Search results for: data based modeling

Authors: C. V. Pietreanu, S. E. Zaharia, C. Dinu

Abstract:

The present research is built on three major pillars, commencing by making some considerations on accident investigation methods and pointing out both defining aspects and differences between linear and non-linear analysis. The traditional linear focus on accident analysis describes accidents as a sequence of events, while the latest systemic models outline interdependencies between different factors and define the processes evolution related to a specific (normal) situation. Linear and non-linear accident analysis methods have specific limitations, so the second point of interest is mirrored by the aim to discover the drawbacks of systemic models which becomes a starting point for developing new directions to identify risks or data closer to the cause of incidents/accidents. Since communication represents a critical issue in the interaction of human factor and has been proved to be the answer of the problems made by possible breakdowns in different communication procedures, from this focus point, on the third pylon a new error-modeling instrument suitable for risk assessment/accident analysis will be elaborated.

Keywords: accident analysis, multi-factorial error modeling, risk, systemic methods

Procedia PDF Downloads 193

Authors: Einav Srulovici, Michal Grinstein-Weiss, George Knafl, Linda Beeber, Shawn Kneipp, Barbara Mark

Abstract:

Background: The asset-building theoretical framework (ABTF) is acknowledged as the most complete framework thus far for depicting the relationships between asset accumulation (the stock of a household’s saved resources available for future investment) and health outcomes. Although the ABTF takes into consideration the reciprocal relationship between asset accumulation and health, no ABTF based study has yet examined this relationship. Therefore, the purpose of this study was to test the ABTF and psychological distress, focusing on the reciprocal relationship between assets accumulation and psychological distress. Methods: The study employed longitudinal data from 6,295 families from the 2001 and 2007 Panel Study of Income Dynamics data sets. Structural equation modeling (SEM) was used to test the reciprocal relationship between asset accumulation and psychological distress. Results: In general, the data displayed a good fit to the model. The longitudinal SEM found that asset accumulation significantly increased with a decreased in psychological distress over time, while psychological distress significantly increased with an increase in asset accumulation over time, confirming the existence of the hypothesized reciprocal relationship. Conclusions: Individuals who are less psychological distressed might have more energy to engage in activities, such as furthering their education or obtaining better jobs that are in turn associated with greater asset accumulation, while those who have greater assets may invest those assets in riskier investments, resulting in increased psychological distress. The confirmation of this reciprocal relationship highlights the importance of conducting longitudinal studies and testing the reciprocal relationship between asset accumulation and other health outcomes.

Keywords: asset-building theoretical framework, psychological distress, structural equation modeling, reciprocal relationship

Procedia PDF Downloads 370

Authors: Bekim Berisha, Sebastian Hirsiger, Pavel Hora

Abstract:

Advanced material models involving several sets of model parameters require a big experimental effort. As models are getting more and more complex like e.g. the so called “Homogeneous Anisotropic Hardening - HAH” model for description of the yielding behavior in the 2D/3D stress space, the number and complexity of the required experiments are also increasing continuously. In the context of sheet metal forming, these requirements are even more pronounced, because of the anisotropic behavior or sheet materials. In addition, some of the experiments are very difficult to perform e.g. the plane stress biaxial compression test. Accordingly, tensile tests in at least three directions, biaxial tests and tension-compression or shear-reverse shear experiments are performed to determine the parameters of the macroscopic models. Therefore, determination of the macroscopic model parameters based on virtual experiments is a very promising strategy to overcome these difficulties. For this purpose, in the framework of multiscale material modeling, a dislocation density based crystal plasticity model in combination with a FFT-based spectral solver is applied to perform virtual experiments. Modeling of the plastic behavior of metals based on crystal plasticity theory is a well-established methodology. However, in general, the computation time is very high and therefore, the computations are restricted to simplified microstructures as well as simple polycrystal models. In this study, a dislocation density based crystal plasticity model – including an implementation of the backstress – is used in a spectral solver framework to generate virtual experiments for three deep drawing materials, DC05-steel, AA6111-T4 and AA4045 aluminum alloys. For this purpose, uniaxial as well as multiaxial loading cases, including various pre-strain histories, has been computed and validated with real experiments. These investigations showed that crystal plasticity modeling in the framework of Representative Volume Elements (RVEs) can be used to replace most of the expensive real experiments. Further, model parameters of advanced macroscopic models like the HAH model can be determined from virtual experiments, even for multiaxial deformation histories. It was also found that crystal plasticity modeling can be used to model anisotropic hardening more accurately by considering the backstress, similar to well-established macroscopic kinematic hardening models. It can be concluded that an efficient coupling of crystal plasticity models and the spectral solver leads to a significant reduction of the amount of real experiments needed to calibrate macroscopic models. This advantage leads also to a significant reduction of computational effort needed for the optimization of metal forming process. Further, due to the time efficient spectral solver used in the computation of the RVE models, detailed modeling of the microstructure are possible.

