Search results for: generative models

Authors: Velimir Monty Vesselinov, Trais Kliplhuis, Hope Jasperson

Abstract:

Artificial intelligence (AI) is a powerful tool in the geothermal energy sector, aiding in both exploration and utilization. Identifying promising geothermal sites can be challenging due to limited surface indicators and the need for expensive drilling to confirm subsurface resources. Geothermal reservoirs can be located deep underground and exhibit complex geological structures, making traditional exploration methods time-consuming and imprecise. AI algorithms can analyze vast datasets of geological, geophysical, and remote sensing data, including satellite imagery, seismic surveys, geochemistry, geology, etc. Machine learning algorithms can identify subtle patterns and relationships within this data, potentially revealing hidden geothermal potential in areas previously overlooked. To address these challenges, a SIML (Science-Informed Machine Learning) technology has been developed. SIML methods are different from traditional ML techniques. In both cases, the ML models are trained to predict the spatial distribution of an output (e.g., pressure, temperature, heat flux) based on a series of inputs (e.g., permeability, porosity, etc.). The traditional ML (a) relies on deep and wide neural networks (NNs) based on simple algebraic mappings to represent complex processes. In contrast, the SIML neurons incorporate complex mappings (including constitutive relationships and physics/chemistry models). This results in ML models that have a physical meaning and satisfy physics laws and constraints. The prototype of the developed software, called GeoTGO, is accessible through the cloud. Our software prototype demonstrates how different data sources can be made available for processing, executed demonstrative SIML analyses, and presents the results in a table and graphic form.

Keywords: science-informed machine learning, artificial inteligence, exploration, utilization, hidden geothermal

Procedia PDF Downloads 53

Authors: W. Meron Mebrahtu, R. Absi

Abstract:

Velocity distribution in turbulent open-channel flows is organized in a complex manner. This is due to the large spatial and temporal variability of fluid motion resulting from the free-surface turbulent flow condition. This phenomenon is complicated further due to the complex geometry of channels and the presence of solids transported. Thus, several efforts were made to understand the phenomenon and obtain accurate mathematical models that are suitable for engineering applications. However, predictions are inaccurate because oversimplified assumptions are involved in modeling this complex phenomenon. Therefore, the aim of this work is to study velocity distribution profiles and obtain simple, more accurate, and predictive mathematical models. Particular focus will be made on the acceptable simplification of the general transport equations and an accurate representation of eddy viscosity. Wide rectangular open-channel seems suitable to begin the study; other assumptions are smooth-wall, and sediment-free flow under steady and uniform flow conditions. These assumptions will allow examining the effect of the bottom wall and the free surface only, which is a necessary step before dealing with more complex flow scenarios. For this flow condition, two ordinary differential equations are obtained for velocity profiles; from the Reynolds-averaged Navier-Stokes (RANS) equation and equilibrium consideration between turbulent kinetic energy (TKE) production and dissipation. Then different analytic models for eddy viscosity, TKE, and mixing length were assessed. Computation results for velocity profiles were compared to experimental data for different flow conditions and the well-known linear, log, and log-wake laws. Results show that the model based on the RANS equation provides more accurate velocity profiles. In the viscous sublayer and buffer layer, the method based on Prandtl’s eddy viscosity model and Van Driest mixing length give a more precise result. For the log layer and outer region, a mixing length equation derived from Von Karman’s similarity hypothesis provides the best agreement with measured data except near the free surface where an additional correction based on a damping function for eddy viscosity is used. This method allows more accurate velocity profiles with the same value of the damping coefficient that is valid under different flow conditions. This work continues with investigating narrow channels, complex geometries, and the effect of solids transported in sewers.

Keywords: accuracy, eddy viscosity, sewers, velocity profile

Procedia PDF Downloads 112

Authors: Abolfazl Hosseinkhani, Sepehr Sanaye

Abstract:

Different approaches have been used to predict the performance of the vertical axis wind turbines (VAWT), such as experimental, computational fluid dynamics (CFD), and analytical methods. Analytical methods, such as momentum models that use streamtubes, have low computational cost and sufficient accuracy. The double multiple streamtube (DMST) is one of the most commonly used of momentum models, which divide the rotor plane of VAWT into upwind and downwind. In fact, results from the DMST method have shown some discrepancy compared with experiment results; that is because the Darrieus turbine is a complex and aerodynamically unsteady configuration. In this study, analytical-experimental-based corrections, including dynamic stall, streamtube expansion, and finite blade length correction are used to improve the DMST method. Results indicated that using these corrections for a SANDIA 17-m VAWT will lead to improving the results of DMST.

Keywords: vertical axis wind turbine, analytical, double multiple streamtube, streamtube expansion model, dynamic stall model, finite blade length correction

Procedia PDF Downloads 135

Authors: Xiyue Wang, Shaoning Yan

Abstract:

Cities in China today is faced with an increasingly serious river ecological crisis accompanying with the development of urbanization: waterlogging on account of the fragmented urban natural hydrological system; the limited ecological function of the hydrological system caused by a destruction of water system and waterfront ecological environment. Additionally, the eco-hydrological processes of rivers are affected by various environmental factors, which are more complex in the context of urban environment. Therefore, efficient hydrological monitoring and analysis tools, accurate and visual hydrological and hydraulic models are becoming more important basis for decision-makers and an important way for landscape architects to solve urban hydrological problems, formulating sustainable and forward-looking schemes. The study mainly introduces the river and flood analysis model based on the platform of Autodesk Civil 3D. Taking the Luanhe River in Qian'an City of Hebei Province as an example, the 3D models of the landform, river, embankment, shoal, pond, underground stream and other land features were initially built, with which the water transfer simulation analysis, river floodplain analysis, and river ecology analysis were carried out, ultimately the real-time visualized simulation and analysis of rivers in various hypothetical scenarios were realized. Through the establishment of digital hydrological and hydraulic model, the hydraulic data can be accurately and intuitively simulated, which provides basis for rational water system and benign urban ecological system design. Though, the hydrological and hydraulic model based on Autodesk Civil3D own its boundedness: the interaction between the model and other data and software is unfavorable; the huge amount of 3D data and the lack of basic data restrict the accuracy and application range. The hydrological and hydraulic model based on Autodesk Civil3D platform provides more possibility to access convenient and intelligent tool for urban planning and monitoring, a solid basis for further urban research and design.

