Search results for: pre-trained models

Authors: Vinayak Bassi, Rajpreet Singh

Abstract:

Over the years, with the emergence of sophisticated computers and algorithms, finance has been quantified using computational prowess. Asset valuation has been one of the key components of quantitative finance. In fact, it has become one of the embryonic steps in determining risk related to a portfolio, the main goal of quantitative finance. This study comprises a drawing comparison between valuation output generated by two stochastic dynamic models, namely Black-Scholes and Dupire’s bi-dimensionality model. Both of these models are formulated for computing the valuation function for a portfolio of European options using Monte Carlo simulation methods. Although Monte Carlo algorithms have a slower convergence rate than calculus-based simulation techniques (like FDM), they work quite effectively over high-dimensional dynamic models. A fidelity gap is analyzed between the static (historical) and stochastic inputs for a sample portfolio of underlying assets. In order to enhance the performance efficiency of the model, the study emphasized the use of variable reduction methods and customizing random number generators to implement parallelization. An attempt has been made to further implement the Dupire’s model on a GPU to achieve higher computational performance. Furthermore, ideas have been discussed around the performance enhancement and bottleneck identification related to the implementation of options-pricing models on GPUs.

Keywords: monte carlo, stochastic models, computational finance, parallel programming, scientific computing

Procedia PDF Downloads 164

Authors: Fidelia A. Orji, Julita Vassileva

Abstract:

This research aims to develop machine learning models for students' academic performance and study strategy prediction, which could be generalized to all courses in higher education. Key learning attributes (intrinsic, extrinsic, autonomy, relatedness, competence, and self-esteem) used in building the models are chosen based on prior studies, which revealed that the attributes are essential in students’ learning process. Previous studies revealed the individual effects of each of these attributes on students’ learning progress. However, few studies have investigated the combined effect of the attributes in predicting student study strategy and academic performance to reduce the dropout rate. To bridge this gap, we used Scikit-learn in python to build five machine learning models (Decision Tree, K-Nearest Neighbour, Random Forest, Linear/Logistic Regression, and Support Vector Machine) for both regression and classification tasks to perform our analysis. The models were trained, evaluated, and tested for accuracy using 924 university dentistry students' data collected by Chilean authors through quantitative research design. A comparative analysis of the models revealed that the tree-based models such as the random forest (with prediction accuracy of 94.9%) and decision tree show the best results compared to the linear, support vector, and k-nearest neighbours. The models built in this research can be used in predicting student performance and study strategy so that appropriate interventions could be implemented to improve student learning progress. Thus, incorporating strategies that could improve diverse student learning attributes in the design of online educational systems may increase the likelihood of students continuing with their learning tasks as required. Moreover, the results show that the attributes could be modelled together and used to adapt/personalize the learning process.

Keywords: classification models, learning strategy, predictive modeling, regression models, student academic performance, student motivation, supervised machine learning

Procedia PDF Downloads 129

Authors: Imene Skhakhfa, Lahbaci Ouerdachi

Abstract:

To ensure the overall coherence of simulated results, it is necessary to develop a robust validation process. In many applications, it is no longer content to calibrate and validate the model only in relation to the hydro graph measured at the outlet, but we try to better simulate the functioning of the watershed in space. Therefore the timing also performs compared to other variables such as water level measurements in intermediate stations or groundwater levels. As part of this work, we limit ourselves to modeling flood of short duration for which the process of evapotranspiration is negligible. The main parameters to identify the models are related to the method of unit hydro graph (HU). Three different models were tested: SNYDER, CLARK and SCS. These models differ in their mathematical structure and parameters to be calibrated while hydrological data are the same, the initial water content and precipitation. The models are compared on the basis of their performance in terms six objective criteria, three global criteria and three criteria representing volume, peak flow, and the mean square error. The first type of criteria gives more weight to strong events whereas the second considers all events to be of equal weight. The results show that the calibrated parameter values are dependent and also highlight the problems associated with the simulation of low flow events and intermittent precipitation.

