Search results for: transferability of models

Authors: Touila Ahmed, Elie Louis, Hamza Gharbi

Abstract:

State of the art question answering models have recently shown impressive performance especially in a zero-shot setting. This approach is particularly useful when confronted with a highly diverse domain such as the legal field, in which it is increasingly difficult to have a dataset covering every notion and concept. In this work, we propose a flexible generative question answering approach to contract analysis as well as a weakly supervised procedure to leverage unannotated data and boost our models’ performance in general, and their zero-shot performance in particular.

Keywords: question answering, contract analysis, zero-shot, natural language processing, generative models, self-supervision

Procedia PDF Downloads 194

Authors: Wendy Flory, Kazi Czarnecki, Matthijs Mercy, Mark Joswiak, Mary Beth Seasholtz

Abstract:

Polyurethane Materials are present in a wide range of industrial segments such as Furniture, Building and Construction, Composites, Automotive, Electronics, and more. Dow is one of the leaders for the manufacture of the two main raw materials, Isocyanates and Polyols used to produce polyurethane products. Dow is also a key player for the manufacture of Polyurethane Systems/Formulations designed for targeted applications. In 1990, the first analytical chemometric models were developed and deployed for use in the Dow QC labs of the polyols business for the quantification of OH, water, cloud point, and viscosity. Over the years many models have been added; there are now over 140 models for quantification and hundreds for product identification, too many to be reasonable for support. There are 29 global models alone for the quantification of OH across > 70 products at many sites. An attempt was made to consolidate these into a single model. While the consolidated model proved good statistics across the entire range of OH, several products had a bias by ASTM E1655 with individual product validation. This project summary will show the strategy for global model updates for OH, to reduce the number of models for quantification from over 140 to 5 or less using chemometric methods. In order to gain an understanding of the best product groupings, we identify clusters by reducing spectra to a few dimensions via Principal Component Analysis (PCA) and Uniform Manifold Approximation and Projection (UMAP). Results from these cluster analyses and a separate validation set allowed dow to reduce the number of models for predicting OH from 29 to 3 without loss of accuracy.

Keywords: hydroxyl, global model, model maintenance, near infrared, polyol

Procedia PDF Downloads 135

Authors: Rachel Y. Zhang, Christopher K. Anderson

Abstract:

A critical aspect of revenue management is a firm’s ability to predict demand as a function of price. Historically hotels have used simple time series models (regression and/or pick-up based models) owing to the complexities of trying to build casual models of demands. Machine learning approaches are slowly attracting attention owing to their flexibility in modeling relationships. This study provides an overview of approaches to forecasting hospitality demand – focusing on the opportunities created by machine learning approaches, including K-Nearest-Neighbors, Support vector machine, Regression Tree, and Artificial Neural Network algorithms. The out-of-sample performances of above approaches to forecasting hotel demand are illustrated by using a proprietary sample of the market level (24 properties) transactional data for Las Vegas NV. Causal predictive models can be built and evaluated owing to the availability of market level (versus firm level) data. This research also compares and contrast model accuracy of firm-level models (i.e. predictive models for hotel A only using hotel A’s data) to models using market level data (prices, review scores, location, chain scale, etc… for all hotels within the market). The prospected models will be valuable for hotel revenue prediction given the basic characters of a hotel property or can be applied in performance evaluation for an existed hotel. The findings will unveil the features that play key roles in a hotel’s revenue performance, which would have considerable potential usefulness in both revenue prediction and evaluation.

Keywords: hotel revenue, k-nearest-neighbors, machine learning, neural network, prediction model, regression tree, support vector machine

Procedia PDF Downloads 132

Authors: Omid Shahmirzadi, Adam Lugowski, Kenneth Younge

Abstract:

Automatic measurement of semantic text similarity is an important task in natural language processing. In this paper, we evaluate the performance of different vector space models to perform this task. We address the real-world problem of modeling patent-to-patent similarity and compare TFIDF (and related extensions), topic models (e.g., latent semantic indexing), and neural models (e.g., paragraph vectors). Contrary to expectations, the added computational cost of text embedding methods is justified only when: 1) the target text is condensed; and 2) the similarity comparison is trivial. Otherwise, TFIDF performs surprisingly well in other cases: in particular for longer and more technical texts or for making finer-grained distinctions between nearest neighbors. Unexpectedly, extensions to the TFIDF method, such as adding noun phrases or calculating term weights incrementally, were not helpful in our context.

