Search results for: propagation models

Authors: Mohammad Abu-Taleb

Abstract:

The final report of the Royal Commission into Australian financial services misconduct, released in February 2019, has had a significant impact on the financial advice industry. The recommendations released in the Commissioner’s final report include changes to ongoing fee arrangements, a new disciplinary system for financial advisers, and mandatory reporting of compliance concerns. This thesis aims to explore the impact of the Royal Commission’s recommendations on the operating model of financial advice firms in terms of advice products, processes, delivery models, and customer segments. Also, this research seeks to investigate whether the Royal Commission’s outcome has accelerated the use of enhanced technology solutions within the operating model of financial advice firms. And to identify the key challenges confronting financial advice firms whilst implementing the Commissioner’s recommendations across their operating models. In order to achieve the objectives of this thesis, a qualitative research design has been adopted through semi-structured in-depth interviews with 24 financial advisers and managers who are engaged in the operation of financial advice services. The study used the thematic analysis approach to interpret the qualitative data collected from the interviews. The findings of this thesis reveal that customer-centric operating models will become more prominent across the financial advice industry in response to the Commissioner’s final report. And the Royal Commission’s outcome has accelerated the use of advice technology solutions within the operating model of financial advice firms. In addition, financial advice firms have started more than before using simpler and more automated web-based advice services, which enable financial advisers to provide simple advice in a greater scale, and also to accelerate the use of robo-advice models and digital delivery to mass customers in the long term. Furthermore, the study identifies process and technology changes as, long with technical and interpersonal skills development, as the key challenges encountered financial advice firms whilst implementing the Commissioner’s recommendations across their operating models.

Keywords: hayne royal commission, financial planning advice, operating model, advice products, advice processes, delivery models, customer segments, digital advice solutions

Procedia PDF Downloads 85

Authors: Solopova Olga

Abstract:

The present paper briefly recalls theoretical preconditions for investigating cognitive-discursive models of future in political discourse. The author reviews theories and methods used for strengthening a future focus in this discourse working out two main tools – a model of future and a metaphorical scenario. The paper examines the implications of metaphorical analogies for modeling future in mass media. It argues that metaphor is not merely a rhetorical ornament in the political discourse of media regulation but a conceptual model that legislates and regulates our understanding of future.

Keywords: cognitive approach, future research, political discourse, model, scenario, metaphor

Procedia PDF Downloads 390

Authors: R. Ramesh, M. Y. M. Yunus, K. Ramesh

Abstract:

The study conducted in this research are Viscosities, η, and Densities ,ρ, of 1, 4-dioxane with Bromobenzene at different mole fractions and various temperatures in the atmospheric pressure condition. From experimentations excess volumes, VE, and deviations in viscosities, Δη, of mixtures at infinite dilutions have been obtained. The measured systems exhibited positive values of VmE and negative values of Δη. The binary mixture 1, 4 dioxane + Bromobenzene show positive VE and negative Δη with increasing temperatures. The outcomes clearly indicate that weak interactions present in mixture. It is mainly because of number and position of methyl groups exist in these aromatic hydrocarbons. These measured data tailored to the nonlinear models to derive the binary coefficients. Standard deviations have been considered between the fitted outcomes and the calculated data is helpful deliberate mixing behavior of the binary mixtures. It can conclude that in our cases, the data found with the values correlated by the corresponding models very well. The molecular interactions existing between the components and comparison of liquid mixtures were also discussed.

Keywords: 1, 4 dioxane, bromobenzene, density, excess molar volume

Procedia PDF Downloads 411

Authors: Rajendra Kumar Dubey

Abstract:

Einstein’s field equations with variable cosmological term Λ are considered in the presence of viscous fluid for Bianchi type I space time. Exact solutions of Einstein’s field equations are obtained by assuming cosmological term Λ Proportional to (R is a scale factor and m is constant). We observed that the shear viscosity is found to be responsible for faster removal of initial anisotropy in the universe. The physical significance of the cosmological models has also been discussed.

Keywords: bianchi type, I cosmological model, viscous fluid, cosmological constant Λ

Procedia PDF Downloads 527

Authors: Mounia El Hafyani, Khalid El Himdi

Abstract:

Precipitation is one of the key variables in water resource planning. The importance of modeling wet and dry durations is a crucial pointer in engineering hydrology. The objective of this study is to model and analyze the distribution of wet and dry durations. For this purpose, the daily rainfall data from 1967 to 2017 of the Moroccan city of Kenitra’s station are used. Three models are implemented for the distribution of wet and dry durations, namely the first-order Markov chain, the second-order Markov chain, and the truncated negative binomial law. The adherence of the data to the proposed models is evaluated using Chi-square and Kolmogorov-Smirnov tests. The Akaike information criterion is applied to assess the most effective model distribution. We go further and study the law of the number of wet and dry days among k consecutive days. The calculation of this law is done through an algorithm that we have implemented based on conditional laws. We complete our work by comparing the observed moments of the numbers of wet/dry days among k consecutive days to the calculated moment of the three estimated models. The study shows the effectiveness of our approach in modeling wet and dry durations of daily precipitation.