Keywords: model calibration, intensity, runoff, hydrograph

Procedia PDF Downloads 486

Authors: Abdunaser Abduelmula, Maria Luisa M. Bastos, José A. Gonçalves

Abstract:

The modeling of the earth's surface and evaluation of urban environment, with 3D models, is an important research topic. New stereo capabilities of high-resolution optical satellites images, such as the tri-stereo mode of Pleiades, combined with new image matching algorithms, are now available and can be applied in urban area analysis. In addition, photogrammetry software packages gained new, more efficient matching algorithms, such as SGM, as well as improved filters to deal with shadow areas, can achieve denser and more precise results. This paper describes a comparison between 3D data extracted from tri-stereo and dual stereo satellite images, combined with pixel based matching and Wallis filter. The aim was to improve the accuracy of 3D models especially in urban areas, in order to assess if satellite images are appropriate for a rapid evaluation of urban environments. The results showed that 3D models achieved by Pleiades tri-stereo outperformed, both in terms of accuracy and detail, the result obtained from a Geo-eye pair. The assessment was made with reference digital surface models derived from high-resolution aerial photography. This could mean that tri-stereo images can be successfully used for the proposed urban change analyses.

Keywords: 3D models, environment, matching, pleiades

Procedia PDF Downloads 330

Authors: Gonzalo García-Reyes

Abstract:

Conformastat spherically symmetric exact solutions of Einstein's field equations representing matter distributions made of fluid both perfect and anisotropic from given solutions of Poisson's equation of Newtonian gravity are investigated. The approach is used in the construction of new relativistic models of thick spherical shells and three-component models of galaxies (bulge, disk, and dark matter halo), writing, in this case, the metric in cylindrical coordinates. In addition, the circular motion of test particles (rotation curves) along geodesics on the equatorial plane of matter configurations and the stability of the orbits against radial perturbations are studied. The models constructed satisfy all the energy conditions.

Keywords: general relativity, exact solutions, spherical symmetry, galaxy, kinematics and dynamics, dark matter

Procedia PDF Downloads 88

Authors: Subhan Ahmad, Pradeep Bhargava, Ajay Chourasia

Abstract:

Shear failure in reinforced concrete beams without shear reinforcement leads to loss of property and life since a very little or no warning occurs before failure as in case of flexural failure. Shear strength of reinforced concrete beams decreases as its depth increases. This phenomenon is generally called as the size effect. In this paper, a comparative analysis is performed to estimate the performance of shear strength models in capturing the size effect of reinforced concrete beams made with conventional concrete, self-compacting concrete, and recycled aggregate concrete. Four shear strength models that account for the size effect in shear are selected from the literature and applied on the datasets of slender reinforced concrete beams. Beams prepared with conventional concrete, self-compacting concrete, and recycled aggregate concrete are considered for the analysis. Results showed that all the four models captured the size effect in shear effectively and produced conservative estimates of the shear strength for beams made with normal strength conventional concrete. These models yielded unconservative estimates for high strength conventional concrete beams with larger effective depths ( > 450 mm). Model of Bazant and Kim (1984) captured the size effect precisely and produced conservative estimates of shear strength of self-compacting concrete beams at all the effective depths. Also, shear strength models considered in this study produced unconservative estimates of shear strength for recycled aggregate concrete beams at all effective depths.

Keywords: reinforced concrete beams; shear strength; prediction models; size effect

Procedia PDF Downloads 161

Authors: Hamidreza Ghazvinian, Khosro Ghazvinian, Touba Khodaiean

Abstract:

The importance of evaporation estimation in water resources and agricultural studies is undeniable. Pan evaporation are used as an indicator to determine the evaporation of lakes and reservoirs around the world due to the ease of interpreting its data. In this research, intelligent models were investigated in estimating pan evaporation on a daily basis. Shahroud and Mayamey were considered as the studied cities. These two cities are located in Semnan province in Iran. The mentioned cities have dry weather conditions that are susceptible to high evaporation potential. Meteorological data of 11 years of synoptic stations of Shahrood and Mayamey cities were used. The intelligent models used in this study are Artificial Neural Network (ANN), Least Squares Support Vector Machine (LSSVM), and M5 tree models. Meteorological parameters of minimum and maximum air temperature (Tmax, Tmin), wind speed (WS), sunshine hours (SH), air pressure (PA), relative humidity (RH) as selected input data and evaporation data from pan (EP) to The output data was considered. 70% of data is used at the education level, and 30 % of the data is used at the test level. Models used with explanation coefficient evaluation (R2) Root of Mean Squares Error (RMSE) and Mean Absolute Error (MAE). The results for the two Shahroud and Mayamey stations showed that the above three models' operations are rather appropriate.

