Search results for: generalised linear model

Authors: Mariyam Arif, Ye Liu, Israr Ul Haq, Ahsan Ashfaq

Abstract:

High cost of fossil fuels and intensifying installations of alternate energy generation sources are intimidating main challenges in power systems. Making accurate load forecasting an important and challenging task for optimal energy planning and management at both distribution and generation side. There are many techniques to forecast load but each technique comes with its own limitation and requires data to accurately predict the forecast load. Artificial Neural Network (ANN) is one such technique to efficiently forecast the load. Comparison between two different ranges of input datasets has been applied to dynamic ANN technique using MATLAB Neural Network Toolbox. It has been observed that selection of input data on training of a network has significant effects on forecasted results. Day-wise input data forecasted the load accurately as compared to year-wise input data. The forecasted load is then distributed among the six generators by using the linear programming to get the optimal point of generation. The algorithm is then verified by comparing the results of each generator with their respective generation limits.

Keywords: artificial neural networks, demand-side management, economic dispatch, linear programming, power generation dispatch

Procedia PDF Downloads 189

Authors: Nanine Fouche

Abstract:

The Cape Flats is a low-lying sand-covered expanse of approximately 460 square kilometres, situated to the southeast of the central business district of Cape Town in the Western Cape of South Africa. The aeolian sands masking this area are often loose and compressible in the upper 1m to 1.5m of the surface, and there is a general exceedance of the maximum allowable settlement in these sands. The settlement of shallow foundations on Cape Flats sands is commonly predicted using the results of in-situ tests such as the SPT or DPSH due to the difficulty of retrieving undisturbed samples for laboratory testing. Varying degrees of accuracy and reliability are associated with these methods. More recently, shear wave velocity (Vs) profiles obtained from seismic testing, such as continuous surface wave tests (CSW), are being used for settlement prediction. Such predictions have the advantage of considering non-linear stress-strain behaviour of soil and the degradation of stiffness with increasing strain. CSW tests are rarely executed in the Cape Flats, whereas SPT’s are commonly performed. For this reason, and to facilitate better settlement predictions in Cape Flats sand, equations representing shear wave velocity (Vs) as a function of SPT blow count (N60) and vertical effective stress (v’) were generated by statistical regression of site investigation data. To reveal the most appropriate method of overburden correction, analyses were performed with a separate overburden term (Pa/σ’v) as well as using stress corrected shear wave velocity and SPT blow counts (correcting Vs. and N60 to Vs1and (N1)60respectively). Shear wave velocity profiles and SPT blow count data from three sites masked by Cape Flats sands were utilised to generate 80 Vs-SPT N data pairs for analysis. Investigated terrains included sites in the suburbs of Athlone, Muizenburg, and Atlantis, all underlain by windblown deposits comprising fine and medium sand with varying fines contents. Elastic settlement analysis was also undertaken for the Cape Flats sands, using a non-linear stepwise method based on small-strain stiffness estimates, which was obtained from the best Vs-N60 model and compared to settlement estimates using the general elastic solution with stiffness profiles determined using Stroud’s (1989) and Webb’s (1969) SPT N60-E transformation models. Stroud’s method considers strain level indirectly whereasWebb’smethod does not take account of the variation in elastic modulus with strain. The expression of Vs. in terms of N60 and Pa/σv’ derived from the Atlantis data set revealed the best fit with R2 = 0.83 and a standard error of 83.5m/s. Less accurate Vs-SPT N relations associated with the combined data set is presumably the result of inversion routines used in the analysis of the CSW results showcasing significant variation in relative density and stiffness with depth. The regression analyses revealed that the inclusion of a separate overburden term in the regression of Vs and N60, produces improved fits, as opposed to the stress corrected equations in which the R2 of the regression is notably lower. It is the correction of Vs and N60 to Vs1 and (N1)60 with empirical constants ‘n’ and ‘m’ prior to regression, that introduces bias with respect to overburden pressure. When comparing settlement prediction methods, both Stroud’s method (considering strain level indirectly) and the small strain stiffness method predict higher stiffnesses for medium dense and dense profiles than Webb’s method, which takes no account of strain level in the determination of soil stiffness. Webb’s method appears to be suitable for loose sands only. The Versak software appears to underestimate differences in settlement between square and strip footings of similar width. In conclusion, settlement analysis using small-strain stiffness data from the proposed Vs-N60 model for Cape Flats sands provides a way to take account of the non-linear stress-strain behaviour of the sands when calculating settlement.

Keywords: sands, settlement prediction, continuous surface wave test, small-strain stiffness, shear wave velocity, penetration resistance

Procedia PDF Downloads 175

Authors: T. Watanabe

Abstract:

Combustion analysis of suspended sodium droplet is performed by solving numerically the Navier-Stokes equations and the energy conservation equations. The combustion model consists of the pre-ignition and post-ignition models. The reaction rate for the pre-ignition model is based on the chemical kinetics, while that for the post-ignition model is based on the mass transfer rate of oxygen. The calculated droplet temperature is shown to be in good agreement with the existing experimental data. The temperature field in and around the droplet is obtained as well as the droplet shape variation, and the present numerical model is confirmed to be effective for the combustion analysis.