Keywords: big data, patent, text embedding, text similarity, vector space model

Procedia PDF Downloads 175

Authors: Avichal Malhotra, Jerome Frisch, Christoph van Treeck

Abstract:

The utilization of semantic, cadastral and topological data from geographic information systems (GIS) has exponentially increased for building and urban-scale energy performance simulations. Urban planners, simulation scientists, and researchers use virtual 3D city models for energy analysis, algorithms and simulation tools. For dynamic energy simulations at city and district level, this paper provides an overview of the available GIS data models and their levels of detail. Adhering to different norms and standards, these models also intend to describe building and construction industry data. For further investigations, CityGML data models are considered for simulations. Though geographical information modelling has considerably many different implementations, extensions of virtual city data can also be made for domain specific applications. Highlighting the use of the extended CityGML models for energy researches, a brief introduction to the Energy Application Domain Extension (ADE) along with its significance is made. Consequently, addressing specific input simulation data, a workflow using Modelica underlining the usage of GIS information and the quantification of its significance over annual heating energy demand is presented in this paper.

Keywords: CityGML, EnergyADE, energy performance simulation, GIS

Procedia PDF Downloads 168

Authors: Shaan Khosla, Jon Krohn

Abstract:

In a recruiting context, machine learning models are valuable for recommendations: to predict the best candidates for a vacancy, to match the best vacancies for a candidate, and compile a set of similar candidates for any given candidate. While useful to create these models, validating their accuracy in a recommendation context is difficult due to a sparsity of data. In this report, we use network graph data to generate useful representations for candidates and vacancies. We use candidates and vacancies as network nodes and designate a bi-directional link between them based on the candidate interviewing for the vacancy. After using node2vec, the embeddings are used to construct a validation dataset with a ranked order, which will help validate new recommender systems.

Keywords: AI, machine learning, NLP, recruiting

Procedia PDF Downloads 84

Authors: Katalina Grigorova, Kaloyan Mironov

Abstract:

The paper focuses on the benefits of business process modeling. Although this discipline is developing for many years, there is still necessity of creating new opportunities to meet the ever-increasing users’ needs. Because one of these needs is related to the conversion of business process models from one standard to another, the authors have developed a converter between BPMN and EPC standards using workflow patterns as intermediate tool. Nowadays there are too many systems for business process modeling. The variety of output formats is almost the same as the systems themselves. This diversity additionally hampers the conversion of the models. The presented study is aimed at discussing problems due to differences in the output formats of various modeling environments.

Keywords: business process modeling, business process modeling standards, workflow patterns, converting models

Procedia PDF Downloads 584

Authors: Fatima-Zahra Eddoug, Jamal Benhra, Rajaa Benabbou

Abstract:

Several project management models exist in the literature and the most used ones are the hybrids for their multiple advantages. Our objective in this paper is to analyze the existing models, which are based on the Lean and Agile approaches and to propose a novel framework with the convenient tools that will allow efficient management of a general project. To create the desired framework, we were based essentially on 7 existing models. Only the Scrum tool among the agile tools was identified by several authors to be appropriate for project management. In contrast, multiple lean tools were proposed in different phases of the project.

Keywords: agility, hybrid project management, lean, scrum

Procedia PDF Downloads 138

Authors: Sabiu Bala Muhammad, Rosli Saad

Abstract:

Multiple linear regression (MLR) models for fast estimation of true subsurface resistivity from apparent resistivity field measurements are developed and assessed in this study. The parameters investigated were apparent resistivity (ρₐ), horizontal location (X) and depth (Z) of measurement as the independent variables; and true resistivity (ρₜ) as the dependent variable. To achieve linearity in both resistivity variables, datasets were first transformed into logarithmic domain following diagnostic checks of normality of the dependent variable and heteroscedasticity to ensure accurate models. Four MLR models were developed based on hierarchical combination of the independent variables. The generated MLR coefficients were applied to another data set to estimate ρₜ values for validation. Contours of the estimated ρₜ values were plotted and compared to the observed data plots at the colour scale and blanking for visual assessment. The accuracy of the models was assessed using coefficient of determination (R²), standard error (SE) and weighted mean absolute percentage error (wMAPE). It is concluded that the MLR models can estimate ρₜ for with high level of accuracy.