Keywords: anisotropic hardening, crystal plasticity, micro structure, spectral solver

Procedia PDF Downloads 298

Authors: Seyed Esmail Seyedi Bariran, Laysheng Ewe, Amy Ling

Abstract:

Since supplier selection appears as a vital decision, selecting supplier based on the best and most accurate ways has a lot of importance for enterprises. In this study, a new Artificial Intelligence approach is exerted to remove weaknesses of supplier selection. The paper has three parts. First part is choosing the appropriate criteria for assessing the suppliers’ performance. Next one is collecting the data set based on experts. Afterwards, the data set is divided into two parts, the training data set and the testing data set. By the training data set the best structure of GEP and ANN are selected and to evaluate the power of the mentioned methods the testing data set is used. The result obtained shows that the accuracy of GEP is more than ANN. Moreover, unlike ANN, a mathematical equation is presented by GEP for the supplier selection.

Keywords: supplier selection, automotive supply chains, ANN, GEP

Procedia PDF Downloads 607

Authors: Thrivikraman Aswathi, S. Advaith

Abstract:

As there can be cases where the use of real data is somehow limited, such as when it is hard to get access to a large volume of real data, we need to go for synthetic data generation. This produces high-quality synthetic data while maintaining the statistical properties of a specific dataset. In the present work, a generative adversarial network (GAN) is trained to produce multivariate time series (MTS) data since the MTS is now being gathered more often in various real-world systems. Furthermore, the GAN-generated MTS data is fed into a transformer-based deep learning architecture that carries out the data categorization into predefined classes. Further, the model is evaluated across various distinct domains by generating corresponding MTS data.

Keywords: GAN, transformer, classification, multivariate time series

Procedia PDF Downloads 105

Authors: Mahdi Aghaei, Saeid Jamshidi, Mastaneh Hajipour

Abstract:

Effective factors on the mechanical wellbore stability are divided in to two categories: 1) Controllable factors, 2) Uncontrollable factors. The purpose of geo-mechanical modeling of wells is to determine the limit of controlled parameters change based on the stress regime at each point and by solving the governing equations the pore-elastic environment around the well. In this research, the mechanical analysis of wellbore stability was carried out for Soroush oilfield. For this purpose, the geo-mechanical model of the field is made using available data. This model provides the necessary parameters for obtaining the distribution of stress around the wellbore. Initially, a basic model was designed to perform various analysis, based on obtained data, using Abaqus software. All of the subsequent sensitivity analysis such as sensitivity analysis on porosity, permeability, etc. was done on the same basic model. The results obtained from these analysis gives various result such as: with the constant geomechanical parameters, and sensitivity analysis on porosity permeability is ineffective. After the most important parameters affecting the wellbore stability and instability are geo-mechanical parameters.

Keywords: wellbore stability, movement, stress, instability

Procedia PDF Downloads 188

Authors: Fábio A. S. Mota, Mauro A. S. S. Ravagnani, E. P. Carvalho

Abstract:

In the present paper the design of plate heat exchangers is formulated as an optimization problem considering two mathematical modeling. The number of plates is the objective function to be minimized, considering implicitly some parameters configuration. Screening is the optimization method used to solve the problem. Thermal and hydraulic constraints are verified, not viable solutions are discarded and the method searches for the convergence to the optimum, case it exists. A case study is presented to test the applicability of the developed algorithm. Results show coherency with the literature.

Keywords: plate heat exchanger, optimization, modeling, simulation

Procedia PDF Downloads 497

Authors: Sanyka Banerjee, Saikat Nandi, P. K. Dan

Abstract:

Synchronizers as an integral part of gearbox is a key element in the transmission system in automotive. The performance of synchronizer affects transmission efficiency and driving comfort. Synchronizing mechanism as a major component of transmission system must be capable of preventing vibration and noise in the gears. Gear shifting efficiency improvement with an aim to achieve smooth, quick and energy efficient power transmission remains a challenge for the automotive industry. Performance of the synchronizer is dependent on the features and characteristics of its sub-components and therefore analysis of the contribution of such characteristics is necessary. An important exercise involved is to identify all such characteristics or factors which are associated with the modeling and analysis and for this purpose the literature was reviewed, rather extensively, to study the mathematical models, formulated considering such. It has been observed that certain factors are rather common across models; however, there are few factors which have specifically been selected for individual models, as reported. In order to obtain a more realistic model, an attempt here has been made to identify and assimilate practically all possible factors which may be considered in formulating the model more comprehensively. A simulation study, formulated as a block model, for such analysis has been carried out in a reliable environment like MATLAB. Lower synchronization time is desirable and hence, it has been considered here as the output factors in the simulation modeling for evaluating transmission efficiency. An improved synchronizer model requires optimized values of sub-component design parameters. A parametric optimization utilizing Taguchi’s design of experiment based response data and their analysis has been carried out for this purpose. The effectiveness of the optimized parameters for the improved synchronizer performance has been validated by the simulation study of the synchronizer block model with improved parameter values as input parameters for better transmission efficiency and driver comfort.