Keywords: analysis, combustion, droplet, sodium

Procedia PDF Downloads 211

Authors: Manjare Chandraprabha A., S. D. Shirbahadurkar, Manjare Anil S., Paithne Ajay N.

Abstract:

This paper proposes Intonation Modeling for Prosody generation in Neutral speech for Marathi (language spoken in Maharashtra, India) story telling applications. Nowadays audio story telling devices are very eminent for children. In this paper, we proposed tilt model for stressed words in Marathi for speech modification. Tilt model predicts modification in tone of neutral speech. GMM is used to identify stressed words for modification.

Keywords: tilt model, fundamental frequency, statistical parametric speech synthesis, GMM

Procedia PDF Downloads 392

Authors: Sarra Roubi, Mohammed Erramdani, Samir Mbarki

Abstract:

This paper presents an approach for the model-driven generating of Rich Internet Application (RIA) focusing on the graphical aspect. We used well known Model-Driven Engineering (MDE) frameworks and technologies, such as Eclipse Modeling Framework (EMF), Graphical Modeling Framework (GMF), Query View Transformation (QVTo) and Acceleo to enable the design and the code automatic generation of the RIA. During the development of the approach, we focused on the graphical aspect of the application in terms of interfaces while opting for the Model View Presenter pattern that is designed for graphics interfaces. The paper describes the process followed to define the approach, the supporting tool and presents the results from a case study.

Keywords: metamodel, model-driven engineering, MVP, rich internet application, transformation, user interface

Procedia PDF Downloads 353

Authors: Johannes J. Schneider, Mathias S. Weyland, Peter Eggenberger Hotz, William D. Jamieson, Oliver Castell, Alessia Faggian, Rudolf M. Füchslin

Abstract:

In the description of the origin of life, there are still some open gaps, e.g., the formation of macromolecules cannot be fully explained so far. The Kauffman model proposes the existence of autocatalytic sets of macromolecules which mutually catalyze reactions leading to each other’s formation. Usually, this model is simulated in one well-stirred pot only, with a continuous inflow of small building blocks, from which larger molecules are created by a set of catalyzed ligation and cleavage reactions. This approach represents the picture of the primordial soup. However, the conditions on the early Earth must have differed geographically, leading to spatially different outcomes whether a specific reaction could be performed or not. Guided by this picture, the Kauffman model is simulated in a large number of containers in parallel, with neighboring containers being connected by diffusion. In each container, only a subset of the overall reaction set can be performed. Under specific conditions, this approach leads to a larger probability for the existence of an autocatalytic metabolism than in the original Kauffman model.

Keywords: agglomeration, autocatalytic set, differential equation, Kauffman model

Procedia PDF Downloads 58

Authors: Claudia García-García, Catalina B. García-García, Román Salmerón-Gómez

Abstract:

Much economic-environmental research includes the analysis of possible interactions by using Moderated Regression Analysis (MRA), which is a specific application of multiple linear regression analysis. This methodology allows analyzing how the effect of one of the independent variables is moderated by a second independent variable by adding a cross-product term between them as an additional explanatory variable. Due to the very specification of the methodology, the moderated factor is often highly correlated with the constitutive terms. Thus, great multicollinearity problems arise. The appearance of strong multicollinearity in a model has important consequences. Inflated variances of the estimators may appear, there is a tendency to consider non-significant regressors that they probably are together with a very high coefficient of determination, incorrect signs of our coefficients may appear and also the high sensibility of the results to small changes in the dataset. Finally, the high relationship among explanatory variables implies difficulties in fixing the individual effects of each one on the model under study. These consequences shifted to the moderated analysis may imply that it is not worth including an interaction term that may be distorting the model. Thus, it is important to manage the problem with some methodology that allows for obtaining reliable results. After a review of those works that applied the MRA among the ten top journals of the field, it is clear that multicollinearity is mostly disregarded. Less than 15% of the reviewed works take into account potential multicollinearity problems. To overcome the issue, this work studies the possible application of recent methodologies to MRA. Particularly, the raised regression is analyzed. This methodology mitigates collinearity from a geometrical point of view: the collinearity problem arises because the variables under study are very close geometrically, so by separating both variables, the problem can be mitigated. Raise regression maintains the available information and modifies the problematic variables instead of deleting variables, for example. Furthermore, the global characteristics of the initial model are also maintained (sum of squared residuals, estimated variance, coefficient of determination, global significance test and prediction). The proposal is implemented to data from countries of the European Union during the last year available regarding greenhouse gas emissions, per capita GDP and a dummy variable that represents the topography of the country. The use of a dummy variable as the moderator is a special variant of MRA, sometimes called “subgroup regression analysis.” The main conclusion of this work is that applying new techniques to the field can improve in a substantial way the results of the analysis. Particularly, the use of raised regression mitigates great multicollinearity problems, so the researcher is able to rely on the interaction term when interpreting the results of a particular study.