Keywords: apparent resistivity, depth, horizontal location, multiple linear regression, true resistivity

Procedia PDF Downloads 276

Authors: Milica Ž. Karadžić, Lidija R. Jevrić, Sanja Podunavac-Kuzmanović, Strahinja Z. Kovačević, Anamarija I. Mandić, Katarina Penov-Gaši, Andrea R. Nikolić, Aleksandar M. Oklješa

Abstract:

This study considered selection of the in silico molecular descriptors and the models for newly synthesized steroid derivatives description and their characterization using chemometric techniques. Multiple linear regression (MLR) models were established and gave the best molecular descriptors for quantitative structure-retention relationship (QSRR) modeling of the retention of the investigated molecules. MLR models were without multicollinearity among the selected molecular descriptors according to the variance inflation factor (VIF) values. Used molecular descriptors were ranked using generalized pair correlation method (GPCM). In this method, the significant difference between independent variables can be noticed regardless almost equal correlation between dependent variable. Generated MLR models were statistically and cross-validated and the best models were kept. Models were ranked using sum of ranking differences (SRD) method. According to this method, the most consistent QSRR model can be found and similarity or dissimilarity between the models could be noticed. In this study, SRD was performed using average values of experimentally observed data as a golden standard. Chemometric analysis was conducted in order to characterize newly synthesized steroid derivatives for further investigation regarding their potential biological activity and further synthesis. This article is based upon work from COST Action (CM1105), supported by COST (European Cooperation in Science and Technology).

Keywords: generalized pair correlation method, molecular descriptors, regression analysis, steroids, sum of ranking differences

Procedia PDF Downloads 347

Authors: Navid Daryasafar, Nima Farshidfar

Abstract:

In this article, we make attempt to hide error in video with an emphasis on the time-wise use of autoregressive (AR) models. To resolve this problem, we assume that all information in one or more video frames is lost. Then, lost frames are estimated using analogous Pixels time information in successive frames. Accordingly, after presenting autoregressive models and how they are applied to estimate lost frames, two general methods are presented for using these models. The first method which is the same standard method of autoregressive models estimates lost frame in unidirectional form. Usually, in such condition, previous frames information is used for estimating lost frame. Yet, in the second method, information from the previous and next frames is used for estimating the lost frame. As a result, this method is known as bidirectional estimation. Then, carrying out a series of tests, performance of each method is assessed in different modes. And, results are compared.

Keywords: error steganography, unidirectional estimation, bidirectional estimation, AR linear estimation

Procedia PDF Downloads 538

Authors: Marcel Chevalier, Léo Dupont, Sylvain Marié, Frédérique Roffet, Elena Stolyarova, William Templier, Costin Vasile

Abstract:

Industrial end-users are currently facing an increasing need to reduce the risk of unexpected failures and optimize their maintenance. This calls for both short-term analysis and long-term ageing anticipation. At Schneider Electric, we tackle those two issues using both machine learning and first principles models. Machine learning models are incrementally trained from normal data to predict expected values and detect statistically significant short-term deviations. Ageing models are constructed by breaking down physical systems into sub-assemblies, then determining relevant degradation modes and associating each one to the right kinetic law. Validating such anomaly detection and maintenance models is challenging, both because actual incident and ageing data are rare and distorted by human interventions, and incremental learning depends on human feedback. To overcome these difficulties, we propose to simulate physics, systems, and humans -including asset maintenance operations- in order to validate the overall approaches in accelerated time and possibly choose between algorithmic alternatives.