Keywords: Markov chain, rainfall, truncated negative binomial law, wet and dry durations

Procedia PDF Downloads 124

Authors: Jamal A. Hassan, Ali Q. Abdulrazzaq, Sadiq J. Abass

Abstract:

In this study, both the photoelastic, as well as the finite element methods, are used to study the stress distribution within human vertebra (L4) under forces similar to those that occur during normal life. Two & three dimensional models of vertebra were created by the software AutoCAD. The coordinates obtained were fed into a computer numerical control (CNC) tensile machine to fabricate the models from photoelastic sheets. Completed models were placed in a transmission polariscope and loaded with static force (up to 1500N). Stresses can be quantified and localized by counting the number of fringes. In both methods the Principle stresses were calculated at different regions. The results noticed that the maximum von-mises stress on the area of the extreme superior vertebral body surface and the facet surface with high normal stress (σ) and shear stress (τ). The facets and other posterior elements have a load-bearing function to help support the weight of the upper body and anything that it carries, and are also acted upon by spinal muscle forces. The numerical FE results have been compared with the experimental method using photoelasticity which shows good agreement between experimental and simulation results.

Keywords: photoelasticity, stress, load, finite element

Procedia PDF Downloads 285

Authors: Zukhrof Romadhon, Nani Kurniati

Abstract:

Availability of Spare parts is critical to support maintenance tasks and the production system. Managing spare part inventory deals with some parameters and objective functions, as well as the tradeoff between inventory costs and spare parts availability. Several mathematical models and methods have been developed to optimize the spare part policy. Many researchers who proposed optimization models need to be considered to identify other potential models. This work presents a review of several pertinent literature on spare part inventory optimization and analyzes the gaps for future research. Initial investigation on scholars and many journal database systems under specific keywords related to spare parts found about 17K papers. Filtering was conducted based on five main aspects, i.e., replenishment policy, objective function, echelon network, lead time, model solving, and additional aspects of part classification. Future topics could be identified based on the number of papers that haven’t addressed specific aspects, including joint optimization of spare part inventory and maintenance.

Keywords: spare part, spare part inventory, inventory model, optimization, maintenance

Procedia PDF Downloads 61

Authors: Yoonsuh Jung

Abstract:

As DNA microarray data contain relatively small sample size compared to the number of genes, high dimensional models are often employed. In high dimensional models, the selection of tuning parameter (or, penalty parameter) is often one of the crucial parts of the modeling. Cross-validation is one of the most common methods for the tuning parameter selection, which selects a parameter value with the smallest cross-validated score. However, selecting a single value as an "optimal" value for the parameter can be very unstable due to the sampling variation since the sample sizes of microarray data are often small. Our approach is to choose multiple candidates of tuning parameter first, then average the candidates with different weights depending on their performance. The additional step of estimating the weights and averaging the candidates rarely increase the computational cost, while it can considerably improve the traditional cross-validation. We show that the selected value from the suggested methods often lead to stable parameter selection as well as improved detection of significant genetic variables compared to the tradition cross-validation via real data and simulated data sets.

Keywords: cross validation, parameter averaging, parameter selection, regularization parameter search

Procedia PDF Downloads 413

Authors: Zhaoan Wang

Abstract:

Research in predictive maintenance modeling has improved in the recent years to predict failures and needed maintenance with high accuracy, saving cost and improving manufacturing efficiency. However, classic prediction models provide little valuable insight towards the most important features contributing to the failure. By analyzing and quantifying feature importance in predictive maintenance models, cost saving can be optimized based on business goals. First, multiple classifiers are evaluated with cross-validation to predict the multi-class of failures. Second, predictive performance with features provided by different feature selection algorithms are further analyzed. Third, features selected by different algorithms are ranked and combined based on their predictive power. Finally, linear explainer SHAP (SHapley Additive exPlanations) is applied to interpret classifier behavior and provide further insight towards the specific roles of features in both local predictions and global model behavior. The results of the experiments suggest that certain features play dominant roles in predictive models while others have significantly less impact on the overall performance. Moreover, for multi-class prediction of machine failures, the most important features vary with type of machine failures. The results may lead to improved productivity and cost saving by prioritizing sensor deployment, data collection, and data processing of more important features over less importance features.