Keywords: multicollinearity, MRA, interaction, raise

Procedia PDF Downloads 104

Authors: Seon Soon Choi

Abstract:

The essential purpose is to present the good fatigue crack propagation model describing a stochastic fatigue crack growth behavior in a rolled magnesium alloy, AZ31, under various load ratio conditions. Fatigue crack propagation experiments were carried out in laboratory air under four conditions of load ratio, R, using AZ31 to investigate the crack growth behavior. The stochastic fatigue crack growth behavior was analyzed using an interpolation of random variable, Z, introduced to an empirical fatigue crack propagation model. The empirical fatigue models used in this study are Paris-Erdogan model, Walker model, Forman model, and modified Forman model. It was found that the random variable is useful in describing the stochastic fatigue crack growth behaviors under various load ratio conditions. The good probabilistic model describing a stochastic fatigue crack growth behavior under various load ratio conditions was also proposed.

Keywords: magnesium alloys, fatigue crack propagation model, load ratio, interpolation of random variable

Procedia PDF Downloads 410

Authors: Wennan Long, Yuhao Nie, Yunan Li, Adam Brandt

Abstract:

To fight against climate change, California government issued the Senate Bill No. 100 (SB-100) in 2018 September, which aims at achieving a target of 100% renewable electricity by the end of 2045. A capacity expansion problem is solved in this case study using a binary quadratic programming model. The optimal locations and capacities of the potential renewable power plants (i.e., solar, wind, biomass, geothermal and hydropower), the phase-out schedule of existing fossil-based (nature gas) power plants and the transmission of electricity across the entire network are determined with the minimal total annualized cost measured by net present value (NPV). The results show that the renewable electricity contribution could increase to 85.9% by 2030 and reach 100% by 2035. Fossil-based power plants will be totally phased out around 2035 and solar and wind will finally become the most dominant renewable energy resource in California electricity mix.

Keywords: 100% renewable electricity, California, capacity expansion, mixed integer non-linear programming

Procedia PDF Downloads 171

Authors: Tudor Barbu

Abstract:

We present a robust nonlinear parabolic partial differential equation (PDE)-based denoising scheme in this article. Our approach is based on a second-order anisotropic diffusion model that is described first. Then, a consistent and explicit numerical approximation algorithm is constructed for this continuous model by using the finite-difference method. Finally, our restoration experiments and method comparison, which prove the effectiveness of this proposed technique, are discussed in this paper.

Keywords: anisotropic diffusion, finite differences, image denoising and restoration, nonlinear PDE model, anisotropic diffusion, numerical approximation schemes

Procedia PDF Downloads 313

Authors: Cheng Zeng, George Michailidis, Hitoshi Iyatomi, Leo L. Duan

Abstract:

The conditional density characterizes the distribution of a response variable y given other predictor x and plays a key role in many statistical tasks, including classification and outlier detection. Although there has been abundant work on the problem of Conditional Density Estimation (CDE) for a low-dimensional response in the presence of a high-dimensional predictor, little work has been done for a high-dimensional response such as images. The promising performance of normalizing flow (NF) neural networks in unconditional density estimation acts as a motivating starting point. In this work, the authors extend NF neural networks when external x is present. Specifically, they use the NF to parameterize a one-to-one transform between a high-dimensional y and a latent z that comprises two components [zₚ, zₙ]. The zₚ component is a low-dimensional subvector obtained from the posterior distribution of an elementary predictive model for x, such as logistic/linear regression. The zₙ component is a high-dimensional independent Gaussian vector, which explains the variations in y not or less related to x. Unlike existing CDE methods, the proposed approach coined Augmented Posterior CDE (AP-CDE) only requires a simple modification of the common normalizing flow framework while significantly improving the interpretation of the latent component since zₚ represents a supervised dimension reduction. In image analytics applications, AP-CDE shows good separation of 𝑥-related variations due to factors such as lighting condition and subject id from the other random variations. Further, the experiments show that an unconditional NF neural network based on an unsupervised model of z, such as a Gaussian mixture, fails to generate interpretable results.

Keywords: conditional density estimation, image generation, normalizing flow, supervised dimension reduction

Procedia PDF Downloads 96

Authors: F. Amirarfaei, K. Khorasani

Abstract:

In this paper, reconfigurable consensus achievement of a team of agents with marginally stable linear dynamics and single input channel has been considered. The control algorithm is based on a first order linear protocol. After occurrence of a LOE fault in one of the actuators, using the imperfect information of the effectiveness of the actuators from fault detection and identification module, the control gain is redesigned in a way to still reach consensus. The idea is based on the modeling of change in effectiveness as change of Laplacian matrix. Then as special cases of this class of systems, a team of single integrators as well as double integrators are considered and their behavior subject to a LOE fault is considered. The well-known relative measurements consensus protocol is applied to a leaderless team of single integrator as well as double integrator systems, and Gersgorin disk theorem is employed to determine whether fault occurrence has an effect on system stability and team consensus achievement or not. The analyses show that loss of effectiveness fault in actuator(s) of integrator systems affects neither system stability nor consensus achievement.