Keywords: pan evaporation, intelligent methods, shahroud, mayamey

Procedia PDF Downloads 75

Authors: Awol Seid Ebrie

Abstract:

HIV results as an incurable disease, AIDS. After a person is infected with virus, the virus gradually destroys all the infection fighting cells called CD4 cells and makes the individual susceptible to opportunistic infections which cause severe or fatal health problems. Several studies show that the CD4 cells count is the most determinant indicator of the effectiveness of the treatment or progression of the disease. The objective of this paper is to investigate the progression of the disease over time among patient under HAART treatment. Two main approaches of the generalized multilevel ordinal models; namely the proportional odds model and the nonproportional odds model have been applied to the HAART data. Also, the multilevel part of both models includes random intercepts and random coefficients. In general, four models are explored in the analysis and then the models are compared using the deviance information criteria. Of these models, the random coefficients nonproportional odds model is selected as the best model for the HAART data used as it has the smallest DIC value. The selected model shows that the progression of the disease increases as the time under the treatment increases. In addition, it reveals that gender, baseline clinical stage and functional status of the patient have a significant association with the progression of the disease.

Keywords: nonproportional odds model, proportional odds model, random coefficients model, random intercepts model

Procedia PDF Downloads 421

Authors: Abhishek Saha, Serene Tay, Gerard Pijcke

Abstract:

The availability of high-resolution topography and rainfall information in urban areas has made it necessary to revise modeling approaches used for simulating flood risk assessments. Lidar derived elevation models that have 1m or lower resolutions are becoming widely accessible. The classical approaches of 1D-2D flow models where channel flow is simulated and coupled with a coarse resolution 2D overland flow models may not fully utilize the information provided by high-resolution data. In this context, a study was undertaken to compare three different modeling approaches to simulate flooding in an urban area. The first model used is the base model used is Sobek, which uses 1D model formulation together with hydrologic boundary conditions and couples with an overland flow model in 2D. The second model uses a full 2D model for the entire area with shallow water equations at the resolution of the digital elevation model (DEM). These models are compared against another shallow water equation solver in 2D, which uses a subgrid method for grid refinement. These models are simulated for different horizontal resolutions of DEM varying between 1m to 5m. The results show a significant difference in inundation extents and water levels for different DEMs. They are also sensitive to the different numerical models with the same physical parameters, such as friction. The study shows the importance of having reliable field observations of inundation extents and levels before a choice of model and data can be made for spatial flood risk assessments.

Keywords: flooding, DEM, shallow water equations, subgrid

Procedia PDF Downloads 142

Authors: Dalin Si, Azizan Aziz, Bertrand Lasternas

Abstract:

To encourage building owners to purchase electricity at the wholesale market and reduce building peak demand, this study aims to develop models that predict day-ahead hourly electricity consumption and demand using artificial neural network (ANN) and support vector machine (SVM). All prediction models are built in Python, with tool Scikit-learn and Pybrain. The input data for both consumption and demand prediction are time stamp, outdoor dry bulb temperature, relative humidity, air handling unit (AHU), supply air temperature and solar radiation. Solar radiation, which is unavailable a day-ahead, is predicted at first, and then this estimation is used as an input to predict consumption and demand. Models to predict consumption and demand are trained in both SVM and ANN, and depend on cooling or heating, weekdays or weekends. The results show that ANN is the better option for both consumption and demand prediction. It can achieve 15.50% to 20.03% coefficient of variance of root mean square error (CVRMSE) for consumption prediction and 22.89% to 32.42% CVRMSE for demand prediction, respectively. To conclude, the presented models have potential to help building owners to purchase electricity at the wholesale market, but they are not robust when used in demand response control.

Keywords: building energy prediction, data mining, demand response, electricity market

Procedia PDF Downloads 317

Authors: Sandeep Kaur, Jenny Vuong, Marcel Julliard, Sean O'Donoghue

Abstract:

Time-series data are useful for modelling as they can enable model-evaluation. However, when reconstructing models from phosphoproteomic data, often non-exact methods are utilised, as the knowledge regarding the network structure, such as, which kinases and phosphatases lead to the observed phosphorylation state, is incomplete. Thus, such reactions are often hypothesised, which gives rise to uncertainty. Here, we propose a framework, implemented via a web-based tool (as an extension to Minardo), which given time-series phosphoproteomic datasets, can generate κ models. The incompleteness and uncertainty in the generated model and reactions are clearly presented to the user via the visual method. Furthermore, we demonstrate, via a toy EGF signalling model, the use of algorithmic verification to verify κ models. Manually formulated requirements were evaluated with regards to the model, leading to the highlighting of the nodes causing unsatisfiability (i.e. error causing nodes). We aim to integrate such methods into our web-based tool and demonstrate how the identified erroneous nodes can be presented to the user via the visual method. Thus, in this research we present a framework, to enable a user to explore phosphorylation proteomic time-series data in the context of models. The observer can visualise which reactions in the model are highly uncertain, and which nodes cause incorrect simulation outputs. A tool such as this enables an end-user to determine the empirical analysis to perform, to reduce uncertainty in the presented model - thus enabling a better understanding of the underlying system.