Keywords: automated supply chain, intelligent manufacturing, predictive maintenance machine learning, feature engineering, model interpretation

Procedia PDF Downloads 131

Authors: Yungtai Lo

Abstract:

Two-part random effects models have been used to fit semi-continuous longitudinal data where the response variable has a point mass at 0 and a continuous right-skewed distribution for positive values. We review methods proposed in the literature for analyzing data with excess zeros. A two-part logit-log-normal random effects model, a two-part logit-truncated normal random effects model, a two-part logit-gamma random effects model, and a two-part logit-skew normal random effects model were used to examine effects of a bottle-weaning intervention on reducing bottle use and daily milk intake from bottles in toddlers aged 11 to 13 months in a randomized controlled trial. We show in all four two-part models that the intervention promoted bottle-weaning and reduced daily milk intake from bottles in toddlers drinking from a bottle. We also show that there are no differences in model fit using either the logit link function or the probit link function for modeling the probability of bottle-weaning in all four models. Furthermore, prediction accuracy of the logit or probit link function is not sensitive to the distribution assumption on daily milk intake from bottles in toddlers not off bottles.

Keywords: two-part model, semi-continuous variable, truncated normal, gamma regression, skew normal, Pearson residual, receiver operating characteristic curve

Procedia PDF Downloads 348

Authors: Sebastian Kohlstädt, Michael Vynnycky, Stephan Goeke, Jan Jäckel, Andreas Gebauer-Teichmann

Abstract:

This paper summarizes the progress in the latest computational fluid dynamics research towards the modeling in of lost core viability in high-pressure die casting. High-pressure die casting is a process that is widely employed in the automotive and neighboring industries due to its advantages in casting quality and cost efficiency. The degrees of freedom are however somewhat limited as it has been so far difficult to use lost cores in the process. This is right now changing and the deployment of lost cores is considered a future growth potential for high-pressure die casting companies. The use of this technology itself is difficult though. The strength of the core material, as chiefly salt is used, is limited and experiments have shown that the cores will not hold under all circumstances and process designs. For this purpose, the publicly available CFD library foam-extend (OpenFOAM) is used, and two additional fluid models for incompressible and compressible two-phase flow are implemented as fluid solver models into the FSI library. For this purpose, the volume-of-fluid (VOF) methodology is used. The necessity for the fluid-structure interaction (FSI) approach is shown by a simple CFD model geometry. The model is benchmarked against analytical models and experimental data. Sufficient agreement is found with the analytical models and good agreement with the experimental data. An outlook on future developments concludes the paper.

Keywords: CFD, fluid-structure interaction, high-pressure die casting, multiphase flow

Procedia PDF Downloads 331

Authors: Bikis Muhammed, Sehra Sedigh Sarvestani, Ali R. Hurson, Lasanthi Gamage

Abstract:

Vehicular traffic events have overly complex spatial correlations and temporal interdependencies and are also influenced by environmental events such as weather conditions. To capture these spatial and temporal interdependencies and make more realistic vehicular traffic predictions, graph neural networks (GNN) based traffic prediction models have been extensively utilized due to their capability of capturing non-Euclidean spatial correlation very effectively. However, most of the already existing GNN-based traffic prediction models have some limitations during learning complex and dynamic spatial and temporal patterns due to the following missing factors. First, most GNN-based traffic prediction models have used static distance or sometimes haversine distance mechanisms between spatially separated traffic observations to estimate spatial correlation. Secondly, most GNN-based traffic prediction models have not incorporated environmental events that have a major impact on the normal traffic states. Finally, most of the GNN-based models did not use an attention mechanism to focus on only important traffic observations. The objective of this paper is to study and make real-time vehicular traffic predictions while incorporating the effect of weather conditions. To fill the previously mentioned gaps, our prediction model uses a real-time driving distance between sensors to build a distance matrix or spatial adjacency matrix and capture spatial correlation. In addition, our prediction model considers the effect of six types of weather conditions and has an attention mechanism in both spatial and temporal data aggregation. Our prediction model efficiently captures the spatial and temporal correlation between traffic events, and it relies on the graph attention network (GAT) and Bidirectional bidirectional long short-term memory (Bi-LSTM) plus attention layers and is called GAT-BILSTMA.

Keywords: deep learning, real time prediction, GAT, Bi-LSTM, attention

Procedia PDF Downloads 70

Authors: John Sweeney, Martin Leeming, Raj Thaker, Cristina L. Tuinea-Bobe

Abstract:

Shrink wrapping is widely used as a method for secondary packaging to assemble individual items, such as cans or other consumer products, into single packages. This method involves conveying the packages into heated tunnels and so has the disadvantages that it is energy-intensive, and, in the case of aerosol products, potentially hazardous. We are developing an automated packaging system that uses stretch wrapping to address both these problems, by using a mechanical rather than a thermal process. In this study, we present a comparative study of shrink wrapping and stretch wrapping materials to assess the relative capability of candidate stretch wrap polymer film in terms of mechanical response. The stretch wrap materials are of oriented polymer and therefore elastically anisotropic. We are developing material constitutive models that include both anisotropy and nonlinearity. These material models are to be incorporated into computer simulations of the automated stretch wrapping system. We present results showing the validity of these models and the feasibility of applying them in the simulations.