Keywords: design of experiments, modeling, parametric optimization, simulation, synchronizer

Procedia PDF Downloads 287

Authors: Kiwon Yeom

Abstract:

Change points are abrupt variations in a data sequence. Detection of change points is useful in modeling, analyzing, and predicting time series in application areas such as robotics and teleoperation. In this paper, a change point is defined to be a discontinuity in one of its derivatives. This paper presents a reliable method for detecting discontinuities within a three-dimensional trajectory data. The problem of determining one or more discontinuities is considered in regular and irregular trajectory data from teleoperation. We examine the geometric detection algorithm and illustrate the use of the method on real data examples.

Keywords: change point, discontinuity, teleoperation, abrupt variation

Procedia PDF Downloads 145

Authors: Xiangtuo Chen, Paul-Henry Cournéde

Abstract:

Crop yield prediction is a paramount issue in agriculture. The main idea of this paper is to find out efficient way to predict the yield of corn based meteorological records. The prediction models used in this paper can be classified into model-driven approaches and data-driven approaches, according to the different modeling methodologies. The model-driven approaches are based on crop mechanistic modeling. They describe crop growth in interaction with their environment as dynamical systems. But the calibration process of the dynamic system comes up with much difficulty, because it turns out to be a multidimensional non-convex optimization problem. An original contribution of this paper is to propose a statistical methodology, Multi-Scenarios Parameters Estimation (MSPE), for the parametrization of potentially complex mechanistic models from a new type of datasets (climatic data, final yield in many situations). It is tested with CORNFLO, a crop model for maize growth. On the other hand, the data-driven approach for yield prediction is free of the complex biophysical process. But it has some strict requirements about the dataset. A second contribution of the paper is the comparison of these model-driven methods with classical data-driven methods. For this purpose, we consider two classes of regression methods, methods derived from linear regression (Ridge and Lasso Regression, Principal Components Regression or Partial Least Squares Regression) and machine learning methods (Random Forest, k-Nearest Neighbor, Artificial Neural Network and SVM regression). The dataset consists of 720 records of corn yield at county scale provided by the United States Department of Agriculture (USDA) and the associated climatic data. A 5-folds cross-validation process and two accuracy metrics: root mean square error of prediction(RMSEP), mean absolute error of prediction(MAEP) were used to evaluate the crop prediction capacity. The results show that among the data-driven approaches, Random Forest is the most robust and generally achieves the best prediction error (MAEP 4.27%). It also outperforms our model-driven approach (MAEP 6.11%). However, the method to calibrate the mechanistic model from dataset easy to access offers several side-perspectives. The mechanistic model can potentially help to underline the stresses suffered by the crop or to identify the biological parameters of interest for breeding purposes. For this reason, an interesting perspective is to combine these two types of approaches.

Keywords: crop yield prediction, crop model, sensitivity analysis, paramater estimation, particle swarm optimization, random forest

Procedia PDF Downloads 211

Authors: Tisciane Perpetuo e Oliveira, Dante Inga Narvaez, Marcelo Gradella Villalva

Abstract:

Installations of solar photovoltaic systems have increased considerably in the last decade. Therefore, it has been noticed that monitoring of meteorological data (solar irradiance, air temperature, wind velocity, etc.) is important to predict the potential of a given geographical area in solar energy production. In this sense, the present work compares two computational tools that are capable of estimating the energy generation of a photovoltaic system through correlation analyzes of solar radiation data: PVsyst software and an algorithm based on the PVlib package implemented in MATLAB. In order to achieve the objective, it was necessary to obtain solar radiation data (measured and from a solarimetric database), analyze the decomposition of global solar irradiance in direct normal and horizontal diffuse components, as well as analyze the modeling of the devices of a photovoltaic system (solar modules and inverters) for energy production calculations. Simulated results were compared with experimental data in order to evaluate the performance of the studied methods. Errors in estimation of energy production were less than 30% for the MATLAB algorithm and less than 20% for the PVsyst software.