Keywords: κ-models, model verification, time-series phosphoproteomic datasets, uncertainty and error visualisation

Procedia PDF Downloads 259

Authors: Abd Elrahman Elgamala, N. Darwish, I. Bondouk, Sh. Hamada

Abstract:

Available experimental angular distributions for ⁶Li elastically scattered from ¹⁶O nucleus in the energy range 13.0–50.0 MeV are investigated and reanalyzed using optical model of the conventional phenomenological potential and also using double folding optical model of different interaction models: DDM3Y1, CDM3Y1, CDM3Y2, and CDM3Y3. All the involved models of interaction are of M3Y Paris except DDM3Y1 which is of M3Y Reid and the main difference between them lies in the different values for the parameters of the incorporated density distribution function F(ρ). We have extracted the renormalization factor N_R for ⁶Li+¹⁶O nuclear system in the energy range 13.0–50.0 MeV using the aforementioned interaction models.

Keywords: elastic scattering, optical model, folding potential, density distribution

Procedia PDF Downloads 142

Authors: D.Mendes, J. Henriques, P. Carvalho, T. Rocha, S. Paredes, R. Cabiddu, R. Trimer, R. Mendes, A. Borghi-Silva, L. Kaminsky, E. Ashley, R. Arena, J. Myers

Abstract:

The continued exploration of clinically relevant predictive models continues to be an important pursuit. Cardiorespiratory fitness (CRF) portends clinical vital information and as such its accurate prediction is of high importance. Therefore, the aim of the current study was to develop a data-driven model, based on computational intelligence techniques and, in particular, clustering approaches, to predict CRF. Two prediction models were implemented and compared: 1) the traditional Wasserman/Hansen Equations; and 2) an interpretable clustering approach. Data used for this analysis were from the 'FRIEND - Fitness Registry and the Importance of Exercise: The National Data Base'; in the present study a subset of 10690 apparently healthy individuals were utilized. The accuracy of the models was performed through the computation of sensitivity, specificity, and geometric mean values. The results show the superiority of the clustering approach in the accurate estimation of CRF (i.e., maximal oxygen consumption).

Keywords: cardiorespiratory fitness, data-driven models, knowledge extraction, machine learning

Procedia PDF Downloads 286

Authors: Elias K. Maragos, Petros E. Maravelakis

Abstract:

In Dynamic Data Envelopment Analysis (DDEA), which is a subfield of Data Envelopment Analysis (DEA), the productivity of Decision Making Units (DMUs) is considered in relation to time. In this case, as it is accepted by the most of the researchers, there are outputs, which are produced by a DMU to be used as inputs in a future time. Those outputs are known as intermediates. The common models, in DDEA, do not take into account the shape of the distribution of those inputs, outputs or intermediates data, assuming that the distribution of the virtual value of them does not deviate from linearity. This weakness causes the limitation of the accuracy of the analytical power of the traditional DDEA models. In this paper, the authors, using the concept of piecewise linear inputs and outputs, propose an extended DDEA model. The proposed model increases the flexibility of the traditional DDEA models and improves the measurement of the dynamic performance of DMUs.

Keywords: Dynamic Data Envelopment Analysis, DDEA, piecewise linear inputs, piecewise linear outputs

Procedia PDF Downloads 162

Authors: A. G. Matveev

Abstract:

The copyrights system is a combination of different elements. The number, content and the correlation of these elements are different for different legal orders. The models of copyrights systems display this system in terms of the interaction of economic and author's moral rights. Monistic and dualistic models are the most popular ones. The article deals with different points of view on the monism and dualism in copyright system. A specific model of the copyright in Switzerland in the XXth century is analyzed. The evolution of a French dualistic model of copyright is shown. The author believes that one should talk not about one, but rather about a number of dualism forms of copyright system.