Keywords: constitutive model, polymer, mechanical testing, wrapping system

Procedia PDF Downloads 292

Authors: Hami Ashraf, Farid Kosari

Abstract:

Graft-versus-host disease (GvHD) is a common complication of allogeneic hematopoietic stem cell transplantation that can lead to significant morbidity and mortality. Histopathological examination of affected tissues is an essential tool for diagnosing and grading GvHD in animal models, which are used to study disease mechanisms and evaluate new therapies. In this systematic review, we identified and analyzed original research articles in PubMed, Scopus, Web of Science, and Google Scholar that described grading systems for GvHD in animal models based on histopathological features. We found that several grading systems have been developed, which vary in the tissues and criteria they assess, the severity scoring scales they use, and the level of detail they provide. Skin, liver, and gut are the most commonly evaluated tissues, but lung and thymus are also included in some systems. Our analysis highlights the need for standardized criteria and consistent use of grading systems to enable comparisons between studies and facilitate the translation of preclinical findings to clinical practice.

Keywords: graft-versus-host disease, GvHD, animal model, histopathology, grading system

Procedia PDF Downloads 63

Authors: Aleksandra Dudkowska, Gabriela Gic-Grusza

Abstract:

Wind wave-induced sediment transport is an important multidimensional and multiscale dynamic process affecting coastal seabed changes and coastline evolution. The knowledge about sediment transport rate is important to solve many environmental and geotechnical issues. There are many types of sediment transport models but none of them is widely accepted. It is bacause the process is not fully defined. Another problem is a lack of sufficient measurment data to verify proposed hypothesis. There are different types of models for longshore sediment transport (LST, which is discussed in this work) and cross-shore transport which is related to different time and space scales of the processes. There are models describing bed-load transport (discussed in this work), suspended and total sediment transport. LST models use among the others the information about (i) the flow velocity near the bottom, which in case of wave-currents interaction in coastal zone is a separate problem (ii) critical bed shear stress that strongly depends on the type of sediment and complicates in the case of heterogeneous sediment. Moreover, LST rate is strongly dependant on the local environmental conditions. To organize existing knowledge a series of sediment transport models intercomparisons was carried out as a part of the project “Development of a predictive model of morphodynamic changes in the coastal zone”. Four classical one-grid-point models were studied and intercompared over wide range of bottom shear stress conditions, corresponding with wind-waves conditions appropriate for coastal zone in polish marine areas. The set of models comprises classical theories that assume simplified influence of turbulence on the sediment transport (Du Boys, Meyer-Peter & Muller, Ribberink, Engelund & Hansen). It turned out that the values of estimated longshore instantaneous mass sediment transport are in general in agreement with earlier studies and measurements conducted in the area of interest. However, none of the formulas really stands out from the rest as being particularly suitable for the test location over the whole analyzed flow velocity range. Therefore, based on the models discussed a new unified formula for longshore sediment transport rate estimation is introduced, which constitutes the main original result of this study. Sediment transport rate is calculated based on the bed shear stress and critical bed shear stress. The dependence of environmental conditions is expressed by one coefficient (in a form of constant or function) thus the model presented can be quite easily adjusted to the local conditions. The discussion of the importance of each model parameter for specific velocity ranges is carried out. Moreover, it is shown that the value of near-bottom flow velocity is the main determinant of longshore bed-load in storm conditions. Thus, the accuracy of the results depends less on the sediment transport model itself and more on the appropriate modeling of the near-bottom velocities.

Keywords: bedload transport, longshore sediment transport, sediment transport models, coastal zone

Procedia PDF Downloads 385

Authors: H. Namazi, H. T. N. Kuan

Abstract:

It is known that in humans, the adaptation to a given odor occurs within a quite short span of time (typically one minute) after the odor is presented to the brain. Different models of human olfaction have been developed by scientists but none of these models consider the diffusion phenomenon in olfaction. A novel microscopic model of the human olfaction is presented in this paper. We develop this model by incorporating the transient diffusivity. In fact, the mathematical model is written based on diffusion of the odorant within the mucus layer. By the use of the model developed in this paper, it becomes possible to provide quantification of the objective strength of odor.

