloads 50

Authors: Gabriele Borg, Alexei Debono, Charlie Abela

Abstract:

There on a constant rise in the availability of high volumes of data gathered from multiple sources, resulting in an abundance of unprocessed information that can be used to monitor patterns and trends in user behaviour. Similarly, year after year, Malta is also constantly experiencing ongoing population growth and an increase in mobilization demand. This research takes advantage of data which is continuously being sourced and converting it into useful information related to the traffic problem on the Maltese roads. The scope of this paper is to provide a methodology to create a custom dataset (MalTra - Malta Traffic) compiled from multiple participants from various locations across the island to identify the most common routes taken to expose the main areas of activity. This use of big data is seen being used in various technologies and is referred to as ITSs (Intelligent Transportation Systems), which has been concluded that there is significant potential in utilising such sources of data on a nationwide scale. Furthermore, a series of traffic prediction graph neural network models are conducted to compare MalTra to large-scale traffic datasets.

Keywords: graph neural networks, traffic management, big data, mobile data patterns

Procedia PDF Downloads 108

Authors: Jaber H. Almutairi, Hosny Z. Abou-Ziyan, Issa F. Almesri, Mosab A. Alrahmani

Abstract:

The present work investigates the behavior of fluid flow inside tunnel kilns using 3D-CFD (Computational Fluid Dynamics) simulations. The CFD simulations are carried out with the FLUENT software and validated against experimental results on fluid flow and heat transfer in tunnel kilns. A grid dependency study is conducted in the current work to improve the accuracy of the results. Three turbulence models k–ω, standard k–ε, and RNG k–ε are tested where k–ω model gives the best results in comparison with the experiment. The numerical results reveal an intriguing phenomenon where a long flow separation zone behind the setting is observed under different geometric and operation conditions. It was found that the uniformity of flow distribution can be substantially improved by rearranging the geometrical parameters of brick setting relative to kiln/setting. This improvement of flow distribution plays a critical role to enhance the quality and quantity of the production. It can be concluded that a better design and operation of tunnel kilns in terms of productivity and energy consumption can be obtained by taking into consideration the flow uniformity inside the tunnel kilns using CFD modelling.

Keywords: tunnel kilns, flow separation, flow uniformity, computational fluid dynamics

Procedia PDF Downloads 312

Authors: Adeline Meriaux, Claire Gaiani, Jennifer Burgain, Frantz Fournier, Lionel Muniglia, Jérémy Petit

Abstract:

Spray-drying process is widely used for the production of dairy powders for food and pharmaceuticals industries. It involves the atomization of a liquid feed into fine droplets, which are subsequently dried through contact with a hot air flow. The resulting powders permit transportation cost reduction and shelf life increase but can also exhibit various interesting functionalities (flowability, solubility, protein modification or acid gelation), depending on operating conditions and milk composition. Indeed, particles porosity, surface composition, lactose crystallization, protein denaturation, protein association or crust formation may change. Links between spray-drying conditions and physicochemical and functional properties of powders were investigated by a design of experiment methodology and analyzed by principal component analysis. Quadratic models were developed, and multicriteria optimization was carried out by the use of genetic algorithm. At the time of abstract submission, verification spray-drying trials are ongoing. To perform experiments, milk from dairy farm was collected, skimmed, froze and spray-dried at different air pressure (between 1 and 3 bars) and outlet temperature (between 75 and 95 °C). Dry matter, minerals content and proteins content were determined by standard method. Solubility index, absorption index and hygroscopicity were determined by method found in literature. Particle size distribution were obtained by laser diffraction granulometry. Location of the powder color in the Cielab color space and water activity were characterized by a colorimeter and an aw-value meter, respectively. Flow properties were characterized with FT4 powder rheometer; in particular compressibility and shearing test were performed. Air pressure and outlet temperature are key factors that directly impact the drying kinetics and powder characteristics during spray-drying process. It was shown that the air pressure affects the particle size distribution by impacting the size of droplet exiting the nozzle. Moreover, small particles lead to more cohesive powder and less saturated color of powders. Higher outlet temperature results in lower moisture level particles which are less sticky and can explain a spray-drying yield increase and the higher cohesiveness; it also leads to particle with low water activity because of the intense evaporation rate. However, it induces a high hygroscopicity, thus, powders tend to get wet rapidly if they are not well stored. On the other hand, high temperature provokes a decrease of native serum proteins which is positively correlated to gelation properties (gel point and firmness). Partial denaturation of serum proteins can improve functional properties of powder. The control of air pressure and outlet temperature during the spray-drying process significantly affects the physicochemical and functional properties of powder. This study permitted to better understand the links between physicochemical and functional properties of powder, to identify correlations between air pressure and outlet temperature. Therefore, mathematical models have been developed and the use of genetic algorithm will allow the optimization of powder functionalities.

Keywords: dairy powders, spray-drying, powders functionalities, design of experiment

Procedia PDF Downloads 65

Authors: Gu Dongxing, Li Yuxuan, Nong Tengxiao, Burra Venkata Durga Kumar

Abstract:

Since computers are widely used in business models, more and more companies choose to store important information in computers to improve productivity. However, this information can be compromised in many cases, such as when it is stored locally on the company's computers or when it is transferred between servers and clients. Of these important information leaks, source code leaks are probably the most costly. Because the source code often represents the core technology of the company, especially for the Internet companies, source code leakage may even lead to the company's core products lose market competitiveness, and then lead to the bankruptcy of the company. In recent years, such as Microsoft, AMD and other large companies have occurred source code leakage events, suffered a huge loss. This reveals to us the importance and necessity of preventing source code leakage. This paper aims to find ways to prevent source code leakage based on the direction of operating system, and based on the fact that most companies use Linux or Linux-like system to realize the interconnection between server and client, to discuss how to reduce the possibility of source code leakage during data transmission.