Keywords: multi-agent system, actuator fault, stability analysis, consensus achievement

Procedia PDF Downloads 337

Authors: Amr Sadek, Abdelrahaman Al-Qahtany, Turkey Salem Al-Qahtany

Abstract:

In this study, a backpropagation artificial neural network (ANN) model has been used to predict the cooling and heating capacities of air conditioners (AC) under different conditions. Sufficiently large measurement results were obtained from the national energy-efficiency laboratories in Saudi Arabia and were used for the learning process of the ANN model. The parameters affecting the performance of the AC, including temperature, humidity level, specific heat enthalpy indoors and outdoors, and the air volume flow rate of indoor units, have been considered. These parameters were used as inputs for the ANN model, while the cooling and heating capacity values were set as the targets. A backpropagation ANN model with two hidden layers and one output layer could successfully correlate the input parameters with the targets. The characteristics of the ANN model including the input-processing, transfer, neurons-distance, topology, and training functions have been discussed. The performance of the ANN model was monitored over the training epochs and assessed using the mean squared error function. The model was then used to predict the performance of the AC under conditions that were not included in the measurement results. The optimum performance of the AC was also predicted under the different environmental conditions in Saudi Arabia. The uncertainty of the ANN model predictions has been evaluated taking into account the randomness of the data and lack of learning.

Keywords: artificial neural network, uncertainty of model predictions, efficiency of air conditioners, cooling and heating capacities

Procedia PDF Downloads 74

Authors: Shahroz Khan, Osman Taha Şen

Abstract:

In automotive brake systems, brake noise has been a major problem, and brake squeal is one of the critical ones which is an instability issue. The brake squeal produces an audible sound at high frequency that is irritating to the human ear. To study this critical problem, first a nonlinear mathematical model with three degree of freedom is developed. This model consists of a point mass that simulates the brake pad and a sliding surface that simulates the brake rotor. The model exposes kinematic and clearance nonlinearities, but no friction nonlinearity. In the formulation, the friction coefficient is assumed to be constant and the friction force does not change direction. The nonlinear governing equations of the model are first obtained, and numerical solutions are sought for different cases. Second, a computational model for the squeal problem is developed with a commercial software, and computational solutions are obtained with two different types of contact cases (solid-to-solid and sphere-to-plane). This model consists of three rigid bodies and several elastic elements that simulate the key characteristics of a brake system. The response obtained from this model is compared with numerical solutions in time and frequency domain.

Keywords: contact force, nonlinearities, brake squeal, vehicle brake

Procedia PDF Downloads 246

Authors: Jerome T. Tolentino, Ma. Victoria Rejuso, Jara Kaye Villanueva, Loureal Camille Inocencio, Ma. Rosario Concepcion O. Ang

Abstract:

Wind energy is rapidly emerging as the primary source of electricity in the Philippines, although developing an accurate wind resource model is difficult. In this study, Weather Research and Forecasting (WRF) Model, an open source mesoscale Numerical Weather Prediction (NWP) model, was used to produce a 1-year atmospheric simulation with 4 km resolution on the Ilocos Region of the Philippines. The WRF output (netCDF) extracts the annual mean wind speed data using a Python-based Graphical User Interface. Lastly, wind resource assessment was produced using a GIS software. Results of the study showed that it is more flexible to use Python scripts than using other post-processing tools in dealing with netCDF files. Using WRF Model, Python, and Geographic Information Systems, a reliable wind resource map is produced.

Keywords: wind resource assessment, weather research and forecasting (WRF) model, python, GIS software

Procedia PDF Downloads 442

Authors: M. Mikušová

Abstract:

The main aim of this paper is to present a clear and comprehensive picture of the process of a crisis in the organization which will help to better understand its possible developments. For a description of the sequence of individual steps and an indication of their causation and possible variants of the developments, a detailed flow diagram with verbal comment is applied. For simplicity, the process of the crisis is observed in four basic phases called: symptoms of the crisis, diagnosis, action and prevention. The model highlights the complexity of the phenomenon of the crisis and that the various phases of the crisis are interweaving.

Keywords: crisis, management, model, organization

Procedia PDF Downloads 291

Authors: Hyun-Woo Cho

Abstract:

It is quite important to utilize right time and intelligent production monitoring and diagnosis of industrial processes in terms of quality and safety issues. When compared with monitoring task, fault diagnosis represents the task of finding process variables responsible causing a specific fault in the process. It can be helpful to process operators who should investigate and eliminate root causes more effectively and efficiently. This work focused on the active use of combining a nonlinear statistical technique with a preprocessing method in order to implement practical real-time fault identification schemes for data-rich cases. To compare its performance to existing identification schemes, a case study on a benchmark process was performed in several scenarios. The results showed that the proposed fault identification scheme produced more reliable diagnosis results than linear methods. In addition, the use of the filtering step improved the identification results for the complicated processes with massive data sets.