Keywords: degradation models, ageing, anomaly detection, soft sensor, incremental learning

Procedia PDF Downloads 126

Authors: Jeongmin Kim, Eunju Lee, Kwang Ryel Ryu

Abstract:

This paper addresses the problem of predictive control for energy management of large-scaled exhibition halls, where a lot of energy is consumed to maintain internal atmosphere under certain required conditions. Predictive control achieves better energy efficiency by optimizing the operation of air-conditioning facilities with not only the current but also some future status taken into account. In this paper, we propose to use predictive models learned from past sensor data of hall environment, for use in optimizing the operating plan for the air-conditioning facilities by simulating future environmental change. We have implemented an emulator of an exhibition hall by using EnergyPlus, a widely used building energy emulation tool, to collect data for learning environment-change models. Experimental results show that the learned models predict future change highly accurately on a short-term basis.

Keywords: predictive control, energy management, machine learning, optimization

Procedia PDF Downloads 274

Authors: Nahla H. Alaswadko, Rayya A. Hassan, Bayar N. Mohammed

Abstract:

Empirical deterministic models have been developed to predict roughness progression of heavy duty spray sealed pavements for a dataset representing rural arterial roads. The dataset provides a good representation of the relevant network and covers a wide range of operating and environmental conditions. A sample with a large size of historical time series data for many pavement sections has been collected and prepared for use in multilevel regression analysis. The modelling parameters include road roughness as performance parameter and traffic loading, time, initial pavement strength, reactivity level of subgrade soil, climate condition, and condition of drainage system as predictor parameters. The purpose of this paper is to report the approaches adopted for models development and validation. The study presents multilevel models that can account for the correlation among time series data of the same section and to capture the effect of unobserved variables. Study results show that the models fit the data very well. The contribution and significance of relevant influencing factors in predicting roughness progression are presented and explained. The paper concludes that the analysis approach used for developing the models confirmed their accuracy and reliability by well-fitting to the validation data.

Keywords: roughness progression, empirical model, pavement performance, heavy duty pavement

Procedia PDF Downloads 168

Authors: Josip Vasilj, Petar Sarajcev, Damir Jakus

Abstract:

One of the major difficulties introduced with wind power penetration is the inherent uncertainty in production originating from uncertain wind conditions. This uncertainty impacts many different aspects of power system operation, especially the balancing power requirements. For this reason, in power system development planing, it is necessary to evaluate the potential uncertainty in future wind power generation. For this purpose, simulation models are required, reproducing the performance of wind power forecasts. This paper presents a wind power forecast error simulation models which are based on the stochastic process simulation. Proposed models capture the most important statistical parameters recognized in wind power forecast error time series. Furthermore, two distinct models are presented based on data availability. First model uses wind speed measurements on potential or existing wind power plant locations, while the seconds model uses statistical distribution of wind speeds.

Keywords: wind power, uncertainty, stochastic process, Monte Carlo simulation

Procedia PDF Downloads 483

Authors: Sudip Kumar Kundu, Charu Singh

Abstract:

As a great physiographic divide, the Himalayas affecting a large system of water and air circulation which helps to determine the climatic condition in the Indian subcontinent to the south and mid-Asian highlands to the north. It creates obstacles by defending chill continental air from north side into India in winter and also defends rain-bearing southwesterly monsoon to give up maximum precipitation in that area in monsoon season. Nowadays extreme weather conditions such as heavy precipitation, cloudburst, flash flood, landslide and extreme avalanches are the regular happening incidents in the region of North Western Himalayan (NWH). The present study has been planned to investigate the suitable model(s) to find out the rainfall pattern over that region. For this investigation, selected models from Coordinated Regional Climate Downscaling Experiment (CORDEX) and Coupled Model Intercomparison Project Phase 5 (CMIP5) has been utilized in a consistent framework for the period of 1976 to 2000 (historical). The ability of these driving models from CORDEX domain and CMIP5 has been examined according to their capability of the spatial distribution as well as time series plot of rainfall over NWH in the rainy season and compared with the ground-based Indian Meteorological Department (IMD) gridded rainfall data set. It is noted from the analysis that the models like MIROC5 and MPI-ESM-LR from the both CORDEX and CMIP5 provide the best spatial distribution of rainfall over NWH region. But the driving models from CORDEX underestimates the daily rainfall amount as compared to CMIP5 driving models as it is unable to capture daily rainfall data properly when it has been plotted for time series (TS) individually for the state of Uttarakhand (UK) and Himachal Pradesh (HP). So finally it can be said that the driving models from CMIP5 are better than CORDEX domain models to investigate the rainfall pattern over NWH region.