Keywords: copyright, exclusive copyright, economic rights, author's moral rights, rights of personality, monistic model, dualistic model

Procedia PDF Downloads 420

Authors: Yogendra Sisodia

Abstract:

Researchers are becoming more interested in extracting useful information from legal documents thanks to the development of large-scale language models in natural language processing (NLP), and deep learning has accelerated the creation of powerful text mining models. Legal fields like contracts benefit greatly from semantic text search since it makes it quick and easy to find related clauses. After collecting sentence embeddings, it is relatively simple to locate sentences with a comparable meaning throughout the entire legal corpus. The author of this research investigated two pre-trained language models for this task: MiniLM and Roberta, and further fine-tuned them on Legal Contracts. The author used Multiple Negative Ranking Loss for the creation of sentence transformers. The fine-tuned language models and sentence transformers showed promising results.

Keywords: legal contracts, multiple negative ranking loss, natural language inference, sentence transformers, semantic textual similarity

Procedia PDF Downloads 109

Authors: Herlandson C. Moura, Jorge H. Bidinotto, Eduardo M. Belo

Abstract:

The present work proposes the development of an adaptive control system which enables the suppression of Pilot Induced Oscillations (PIO) in Digital Fly-By-Wire (DFBW) aircrafts. The proposed system consists of a Modified Model Reference Adaptive Control (M-MRAC) integrated with the Gain Scheduling technique. The PIO oscillations are detected using a Real Time Oscillation Verifier (ROVER) algorithm, which then enables the system to switch between two reference models; one in PIO condition, with low proneness to the phenomenon and another one in normal condition, with high (or medium) proneness. The reference models are defined in a closed loop condition using the Linear Quadratic Regulator (LQR) control methodology for Multiple-Input-Multiple-Output (MIMO) systems. The implemented algorithms are simulated in software implementations with state space models and commercial flight simulators as the controlled elements and with pilot dynamics models. A sequence of pitch angles is considered as the reference signal, named as Synthetic Task (Syntask), which must be tracked by the pilot models. The initial outcomes show that the proposed system can detect and suppress (or mitigate) the PIO oscillations in real time before it reaches high amplitudes.

Keywords: adaptive control, digital Fly-By-Wire, oscillations suppression, PIO

Procedia PDF Downloads 134

Authors: Riona Dighe

Abstract:

This research attempts to identify an alternative approach to the measurement of Gross National Happiness (GNH). It uses artificial intelligence (AI), incorporating natural language processing (NLP) and sentiment analysis to measure GNH. We use ‘off the shelf’ NLP models responsible for the sentiment analysis of a sentence as a building block for this research. We constructed an algorithm using NLP models to derive a sentiment analysis score against sentences. This was then tested against a sample of 20 respondents to derive a sentiment analysis score. The scores generated resembled human responses. By utilising the MLP classifier, decision tree, linear model, and K-nearest neighbors, we were able to obtain a test accuracy of 89.97%, 54.63%, 52.13%, and 47.9%, respectively. This gave us the confidence to use the NLP models against sentences in websites to measure the GNH of a country.

Keywords: artificial intelligence, NLP, sentiment analysis, gross national happiness

Procedia PDF Downloads 123

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Keywords: deep learning, long short term memory, energy, renewable energy load forecasting

Procedia PDF Downloads 267

Authors: Adel Bougamouza, Boualam Remini, Abd El Hadi Ammari, Feteh Sakhraoui

Abstract:

The assessment of sediments being carried by a river is importance for planning and designing of various water resources projects. In this study, Artificial Neural Network Techniques are used to estimate the daily suspended sediment concentration for the corresponding daily discharge flow in the upstream of Foum El Gherza dam, Biskra, Algeria. The FFNN, GRNN, and RBNN models are established for estimating current suspended sediment values. Some statistics involving RMSE and R2 were used to evaluate the performance of applied models. The comparison of three AI models showed that the RBNN model performed better than the FFNN and GRNN models with R2 = 0.967 and RMSE= 5.313 mg/l. Therefore, the ANN model had capability to improve nonlinear relationships between discharge flow and suspended sediment with reasonable precision.