Keywords: visualization, hydrological and hydraulic model, Autodesk Civil 3D, urban river

Procedia PDF Downloads 297

Authors: Yichao Ma, Chengsiong Chin, Wailok Woo

Abstract:

Since the last decade, there has been a rapid growth in digital multimedia, such as high-resolution media files and three-dimentional movies. Hence, there is a need for large digital storage such as Hard Disk Drive (HDD). As such, users expect to have a quieter HDD in their laptop. In this paper, a jury test has been conducted on a group of 34 people where 17 of them are students who is the potential consumer, and the remaining are engineers who know the HDD. A total 13 HDD sound samples have been selected from over hundred HDD noise recordings. These samples are selected based on an agreed subjective feeling. The samples are played to the participants using head acoustic playback system which enabled them to experience as similar as possible the same environment as have been recorded. Analysis has been conducted and the obtained results have indicated different group has different perception over the noises. Two neural network-based acoustic annoyance models are established based on back propagation neural network. Four psychoacoustic metrics, loudness, sharpness, roughness and fluctuation strength, are used as the input of the model, and the subjective evaluation results are taken as the output. The developed models are reasonably accurate in simulating both training and test samples.

Keywords: hdd noise, jury test, neural network model, psychoacoustic annoyance

Procedia PDF Downloads 438

Authors: David F. Nettleton, Christian Wasiak, Jonas Dorissen, David Gillen, Alexandr Tretyak, Elodie Bugnicourt, Alejandro Rosales

Abstract:

In this work, preliminary results are given for the modeling and calibration of two inline processes, pultrusion, and laser ablation, using machine learning techniques. The end product of the processes is the core of a medical guidewire, manufactured to comply with a user specification of diameter and flexibility. An ensemble approach is followed which requires training several models. Two state of the art machine learning algorithms are benchmarked: Kernel Recursive Least Squares (KRLS) and Support Vector Regression (SVR). The final objective is to build a precise digital model of the pultrusion and laser ablation process in order to calibrate the resulting diameter and flexibility of a medical guidewire, which is the end product while taking into account the friction on the forming die. The result is an ensemble of models, whose output is within a strict required tolerance and which covers the required range of diameter and flexibility of the guidewire end product. The modeling and automatic calibration of complex in-line industrial processes is a key aspect of the Industry 4.0 movement for cyber-physical systems.

Keywords: calibration, data modeling, industrial processes, machine learning

Procedia PDF Downloads 299

Authors: Kassaye Balkew Workagegn, Gunnar Klemetsdal, Hans Magnus Gjøen

Abstract:

In this study, the first objective was to investigate whether non-lethal or non-invasive methods, utilizing body measurements, could be used to efficiently predict fillet weight and fillet yield for a complete diallel cross of three Nile tilapia (Oreochromis niloticus) strains collected from three Ethiopian Rift Valley lakes, Lakes Ziway, Koka and Chamo. The second objective was to estimate heritability of body weight, actual and predicted fillet traits, as well as genetic correlations between these traits. A third goal was to estimate additive, reciprocal, and heterosis effects for body weight and the various fillet traits. As in females, early sexual maturation was widespread, only 958 male fish from 81 full-sib families were used, both for the prediction of fillet traits and in genetic analysis. The prediction equations from body measurements were established by forward regression analysis, choosing models with the least predicted residual error sums of squares (PRESS). The results revealed that body measurements on live Nile tilapia is well suited to predict fillet weight but not fillet yield (R²= 0.945 and 0.209, respectively), but both models were seemingly unbiased. The genetic analyses were carried out with bivariate, multibreed models. Body weight, fillet weight, and predicted fillet weight were all estimated with a heritability ranged from 0.23 to 0.28, and with genetic correlations close to one. Contrary, fillet yield was only to a minor degree heritable (0.05), while predicted fillet yield obtained a heritability of 0.19, being a resultant of two body weight variables known to have high heritability. The latter trait was estimated with genetic correlations to body weight and fillet weight traits larger than 0.82. No significant differences among strains were found for their additive genetic, reciprocal, or heterosis effects, while total heterosis effects were estimated as positive and significant (P < 0.05). As a conclusion, prediction of prediction of fillet weight based on body measurements is possible, but not for fillet yield.

Keywords: additive, fillet traits, genetic correlation, heritability, heterosis, prediction, reciprocal

Procedia PDF Downloads 187

Authors: Vikrant Gupta, Amrit Goswami

Abstract:

The fixed income market forms the basis of the modern financial market. All other assets in financial markets derive their value from the bond market. Owing to its over-the-counter nature, corporate bonds have relatively less data publicly available and thus is researched upon far less compared to Equities. Bond price prediction is a complex financial time series forecasting problem and is considered very crucial in the domain of finance. The bond prices are highly volatile and full of noise which makes it very difficult for traditional statistical time-series models to capture the complexity in series patterns which leads to inefficient forecasts. To overcome the inefficiencies of statistical models, various machine learning techniques were initially used in the literature for more accurate forecasting of time-series. However, simple machine learning methods such as linear regression, support vectors, random forests fail to provide efficient results when tested on highly complex sequences such as stock prices and bond prices. hence to capture these intricate sequence patterns, various deep learning-based methodologies have been discussed in the literature. In this study, a recurrent neural network-based deep learning model using long short term networks for prediction of corporate bond prices has been discussed. Long Short Term networks (LSTM) have been widely used in the literature for various sequence learning tasks in various domains such as machine translation, speech recognition, etc. In recent years, various studies have discussed the effectiveness of LSTMs in forecasting complex time-series sequences and have shown promising results when compared to other methodologies. LSTMs are a special kind of recurrent neural networks which are capable of learning long term dependencies due to its memory function which traditional neural networks fail to capture. In this study, a simple LSTM, Stacked LSTM and a Masked LSTM based model has been discussed with respect to varying input sequences (three days, seven days and 14 days). In order to facilitate faster learning and to gradually decompose the complexity of bond price sequence, an Empirical Mode Decomposition (EMD) has been used, which has resulted in accuracy improvement of the standalone LSTM model. With a variety of Technical Indicators and EMD decomposed time series, Masked LSTM outperformed the other two counterparts in terms of prediction accuracy. To benchmark the proposed model, the results have been compared with traditional time series models (ARIMA), shallow neural networks and above discussed three different LSTM models. In summary, our results show that the use of LSTM models provide more accurate results and should be explored more within the asset management industry.