Keywords: diffusion, microscopic model, mucus layer, olfaction

Procedia PDF Downloads 504

Authors: Vemula Amalakrishna, S. Pushpavanam

Abstract:

Change and motion characterize and persistently reshape the world around us, on scales from molecular to global. The subtle interplay between change (Reaction) and motion (Diffusion) gives rise to an astonishing intricate spatial or temporal pattern. These pattern formation in nature has been intellectually appealing for many scientists since antiquity. Periodic precipitation patterns, also known as Liesegang patterns (LP), are one of the stimulating examples of such self-assembling reaction-diffusion (RD) systems. LP formation has a great potential in micro and nanotechnology. So far, the research on LPs has been concentrated mostly on how these patterns are forming, retrieving information to build a universal mathematical model for them. Researchers have developed various theoretical models to comprehensively construct the geometrical diversity of LPs. To the best of our knowledge, simulation studies of LPs assume an arbitrary value of RD parameters to explain experimental observation qualitatively. In this work, existing models were studied to understand the mechanism behind this phenomenon and challenges pertaining to models were understood and explained. These models are not computationally effective due to the presence of discontinuous precipitation rate in RD equations. To overcome the computational challenges, smoothened Heaviside functions have been introduced, which downsizes the computational time as well. Experiments were performed using a conventional LP system (AgNO₃-K₂Cr₂O₇) to understand the effects of different gels and temperatures on formed LPs. The model is extended for real parameter values to compare the simulated results with experimental data for both 1-D (Cartesian test tubes) and 2-D(cylindrical and Petri dish).

Keywords: reaction-diffusion, spatio-temporal patterns, nucleation and growth, supersaturation

Procedia PDF Downloads 151

Authors: Mohamed Amine Ben Henni, Taher Hassaine Daouadji, Boussad Abbes, Yu Ming Li, Fazilay Abbes

Abstract:

The reinforcement and repair of concrete structures by bonding composite materials have become relatively common operations. Different types of composite materials can be used: carbon fiber reinforced polymer (CFRP), glass fiber reinforced polymer (GFRP) as well as functionally graded material (FGM). The development of analytical and numerical models describing the mechanical behavior of structures in civil engineering reinforced by composite materials is necessary. These models will enable engineers to select, design, and size adequate reinforcements for the various types of damaged structures. This study focuses on the free vibration behavior of orthotropic laminated composite plates using a refined shear deformation theory. In these models, the distribution of transverse shear stresses is considered as parabolic satisfying the zero-shear stress condition on the top and bottom surfaces of the plates without using shear correction factors. In this analysis, the equation of motion for simply supported thick laminated rectangular plates is obtained by using the Hamilton’s principle. The accuracy of the developed model is demonstrated by comparing our results with solutions derived from other higher order models and with data found in the literature. Besides, a finite-element analysis is used to calculate the natural frequencies of laminated composite plates and is compared with those obtained by the analytical approach.

Keywords: composites materials, laminated composite plate, finite-element analysis, free vibration

Procedia PDF Downloads 290

Authors: Promise Ekpo Osaine, Daniel Melesse

Abstract:

Image captioning is an active area of research in the multi-modal artificial intelligence (AI) community as it connects vision and language understanding, especially in settings where it is required that a model understands the content shown in an image and generates semantically and grammatically correct descriptions. In this project, we followed a standard approach to a deep learning-based image captioning model, injecting architecture for the encoder-decoder setup, where the encoder extracts image features, and the decoder generates a sequence of words that represents the image content. As such, we investigated image encoders, which are ResNet101, InceptionResNetV2, EfficientNetB7, EfficientNetV2M, and CLIP. As a caption generation structure, we explored long short-term memory (LSTM). The CLIP-LSTM model demonstrated superior performance compared to the encoder-decoder models, achieving a BLEU-1 score of 0.904 and a BLEU-4 score of 0.640. Additionally, among the CNN-LSTM models, EfficientNetV2M-LSTM exhibited the highest performance with a BLEU-1 score of 0.896 and a BLEU-4 score of 0.586 while using a single-layer LSTM.

Keywords: multi-modal AI systems, image captioning, encoder, decoder, BLUE score

Procedia PDF Downloads 74

Authors: Adetunji Abiola Olaoye

Abstract:

The study examined the students’ self-concepts and mathematics achievement viz-a-viz the existing three theoretical models: Humanist self-concept (M1), Contemporary self-concept (M2) and Skills development self-concept (M3). As a qualitative research study, it comprised of one research question, which was transformed into hypothesis viz-a-viz the existing theoretical models. Sample to the study comprised of twelve public secondary schools from which twenty-five mathematics teachers, twelve counselling officers and one thousand students of Upper Basic II were selected based on intact class as school administrations and system did not allow for randomization. Two instruments namely 10 items ‘Achievement test in Mathematics’ (r1=0.81) and 10 items Student’s self-concept questionnaire (r2=0.75) were adapted, validated and used for the study. Data were analysed through descriptive, one way ANOVA, t-test and correlation statistics at 5% level of significance. Finding revealed mean and standard deviation of pre-achievement test scores of (51.322, 16.10), (54.461, 17.85) and (56.451, 18.22) for the Humanist Self-Concept, Contemporary Self-Concept and Skill Development Self-Concept respectively. Apart from that study showed that there was significant different in the academic performance of students along the existing models (F-cal>F-value, df = (2,997); P<0.05). Furthermore, study revealed students’ achievement in mathematics and self-concept questionnaire with the mean and standard deviation of (57.4, 11.35) and (81.6, 16.49) respectively. Result confirmed an affirmative relationship with the Contemporary Self-Concept model that expressed an individual subject and specific self-concept as the primary determinants of higher academic achievement in the subject as there is a statistical correlation between students’ self-concept and mathematics achievement viz-a-viz the existing three theoretical models of Contemporary (M2) with -Z_cal<-Z_val, df=998: P<0.05*. The implication of the study was discussed with recommendations and suggestion for further studies proffered.