Keywords: energy production, meteorological data, irradiance decomposition, solar photovoltaic system

Procedia PDF Downloads 120

Authors: Jing Yuan, Hongwei Yang

Abstract:

This paper aims to understand U.S. middle school students’ mathematics achievements by examining relevant student and school-level predictors. Through a variance component analysis, the study first identifies evidence supporting the use of multilevel modeling. Then, a multilevel analysis is performed under Bayesian statistical inference where prior information is incorporated into the modeling process. During the analysis, independent variables are entered sequentially in the order of theoretical importance to create a hierarchy of models. By evaluating each model using Bayesian fit indices, a best-fit and most parsimonious model is selected where Bayesian statistical inference is performed for the purpose of result interpretation and discussion. The primary dataset for Bayesian modeling is derived from the Program for International Student Assessment (PISA) in 2012 with a secondary PISA dataset from 2003 analyzed under the traditional ordinary least squares method to provide the information needed to specify informative priors for a subset of the model parameters. The dependent variable is a composite measure of mathematics literacy, calculated from an exploratory factor analysis of all five PISA 2012 mathematics achievement plausible values for which multiple evidences are found supporting data unidimensionality. The independent variables include demographics variables and content-specific variables: mathematics efficacy, teacher-student ratio, proportion of girls in the school, etc. Finally, the entire analysis is performed using the MCMCpack and MCMCglmm packages in R.

Keywords: Bayesian multilevel modeling, mathematics education, PISA, multilevel

Procedia PDF Downloads 311

Authors: Radul Shishkov, Orlin Davchev

Abstract:

The digital era has revolutionized architectural practices, with building information modeling (BIM) emerging as a pivotal tool for architects, engineers, and construction professionals. However, the transition from traditional methods to BIM-centric approaches poses significant challenges, particularly in the context of existing structures. This research introduces a technical approach to bridge this gap through the development of algorithms that facilitate the automated transformation of 3D point cloud data into detailed BIM models. The core of this research lies in the application of algorithmic modeling and computational design methods to interpret and reconstruct point cloud data -a collection of data points in space, typically produced by 3D scanners- into comprehensive BIM models. This process involves complex stages of data cleaning, feature extraction, and geometric reconstruction, which are traditionally time-consuming and prone to human error. By automating these stages, our approach significantly enhances the efficiency and accuracy of creating BIM models for existing buildings. The proposed algorithms are designed to identify key architectural elements within point clouds, such as walls, windows, doors, and other structural components, and to translate these elements into their corresponding BIM representations. This includes the integration of parametric modeling techniques to ensure that the generated BIM models are not only geometrically accurate but also embedded with essential architectural and structural information. Our methodology has been tested on several real-world case studies, demonstrating its capability to handle diverse architectural styles and complexities. The results showcase a substantial reduction in time and resources required for BIM model generation while maintaining high levels of accuracy and detail. This research contributes significantly to the field of architectural technology by providing a scalable and efficient solution for the integration of existing structures into the BIM framework. It paves the way for more seamless and integrated workflows in renovation and heritage conservation projects, where the accuracy of existing conditions plays a critical role. The implications of this study extend beyond architectural practices, offering potential benefits in urban planning, facility management, and historic preservation.

Keywords: BIM, 3D point cloud, algorithmic modeling, computational design, architectural reconstruction

Procedia PDF Downloads 35

Authors: V. B. Bastos, M. P. Lima, P. R. G. Kurka

Abstract:

This paper applies to the creation of virtual 3D environments for the study and development of mobile robot image based navigation algorithms and techniques, which need to operate robustly and efficiently. The test of these algorithms can be performed in a physical way, from conducting experiments on a prototype, or by numerical simulations. Current simulation platforms for robotic applications do not have flexible and updated models for image rendering, being unable to reproduce complex light effects and materials. Thus, it is necessary to create a test platform that integrates sophisticated simulated applications of real environments for navigation, with data and image processing. This work proposes the development of a high-level platform for building 3D model’s environments and the test of image-based navigation algorithms for mobile robots. Techniques were used for applying texture and lighting effects in order to accurately represent the generation of rendered images regarding the real world version. The application will integrate image processing scripts, trajectory control, dynamic modeling and simulation techniques for physics representation and picture rendering with the open source 3D creation suite - Blender.

Keywords: simulation, visual navigation, mobile robot, data visualization

Procedia PDF Downloads 233

Authors: J. G. Batista, T. S. Santiago, E. A. Ribeiro, G. A. P. Thé

Abstract:

This work deals with parameter identification of permanent magnet motors, a class of ac motor which is particularly important in industrial automation due to characteristics like applications high performance, are very attractive for applications with limited space and reducing the need to eliminate because they have reduced size and volume and can operate in a wide speed range, without independent ventilation. By using experimental data and genetic algorithm we have been able to extract values for both the motor inductance and the electromechanical coupling constant, which are then compared to measure and/or expected values.