Keywords: diagnosis, filtering, nonlinear statistical techniques, process monitoring

Procedia PDF Downloads 243

Authors: Mujtaba Roshan, John A. Schormans

Abstract:

Quality of Experience (QoE) drives churn in the broadband networks industry, and good QoE plays a large part in the retention of customers. QoE is known to be affected by the Quality of Service (QoS) factors packet loss probability (PLP), delay and delay jitter caused by the network. Earlier results have shown that the relationship between these QoS factors and QoE is non-linear, and may vary from application to application. We use the network emulator Netem as the basis for experimentation, and evaluate how QoE varies as we change the emulated QoS metrics. Focusing on Video-on-Demand, we discovered that the reported QoE may differ widely for users of different age groups, and that the most demanding age group (the youngest) can require an order of magnitude lower PLP to achieve the same QoE than is required by the most widely studied age group of users. We then used a bottleneck TCP model to evaluate the capacity cost of achieving an order of magnitude decrease in PLP, and found it be (almost always) a 3-fold increase in link capacity that was required.

Keywords: network capacity, packet loss probability, quality of experience, quality of service

Procedia PDF Downloads 273

Authors: Yasser F. Hassan

Abstract:

Deep learning structure is a branch of machine learning science and greet achievement in research and applications. Cellular neural networks are regarded as array of nonlinear analog processors called cells connected in a way allowing parallel computations. The paper discusses how to use deep learning structure for representing neural cellular automata model. The proposed learning technique in cellular automata model will be examined from structure of deep learning. A deep automata neural cellular system modifies each neuron based on the behavior of the individual and its decision as a result of multi-level deep structure learning. The paper will present the architecture of the model and the results of simulation of approach are given. Results from the implementation enrich deep neural cellular automata system and shed a light on concept formulation of the model and the learning in it.

Keywords: cellular automata, neural cellular automata, deep learning, classification

Procedia PDF Downloads 198

Authors: Zouhair Issa Ahmed, Ahmed Abdulrasool Ahmed, Falah Hassan Abdulsada

Abstract:

This paper presents a layout of a factory using Pro-Model simulation by choosing the best layout that gives the highest productivity and least work in process. The general problem is to find the best sequence in which jobs pass between the machines which are compatible with the technological constraints and optimal with respect to some performance criteria. The best simulation with Pro-Model program increased productivity and reduced work in process by balancing lines of production compared with the current layout of factory when productivity increased from 45 products to 180 products through 720 hours.

Keywords: scheduling, Pro-Model, simulation, balancing lines of production, layout planning, WIP

Procedia PDF Downloads 636

Authors: Abrehet Kahsay Mehari

Abstract:

Aquatic plants provide the physical structure of wetlands and increase their habitat complexity and heterogeneity, and as such, have a profound influence on other biotas. In this study, we investigated how human disturbance activities influenced the species richness and community composition of aquatic plants in the wetlands of Lake Tana, Ethiopia. Twelve wetlands were selected: four lacustrine, four river mouths, and four riverine papyrus swamps. Data on aquatic plants, environmental variables, and human activities were collected during the dry and wet seasons of 2018. A linear mixed effect model and a distance-based Redundancy Analysis (db-RDA) were used to relate aquatic plant species richness and community composition, respectively, to human activities and environmental variables. A total of 113 aquatic plant species, belonging to 38 families, were identified across all wetlands during the dry and wet seasons. Emergent species had the maximum area covered at 73.45 % and attained the highest relative abundance, followed by amphibious and other forms. The mean taxonomic richness of aquatic plants was significantly lower in wetlands with high overall human disturbance scores compared to wetlands with low overall human disturbance scores. Moreover, taxonomic richness showed a negative correlation with livestock grazing, tree plantation, and sand mining. The community composition also varied across wetlands with varying levels of human disturbance and was primarily driven by turnover (i.e., replacement of species) rather than nestedness resultant(i.e., loss of species). Distance-based redundancy analysis revealed that livestock grazing, tree plantation, sand mining, waste dumping, and crop cultivation were significant predictors of variation in aquatic plant communities’ composition in the wetlands. Linear mixed effect models and distance-based redundancy analysis also revealed that water depth, turbidity, conductivity, pH, sediment depth, and temperature were important drivers of variations in aquatic plant species richness and community composition. Papyrus swamps had the highest species richness and supported different plant communities. Conservation efforts should therefore focus on these habitats and measures should be taken to restore the highly disturbed and species poor wetlands near the river mouths.