Keywords: contemporary, humanists, self-concepts, skill development

Procedia PDF Downloads 236

Authors: Jianhua Wang

Abstract:

To obtain key information quickly from long texts on small screens of mobile devices, sight-interpreters need to establish optimized summarization model for fast information retrieval. Four summarization models based on previous studies were studied including title+key words (TKW), title+topic sentences (TTS), key words+topic sentences (KWTS) and title+key words+topic sentences (TKWTS). Psychological experiments were conducted on the four models for three different genres of interpreting texts to establish the optimized summarization model for sight-interpreters. This empirical study shows that the optimized summarization model for sight-interpreters to quickly grasp the key information of the texts they interpret is title+key words (TKW) for cultural texts, title+key words+topic sentences (TKWTS) for economic texts and topic sentences+key words (TSKW) for political texts.

Keywords: different genres, mobile screens, optimized summarization models, sight-interpreters

Procedia PDF Downloads 313

Authors: Amreth Chandrasehar

Abstract:

Machine Learning (ML) Models are developed and run in production to solve various use cases that help organizations to be more efficient and help drive the business. But this comes at a massive development cost and lost business opportunities. According to the Gartner report, 85% of data science projects fail, and one of the factors impacting this is not paying attention to Model Observability. Model Observability helps the developers and operators to pinpoint the model performance issues data drift and help identify root cause of issues. This paper focuses on providing insights into incorporating model observability in model development and operationalizing it in production.

Keywords: model observability, monitoring, drift detection, ML observability platform

Procedia PDF Downloads 110

Authors: Altaf H. Khan, Frank Stenger, Mohammed A. Hussein, Reaz A. Chaudhuri, Sameera Asif

Abstract:

This paper discusses a novel approach to approximate quadrature integrals that arise in the estimation of likelihood parameters for the generalized linear mixed models (GLMM) as well as Bayesian methodology also requires computation of multidimensional integrals with respect to the posterior distributions in which computation are not only tedious and cumbersome rather in some situations impossible to find solutions because of singularities, irregular domains, etc. An attempt has been made in this work to apply Sinc function based quadrature rules to approximate intractable integrals, as there are several advantages of using Sinc based methods, for example: order of convergence is exponential, works very well in the neighborhood of singularities, in general quite stable and provide high accurate and double precisions estimates. The Sinc function based approach seems to be utilized first time in statistical domain to our knowledge, and it's viability and future scopes have been discussed to apply in the estimation of parameters for GLMM models as well as some other statistical areas.

Keywords: generalized linear mixed model, likelihood parameters, qudarature, Sinc function

Procedia PDF Downloads 393

Authors: Pedro M. Abreu, Bruno R. Mendes

Abstract:

The management of pharmacotherapy and the process of dispensing medicines is becoming critical in clinical pharmacy due to the increase of incidence and prevalence of chronic diseases, the complexity and customization of therapeutic regimens, the introduction of innovative and more expensive medicines, the unbalanced relation between expenditure and revenue as well as due to the lack of rationalization associated with medication use. For these reasons, co-payments emerged in Europe in the 70s and have been applied over the past few years in healthcare. Co-payments lead to a rationing and rationalization of user’s access under healthcare services and products, and simultaneously, to a qualification and improvement of the services and products for the end-user. This analysis, under hospital practices particularly and co-payment strategies in general, was carried out on all the European regions and identified four reference countries, that apply repeatedly this tool and with different approaches. The structure, content and adaptation of European co-payments were analyzed through 7 qualitative attributes and 19 performance indicators, and the results expressed in a scorecard, allowing to conclude that the German models (total score of 68,2% and 63,6% in both elected co-payments) can collect more compliance and effectiveness, the English models (total score of 50%) can be more accessible, and the French models (total score of 50%) can be more adequate to the socio-economic and legal framework. Other European models did not show the same quality and/or performance, so were not taken as a standard in the future design of co-payments strategies. In this sense, we can see in the co-payments a strategy not only to moderate the consumption of healthcare products and services, but especially to improve them, as well as a strategy to increment the value that the end-user assigns to these services and products, such as medicines.