Keywords: data transmission, Linux, source code, operating system

Procedia PDF Downloads 237

Authors: Dirk Zapf, Bastian Leuger

Abstract:

For several years, natural gas and crude oil have been stored in salt caverns in Germany and also worldwide. The dimensioning concepts have been continuously developed from a rock mechanics point of view. In addition to the possibilities of realizing large numerical calculation models based on real survey data nowadays, especially the consideration of mechanical processes such as damage and healing played a role in the development of adequate material laws. In addition, thermodynamic aspects have had to be considered for some years in the operation of a gas storage cavern since temperature changes have a significant influence on the stress states in the vicinity of a storage cavern. The possibility of thermally induced fracturing processes is also investigated in the context of rock mechanics dimensioning. In recent years, the energy crisis and the finite nature of fossil fuel use have led to increased discussion of the use of salt caverns for hydrogen storage. In this paper, state of the art is presented, the current research work is described, and an outlook is given as to which questions still need to be answered from a rock mechanics point of view in connection with large-scale storage of hydrogen in salt caverns.

Keywords: cavern design, hydrogen, rock salt, thermomechanical coupled calculations

Procedia PDF Downloads 91

Authors: Aristeidis Samitas, Evangelos Vasileiou

Abstract:

The aim of this study is to examine the month and the trading month effect under changing financial trends. We choose the Greek stock market to implement our assumption because there are clear and long term periods of financial growth and recession. Daily financial data from Athens Exchange General Index for the period 2002-2012 are considered. The paper employs several linear and non-linear models, although the TGARCH asymmetry model best fits in this sample and for this reason we mainly present the TGARCH results. Empirical results show that changing economic and financial conditions influences the calendar effects. Especially, the trading month effect totally changes in each fortnight according to the financial trend. On the other hand, in Greece the January effect exists during the growth periods, although it does not exist when the financial trend changes. The findings are helpful to anybody who invest and deals with the Greek stock market. Moreover, they may pave the way for an alternative calendar anomalies research approach, so it may be useful to investors who take into account these anomalies when they draw their investment strategy.

Keywords: month effect, trading month effect, economic cycles, crisis

Procedia PDF Downloads 402

Authors: S. Perera, T. R. Walsh, M. Solvang

Abstract:

The structure-property relationships of calcium aluminosilicate (CAS) glass surfaces are of scientific and technological interest regarding dissolution phenomena. Molecular dynamics (MD) simulations can provide atomic-scale insights into the structure and properties of the CAS interfaces in vacuo as the first step to conducting computational dissolution studies on CAS surfaces. However, one limitation to date is that although the bulk properties of CAS glasses have been well studied by MD simulation, corresponding efforts on CAS surface properties are relatively few in number (both theoretical and experimental). Here, a systematic computational protocol to create CAS surfaces in vacuo is developed by evaluating the sensitivity of the resultant surface structure with respect to different factors. Factors such as the relative thickness of the surface layer, the relative thickness of the bulk region, the cooling rate, and the annealing schedule (time and temperature) are explored. Structural features such as ring size distribution, defect concentrations (five-coordinated aluminium (AlV), non-bridging oxygen (NBO), and tri-cluster oxygen (TBO)), and linkage distribution are identified as significant features in dissolution studies.

Keywords: MD simulation, CAS glasses, surface structure, structure-property, CAS interface

Procedia PDF Downloads 78

Authors: Farhad Asadi, Mohammad Javad Mollakazemi, Aref Ghafouri

Abstract:

Recent research in neural networks science and neuroscience for modeling complex time series data and statistical learning has focused mostly on learning from high input space and signals. Local linear models are a strong choice for modeling local nonlinearity in data series. Locally weighted projection regression is a flexible and powerful algorithm for nonlinear approximation in high dimensional signal spaces. In this paper, different learning scenario of one and two dimensional data series with different distributions are investigated for simulation and further noise is inputted to data distribution for making different disordered distribution in time series data and for evaluation of algorithm in locality prediction of nonlinearity. Then, the performance of this algorithm is simulated and also when the distribution of data is high or when the number of data is less the sensitivity of this approach to data distribution and influence of important parameter of local validity in this algorithm with different data distribution is explained.

Keywords: local nonlinear estimation, LWPR algorithm, online training method, locally weighted projection regression method

Procedia PDF Downloads 481

Authors: Daniel James Pitchforth, Timothy James Rogers, Ulf Tyge Tygesen, Elizabeth Jane Cross

Abstract:

Wave loading is a primary cause of fatigue within offshore structures and its quantification presents a challenging and important subtask within the SHM framework. The accurate representation of physics in such environments is difficult, however, driving the development of data-driven techniques in recent years. Within many industrial applications, empirical laws remain the preferred method of wave loading prediction due to their low computational cost and ease of implementation. This paper aims to develop an approach that combines data-driven Gaussian process models with physical empirical solutions for wave loading, including Morison’s Equation. The aim here is to incorporate physics directly into the covariance function (kernel) of the Gaussian process, enforcing derived behaviors whilst still allowing enough flexibility to account for phenomena such as vortex shedding, which may not be represented within the empirical laws. The combined approach has a number of advantages, including improved performance over either component used independently and interpretable hyperparameters.

Keywords: offshore structures, Gaussian processes, Physics informed machine learning, Kernel design

Procedia PDF Downloads 170