Keywords: bond prices, long short-term memory, time series forecasting, empirical mode decomposition

Procedia PDF Downloads 136

Authors: Pooria Norouzi, Nicholas Tsang, Adam van der Goes, Joseph Yu, Douglas Zheng, Sirine Maleej

Abstract:

In this study, virtual meters will be designed and used for energy balance measurements of an air handling unit (AHU). The method aims to replace traditional physical sensors in heating, ventilation, and air conditioning (HVAC) systems with simulated virtual meters. Due to the inability to manage and monitor these systems, many HVAC systems have a high level of inefficiency and energy wastage. Virtual meters are implemented and applied in an actual HVAC system, and the result confirms the practicality of mathematical sensors for alternative energy measurement. While most residential buildings and offices are commonly not equipped with advanced sensors, adding, exploiting, and monitoring sensors and measurement devices in the existing systems can cost thousands of dollars. The first purpose of this study is to provide an energy consumption rate based on available sensors and without any physical energy meters. It proves the performance of virtual meters in HVAC systems as reliable measurement devices. To demonstrate this concept, mathematical models are created for AHU-07, located in building NE01 of the British Columbia Institute of Technology (BCIT) Burnaby campus. The models will be created and integrated with the system’s historical data and physical spot measurements. The actual measurements will be investigated to prove the models' accuracy. Based on preliminary analysis, the resulting mathematical models are successful in plotting energy consumption patterns, and it is concluded confidently that the results of the virtual meter will be close to the results that physical meters could achieve. In the second part of this study, the use of virtual meters is further assisted by artificial intelligence (AI) in the HVAC systems of building to improve energy management and efficiency. By the data mining approach, virtual meters’ data is recorded as historical data, and HVAC system energy consumption prediction is also implemented in order to harness great energy savings and manage the demand and supply chain effectively. Energy prediction can lead to energy-saving strategies and considerations that can open a window in predictive control in order to reach lower energy consumption. To solve these challenges, the energy prediction could optimize the HVAC system and automates energy consumption to capture savings. This study also investigates AI solutions possibility for autonomous HVAC efficiency that will allow quick and efficient response to energy consumption and cost spikes in the energy market.

Keywords: virtual meters, HVAC, artificial intelligence, energy consumption prediction

Procedia PDF Downloads 105

Authors: Misagh Faezipour

Abstract:

System dynamics is a systems engineering approach that can help address the complex challenges in different systems. Little is known about how the brain represents people to predict behavior. This work is based on how the brain simulates different personal behavior and responds to them in the case of young children ages one to five. As we know, children’s minds/brains are just as clean as a crystal, and throughout time, in their surroundings, families, and education center, they grow to develop and have different kinds of behavior towards the world and the society they live in. Hence, this work aims to identify how young children respond to various personality behavior and observes their reactions towards them from a system dynamics perspective. We will be exploring the Big Five personality traits in young children. A causal model is developed in support of the system dynamics approach. These models graphically present the factors and factor relationships that contribute to the big five personality traits and provide a better understanding of the entire behavior model. A simulator will be developed that includes a set of causal model factors and factor relationships. The simulator models the behavior of different factors related to personality traits and their impacts and can help make more informed decisions in a risk-free environment.

Keywords: personality traits, systems engineering, system dynamics, causal model, behavior model

Procedia PDF Downloads 96

Authors: Safa’ Abdelkarim Hammad

Abstract:

The electrical power system is one of the main parts of the nation's infrastructure, and the availability and cost of electricity are critical factors in industrial competitiveness and strategy. Restructuring of the electricity supply industries is a very complex exercise based on national energy strategies and policies, macroeconomic developments, and national conditions, and its application varies from country to country. Electricity regulation of natural monopolies is a challenging task. Regulators face the problem of providing appropriate incentives for improvement of efficiency. Incentive regulation is often considered as an efficient regulatory tool to handle the problem, and it is widely applied in several countries. However, the exact regulation methodologies differ from one country to another. Network quantitative reliability evaluation is an essential factor with regard to the quality of supply. The main factors used to judge the reliability of supply is measured by the number and duration of interruptions experienced by customers. Several indicators are used to evaluate reliability in distribution networks. This paper addresses the impact of incentive regulation and performance benchmarking in the field of electricity distribution in Jordan. The theory of efficiency measurement and the most common models; NCSQS and DEA models are presented.