Keywords: species richness, community composition, aquatic plants, wetlands, Lake Tana, human disturbance activities

Procedia PDF Downloads 123

Authors: Minna Theres James, Nirmal K Sebastian, Shoubhik Mandal, Pramita Mishra, R Ganesan, P S Anil Kumar

Abstract:

We report the temperature-dependent evolution of Raman spectra of type-II Dirac semimetal (DSM) NiTe2 (001) in the form of bulk single crystal and a nanoflake (200 nm thick) for the first time. A physical model that can quantitatively explain the evolution of out of plane A1g and in-plane E1g Raman modes is used. The non-linear variation of peak positions of the Raman modes with temperature is explained by anharmonic three-phonon and four-phonon processes along with thermal expansion of the lattice. We also observe prominent effect of electron-phonon coupling from the variation of FWHM of the peaks with temperature, indicating the metallicity of the samples. Raman mode E1 1g corresponding to an in plane vibration disappears on decreasing the thickness from bulk to nanoflake.

Keywords: raman spectroscopy, type 2 dirac semimetal, nickel telluride, phonon-phonon coupling, electron phonon coupling, transition metal dichalcogonide

Procedia PDF Downloads 115

Authors: Nicolas Plamondon, Stuart Atkinson, Shuzi Zhou

Abstract:

The insurance industry is usually not the first topic one has in mind when thinking about applications of data science. However, the use of data science in the finance and insurance industry is growing quickly for several reasons, including an abundance of reliable customer data, ferocious competition requiring more accurate pricing, etc. Among the top use cases of data science, we find pricing optimization, customer segmentation, customer risk assessment, fraud detection, marketing, and triage analytics. The objective of this paper is to present an application of the generalized additive model (GAM) on a commercial automobile insurance product: an individually rated commercial automobile. These are vehicles used for commercial purposes, but for which there is not enough volume to apply pricing to several vehicles at the same time. The GAM model was selected as an improvement over GLM for its ease of use and its wide range of applications. The model was trained using the largest split of the data to determine model parameters. The remaining part of the data was used as testing data to verify the quality of the modeling activity. We used the Gini coefficient to evaluate the performance of the model. For long-term monitoring, commonly used metrics such as RMSE and MAE will be used. Another topic of interest in the insurance industry is to process of producing the model. We will discuss at a high level the interactions between the different teams with an insurance company that needs to work together to produce a model and then monitor the performance of the model over time. Moreover, we will discuss the regulations in place in the insurance industry. Finally, we will discuss the maintenance of the model and the fact that new data does not come constantly and that some metrics can take a long time to become meaningful.

Keywords: insurance, data science, modeling, monitoring, regulation, processes

Procedia PDF Downloads 76

Authors: Aemro Tazeze Terefe, Mengistu K. Aredo, Abule M. Workagegnehu, Wondimagegn M. Tesfaye

Abstract:

Climate-induced shocks have been shown to reduce agricultural production and cause fluctuation in output in developing countries. When livelihoods depend on rain-fed agriculture, climate-induced shocks translate into consumption shocks. Despite the substantial improvements in household consumption, climate-induced shocks, and other factors adversely affect consumption dynamics at the household level in Ethiopia. Therefore, household consumption dynamics in the context of climate-induced shocks help to guide resilience capacity and establish appropriate interventions and programs. The research employed three-round panel data based on the Ethiopian Socioeconomic Survey with spatial rainfall data to define unique measures of rainfall variability. The linear dynamic panel model results show that the lagged value of consumption, market shocks, and rainfall variability positively affected consumption dynamics. In contrast, production shocks, temperature, and amount of rainfall had a negative relationship. Coping strategies mitigate adverse climate-induced shocks on consumption aftershocks that smooth consumption over time. Support to increase the resilience capacity of households can involve efforts to make existing livelihoods and forms of production or reductions in the vulnerability of households. Therefore, government interventions are mandatory for asset accumulation agendas that support household coping strategies and respond to shocks. In addition, the dynamic linkage between consumption and significant socioeconomic and institutional factors should be taken into account to minimize the effect of climate-induced shocks on consumption dynamics.

Keywords: climate shock, Ethiopia, fixed-effect model, food security

Procedia PDF Downloads 116

Authors: Mian Huang, Chi Ma, Junyu Lin, William Lu

Abstract:

Introduction: Bone health attracts more attention recently and an intelligent question and answer (QA) chatbot for osteoporosis is helpful for science popularization. With Generative Pretrained Transformer (GPT) technology developing, we build an osteoporosis corpus dataset and then fine-tune LLaMA, a famous open-source GPT foundation large language model(LLM), on our self-constructed osteoporosis corpus. Evaluated by clinical orthopedic experts, our fine-tuned model outperforms vanilla LLaMA on osteoporosis QA task in Chinese. Three-dimensional quantitative computed tomography (QCT) measured bone mineral density (BMD) is considered as more accurate than DXA for BMD measurement in recent years. We develop an automatic Phantom-less QCT(PL-QCT) that is more efficient for BMD measurement since no need of an external phantom for calibration. Combined with LLM on osteoporosis, our PL-QCT provides efficient and accurate BMD measurement for our chatbot users. Material and Methods: We build an osteoporosis corpus containing about 30,000 Chinese literatures whose titles are related to osteoporosis. The whole process is done automatically, including crawling literatures in .pdf format, localizing text/figure/table region by layout segmentation algorithm and recognizing text by OCR algorithm. We train our model by continuous pre-training with Low-rank Adaptation (LoRA, rank=10) technology to adapt LLaMA-7B model to osteoporosis domain, whose basic principle is to mask the next word in the text and make the model predict that word. The loss function is defined as cross-entropy between the predicted and ground-truth word. Experiment is implemented on single NVIDIA A800 GPU for 15 days. Our automatic PL-QCT BMD measurement adopt AI-associated region-of-interest (ROI) generation algorithm for localizing vertebrae-parallel cylinder in cancellous bone. Due to no phantom for BMD calibration, we calculate ROI BMD by CT-BMD of personal muscle and fat. Results & Discussion: Clinical orthopaedic experts are invited to design 5 osteoporosis questions in Chinese, evaluating performance of vanilla LLaMA and our fine-tuned model. Our model outperforms LLaMA on over 80% of these questions, understanding ‘Expert Consensus on Osteoporosis’, ‘QCT for osteoporosis diagnosis’ and ‘Effect of age on osteoporosis’. Detailed results are shown in appendix. Future work may be done by training a larger LLM on the whole orthopaedics with more high-quality domain data, or a multi-modal GPT combining and understanding X-ray and medical text for orthopaedic computer-aided-diagnosis. However, GPT model gives unexpected outputs sometimes, such as repetitive text or seemingly normal but wrong answer (called ‘hallucination’). Even though GPT give correct answers, it cannot be considered as valid clinical diagnoses instead of clinical doctors. The PL-QCT BMD system provided by Bone’s QCT(Bone’s Technology(Shenzhen) Limited) achieves 0.1448mg/cm2(spine) and 0.0002 mg/cm2(hip) mean absolute error(MAE) and linear correlation coefficient R2=0.9970(spine) and R2=0.9991(hip)(compared to QCT-Pro(Mindways)) on 155 patients in three-center clinical trial in Guangzhou, China. Conclusion: This study builds a Chinese osteoporosis corpus and develops a fine-tuned and domain-adapted LLM as well as a PL-QCT BMD measurement system. Our fine-tuned GPT model shows better capability than LLaMA model on most testing questions on osteoporosis. Combined with our PL-QCT BMD system, we are looking forward to providing science popularization and early morning screening for potential osteoporotic patients.

Keywords: GPT, phantom-less QCT, large language model, osteoporosis

Procedia PDF Downloads 71

Authors: I. Behroyan, P. Ganesan, S. He, S. Sivasankaran

Abstract:

This study compares the predictions of five types of Computational Fluid Dynamics (CFD) models, including two single-phase models (i.e. Newtonian and non-Newtonian) and three two-phase models (Eulerian-Eulerian, mixture and Eulerian-Lagrangian), to investigate turbulent forced convection of Cu-water nanofluid in a tube with a constant heat flux on the tube wall. The Reynolds (Re) number of the flow is between 10,000 and 25,000, while the volume fraction of Cu particles used is in the range of 0 to 2%. The commercial CFD package of ANSYS-Fluent is used. The results from the CFD models are compared with results from experimental investigations from literature. According to the results of this study, non-Newtonian single-phase model, in general, does not show a good agreement with Xuan and Li correlation in prediction of Nu number. Eulerian-Eulerian model gives inaccurate results expect for φ=0.5%. Mixture model gives a maximum error of 15%. Newtonian single-phase model and Eulerian-Lagrangian model, in overall, are the recommended models. This work can be used as a reference for selecting an appreciate model for future investigation. The study also gives a proper insight about the important factors such as Brownian motion, fluid behavior parameters and effective nanoparticle conductivity which should be considered or changed by the each model.

Keywords: heat transfer, nanofluid, single-phase models, two-phase models

Procedia PDF Downloads 484

Authors: Pallavi Gajjar, Vinayak Malhotra

Abstract:

Rockets have been known to have played a predominant role in spacecraft propulsion. The quintessential aspect of combustion-related requirements of a rocket engine is the minimization of the surrounding risks/hazards. Over time, it has become imperative to understand the combustion rate variation in presence of external energy source(s). Rocket propulsion represents a special domain of chemical propulsion assisted by high speed flows in presence of acoustics and thermal source(s). Jet noise leads to a significant loss of resources and every year a huge amount of financial aid is spent to prevent it. External heat source(s) induce high possibility of fire risk/hazards which can sufficiently endanger the operation of a space vehicle. Appreciable work had been done with justifiable simplification and emphasis on the linear variation of external energy source(s), which yields good physical insight but does not cater to accurate predictions. Present work experimentally attempts to understand the correlation between inter-energy conversions with the non-linear placement of external energy source(s). The work is motivated by the need to have better fire safety and enhanced combustion. The specific objectives of the work are a) To interpret the related energy transfer for combustion in presence of alternate external energy source(s) viz., thermal and acoustic, b) To fundamentally understand the role of key controlling parameters viz., separation distance, the number of the source(s), selected configurations and their non-linear variation to resemble real-life cases. An experimental setup was prepared using incense sticks as potential fuel and paraffin wax candles as the external energy source(s). The acoustics was generated using frequency generator, and source(s) were placed at selected locations. Non-equidistant parametric experimentation was carried out, and the effects were noted on regression rate changes. The results are expected to be very helpful in offering a new perspective into futuristic rocket designs and safety.