Keywords: modeling, AC servomotor, permanent magnet synchronous motor-PMSM, genetic algorithm, vector control, robotic manipulator, control

Procedia PDF Downloads 500

Authors: Neslihan Sahin Celik, Ali Eraslan

Abstract:

As a result of PISA (Program for International Student Assessments) survey that tests how well students can apply the knowledge and skills they have learned at school to real-life challenges, the new and redesigned mathematics education programs in many countries emphasize the necessity for the students to face complex and multifaceted problem situations and gain experience in this sense allowing them to develop new skills and mathematical thinking to prepare them for their future life after school. At this point, mathematical models and modeling approaches can be utilized in the analysis of complex problems which represent real-life situations in which students can actively participate. In particular, model eliciting activities that bring about situations which allow the students to create solutions to problems and which involve mathematical modeling must be used right from primary school years, allowing them to face such complex, real-life situations from early childhood period. A qualitative study was conducted in a university foundation primary school in the city center of a big province in 2013-2014 academic years. The participants were 4th grade students in a primary school. After a four-week preliminary study applied to a fourth-grade classroom, three students included in the focus group were selected using criterion sampling technique. A focus group of three students was videotaped as they worked on the Crime Problem. The conversation of the group was transcribed, examined with students’ written work and then analyzed through the lens of Blum and Ferri’s modeling processing cycle. The results showed that primary fourth-grade students can successfully work with model eliciting problem while they encounter some difficulties in the modeling processes. In particular, they developed new ideas based on different assumptions, identified the patterns among variables and established a variety of models. On the other hand, they had trouble focusing on problems and occasionally had breaks in the process.

Keywords: primary school, modeling, mathematical modeling, crime problem

Procedia PDF Downloads 381

Authors: Lan Luo

Abstract:

In China’s construction industry, it is a normal practice to separately subcontract the decoration engineering part from construction engineering, and Building Information Modeling (BIM) is also done separately. Application of BIM in decoration engineering should be integrated with other disciplines, but Chinese current practice makes this very difficult and complicated. Currently, there are three barriers in the auditing of BIM application in decoration engineering in China: heavy workload; scarcity of qualified professionals; and lack of literature concerning audit contents, standards, and methods. Therefore, it is significant to perform research on what (contents) should be evaluated, in which phase, and by whom (professional qualifications) in BIM application in decoration construction so that the application of BIM can be promoted in a better manner. Based on this consideration, four principles of BIM auditing are proposed: Comprehensiveness of information, accuracy of data, aesthetic attractiveness of appearance, and scheme optimization. In the model audit, three methods should be used: Collision, observation, and contrast. In addition, BIM auditing at six stages is discussed and a checklist for work items and results to be submitted is proposed. This checklist can be used for reference by decoration project participants.

Keywords: audit, evaluation, dimensions, methods, standards, BIM application in decoration engineering projects

Procedia PDF Downloads 327

Authors: Jaechoul Shin, Juhwan Hwang

Abstract:

In case of applying the BIM method to the civil engineering in the area of free formed structure, we can expect comparatively high rate of construction productivity as it is in the building engineering area. In this research, we developed quantity calculation error applying it to earthwork and bridge construction (e.g. PSC-I type segmental girder bridge amd integrated bridge of steel I-girders and inverted-Tee bent cap), NATM (New Austrian Tunneling Method) tunnel construction, retaining wall construction, culvert construction and implemented BIM based 3D modeling quantity survey. we confirmed high reliability of the BIM-based method in structure work in which errors occurred in range between -6% ~ +5%. Especially, understanding of the problem and improvement of the existing 2D-CAD based of quantity calculation through rock type quantity calculation error in range of -14% ~ +13% of earthwork quantity calculation. It is benefit and applicability of BIM method in civil engineering. In addition, routine method for quantity of earthwork has the same error tolerance negligible for that of structure work. But, rock type's quantity calculated as the error appears significantly to the reliability of 2D-based volume calculation shows that the problem could be. Through the estimating quantity of earthwork based 3D-BIM, proposed method has better reliability than routine method. BIM, as well as the design, construction, maintenance levels of information when you consider the benefits of integration, the introduction of BIM design in civil engineering and the possibility of applying for the effectiveness was confirmed.

Keywords: BIM, 3D modeling, 3D-BIM, quantity of earthwork

Procedia PDF Downloads 423

Authors: Shahrokh Barati

Abstract:

In this paper, we introduced AIDS disease at first, then proposed dynamic model illustrate its progress, after expression of a short history of nonlinear modeling by polynomial phasing systems, we considered the stability conditions of the systems, which contained a huge amount of researches in order to modeling and control of AIDS in dynamic nonlinear form, in this approach using a frame work of control any polynomial phasing modeling system which have been generalized by part of phasing model of T-S, in order to control the system in better way, the stability conditions were achieved based on polynomial functions, then we focused to design the appropriate controller, firstly we considered the equilibrium points of system and their conditions and in order to examine changes in the parameters, we presented polynomial phase model that was the generalized approach rather than previous Takagi Sugeno models, then with using case we evaluated the equations in both open loop and close loop and with helping the controlling feedback, the close loop equations of system were calculated, to simulate nonlinear model of AIDS disease, we used polynomial phasing controller output that was capable to make the parameters of a nonlinear system to follow a sustainable reference model properly.