Keywords: incentive regulations, reliability, restructuring, Tarrif

Procedia PDF Downloads 122

Authors: Roohallah Yousefi

Abstract:

Introduction: Voxelotor, also known as GBT 440, binds to the alpha cleft in HbS tetramers and promotes the stability of the relaxed or oxygenated state of HbS. This process hinders the conformational change of the HbS tetramers into the deoxygenated state. Voxelotor prevents interactions between HbS tetramers in the deoxygenated state, ultimately inhibiting the polymerization of HbS tetramers and resulting in significant clinical improvements, particularly in raising hemoglobin levels in patients. In this study, we have explored the use of herbal compound models, such as rosmarinic acid and compounds with similar structures that exhibit high binding affinity to Voxelotor's hemoglobin binding site. Materials and methods: The molecular model of hemoglobin (PDB: 5E83) was initially obtained from the RCSB PDB database. In addition, we collected 453 ligand models with structural similarity to rosmarinic acid from the PubChem database. To prepare these models for molecular docking, we utilized the Molegro Virtual Docker tool. Subsequently, we used the SwissADME web tool to predict the physicochemical properties and pharmacokinetics of these compounds. Results: We investigated the affinity and binding site of 453 compounds similar to rosmarinic acid on the hemoglobin model (PDB: 5E83). Our focus was on the alpha cleft between two alpha chains of the hemoglobin model (PDB: 5E83). The results showed that most compounds had molecular weights above 500 daltons, and some exhibited acceptable hydrophobicity. Furthermore, their solubility in aqueous solutions was good. None of the compounds were able to cross the blood-brain barrier or have gastrointestinal absorption. However, they did have varying inhibitory effects on CYP2C9 cytochromes. The skin penetration rate was generally low. Conclusion: Through our study, we identified three compounds (CID: 162739375, CID: 141386569, and CID: 24015539) with promising potential for further research. These compounds demonstrated high binding affinity to the hemoglobin model, favorable dissolution and digestive absorption rates, as well as suitable hydrophobicity, making them ideal candidates for continued laboratory investigation.

Keywords: voxelotor, binding site, hemoglobin, rosmarinic acid

Procedia PDF Downloads 8

Authors: Siddhant Rao

Abstract:

Studies estimate that there will be 266,120 new cases of invasive breast cancer and 40,920 breast cancer induced deaths in the year of 2018 alone. Despite the pervasiveness of this affliction, the current process to obtain an accurate breast cancer prognosis is tedious and time consuming. It usually requires a trained pathologist to manually examine histopathological images and identify the features that characterize various cancer severity levels. We propose MITOS-RCNN: a region based convolutional neural network (RCNN) geared for small object detection to accurately grade one of the three factors that characterize tumor belligerence described by the Nottingham Grading System: mitotic count. Other computational approaches to mitotic figure counting and detection do not demonstrate ample recall or precision to be clinically viable. Our models outperformed all previous participants in the ICPR 2012 challenge, the AMIDA 2013 challenge and the MITOS-ATYPIA-14 challenge along with recently published works. Our model achieved an F- measure score of 0.955, a 6.11% improvement in accuracy from the most accurate of the previously proposed models.

Keywords: breast cancer, mitotic count, machine learning, convolutional neural networks

Procedia PDF Downloads 223

Authors: Maruf Ariyo Raheem, Patrick Oseloka Ezepue

Abstract:

This research aimed at determining most appropriate heteroskedastic model to predicting volatility of 10 major Nigerian banks: Access, United Bank for Africa (UBA), Guaranty Trust, Skye, Diamond, Fidelity, Sterling, Union, ETI and Zenith banks using daily closing stock prices of each of the banks from 2004 to 2014. The models employed include ARCH (1), GARCH (1, 1), EGARCH (1, 1) and TARCH (1, 1). The results show that all the banks returns are highly leptokurtic, significantly skewed and thus non-normal across the four periods except for Fidelity bank during financial crises; findings similar to those of other global markets. There is also strong evidence for the presence of heteroscedasticity, and that volatility persistence during crisis is higher than before the crisis across the 10 banks, with that of UBA taking the lead, about 11 times higher during the crisis. Findings further revealed that Asymmetric GARCH models became dominant especially during financial crises and post crises when the second reforms were introduced into the banking industry by the Central Bank of Nigeria (CBN). Generally, one could say that Nigerian banks returns are volatility persistent during and after the crises, and characterised by leverage effects of negative and positive shocks during these periods

Keywords: global financial crisis, leverage effect, persistence, volatility clustering

Procedia PDF Downloads 526

Authors: Alessandra Marcelletti, Giovanni Trovato

Abstract:

Corruption in public offices is found to be the reflection of country-specific features, however, the exact magnitude and the statistical significance of its determinants effect has not yet been identified. The paper aims to propose an estimation method to measure the impact of country fundamentals on corruption, showing that covariates could differently affect the extent of corruption across countries. Thus, we exploit a model able to take into account different factors affecting the incentive to ask or to be asked for a bribe, coherently with the use of the Corruption Perception Index. We assume that discordant results achieved in literature may be explained by omitted hidden factors affecting the agents' decision process. Moreover, assuming homogeneous covariates effect may lead to unreliable conclusions since the country-specific environment is not accounted for. We apply a Finite Mixture Model with concomitant variables to 129 countries from 1995 to 2006, accounting for the impact of the initial conditions in the socio-economic structure on the corruption patterns. Our findings confirm the hypothesis of the decision process of accepting or asking for a bribe varies with specific country fundamental features.

Keywords: Corruption, Finite Mixture Models, Concomitant Variables, Countries Classification

Procedia PDF Downloads 264

Authors: J. Mizuno, S. Takahashi

Abstract:

In this paper, design and fabrication of an actuated parallel-plate mirror based on a 3D-printer is described. The mirror and electrode layers are fabricated separately and assembled thereafter. The alignment is performed by dowel pin-hole pairs fabricated on the respective layers. The electrodes are formed on the surface of the electrode layer by Au ion sputtering using a suitable mask, which is also fabricated by a 3D-printer.For grounding the mirror layer, except the contact area with the electrode paths, all the surface is Au ion sputtered. 3D-printers are widely used for creating 3D models or mock-ups. The authors have recently proposed that these models can perform electromechanical functions such as actuators by suitably masking them followed by metallization process. Since the smallest possible fabrication size is in the order of sub-millimeters, these electromechanical devices are named by the authors as SMEMS (Sub-Milli Electro-Mechanical Systems) devices. The proposed mirror described in this paper which consists of parallel-plate electrostatic actuators is also one type of SMEMS devices. In addition, SMEMS is totally environment-clean compared to MEMS (Micro Electro-Mechanical Systems) fabrication processes because any hazardous chemicals or gases are utilized.