Keywords: global warming, rainfall, CMIP5, CORDEX, NWH

Procedia PDF Downloads 169

Authors: Krishang Surapaneni

Abstract:

The goal of this project is to determine how to predict important aspects of options, including the ask price. We want to compare different machine learning models to learn the best model and the best hyperparameters for that model for this purpose and data set. Option pricing is a relatively new field, and it can be very complicated and intimidating, especially to inexperienced people, so we want to create a machine learning model that can predict important aspects of an option stock, which can aid in future research. We tested multiple different models and experimented with hyperparameter tuning, trying to find some of the best parameters for a machine-learning model. We tested three different models: a Random Forest Regressor, a linear regressor, and an MLP (multi-layer perceptron) regressor. The most important feature in this experiment is the ask price; this is what we were trying to predict. In the field of stock pricing prediction, there is a large potential for error, so we are unable to determine the accuracy of the models based on if they predict the pricing perfectly. Due to this factor, we determined the accuracy of the model by finding the average percentage difference between the predicted and actual values. We tested the accuracy of the machine learning models by comparing the actual results in the testing data and the predictions made by the models. The linear regression model performed worst, with an average percentage error of 17.46%. The MLP regressor had an average percentage error of 11.45%, and the random forest regressor had an average percentage error of 7.42%

Keywords: finance, linear regression model, machine learning model, neural network, stock price

Procedia PDF Downloads 75

Authors: H. C. Chinwenyi, H. D. Ibrahim, F. A. Ahmed

Abstract:

In modern financial mathematics, valuing derivatives such as options is often a tedious task. This is simply because their fair and correct prices in the future are often probabilistic. This paper examines three different Stochastic Differential Equation (SDE) models in finance; the Constant Elasticity of Variance (CEV) model, the Balck-Karasinski model, and the Heston model. The various Martingales option price valuation formulas for these three models were obtained using the replicating portfolio method. Also, the numerical solution of the derived Martingales options price valuation equations for the SDEs models was carried out using the Monte Carlo method which was implemented using MATLAB. Furthermore, results from the numerical examples using published data from the Nigeria Stock Exchange (NSE), all share index data show the effect of increase in the underlying asset value (stock price) on the value of the European Put Option for these models. From the results obtained, we see that an increase in the stock price yields a decrease in the value of the European put option price. Hence, this guides the option holder in making a quality decision by not exercising his right on the option.

Keywords: equivalent martingale measure, European put option, girsanov theorem, martingales, monte carlo method, option price valuation formula

Procedia PDF Downloads 132

Authors: Adilson Elias Xavier, Otto Corrêa Rotunno Filho, Paulo Canedo De Magalhães

Abstract:

This paper addresses the issue of automatic parameter estimation in conceptual rainfall-runoff (CRR) models. Due to threshold structures commonly occurring in CRR models, the associated mathematical optimization problems have the significant characteristic of being strongly non-differentiable. In order to face this enormous task, the resolution method proposed adopts a smoothing strategy using a special C∞ differentiable class function. The final estimation solution is obtained by solving a sequence of differentiable subproblems which gradually approach the original conceptual problem. The use of this technique, called Hyperbolic Smoothing Method (HSM), makes possible the application of the most powerful minimization algorithms, and also allows for the main difficulties presented by the original CRR problem to be overcome. A set of computational experiments is presented for the purpose of illustrating both the reliability and the efficiency of the proposed approach.

Keywords: rainfall-runoff models, automatic calibration, hyperbolic smoothing method

Procedia PDF Downloads 149

Authors: Mehdi Seifbarghy, Zahra Mansouri

Abstract:

In this paper a few location-allocation models are developed in a multi-echelon supply chain including suppliers, manufacturers, distributors and retailers. The objectives are maximizing demand coverage, minimizing the total distance of distributors from suppliers, minimizing some facility establishment costs and minimizing the environmental effects. Since nature of the given models is multi-objective, we suggest a number of goal-based solution techniques such L-P metric, goal programming, multi-choice goal programming and goal attainment in order to solve the problems.