Keywords: polynomial fuzzy, AIDS, nonlinear AIDS model, fuzzy control systems

Procedia PDF Downloads 447

Authors: Noura Al Akkari, Aurélie Foucquier, Sylvain Lespinats

Abstract:

Load monitoring is a management process for energy consumption towards energy savings and energy efficiency. Non Intrusive Load Monitoring (NILM) is one method of load monitoring used for disaggregation purposes. NILM is a technique for identifying individual appliances based on the analysis of the whole residence data retrieved from the main power meter of the house. Our NILM framework starts with data acquisition, followed by data preprocessing, then event detection, feature extraction, then general appliance modeling and identification at the final stage. The event detection stage is a core component of NILM process since event detection techniques lead to the extraction of appliance features. Appliance features are required for the accurate identification of the household devices. In this research work, we aim at developing a new event detection methodology with accurate load disaggregation to extract appliance features. Time-domain features extracted are used for tuning general appliance models for appliance identification and classification steps. We use unsupervised algorithms such as Dynamic Time Warping (DTW). The proposed method relies on detecting areas of operation of each residential appliance based on the power demand. Then, detecting the time at which each selected appliance changes its states. In order to fit with practical existing smart meters capabilities, we work on low sampling data with a frequency of (1/60) Hz. The data is simulated on Load Profile Generator software (LPG), which was not previously taken into consideration for NILM purposes in the literature. LPG is a numerical software that uses behaviour simulation of people inside the house to generate residential energy consumption data. The proposed event detection method targets low consumption loads that are difficult to detect. Also, it facilitates the extraction of specific features used for general appliance modeling. In addition to this, the identification process includes unsupervised techniques such as DTW. To our best knowledge, there exist few unsupervised techniques employed with low sampling data in comparison to the many supervised techniques used for such cases. We extract a power interval at which falls the operation of the selected appliance along with a time vector for the values delimiting the state transitions of the appliance. After this, appliance signatures are formed from extracted power, geometrical and statistical features. Afterwards, those formed signatures are used to tune general model types for appliances identification using unsupervised algorithms. This method is evaluated using both simulated data on LPG and real-time Reference Energy Disaggregation Dataset (REDD). For that, we compute performance metrics using confusion matrix based metrics, considering accuracy, precision, recall and error-rate. The performance analysis of our methodology is then compared with other detection techniques previously used in the literature review, such as detection techniques based on statistical variations and abrupt changes (Variance Sliding Window and Cumulative Sum).

Keywords: general appliance model, non intrusive load monitoring, events detection, unsupervised techniques;

Procedia PDF Downloads 58

Authors: Ananya Gangavarapu

Abstract:

Convolutional Neural Networks (CNN) based models are providing diagnostic capabilities on par with the medical specialists in many specialty areas. However, collecting the medical data for training purposes is very challenging because of the increased regulations around data collections and privacy concerns around personal health data. The gathering of the data becomes even more difficult if the capture devices are edge-based mobile devices (like smartphones) with feeble wireless connectivity in rural/remote areas. In this paper, I would like to highlight Federated Learning approach to mitigate data privacy and security issues.

Keywords: deep learning in healthcare, data privacy, federated learning, training in distributed environment

Procedia PDF Downloads 121

Authors: Sadia Arshad

Abstract:

The new coronavirus disease or COVID-19 still poses an alarming situation around the world. Modeling based on the derivative of fractional order is relatively important to capture real-world problems and to analyze the realistic situation of the proposed model. Weproposed a mathematical model for the investigation of COVID-19 dynamics in a generalized fractional framework. The new model is formulated in the Caputo sense and employs a nonlinear time-varying transmission rate. The existence and uniqueness solutions of the fractional order derivative have been studied using the fixed-point theory. The associated dynamical behaviors are discussed in terms of equilibrium, stability, and basic reproduction number. For the purpose of numerical implementation, an effcient approximation scheme is also employed to solve the fractional COVID-19 model. Numerical simulations are reported for various fractional orders, and simulation results are compared with a real case of COVID-19 pandemic. According to the comparative results with real data, we find the best value of fractional orderand justify the use of the fractional concept in the mathematical modelling, for the new fractional modelsimulates the reality more accurately than the other classical frameworks.