Keywords: MEMS, parallel-plate mirror, SMEMS, 3D-printer

Procedia PDF Downloads 437

Authors: Muhammad Arif Mahmood, Andrei C. Popescu, Mihai Oane, Diana Chioibascu, Carmen Ristoscu, Ion N. Mihailescu

Abstract:

Powder flow and temperature distributions are recognized as influencing factors during laser melting deposition (LMD) process, that not only affect the consolidation rate but also characteristics of the deposited layers. Herewith, two simplified analytical models will be presented to simulate the powder flow with the inclusion of powder particles size distribution in Gaussian form, under three powder jet nozzles, and temperature analyses during LMD process. The output of the 1st model will serve as the input in the 2nd model. The models will be validated with experimental data, i.e., weight measurement method for powder particles distribution and infrared imaging for temperature analyses. This study will increase the cost-efficiency of the LMD process by adjustment of the operating parameters for reaching optimal powder debit and energy. This research has received funds under the Marie Sklodowska-Curie grant agreement No. 764935, from the European Union’s Horizon 2020 research and innovation program.

Keywords: laser additive manufacturing, powder particles size distribution in Gaussian form, powder stream distribution, temperature analyses

Procedia PDF Downloads 135

Authors: Badache Messaoud

Abstract:

Geothermal thermosyphons (GTs) are increasingly used in many heating and cooling geothermal applications owing to their high heat transfer performance. This paper proposes a response surface methodology (RSM) to investigate and optimize the performance of a CO2 geothermal thermosyphon. The filling ratio (FR), temperature, and flow rate of the heat transfer fluid are selected as the designing parameters, and heat transfer rate and effectiveness are adopted as response parameters (objective functions). First, a dedicated experimental GT test bench filled with CO2 was built and subjected to different test conditions. An RSM was used to establish corresponding models between the input parameters and responses. Various diagnostic tests were used to assess evaluate the quality and validity of the best-fit models, which explain respectively 98.9% and 99.2% of the output result’s variability. Overall, it is concluded from the RSM analysis that the heat transfer fluid inlet temperatures and the flow rate are the factors that have the greatest impact on heat transfer (Q) rate and effectiveness (εff), while the FR has only a slight effect on Q and no effect on εff. The maximal heat transfer rate and effectiveness achieved are 1.86 kW and 47.81%, respectively. Moreover, these optimal values are associated with different flow rate levels (mc level = 1 for Q and -1 for εff), indicating distinct operating regions for maximizing Q and εff within the GT system. Therefore, a multilevel optimization approach is necessary to optimize both the heat transfer rate and effectiveness simultaneously.

Keywords: geothermal thermosiphon, co2, Response surface methodology, heat transfer performance

Procedia PDF Downloads 70

Authors: Virginie Hergault, Siham Chebbah, Bertrand Frere

Abstract:

Following in-house objectives, Central laboratory of Paris police Prefecture conducted a general review on models and Computational Fluid Dynamics (CFD) codes used to simulate pollutant dispersion in the atmosphere. Starting from that review and considering main features of Large Eddy Simulation, Central Laboratory Of Paris Police Prefecture (LCPP) postulates that the Fire Dynamics Simulator (FDS) model, from National Institute of Standards and Technology (NIST), should be well suited for air pollutant dispersion modeling. This paper focuses on the implementation and the evaluation of FDS in the frame of the European COST ES1006 Action. This action aimed at quantifying the performance of modeling approaches. In this paper, the CUTE dataset carried out in the city of Hamburg, and its mock-up has been used. We have performed a comparison of FDS results with wind tunnel measurements from CUTE trials on the one hand, and, on the other, with the models results involved in the COST Action. The most time-consuming part of creating input data for simulations is the transfer of obstacle geometry information to the format required by SDS. Thus, we have developed Python codes to convert automatically building and topographic data to the FDS input file. In order to evaluate the predictions of FDS with observations, statistical performance measures have been used. These metrics include the fractional bias (FB), the normalized mean square error (NMSE) and the fraction of predictions within a factor of two of observations (FAC2). As well as the CFD models tested in the COST Action, FDS results demonstrate a good agreement with measured concentrations. Furthermore, the metrics assessment indicate that FB and NMSE meet the tolerance acceptable.

Keywords: numerical simulations, atmospheric dispersion, cost ES1006 action, CFD model, cute experiments, wind tunnel data, numerical results

Procedia PDF Downloads 133

Authors: Afsaneh Mohammadnejad, Marianne Nygaard, Jan Baumbach, Shuxia Li, Weilong Li, Jesper Lund, Jacob v. B. Hjelmborg, Lene Christensen, Qihua Tan

Abstract:

Cognitive impairment in the elderly is a key issue affecting the quality of life. Despite a strong genetic background in cognition, only a limited number of single nucleotide polymorphisms (SNPs) have been found. These explain a small proportion of the genetic component of cognitive function, thus leaving a large proportion unaccounted for. We hypothesize that one reason for this missing heritability is the misspecified modeling in data analysis concerning phenotype distribution as well as the relationship between SNP dosage and the phenotype of interest. In an attempt to overcome these issues, we introduced a model-free method based on the generalized correlation coefficient (GCC) in a genome-wide association study (GWAS) of cognitive function in twin samples and compared its performance with two popular linear regression models. The GCC-based GWAS identified two genome-wide significant (P-value < 5e-8) SNPs; rs2904650 near ZDHHC2 on chromosome 8 and rs111256489 near CD6 on chromosome 11. The kinship model also detected two genome-wide significant SNPs, rs112169253 on chromosome 4 and rs17417920 on chromosome 7, whereas no genome-wide significant SNPs were found by the linear mixed model (LME). Compared to the linear models, more meaningful biological pathways like GABA receptor activation, ion channel transport, neuroactive ligand-receptor interaction, and the renin-angiotensin system were found to be enriched by SNPs from GCC. The GCC model outperformed the linear regression models by identifying more genome-wide significant genetic variants and more meaningful biological pathways related to cognitive function. Moreover, GCC-based GWAS was robust in handling genetically related twin samples, which is an important feature in handling genetic confounding in association studies.