Keywords: location, multi-echelon supply chain, covering, goal programming

Procedia PDF Downloads 559

Authors: Amadou Wurry Jallow, Adama N. S. Bah, Karamo Bah, Shih-Ye Wang, Kuo-Chung Chu, Chien-Yeh Hsu

Abstract:

Chronic kidney disease (CKD) is a major public health challenge with high prevalence, rising incidence, and serious adverse consequences. Developing effective risk prediction models is a cost-effective approach to predicting and preventing complications of chronic kidney disease (CKD). This study aimed to develop an accurate machine learning model that can dynamically identify individuals at risk of CKD using various kinds of diagnostic data, with or without laboratory data, at different follow-up points. Creatinine is a key component used to predict CKD. These models will enable affordable and effective screening for CKD even with incomplete patient data, such as the absence of creatinine testing. This retrospective cohort study included data on 19,429 adults provided by a private research institute and screening laboratory in Taiwan, gathered between 2001 and 2015. Univariate Cox proportional hazard regression analyses were performed to determine the variables with high prognostic values for predicting CKD. We then identified interacting variables and grouped them according to diagnostic data categories. Our models used three types of data gathered at three points in time: non-laboratory, laboratory, and metabolic indices data. Next, we used subgroups of variables within each category to train two machine learning models (Random Forest and XGBoost). Our machine learning models can dynamically discriminate individuals at risk for developing CKD. All the models performed well using all three kinds of data, with or without laboratory data. Using only non-laboratory-based data (such as age, sex, body mass index (BMI), and waist circumference), both models predict chronic kidney disease as accurately as models using laboratory and metabolic indices data. Our machine learning models have demonstrated the use of different categories of diagnostic data for CKD prediction, with or without laboratory data. The machine learning models are simple to use and flexible because they work even with incomplete data and can be applied in any clinical setting, including settings where laboratory data is difficult to obtain.

Keywords: chronic kidney disease, glomerular filtration rate, creatinine, novel metabolic indices, machine learning, risk prediction

Procedia PDF Downloads 105

Authors: Nodelman V.

Abstract:

Despite serious difficulties in the assimilation of the conceptual system of Calculus, software in the educational process is used only occasionally, and even then, mainly for illustration purposes. The following are a few reasons: The non-trivial nature of the studied material, Lack of skills in working with software, Fear of losing time working with software, The variety of the software itself, the corresponding interface, syntax, and the methods of working with the software, The need to find suitable models, and familiarize yourself with working with them, Incomplete compatibility of the found models with the content and teaching methods of the studied material. This paper proposes an active use of the developed non-commercial software VusuMatica, which allows removing these restrictions through Broad support for the studied mathematical material (and not only Calculus). As a result - no need to select the right software, Emphasizing the unity of mathematics, its intrasubject and interdisciplinary relations, User-friendly interface, Absence of special syntax in defining mathematical objects, Ease of building models of the studied material and manipulating them, Unlimited flexibility of models thanks to the ability to redefine objects, which allows exploring objects characteristics, and considering examples and counterexamples of the concepts under study. The construction of models is based on an original approach to the analysis of the structure of the studied concepts. Thanks to the ease of construction, students are able not only to use ready-made models but also to create them on their own and explore the material studied with their help. The presentation includes examples of using VusuMatica in studying the concepts of limit and continuity of a function, its derivative, and integral.

Keywords: counterexamples, limitations and requirements, software, teaching and learning calculus, user-friendly interface and syntax

Procedia PDF Downloads 81

Authors: H. Djebar, L. Khene, M. Boucenna, M. R. Djebar, M. N. Khebbeb, M. Djekoun

Abstract:

Currently in toxicology, use of alternative models permits to understand the mechanisms of toxicity at different levels of cells. Objectives of our research concern the determination of NPs ZnO, TiO2, AlO2, and FeO2 effect on ciliate protist freshwater Paramecium sp and Helix aspersa. The result obtained show that NPs increased antioxidative enzyme activity like catalase, glutathione –S-transferase and level GSH. Also, cells treated with high concentrations of NPs showed a high level of MDA. In conclusion, observations from growth and enzymatic parameters suggest on one hand that treatment with NPs provokes an oxidative stress and on the other that snale and paramecium are excellent alternatives models for ecotoxicological studies.