Keywords: fractional calculus, modeling, stability, numerical solution

Procedia PDF Downloads 89

Authors: Habib Ur Rahman Habib

Abstract:

Renewable energy resources are being realized as suitable options in hybrid energy planning for on-grid and micro grid. In this paper, operation, planning and optimal design of on-grid distributed energy resources based hybrid system are investigated. The aim is to minimize the cost of the overall energy system keeping in view the environmental emission and minimum penetration of conventional energy resources. Seven grid connected different case studies including diesel only, diesel-renewable based, and renewable based only are designed to perform economic analysis, operational planning and emission. Sensitivity analysis is implemented to investigate the impact of different parameters on the performance of energy resources.

Keywords: data management, renewable energy, distributed energy, smart grid, micro-grid, modeling, energy planning, design optimization

Procedia PDF Downloads 434

Authors: K. Hardy, A. Maurushat

Abstract:

Policy makers are increasingly looking to make evidence-based decisions. Evidence-based decisions have historically used rigorous methodologies of empirical studies by research institutes, as well as less reliable immediate survey/polls often with limited sample sizes. As we move into the era of Big Data analytics, policy makers are looking to different methodologies to deliver reliable empirics in real-time. The question is not why did these people do this for the last 10 years, but why are these people doing this now, and if the this is undesirable, and how can we have an impact to promote change immediately. Big data analytics rely heavily on government data that has been released in to the public domain. The open data movement promises greater productivity and more efficient delivery of services; however, Australian government agencies remain reluctant to release their data to the general public. This paper considers the barriers to releasing government data as open data, and how these barriers might be overcome.

Keywords: big data, open data, productivity, data governance

Procedia PDF Downloads 351

Authors: R. Mohan, V. Jadhav, A. Ahmed, J. Rivas, A. Kelkar

Abstract:

Cementitious materials are an excellent example of a composite material with complex hierarchical features and random features that range from nanometer (nm) to millimeter (mm) scale. Multi-scale modeling of complex material systems requires starting from fundamental building blocks to capture the scale relevant features through associated computational models. In this paper, molecular dynamics (MD) modeling is employed to predict the effect of plasticizer additive on the mechanical properties of key hydrated cement constituent calcium-silicate-hydrate (CSH) at the molecular, nanometer scale level. Due to complexity, still unknown molecular configuration of CSH, a representative configuration widely accepted in the field of mineral Jennite is employed. The effectiveness of the Molecular Dynamics modeling to understand the predictive influence of material chemistry changes based on molecular/nanoscale models is demonstrated.

Keywords: cement composite, mechanical properties, molecular dynamics, plasticizer additives

Procedia PDF Downloads 430

Authors: Shrabani Ghosh

Abstract:

Automatic offensive language detection in social media has become a stirring task in today's NLP. Manual Offensive language detection is tedious and laborious work where automatic methods based on machine learning are only alternatives. Previous works have done sentiment analysis over social media in different ways such as supervised, semi-supervised, and unsupervised manner. Domain adaptation in a semi-supervised way has also been explored in NLP, where the source domain and the target domain are different. In domain adaptation, the source domain usually has a large amount of labeled data, while only a limited amount of labeled data is available in the target domain. Pretrained transformers like BERT, RoBERTa models are fine-tuned to perform text classification in an unsupervised manner to perform further pre-train masked language modeling (MLM) tasks. In previous work, hate speech detection has been explored in Gab.ai, which is a free speech platform described as a platform of extremist in varying degrees in online social media. In domain adaptation process, Twitter data is used as the source domain, and Gab data is used as the target domain. The performance of domain adaptation also depends on the cross-domain similarity. Different distance measure methods such as L2 distance, cosine distance, Maximum Mean Discrepancy (MMD), Fisher Linear Discriminant (FLD), and CORAL have been used to estimate domain similarity. Certainly, in-domain distances are small, and between-domain distances are expected to be large. The previous work finding shows that pretrain masked language model (MLM) fine-tuned with a mixture of posts of source and target domain gives higher accuracy. However, in-domain performance of the hate classifier on Twitter data accuracy is 71.78%, and out-of-domain performance of the hate classifier on Gab data goes down to 56.53%. Recently self-supervised learning got a lot of attention as it is more applicable when labeled data are scarce. Few works have already been explored to apply self-supervised learning on NLP tasks such as sentiment classification. Self-supervised language representation model ALBERTA focuses on modeling inter-sentence coherence and helps downstream tasks with multi-sentence inputs. Self-supervised attention learning approach shows better performance as it exploits extracted context word in the training process. In this work, a self-supervised attention mechanism has been proposed to detect hate speech on Gab.ai. This framework initially classifies the Gab dataset in an attention-based self-supervised manner. On the next step, a semi-supervised classifier trained on the combination of labeled data from the first step and unlabeled data. The performance of the proposed framework will be compared with the results described earlier and also with optimized outcomes obtained from different optimization techniques.