Keywords: cognition, generalized correlation coefficient, GWAS, twins

Procedia PDF Downloads 124

Authors: Aliya Grig, Konstantin Sokolov, Igor Shatalin

Abstract:

The report describes the methodology for collecting data and building an ML model for determining the personality psychotype using profiling and personality traits methods based on several short messages of a user communicating on an arbitrary topic with a chitchat bot. In the course of the experiments, the minimum amount of text was revealed to confidently determine aspects of personality. Model accuracy - 85%. Users' language of communication is English. AI for a personalized communication with a user based on his mood, personality, and current emotional state. Features investigated during the research: personalized communication; providing empathy; adaptation to a user; predictive analytics. In the report, we describe the processes that captures both structured and unstructured data pertaining to a user in large quantities and diverse forms. This data is then effectively processed through ML tools to construct a knowledge graph and draw inferences regarding users of text messages in a comprehensive manner. Specifically, the system analyzes users' behavioral patterns and predicts future scenarios based on this analysis. As a result of the experiments, we provide for further research on training AI models to be empathetic, creating personalized communication for a user

Keywords: AI, empathetic, chatbot, AI models

Procedia PDF Downloads 92

Authors: Stefan Papastefanou

Abstract:

Artificial intelligence (AI) is an interdisciplinary field of computer science with the aim of creating intelligent machine behavior. Early approaches to AI have been configured to operate in very constrained environments where the behavior of the AI system was previously determined by formal rules. Knowledge was presented as a set of rules that allowed the AI system to determine the results for specific problems; as a structure of if-else rules that could be traversed to find a solution to a particular problem or question. However, such rule-based systems typically have not been able to generalize beyond the knowledge provided. All over the world and especially in IT-heavy industries such as the United States, the European Union, Singapore, and China, machine learning has developed to be an immense asset, and its applications are becoming more and more significant. It has to be examined how such products of machine learning models can and should be protected by IP law and for the purpose of this paper patent law specifically, since it is the IP law regime closest to technical inventions and computing methods in technical applications. Genetic breeding models are currently less popular than recursive neural network method and deep learning, but this approach can be more easily described by referring to the evolution of natural organisms, and with increasing computational power; the genetic breeding method as a subset of the evolutionary algorithms models is expected to be regaining popularity. The research method focuses on patentability (according to the world’s most significant patent law regimes such as China, Singapore, the European Union, and the United States) of AI inventions and machine learning. Questions of the technical nature of the problem to be solved, the inventive step as such, and the question of the state of the art and the associated obviousness of the solution arise in the current patenting processes. Most importantly, and the key focus of this paper is the problem of patenting inventions that themselves are developed through machine learning. The inventor of a patent application must be a natural person or a group of persons according to the current legal situation in most patent law regimes. In order to be considered an 'inventor', a person must actually have developed part of the inventive concept. The mere application of machine learning or an AI algorithm to a particular problem should not be construed as the algorithm that contributes to a part of the inventive concept. However, when machine learning or the AI algorithm has contributed to a part of the inventive concept, there is currently a lack of clarity regarding the ownership of artificially created inventions. Since not only all European patent law regimes but also the Chinese and Singaporean patent law approaches include identical terms, this paper ultimately offers a comparative analysis of the most relevant patent law regimes.

Keywords: algorithms, inventor, genetic breeding models, machine learning, patentability

Procedia PDF Downloads 108

Authors: Tatiana G. Smirnova, Stan G. Benjamin

Abstract:

Rapid Update Cycle (RUC) land surface model (LSM) was a land-surface component in several generations of operational weather prediction models at the National Center for Environment Prediction (NCEP) at the National Oceanic and Atmospheric Administration (NOAA). It was designed for short-range weather predictions with an emphasis on severe weather and originally was intentionally simple to avoid uncertainties from poorly known parameters. Nevertheless, the RUC LSM, when coupled with the hourly-assimilating atmospheric model, can produce a realistic evolution of time-varying soil moisture and temperature, as well as the evolution of snow cover on the ground surface. This result is possible only if the soil/vegetation/snow component of the coupled weather prediction model has sufficient skill to avoid long-term drift. RUC LSM was first implemented in the operational NCEP Rapid Update Cycle (RUC) weather model in 1998 and later in the Weather Research Forecasting Model (WRF)-based Rapid Refresh (RAP) and High-resolution Rapid Refresh (HRRR). Being available to the international WRF community, it was implemented in operational weather models in Austria, New Zealand, and Switzerland. Based on the feedback from the US weather service offices and the international WRF community and also based on our own validation, RUC LSM has matured over the years. Also, a sea-ice module was added to RUC LSM for surface predictions over the Arctic sea-ice. Other modifications include refinements to the snow model and a more accurate specification of albedo, roughness length, and other surface properties. At present, RUC LSM is being tested in the regional application of the Unified Forecast System (UFS). The next generation UFS-based regional Rapid Refresh FV3 Standalone (RRFS) model will replace operational RAP and HRRR at NCEP. Over time, RUC LSM participated in several international model intercomparison projects to verify its skill using observed atmospheric forcing. The ESM-SnowMIP was the last of these experiments focused on the verification of snow models for open and forested regions. The simulations were performed for ten sites located in different climatic zones of the world forced with observed atmospheric conditions. While most of the 26 participating models have more sophisticated snow parameterizations than in RUC, RUC LSM got a high ranking in simulations of both snow water equivalent and surface temperature. However, ESM-SnowMIP experiment also revealed some issues in the RUC snow model, which will be addressed in this paper. One of them is the treatment of grid cells partially covered with snow. RUC snow module computes energy and moisture budgets of snow-covered and snow-free areas separately by aggregating the solutions at the end of each time step. Such treatment elevates the importance of computing in the model snow cover fraction. Improvements to the original simplistic threshold-based approach have been implemented and tested both offline and in the coupled weather model. The detailed description of changes to the snow cover fraction and other modifications to RUC soil and snow parameterizations will be described in this paper.