Keywords: clinical pharmacy, co-payments, healthcare, medicines

Procedia PDF Downloads 250

Authors: Uduak Umoh, Imo Eyoh, Emmauel Nyoho

Abstract:

This paper compares fuzzy-machine learning algorithms such as Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) for the predicting cases of fire outbreak. The paper uses the fire outbreak dataset with three features (Temperature, Smoke, and Flame). The data is pre-processed using Interval Type-2 Fuzzy Logic (IT2FL) algorithm. Min-Max Normalization and Principal Component Analysis (PCA) are used to predict feature labels in the dataset, normalize the dataset, and select relevant features respectively. The output of the pre-processing is a dataset with two principal components (PC1 and PC2). The pre-processed dataset is then used in the training of the aforementioned machine learning models. K-fold (with K=10) cross-validation method is used to evaluate the performance of the models using the matrices – ROC (Receiver Operating Curve), Specificity, and Sensitivity. The model is also tested with 20% of the dataset. The validation result shows KNN is the better model for fire outbreak detection with an ROC value of 0.99878, followed by SVM with an ROC value of 0.99753.

Keywords: Machine Learning Algorithms , Interval Type-2 Fuzzy Logic, Fire Outbreak, Support Vector Machine, K-Nearest Neighbour, Principal Component Analysis

Procedia PDF Downloads 179

Authors: Mohammed Nasser Al-Suqri

Abstract:

Former information-seeking models are proposed more than two decades ago. These already existed models were given prior to the evolution of digital information era and Artificial Intelligence (AI) technologies. Lack of current information seeking models within Library and Information Studies resulted in fewer advancements for teaching students about information-seeking behaviors, design of library tools and services. In order to better facilitate the aforementioned concerns, this study aims to propose state-of-the-art model while focusing on the information seeking behavior of library users in the Sultanate of Oman. This study aims for the development, designing and contextualizing the real-time user-centric information seeking model capable of enhancing information needs and information usage along with incorporating critical insights for the digital library practices. Another aim is to establish far-sighted and state-of-the-art frame of reference covering Artificial Intelligence (AI) while synthesizing digital resources and information for optimizing information-seeking behavior. The proposed study is empirically designed based on a mix-method process flow, technical surveys, in-depth interviews, focus groups evaluations and stakeholder investigations. The study data pool is consist of users and specialist LIS staff at 4 public libraries and 26 academic libraries in Oman. The designed research model is expected to facilitate LIS by assisting multi-dimensional insights with AI integration for redefining the information-seeking process, and developing a technology rich model.

Keywords: artificial intelligence, information seeking, information behavior, information seeking models, libraries, Sultanate of Oman

Procedia PDF Downloads 115

Authors: H. Hruschka

Abstract:

This paper presents the first comparison of the performance of the restricted Boltzmann machine and the deep belief net on binary market basket data relative to binary factor analysis and the two best-known topic models, namely Dirichlet allocation and the correlated topic model. This comparison shows that the restricted Boltzmann machine and the deep belief net are superior to both binary factor analysis and topic models. Managerial implications that differ between the investigated models are treated as well. The restricted Boltzmann machine is defined as joint Boltzmann distribution of hidden variables and observed variables (purchases). It comprises one layer of observed variables and one layer of hidden variables. Note that variables of the same layer are not connected. The comparison also includes deep belief nets with three layers. The first layer is a restricted Boltzmann machine based on category purchases. Hidden variables of the first layer are used as input variables by the second-layer restricted Boltzmann machine which then generates second-layer hidden variables. Finally, in the third layer hidden variables are related to purchases. A public data set is analyzed which contains one month of real-world point-of-sale transactions in a typical local grocery outlet. It consists of 9,835 market baskets referring to 169 product categories. This data set is randomly split into two halves. One half is used for estimation, the other serves as holdout data. Each model is evaluated by the log likelihood for the holdout data. Performance of the topic models is disappointing as the holdout log likelihood of the correlated topic model – which is better than Dirichlet allocation - is lower by more than 25,000 compared to the best binary factor analysis model. On the other hand, binary factor analysis on its own is clearly surpassed by both the restricted Boltzmann machine and the deep belief net whose holdout log likelihoods are higher by more than 23,000. Overall, the deep belief net performs best. We also interpret hidden variables discovered by binary factor analysis, the restricted Boltzmann machine and the deep belief net. Hidden variables characterized by the product categories to which they are related differ strongly between these three models. To derive managerial implications we assess the effect of promoting each category on total basket size, i.e., the number of purchased product categories, due to each category's interdependence with all the other categories. The investigated models lead to very different implications as they disagree about which categories are associated with higher basket size increases due to a promotion. Of course, recommendations based on better performing models should be preferred. The impressive performance advantages of the restricted Boltzmann machine and the deep belief net suggest continuing research by appropriate extensions. To include predictors, especially marketing variables such as price, seems to be an obvious next step. It might also be feasible to take a more detailed perspective by considering purchases of brands instead of purchases of product categories.