Keywords: attention learning, language model, offensive language detection, self-supervised learning

Procedia PDF Downloads 90

Authors: Hacene Benkhoula, Mohamed Badreddine Benabdella, Hamid Bouzeboudja, Abderrahmane Asraoui

Abstract:

The wind is a random variable difficult to master, for this, we developed a mathematical and statistical methods enable to modeling and forecast wind power. Gaussian Processes (GP) is one of the most widely used families of stochastic processes for modeling dependent data observed over time, or space or time and space. GP is an underlying process formed by unrecognized operator’s uses to solve a problem. The purpose of this paper is to present how to forecast wind power by using the GP. The Gaussian process method for forecasting are presented. To validate the presented approach, a simulation under the MATLAB environment has been given.

Keywords: wind power, Gaussien process, modelling, forecasting

Procedia PDF Downloads 386

Authors: Marius Gavrilescu, Sabina-Adriana Floria, Florin Leon, Silvia Curteanu, Costel Anton

Abstract:

Natural sciences provide a wide range of experimental data whose related problems require study and modeling beyond the capabilities of conventional methodologies. Such problems have solution spaces whose complexity and high dimensionality require correspondingly complex regression methods for proper characterization. In this context, we propose an optimization method which consists in a hybrid dual optimizer setup: a global optimizer based on a modified variant of the popular Imperialist Competitive Algorithm (ICA), and a local optimizer based on a gradient descent approach. The ICA is modified such that intermediate solution populations are more quickly and efficiently pruned of low-fitness individuals by appropriately altering the assimilation, revolution and competition phases, which, combined with an initialization strategy based on low-discrepancy sampling, allows for a more effective exploration of the corresponding solution space. Subsequently, gradient-based optimization is used locally to seek the optimal solution in the neighborhoods of the solutions found through the modified ICA. We use this combined approach to find the optimal configuration and weights of a fully-connected neural network, resulting in regression models used to characterize the process of obtained bricks using silicon-based materials. Installations in the raw ceramics industry, i.e., bricks, are characterized by significant energy consumption and large quantities of emissions. Thus, the purpose of our approach is to determine by simulation the working conditions, including the manufacturing mix recipe with the addition of different materials, to minimize the emissions represented by CO and CH4. Our approach determines regression models which perform significantly better than those found using the traditional ICA for the aforementioned problem, resulting in better convergence and a substantially lower error.

Keywords: optimization, biologically inspired algorithm, regression models, bricks, emissions

Procedia PDF Downloads 64

Authors: Samira Karimi-Mansoub, Rahem Abri

Abstract:

Currently, users expect high quality and personalized information from search results. To satisfy user’s needs, personalized approaches to web search have been proposed. These approaches can provide the most appropriate answer for user’s needs by using user context and incorporating information about query provided by combining search technologies. To carry out personalized web search, there is a need to make different techniques on whole of user search process. There are the number of possible deployment of personalized approaches such as personalized web search, personalized recommendation, personalized summarization and filtering systems and etc. but the common feature of all approaches in various domains is that user modeling is utilized to provide personalized information from the Web. So the most important work in personalized approaches is user model mining. User modeling applications and technologies can be used in various domains depending on how the user collected information may be extracted. In addition to, the used techniques to create user model is also different in each of these applications. Since in the previous studies, there was not a complete survey in this field, our purpose is to present a survey on applications and techniques of user modeling from the viewpoint of improvement in search results by considering the existing literature and researches.

Keywords: filtering systems, personalized web search, user modeling, user search behavior

Procedia PDF Downloads 261

Authors: Murat Gunduz, Mustafa Ozdemir

Abstract:

In this research, a framework is to be proposed to model the safety performance in construction sites. Determinants of safety performance are to be defined through extensive literature review and a multidimensional safety performance model is to be developed. In this context, a questionnaire is to be administered to construction companies with sites. The collected data through questionnaires including linguistic terms are then to be defuzzified to get concrete numbers by using fuzzy set theory which provides strong and significant instruments for the measurement of ambiguities and provides the opportunity to meaningfully represent concepts expressed in the natural language. The validity of the proposed safety performance model, relationships between determinants of safety performance are to be analyzed using the structural equation modeling (SEM) which is a highly strong multi variable analysis technique that makes possible the evaluation of latent structures. After validation of the model, a safety performance index assessment tool is to be proposed by the help of software. The proposed safety performance assessment tool will be based on the empirically validated theoretical model.

Keywords: Fuzzy set theory, safety performance assessment, safety index, structural equation modeling (SEM), construction sites

Procedia PDF Downloads 496