Keywords: land-surface models, weather prediction, hydrology, boundary-layer processes

Procedia PDF Downloads 88

Authors: Soma Chatterjee, I. Das

Abstract:

In the present study, we have investigated the structural, electrical and magneto-transport properties of polycrystalline and nanocrystalline Gd0.5Sr0.5MnO3 compounds. The variation of transport properties is modified by tuning the grain size of the material. In the high-temperature semiconducting region, temperature-dependent resistivity data can be well explained by the non-adiabatic small polaron hopping (SPH) mechanism. In addition, the resistivity data for all compounds in the low-temperature paramagnetic region can also be well explained by the variable range hopping (VRH) model. The parameters obtained from SPH and VRH mechanisms are found to be reasonable. In the case of nanocrystalline compounds, there is an overlapping temperature range where both SPH and VRH models are valid simultaneously, and a new conduction mechanism - variable range hopping of small polaron s(VR-SPH) is satisfactorily valid for the whole temperature range of these compounds. However, for the polycrystalline compound, the overlapping temperature region between VRH and SPH models does not exist and the VR-SPH mechanism is not valid here. Thus, polarons play a leading role in selecting different conduction mechanisms in different temperature ranges.

Keywords: electrical resistivity, manganite, small polaron hopping, variable range hopping, variable range of small polaron hopping

Procedia PDF Downloads 89

Authors: Faruk Ozdemir, Roy Kalawsky, Peter Hubbard

Abstract:

Accurate estimation of RUL provides a basis for effective predictive maintenance, reducing unexpected downtime for industrial equipment. However, while models such as the Random Forest have effective predictive capabilities, they are the so-called ‘black box’ models, where interpretability is at a threshold to make critical diagnostic decisions involved in industries related to aviation. The purpose of this work is to present a prognostic framework that embeds Explainable Artificial Intelligence (XAI) techniques in order to provide essential transparency in Machine Learning methods' decision-making mechanisms based on sensor data, with the objective of procuring actionable insights for the aviation industry. Sensor readings have been gathered from critical equipment such as turbofan jet engine and landing gear, and the prediction of the RUL is done by a Random Forest model. It involves steps such as data gathering, feature engineering, model training, and evaluation. These critical components’ datasets are independently trained and evaluated by the models. While suitable predictions are served, their performance metrics are reasonably good; such complex models, however obscure reasoning for the predictions made by them and may even undermine the confidence of the decision-maker or the maintenance teams. This is followed by global explanations using SHAP and local explanations using LIME in the second phase to bridge the gap in reliability within industrial contexts. These tools analyze model decisions, highlighting feature importance and explaining how each input variable affects the output. This dual approach offers a general comprehension of the overall model behavior and detailed insight into specific predictions. The proposed framework, in its third component, incorporates the techniques of causal analysis in the form of Granger causality tests in order to move beyond correlation toward causation. This will not only allow the model to predict failures but also present reasons, from the key sensor features linked to possible failure mechanisms to relevant personnel. The causality between sensor behaviors and equipment failures creates much value for maintenance teams due to better root cause identification and effective preventive measures. This step contributes to the system being more explainable. Surrogate Several simple models, including Decision Trees and Linear Models, can be used in yet another stage to approximately represent the complex Random Forest model. These simpler models act as backups, replicating important jobs of the original model's behavior. If the feature explanations obtained from the surrogate model are cross-validated with the primary model, the insights derived would be more reliable and provide an intuitive sense of how the input variables affect the predictions. We then create an iterative explainable feedback loop, where the knowledge learned from the explainability methods feeds back into the training of the models. This feeds into a cycle of continuous improvement both in model accuracy and interpretability over time. By systematically integrating new findings, the model is expected to adapt to changed conditions and further develop its prognosis capability. These components are then presented to the decision-makers through the development of a fully transparent condition monitoring and alert system. The system provides a holistic tool for maintenance operations by leveraging RUL predictions, feature importance scores, persistent sensor threshold values, and autonomous alert mechanisms. Since the system will provide explanations for the predictions given, along with active alerts, the maintenance personnel can make informed decisions on their end regarding correct interventions to extend the life of the critical machinery.

Keywords: predictive maintenance, explainable artificial intelligence, prognostic, RUL, machine learning, turbofan engines, C-MAPSS dataset

Procedia PDF Downloads 6

Authors: Amil Suleimanov, Aigul Saduakassova, Denis Vinnikov

Abstract:

Objective: To assess functional visceral fat (VAT) activity evaluated by ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) positron emission tomography/computed tomography (PET/CT) as a predictor of metastases in colorectal cancer (CRC). Materials and methods: We assessed 60 patients with histologically confirmed CRC who underwent 18F-FDG PET/CT after a surgical treatment and courses of chemotherapy. Age, histology, stage, and tumor grade were recorded. Functional VAT activity was measured by maximum standardized uptake value (SUVmax) using ¹⁸F-FDG PET/CT and tested as a predictor of later metastases in eight abdominal locations (RE – Epigastric Region, RLH – Left Hypochondriac Region, RRL – Right Lumbar Region, RU – Umbilical Region, RLL – Left Lumbar Region, RRI – Right Inguinal Region, RP – Hypogastric (Pubic) Region, RLI – Left Inguinal Region) and pelvic cavity (P) in the adjusted regression models. We also report the best areas under the curve (AUC) for SUVmax with the corresponding sensitivity (Se) and specificity (Sp). Results: In both adjusted for age regression models and ROC analysis, 18F-FDG accumulation in RLH (cutoff SUVmax 0.74; Se 75%; Sp 61%; AUC 0.668; p = 0.049), RU (cutoff SUVmax 0.78; Se 69%; Sp 61%; AUC 0.679; p = 0.035), RRL (cutoff SUVmax 1.05; Se 69%; Sp 77%; AUC 0.682; p = 0.032) and RRI (cutoff SUVmax 0.85; Se 63%; Sp 61%; AUC 0.672; p = 0.043) could predict later metastases in CRC patients, as opposed to age, sex, primary tumor location, tumor grade and histology. Conclusions: VAT SUVmax is significantly associated with later metastases in CRC patients and can be used as their predictor.