Keywords: NPs, GST, catalase, GSH, MDA, toxicity, snale and paramecium

Procedia PDF Downloads 281

Authors: Yake Zhang, Peng Xu

Abstract:

The development of building energy models (BEM) required for architectural design and analysis is a time-consuming and complex process, demanding a deep understanding and proficient use of simulation software. To streamline the generation of complex building energy models, this study proposes an automated method for generating building energy models using a large language model and the BEM library aimed at improving the efficiency of model generation. This method leverages a large language model to parse user-specified requirements for target building models, extracting key features such as building location, window-to-wall ratio, and thermal performance of the building envelope. The BEM library is utilized to retrieve energy models that match the target building’s characteristics, serving as reference information for the large language model to enhance the accuracy and relevance of the generated model, allowing for the creation of a building energy model that adapts to the user’s modeling requirements. This study enables the automatic creation of building energy models based on natural language inputs, reducing the professional expertise required for model development while significantly decreasing the time and complexity of manual configuration. In summary, this study provides an efficient and intelligent solution for building energy analysis and simulation, demonstrating the potential of a large language model in the field of building simulation and performance modeling.

Keywords: artificial intelligence, building energy modelling, building simulation, large language model

Procedia PDF Downloads 25

Authors: Raninder Kaur Dhillon, Mayur Jethwa, Hardeep Singh Rai

Abstract:

Information technology has made a pivotal progress across disparate disciplines, one of which is AEC (Architecture, Engineering and Construction) industry. CAD is a form of computer-aided building modulation that architects, engineers and contractors use to create and view two- and three-dimensional models. The AEC industry also uses building information modeling (BIM), a newer computerized modeling system that can create four-dimensional models; this software can greatly increase productivity in the AEC industry. BIM models generate open source IFC (Industry Foundation Classes) files which aim for interoperability for exchanging information throughout the project lifecycle among various disciplines. The methods developed in previous studies require either an IFC schema or MVD and software applications, such as an IFC model server or a Building Information Modeling (BIM) authoring tool, to extract a partial or complete IFC instance model. This paper proposes an efficient algorithm for extracting a partial and total model from an Industry Foundation Classes (IFC) instance model without an IFC schema or a complete IFC model view definition (MVD).

Keywords: BIM, CAD, IFC, MVD

Procedia PDF Downloads 300

Authors: Daniel Fulus Fom, Gau Patrick Damulak

Abstract:

In this study, the Autoregressive Fractional Integrated Moving Average (ARFIMA) and Jordan Recurrent Neural Network (JRNN) models were employed to model the forecasting performance of the daily turbidity flow of White Clay Creek (WCC). The two methods were applied to the log difference series of the daily turbidity flow series of WCC. The measurements of error employed to investigate the forecasting performance of the ARFIMA and JRNN models are the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE). The outcome of the investigation revealed that the forecasting performance of the JRNN technique is better than the forecasting performance of the ARFIMA technique in the mean square error sense. The results of the ARFIMA and JRNN models were obtained by the simulation of the models using MATLAB version 8.03. The significance of using the log difference series rather than the difference series is that the log difference series stabilizes the turbidity flow series than the difference series on the ARFIMA and JRNN.