Keywords: combustion, acoustic energy, external energy sources, regression rate

Procedia PDF Downloads 140

Authors: Katja Siefken, Astrid Junge

Abstract:

Background: Research indicates that physical activity (PA) protects us from developing mental disorders. The knowledge regarding optimal domain, intensity, type, context, and amount of PA promotion for the prevention of mental disorders is sparse and incoherent. The objective of this study is to determine the relationship between PA domains and mental well-being, and whether associations vary by domain, amount, context, intensity, and type of PA. Methods: 310 individuals (age: 25 yrs., SD 7; 73% female) completed a questionnaire on personal patterns of their PA behaviour (IPQA) and their mental health (Centre of Epidemiologic Studies Depression Scale (CES-D), Generalized Anxiety Disorder (GAD-7) scale, the subjective physical well-being (FEW-16)). Linear and multiple regression were used for analysis. Findings: Individuals who met the PA recommendation (N=269) reported higher scores on subjective physical well-being than those who did not meet the PA recommendations (N=41). Whilst vigorous intensity PA predicts subjective well-being (β = .122, p = .028), it also correlates with depression. The more vigorously physically active a person is, the higher the depression score (β = .127, p = .026). The strongest impact of PA on mental well-being can be seen in the transport domain. A positive linear correlation on subjective physical well-being (β =.175, p = .002), and a negative linear correlation for anxiety (β =-.142, p = .011) and depression (β = -.164, p = .004) was found. Multiple regression analysis indicates similar results: Time spent in active transport on the bicycle significantly lowers anxiety and depression scores and enhances subjective physical well-being. The more time a participant spends using the bicycle for transport, the lower the depression (β = -.143, p = .013) and anxiety scores (β = -.111,p = .050). Conclusions: Meeting the PA recommendations enhances subjective physical well-being. Active transport has a substantial impact on mental well-being. Findings have implications for policymakers, employers, public health experts and civil society. A stronger focus on the promotion and protection of health through active transport is recommended. Inter-sectoral exchange, outside the health sector, is required. Health systems must engage other sectors in adopting policies that maximize possible health gains.

Keywords: active transport, mental well-being, health promotion, psychological disorders

Procedia PDF Downloads 320

Authors: Pompa Marcello, Mauro Capocelli, Vincenzo Piemonte

Abstract:

This work focuses on a mathematical model able to describe the gastro-intestinal physiology and providing a rational tool for the design of an artificial gastro-intestinal system. This latter is mainly devoted to analyse the absorption and bioavailability of drugs and nutrients through in vitro tests in order to overcome (or, at least, to partially replace) in vivo trials. The provided model realizes a conjunction ring (with extended prediction capability) between in vivo tests and mechanical-laboratory models emulating the human body. On this basis, no empirical equations controlling the gastric emptying are implemented in this model as frequent in the cited literature and all the sub-unit and the related system of equations are physiologically based. More in detail, the model structure consists of six compartments (stomach, duodenum, jejunum, ileum, colon and blood) interconnected through pipes and valves. Paracetamol, Ketoprofen, Irbesartan and Ketoconazole are considered and analysed in this work as reference drugs. The mathematical model has been validated against in vivo literature data. Results obtained show a very good model reliability and highlight the possibility to realize tailored simulations for different couples patient-drug, including food adsorption dynamics.

Keywords: gastro-intestinal model, drugs bioavailability, paracetamol, ketoprofen

Procedia PDF Downloads 168

Authors: Yilei Song, Linlin Tian, Ning Zhao

Abstract:

Turbulence energetics and structures in the wake of large-scale wind turbines under the stably-stratified atmospheric boundary layer (SABL) can be complicated due to the presence of low-level jets (LLJs), a region of higher wind speeds than the geostrophic wind speed. With a modified one-k-equation, eddy viscosity model specified for atmospheric flows as the sub-grid scale (SGS) model, a realistic atmospheric state of the stable ABL is well reproduced by large-eddy simulation (LES) techniques. Corresponding to the precursor stably stratification, the detailed wake properties of a standard 5-MW wind turbine represented as an actuator line model are provided. An engineering model is proposed for wake prediction based on the simulation statistics and gets validated. Results confirm that the proposed wake model can provide good predictions for wind turbines under the SABL.

Keywords: large-eddy simulation, stably-stratified atmospheric boundary layer, wake model, wind turbine wake

Procedia PDF Downloads 174