Keywords: ¹⁸F-FDG, PET/CT, colorectal cancer, predictive value

Procedia PDF Downloads 117

Authors: Sirilak Areerachakul

Abstract:

Water quality has initiated serious management efforts in many countries. Artificial Neural Network (ANN) models are developed as forecasting tools in predicting water quality trend based on historical data. This study endeavors to automatically classify water quality. The water quality classes are evaluated using 6 factor indices. These factors are pH value (pH), Dissolved Oxygen (DO), Biochemical Oxygen Demand (BOD), Nitrate Nitrogen (NO3N), Ammonia Nitrogen (NH3N) and Total Coliform (T-Coliform). The methodology involves applying data mining techniques using multilayer perceptron (MLP) neural network models. The data consisted of 11 sites of Saen Saep canal in Bangkok, Thailand. The data is obtained from the Department of Drainage and Sewerage Bangkok Metropolitan Administration during 2007-2011. The results of multilayer perceptron neural network exhibit a high accuracy multilayer perception rate at 94.23% in classifying the water quality of Saen Saep canal in Bangkok. Subsequently, this encouraging result could be combined with GIS data improves the classification accuracy significantly.

Keywords: artificial neural network, geographic information system, water quality, computer science

Procedia PDF Downloads 343

Authors: Baladitya Swaika, Rahul Khatry

Abstract:

Computer Adaptive Tests (CATs) is one of the most efficient ways for testing the cognitive abilities of students. CATs are based on Item Response Theory (IRT) which is based on item selection and ability estimation using statistical methods of maximum information selection/selection from posterior and maximum-likelihood (ML)/maximum a posteriori (MAP) estimators respectively. This study aims at combining both classical and Bayesian approaches to IRT to create a dataset which is then fed to a neural network which automates the process of ability estimation and then comparing it to traditional CAT models designed using IRT. This study uses python as the base coding language, pymc for statistical modelling of the IRT and scikit-learn for neural network implementations. On creation of the model and on comparison, it is found that the Neural Network based model performs 7-10% worse than the IRT model for score estimations. Although performing poorly, compared to the IRT model, the neural network model can be beneficially used in back-ends for reducing time complexity as the IRT model would have to re-calculate the ability every-time it gets a request whereas the prediction from a neural network could be done in a single step for an existing trained Regressor. This study also proposes a new kind of framework whereby the neural network model could be used to incorporate feature sets, other than the normal IRT feature set and use a neural network’s capacity of learning unknown functions to give rise to better CAT models. Categorical features like test type, etc. could be learnt and incorporated in IRT functions with the help of techniques like logistic regression and can be used to learn functions and expressed as models which may not be trivial to be expressed via equations. This kind of a framework, when implemented would be highly advantageous in psychometrics and cognitive assessments. This study gives a brief overview as to how neural networks can be used in adaptive testing, not only by reducing time-complexity but also by being able to incorporate newer and better datasets which would eventually lead to higher quality testing.

Keywords: computer adaptive tests, item response theory, machine learning, neural networks

Procedia PDF Downloads 175

Authors: Yunus Onur Yildiz, Mesut Kirca

Abstract:

In this study, mechanical properties of a nanoporous metal coated with a different metallic material are studied through a new atomistic modelling technique and molecular dynamics (MD) simulations. This new atomistic modelling technique is based on the Voronoi tessellation method for the purpose of geometric representation of the ligaments. With the proposed technique, atomistic models of nanoporous metals which have randomly oriented ligaments with non-uniform mass distribution along the ligament axis can be generated by enabling researchers to control both ligament length and diameter. Furthermore, by the utilization of this technique, atomistic models of coated nanoporous materials can be numerically obtained for further mechanical or thermal characterization. In general, this study consists of two stages. At the first stage, we use algorithms developed for generating atomic coordinates of the coated nanoporous material. In this regard, coordinates of randomly distributed points are determined in a controlled way to be employed in the establishment of the Voronoi tessellation, which results in randomly oriented and intersected line segments. Then, line segment representation of the Voronoi tessellation is transformed to atomic structure by a special process. This special process includes generation of non-uniform volumetric core region in which atoms can be generated based on a specific crystal structure. As an extension, this technique can be used for coating of nanoporous structures by creating another volumetric region encapsulating the core region in which atoms for the coating material are generated. The ultimate goal of the study at this stage is to generate atomic coordinates that can be employed in the MD simulations of randomly organized coated nanoporous structures. At the second stage of the study, mechanical behavior of the coated nanoporous models is investigated by examining deformation mechanisms through MD simulations. In this way, the effect of coating on the mechanical behavior of the selected material couple is investigated.

Keywords: atomistic modelling, molecular dynamic, nanoporous metals, voronoi tessellation

Procedia PDF Downloads 277

Authors: L. Benaaouinate, M. Khafallah, A. Martinez, A. Mesbahi, T. Bouragba

Abstract:

This paper concerns with the modeling, simulation, and emulation of a wind turbine emulator for standalone wind energy conversion systems. By using emulation system, we aim to reproduce the dynamic behavior of the wind turbine torque on the generator shaft: it provides the testing facilities to optimize generator control strategies in a controlled environment, without reliance on natural resources. The aerodynamic, mechanical, electrical models have been detailed as well as the control of pitch angle using Fuzzy Logic for horizontal axis wind turbines. The wind turbine emulator consists mainly of an induction motor with AC power drive with torque control. The control of the induction motor and the mathematical models of the wind turbine are designed with MATLAB/Simulink environment. The simulation results confirm the effectiveness of the induction motor control system and the functionality of the wind turbine emulator for providing all necessary parameters of the wind turbine system such as wind speed, output torque, power coefficient and tip speed ratio. The findings are of direct practical relevance.

Keywords: electrical generator, induction motor drive, modeling, pitch angle control, real time control, renewable energy, wind turbine, wind turbine emulator

Procedia PDF Downloads 234