Keywords: auto regressive, mean absolute error, neural network, root square mean error

Procedia PDF Downloads 268

Authors: Thiago Victor Cordeiro Marcos, Joao Felipe de Araujo Martos, Ronaldo de Lima Cardoso, David Romanelli Pinto, Paulo Gilberto de Paula Toro, Israel da Silveira Rego, Antonio Carlos de Oliveira

Abstract:

Currently, the use of 3D rapid prototyping, also known as 3D printing, has been investigated by some universities around the world as an innovative technique, fast, flexible and cheap for a direct plastic models manufacturing that are lighter and with complex geometries to be tested for hypersonic shock tunnel. Initially, the purpose is integrated prototyped parts with metal models that actually are manufactured through of the conventional machining and hereafter replace them with completely prototyped models. The mechanical design models to be tested in hypersonic shock tunnel are based on conventional manufacturing processes, therefore are limited forms and standard geometries. The use of 3D rapid prototyping offers a range of options that enables geometries innovation and ways to be used for the design new models. The conception and project of a prototyped model for hypersonic shock tunnel should be rethought and adapted when comparing the conventional manufacturing processes, in order to fully exploit the creativity and flexibility that are allowed by the 3D prototyping process. The objective of this paper is to compare the conception and project of a 3D rapid prototyping model and a conventional machining model, while showing the advantages and disadvantages of each process and the benefits that 3D prototyping can bring to the manufacture of models to be tested in hypersonic shock tunnel.

Keywords: 3D printing, 3D prototyping, experimental research, hypersonic shock tunnel

Procedia PDF Downloads 469

Authors: Cheikh Bamba Dione, Alla Lo, Elhadji Mamadou Nguer, Siley O. Ba

Abstract:

In this paper, we propose two neural machine translation (NMT) systems (French-to-Wolof and Wolof-to-French) based on sequence-to-sequence with attention and transformer architectures. We trained our models on a parallel French-Wolof corpus of about 83k sentence pairs. Because of the low-resource setting, we experimented with advanced methods for handling data sparsity, including subword segmentation, back translation, and the copied corpus method. We evaluate the models using the BLEU score and find that transformer outperforms the classic seq2seq model in all settings, in addition to being less sensitive to noise. In general, the best scores are achieved when training the models on word-level-based units. For subword-level models, using back translation proves to be slightly beneficial in low-resource (WO) to high-resource (FR) language translation for the transformer (but not for the seq2seq) models. A slight improvement can also be observed when injecting copied monolingual text in the target language. Moreover, combining the copied method data with back translation leads to a substantial improvement of the translation quality.

Keywords: backtranslation, low-resource language, neural machine translation, sequence-to-sequence, transformer, Wolof

Procedia PDF Downloads 147

Authors: Peyman Aela, Lu Zong, Guoqing Jing

Abstract:

Recently, there has been growing interest in numerical modeling of ballast railway tracks. A commonly used mechanistic modeling approach for ballast is the discrete element method (DEM). Up to now, the effects of the contact model on ballast particle behavior have not been precisely examined. In this regard, selecting the appropriate contact model is mainly associated with the particle characteristics and the loading condition. Since ballast is cohesionless material, different contact models, including the linear spring, Hertz-Mindlin, and Hysteretic models, could be used to calculate particle-particle or wall-particle contact forces. Moreover, the simulation of a dynamic test is vital to investigate the effect of damping parameters on the ballast deformation. In this study, ballast box tests were simulated by DEM to examine the influence of different contact models on the mechanical behavior of the ballast layer under cyclic loading. This paper shows how the contact model can affect the deformation and damping of a ballast layer subjected to cyclic loading in a ballast box.

Keywords: ballast, contact model, cyclic loading, DEM

Procedia PDF Downloads 196

Authors: Stuart Bradley, Mathew Legg, Lilyan Panton

Abstract:

Ultrasonic remote sensing is a useful tool for assessing the interior structure of complex targets. For these methods, significantly enhanced spatial resolution is obtained if the pulse is coded, for example using a linearly changing frequency during the pulse duration. Such pulses have a time-dependent spectral structure. Interpretation of the backscatter from targets is, therefore, complicated if the scattering is frequency-dependent. While analytic models are well established for steady sinusoidal excitations applied to simple shapes such as spheres, such models do not generally exist for temporally evolving excitations. Therefore, models are developed in the current paper for handling such signals so that the properties of the targets can be quantitatively evaluated while maintaining very high spatial resolution. Laboratory measurements on simple shapes are used to confirm the validity of the models.

Keywords: linear FM chirp, time-dependent acoustic scattering, ultrasonic remote sensing, ultrasonic scattering

Procedia PDF Downloads 316