Keywords: binary factor analysis, deep belief net, market basket analysis, restricted Boltzmann machine, topic models

Procedia PDF Downloads 199

Authors: Huijuan Liu, Fukun Li, Hao Yuan

Abstract:

The bolted spherical node is a common type of joint in space steel structures. The bolt-sphere joint portion almost always controls the bearing capacity of the bolted spherical node. The investigation of the bearing performance and progressive failure in service often requires high-fidelity numerical models. This paper focuses on the constitutive models of bolt steel and sphere steel used in China’s space structure construction. The elastoplastic model is determined by a standard tensile test and calibrated Voce saturated hardening rule. The ductile damage is found dominant based on the fractography analysis. Then Rice-Tracey ductile fracture rule is selected and the model parameters are calibrated based on tensile tests of notched specimens. These calibrated material models can benefit research or engineering work in similar fields.

Keywords: bolt-sphere joint, steel, constitutive model, ductile damage, model calibration

Procedia PDF Downloads 135

Authors: Avinoam Rabinovich

Abstract:

CO₂ geological storage is a proven technology for reducing anthropogenic carbon emissions, which is paramount for achieving the ambitious net zero emissions goal. Core flooding experiments are an important step in any CO₂ storage project, allowing us to gain information on the flow of CO₂ and brine in the porous rock extracted from the reservoir. This information is important for understanding basic mechanisms related to CO₂ geological storage as well as for reservoir modeling, which is an integral part of a field project. In this work, a different method for constructing accurate models of CO₂-brine core flooding will be presented. Results for synthetic cases and real experiments will be shown and compared with numerical models to exhibit their predictive capabilities. Furthermore, the various mechanisms which impact the CO₂ distribution and trapping in the rock samples will be discussed, and examples from models and experiments will be provided. The new method entails solving an inverse problem to obtain a three-dimensional permeability distribution which, along with the relative permeability and capillary pressure functions, constitutes a model of the flow experiments. The model is more accurate when data from a number of experiments are combined to solve the inverse problem. This model can then be used to test various other injection flow rates and fluid fractions which have not been tested in experiments. The models can also be used to bridge the gap between small-scale capillary heterogeneity effects (sub-core and core scale) and large-scale (reservoir scale) effects, known as the upscaling problem.

Keywords: CO₂ geological storage, residual trapping, capillary heterogeneity, core flooding, CO₂-brine flow

Procedia PDF Downloads 66

Authors: Dino Carpentras, Alejandro Dinkelberg, Michael Quayle

Abstract:

Opinion dynamics models use an agent-based modeling approach to model people’s opinions. Model's properties are usually explored by testing the two 'degrees of freedom': the interaction rule and the network topology. The latter defines the connection, and thus the possible interaction, among agents. The interaction rule, instead, determines how agents select each other and update their own opinion. Here we show the existence of the third degree of freedom. This can be used for turning one model into each other or to change the model’s output up to 100% of its initial value. Opinion dynamics models represent the evolution of real-world opinions parsimoniously. Thus, it is fundamental to know how real-world opinion (e.g., supporting a candidate) could be turned into a number. Specifically, we want to know if, by choosing a different opinion-to-number transformation, the model’s dynamics would be preserved. This transformation is typically not addressed in opinion dynamics literature. However, it has already been studied in psychometrics, a branch of psychology. In this field, real-world opinions are converted into numbers using abstract objects called 'scales.' These scales can be converted one into the other, in the same way as we convert meters to feet. Thus, in our work, we analyze how this scale transformation may affect opinion dynamics models. We perform our analysis both using mathematical modeling and validating it via agent-based simulations. To distinguish between scale transformation and measurement error, we first analyze the case of perfect scales (i.e., no error or noise). Here we show that a scale transformation may change the model’s dynamics up to a qualitative level. Meaning that a researcher may reach a totally different conclusion, even using the same dataset just by slightly changing the way data are pre-processed. Indeed, we quantify that this effect may alter the model’s output by 100%. By using two models from the standard literature, we show that a scale transformation can transform one model into the other. This transformation is exact, and it holds for every result. Lastly, we also test the case of using real-world data (i.e., finite precision). We perform this test using a 7-points Likert scale, showing how even a small scale change may result in different predictions or a number of opinion clusters. Because of this, we think that scale transformation should be considered as a third-degree of freedom for opinion dynamics. Indeed, its properties have a strong impact both on theoretical models and for their application to real-world data.

Keywords: degrees of freedom, empirical validation, opinion scale, opinion dynamics

Procedia PDF Downloads 154