Keywords: artificial neural network, Oued Abiod watershed, feedforward network, generalized regression network, radial basis network, sediment concentration

Procedia PDF Downloads 420

Authors: Do-Jin Jang, Sung-Ah Kim

Abstract:

In designing a kinetic façade, it is hard for the designer to make digital models due to its complex geometry with motion. This paper aims to present a methodology of converting a point cloud of a physical model into a single digital model with a certain topology and motion. The method uses a Microsoft Kinect sensor, and color markers were defined and applied to three paper folding-inspired designs. Although the resulted digital model cannot represent the whole folding range of the physical model, the method supports the designer to conduct a performance-oriented design process with the rough physical model in the reduced folding range.

Keywords: design media, kinetic facades, tangible user interface, 3D scanning

Procedia PDF Downloads 414

Authors: Ojoniyi Oluwafeyekikunmi Okiki

Abstract:

Notwithstanding advances in disturbing wound care and control, infections remain a main motive of mortality, morbidity, and financial disruption in tens of millions of wound sufferers around the sector. Animal models have become popular gear for analyzing a big selection of outside worrying wound infections and trying out new antimicrobial techniques. This evaluation covers experimental infections in animal models of surgical wounds, pores and skin abrasions, burns, lacerations, excisional wounds, and open fractures. Animal modes of external stressful wound infections stated via extraordinary investigators vary in animal species used, microorganism traces, the quantity of microorganisms carried out, the dimensions of the wounds, and, for burn infections, the period of time the heated object or liquid is in contact with the skin. As antibiotic resistance continues to grow, new antimicrobial procedures are urgently needed. Those have to be examined using popular protocols for infections in external stressful wounds in animal models.

Keywords: surgical wounds, animals, wound infections, burns, wound models, colony-forming gadgets, lacerated wounds

Procedia PDF Downloads 13

Authors: Debarati Bhaumik, Diptish Dey

Abstract:

Multilevel models, increasingly deployed in industries such as insurance, food production, and entertainment within functions such as marketing and supply chain management, need to be transparent and ethical. Applications usually result in binary classification within groups or hierarchies based on a set of input features. Using open-source datasets, we demonstrate that popular explainability methods, such as SHAP and LIME, consistently underperform inaccuracy when interpreting these models. They fail to predict the order of feature importance, the magnitudes, and occasionally even the nature of the feature contribution (negative versus positive contribution to the outcome). Besides accuracy, the computational intractability of SHAP for binomial classification is a cause of concern. For transparent and ethical applications of these hierarchical statistical models, sound audit frameworks need to be developed. In this paper, we propose an audit framework for technical assessment of multilevel regression models focusing on three aspects: (i) model assumptions & statistical properties, (ii) model transparency using different explainability methods, and (iii) discrimination assessment. To this end, we undertake a quantitative approach and compare intrinsic model methods with SHAP and LIME. The framework comprises a shortlist of KPIs, such as PoCE (Percentage of Correct Explanations) and MDG (Mean Discriminatory Gap) per feature, for each of these three aspects. A traffic light risk assessment method is furthermore coupled to these KPIs. The audit framework will assist regulatory bodies in performing conformity assessments of AI systems using multilevel binomial classification models at businesses. It will also benefit businesses deploying multilevel models to be future-proof and aligned with the European Commission’s proposed Regulation on Artificial Intelligence.

Keywords: audit, multilevel model, model transparency, model explainability, discrimination, ethics

Procedia PDF Downloads 95

Authors: Nima Pirhadi, Shao Yong Bo, Xusheng Wan, Jianguo Lu, Jilei Hu

Abstract:

Although gravels and gravelly soils are assumed to be non-liquefiable because of high conductivity and small modulus; however, the occurrence of this phenomenon in some historical earthquakes, especially recently earthquakes during 2008 Wenchuan, Mw= 7.9, 2014 Cephalonia, Greece, Mw= 6.1 and 2016, Kaikoura, New Zealand, Mw = 7.8, has been promoted the essential consideration to evaluate risk assessment and hazard analysis of seismic gravelly soil liquefaction. Due to the limitation in sampling and laboratory testing of this type of soil, in situ tests and site exploration of case histories are the most accepted procedures. Of all in situ tests, dynamic penetration test (DPT), Which is well known as the Chinese dynamic penetration test, and shear wave velocity (Vs) test, have been demonstrated high performance to evaluate seismic gravelly soil liquefaction. However, the lack of a sufficient number of case histories provides an essential limitation for developing new models. This study at first investigates recent earthquakes that caused liquefaction in gravelly soils to collect new data. Then, it adds these data to the available literature’s dataset to extend them and finally develops new models to assess seismic gravelly soil liquefaction. To validate the presented models, their results are compared to extra available models. The results show the reasonable performance of the proposed models and the critical effect of gravel content (GC)% on the assessment.

Keywords: liquefaction, gravel, dynamic penetration test, shear wave velocity

Procedia PDF Downloads 201

Authors: S. M. Gupta, Vanita Aggarwal, Som Nath Sachdeva

Abstract:

The work reported through this paper is an experimental work conducted on High Performance Concrete (HPC) with super plasticizer with the aim to develop some models suitable for prediction of compressive strength of HPC mixes. In this study, the effect of varying proportions of fly ash (0% to 50% at 10% increment) on compressive strength of high performance concrete has been evaluated. The mix designs studied were M30, M40 and M50 to compare the effect of fly ash addition on the properties of these concrete mixes. In all eighteen concrete mixes have been designed, three as conventional concretes for three grades under discussion and fifteen as HPC with fly ash with varying percentages of fly ash. The concrete mix designing has been done in accordance with Indian standard recommended guidelines i.e. IS: 10262. All the concrete mixes have been studied in terms of compressive strength at 7 days, 28 days, 90 days and 365 days. All the materials used have been kept same throughout the study to get a perfect comparison of values of results. The models for compressive strength prediction have been developed using Linear Regression method (LR), Artificial Neural Network (ANN) and Leave One Out Validation (LOOV) methods.

Keywords: high performance concrete, fly ash, concrete mixes, compressive strength, strength prediction models, linear regression, ANN

Procedia PDF Downloads 446

Authors: Duncan Oteki, Andebut Yeneneh, Daba Gedafa, Nabil Suleiman

Abstract:

Most agencies lack the equipment required to measure the dynamic modulus (|E*|) of asphalt mixtures, necessitating the need to use predictive models. This study compared measured |E*| values for nine North Dakota asphalt mixes using the original Witczak, modified Witczak, and Hirsch models. The influence of temperature on the |E*| models was investigated, and Pavement ME simulations were conducted using measured |E*| and predictions from the most accurate |E*| model. The results revealed that the original Witczak model yielded the lowest Se/Sy and highest R² values, indicating the lowest bias and highest accuracy, while the poorest overall performance was exhibited by the Hirsch model. Using predicted |E*| as inputs in the Pavement ME generated conservative distress predictions compared to using measured |E*|. The original Witczak model was recommended for predicting |E*| for low-reliability pavements in North Dakota.

Keywords: asphalt mixture, binder, dynamic modulus, MEPDG, pavement ME, performance, prediction

Procedia PDF Downloads 49

Authors: Andrey Khalov

Abstract:

The rapid proliferation of unstructured data in IT infrastructure management demands innovative approaches for extracting actionable knowledge. This paper presents a framework for ontology-based knowledge extraction that combines relational graph neural networks (R-GNN) with large language models (LLMs). The proposed method leverages the DOLCE framework as the foundational ontology, extending it with concepts from ITSMO for domain-specific applications in IT service management and outsourcing. A key component of this research is the use of transformer-based models, such as DeBERTa-v3-large, for automatic entity and relationship extraction from unstructured texts. Furthermore, the paper explores how transfer learning techniques can be applied to fine-tune large language models (LLaMA) for using to generate synthetic datasets to improve precision in BERT-based entity recognition and ontology alignment. The resulting IT Ontology (ITO) serves as a comprehensive knowledge base that integrates domain-specific insights from ITIL processes, enabling more efficient decision-making. Experimental results demonstrate significant improvements in knowledge extraction and relationship mapping, offering a cutting-edge solution for enhancing cognitive computing in IT service environments.

Keywords: ontology mapping, R-GNN, knowledge extraction, large language models, NER, knowlege graph

Procedia PDF Downloads 19

Authors: Dennis Kreutzer, Sarah Müller-Abdelrazeq, Ingrid Isenhardt

Abstract:

Resource scarcity, energy transition and the planned climate neutrality pose enormous challenges for manufacturing companies. In order to achieve these goals and a holistic sustainable development, the European Union has listed the circular economy as part of the Circular Economy Action Plan. In addition to a reduction in resource consumption, reduced emissions of greenhouse gases and a reduced volume of waste, the principles of the circular economy also offer enormous economic potential for companies, such as the generation of new circular business models. However, many manufacturing companies, especially small and medium-sized enterprises, do not have the necessary capacity to plan their transformation. They need support and strategies on the path to circular transformation, because this change affects not only production but also the entire company. Maturity models offer an approach, as they enable companies to determine the current status of their transformation processes. In addition, companies can use the models to identify transformation strategies and thus promote the transformation process. While maturity models are established in other areas, e.g. IT or project management, only a few circular economy maturity models can be found in the scientific literature. The aim of this paper is to analyse the identified maturity models of the circular economy through a systematic literature review (SLR) and, besides other aspects, to check their completeness as well as their quality. Since the terms "maturity model" and "readiness model" are often used to assess the transformation process, this paper considers both types of models to provide a more comprehensive result. For this purpose, circular economy maturity models at the company (micro) level were identified from the literature, compared, and analysed with regard to their theoretical and methodological structure. A specific focus was placed, on the one hand, on the analysis of the business units considered in the respective models and, on the other hand, on the underlying metrics and indicators in order to determine the individual maturity level of the entire company. The results of the literature review show, for instance, a significant difference in the holism of their assessment framework. Only a few models include the entire company with supporting areas outside the value-creating core process, e.g. strategy and vision. Additionally, there are large differences in the number and type of indicators as well as their metrics. For example, most models often use subjective indicators and very few objective indicators in their surveys. It was also found that there are rarely well-founded thresholds between the levels. Based on the generated results, concrete ideas and proposals for a research agenda in the field of circular economy maturity models are made.

Keywords: maturity model, circular economy, transformation, metric, assessment

Procedia PDF Downloads 114

Authors: Snezhana G. Gocheva-Ilieva, Maya P. Stoimenova

Abstract:

Ambient air pollution with fine particulate matter (PM10) is a systematic permanent problem in many countries around the world. The accumulation of a large number of measurements of both the PM10 concentrations and the accompanying atmospheric factors allow for their statistical modeling to detect dependencies and forecast future pollution. This study applies the classification and regression trees (CART) method for building and analyzing PM10 models. In the empirical study, average daily air data for the city of Pleven, Bulgaria for a period of 5 years are used. Predictors in the models are seven meteorological variables, time variables, as well as lagged PM10 variables and some lagged meteorological variables, delayed by 1 or 2 days with respect to the initial time series, respectively. The degree of influence of the predictors in the models is determined. The selected best CART models are used to forecast future PM10 concentrations for two days ahead after the last date in the modeling procedure and show very accurate results.

Keywords: cross-validation, decision tree, lagged variables, short-term forecasting

Procedia PDF Downloads 195

Authors: Zachary Huffman, Joana Rocha

Abstract:

Wall-pressure fluctuations induced by the turbulent boundary layer (TBL) developed over aircraft are a significant source of aircraft cabin noise. Since the power spectral density (PSD) of these pressure fluctuations is directly correlated with the amount of sound radiated into the cabin, the development of accurate empirical models that predict the PSD has been an important ongoing research topic. The sound emitted can be represented from the pressure fluctuations term in the Reynoldsaveraged Navier-Stokes equations (RANS). Therefore, early TBL empirical models (including those from Lowson, Robertson, Chase, and Howe) were primarily derived by simplifying and solving the RANS for pressure fluctuation and adding appropriate scales. Most subsequent models (including Goody, Efimtsov, Laganelli, Smol’yakov, and Rackl and Weston models) were derived by making modifications to these early models or by physical principles. Overall, these models have had varying levels of accuracy, but, in general, they are most accurate under the specific Reynolds and Mach numbers they were developed for, while being less accurate under other flow conditions. Despite this, recent research into the possibility of using alternative methods for deriving the models has been rather limited. More recent studies have demonstrated that an artificial neural network model was more accurate than traditional models and could be applied more generally, but the accuracy of other machine learning techniques has not been explored. In the current study, an original model is derived using a stepwise regression algorithm in the statistical programming language R, and TBL wall-pressure fluctuations PSD data gathered at the Carleton University wind tunnel. The theoretical advantage of a stepwise regression approach is that it will automatically filter out redundant or uncorrelated input variables (through the process of feature selection), and it is computationally faster than machine learning. The main disadvantage is the potential risk of overfitting. The accuracy of the developed model is assessed by comparing it to independently sourced datasets.

Keywords: aircraft noise, machine learning, power spectral density models, regression models, turbulent boundary layer wall-pressure fluctuations

Procedia PDF Downloads 135