Search results for: bioinformatic predictions

Authors: Sara Hasani

Abstract:

This research focuses on natural sudden onset disasters characterised as ‘occurring with little or no warning and often cause excessive injuries far surpassing the national response capacities’. Based on the panel analysis of the historic record of 4,252 natural onset disasters between 1980 to 2015, a predictive method was developed to predict the human impact of the disaster (fatality, injured, homeless) with less than 3% of errors. The geographical dispersion of the disasters includes every country where the data were available and cross-examined from various humanitarian sources. The records were then filtered into 4252 records of the disasters where the five predictive variables (disaster type, HDI, DRI, population, and population density) were clearly stated. The procedure was designed based on a combination of pattern recognition techniques and rule-based clustering for prediction and discrimination analysis to validate the results further. The result indicates that there is a relationship between the disaster human impact and the five socio-economic characteristics of the affected country mentioned above. As a result, a framework was put forward, which could predict the disaster’s human impact based on their severity rank in the early hours of disaster strike. The predictions in this model were outlined in two worst and best-case scenarios, which respectively inform the lower range and higher range of the prediction. A necessity to develop the predictive framework can be highlighted by noticing that despite the existing research in literature, a framework for predicting the human impact and estimating the needs at the time of the disaster is yet to be developed. This can further be used to allocate the resources at the response phase of the disaster where the data is scarce.

Keywords: disaster management, natural disaster, pattern recognition, prediction

Procedia PDF Downloads 153

Authors: Jude K. Safo

Abstract:

Knowledge Graphs KG) and their relation to Graph Embeddings (GE) represent a unique data structure in the landscape of machine learning (relative to image, text and acoustic data). Unlike the latter, GEs are the only data structure sufficient for representing hierarchically dense, semantic information needed for use-cases like supply chain data and protein folding where the search space exceeds the limits traditional search methods (e.g. page-rank, Dijkstra, etc.). While GEs are effective for compressing low rank tensor data, at scale, they begin to introduce a new problem of ’data retreival’ which we observe in Large Language Models. Notable attempts by transE, TransR and other prominent industry standards have shown a peak performance just north of 57% on WN18 and FB15K benchmarks, insufficient practical industry applications. They’re also limited, in scope, to next node/link predictions. Traditional linear methods like Tucker, CP, PARAFAC and CANDECOMP quickly hit memory limits on tensors exceeding 6.4 million nodes. This paper outlines a topological framework for linear mapping between concepts in KG space and GE space that preserve cardinality. Most importantly we introduce a traceable framework for composing dense linguistic strcutures. We demonstrate performance on WN18 benchmark this model hits. This model does not rely on Large Langauge Models (LLM) though the applications are certainy relevant here as well.

Keywords: representation theory, large language models, graph embeddings, applied algebraic topology, applied knot theory, combinatorics

Procedia PDF Downloads 68

Authors: Teng lin, Li Yuxing, Han Hui, Zhao Pengfei, Zhang Datong

Abstract:

With the development of carbon capture and storage (CCS), the flow assurance of CO2 transportation becomes more important, particularly for supercritical CO2 pipelines. The relieving system using the choke valve is applied to control the pressure in CO2 pipeline. However, the temperature of fluid would drop rapidly because of Joule-Thomson cooling (JTC), which may cause solid CO2 form and block the pipe. In this paper, a Computational Fluid Dynamic (CFD) model, using the modified Lagrangian method, Reynold's Stress Transport model (RSM) for turbulence and stochastic tracking model (STM) for particle trajectory, was developed to predict the deposition characteristic of solid carbon dioxide. The model predictions were in good agreement with the experiment data published in the literature. It can be observed that the particle distribution affected the deposition behavior. In the region of the sudden expansion, the smaller particles accumulated tightly on the wall were dominant for pipe blockage. On the contrary, the size of solid CO2 particles deposited near the outlet usually was bigger and the stacked structure was looser. According to the calculation results, the movement of the particles can be regarded as the main four types: turbulent motion close to the sudden expansion structure, balanced motion at sudden expansion-middle region, inertial motion near the outlet and the escape. Furthermore the particle deposits accumulated primarily in the sudden expansion region, reattachment region and outlet region because of the four type of motion. Also the Stokes number had an effect on the deposition ratio and it is recommended for Stokes number to avoid 3-8St.

Keywords: carbon capture and storage, carbon dioxide pipeline, gas-particle flow, deposition

Procedia PDF Downloads 369

Authors: Mamadou Dione, Eric Matzner-lober, Philippe Alexandre

Abstract:

The Energy Transition Act defined by the French State has precise implications on Renewable Energies, in particular on its remuneration mechanism. Until then, a purchase obligation contract permitted the sale of wind-generated electricity at a fixed rate. Tomorrow, it will be necessary to sell this electricity on the Market (at variable rates) before obtaining additional compensation intended to reduce the risk. This sale on the market requires to announce in advance (about 48 hours before) the production that will be delivered on the network, so to be able to predict (in the short term) this production. The fundamental problem remains the variability of the Wind accentuated by the geographical situation. The objective of the project is to provide, every day, short-term forecasts (48-hour horizon) of wind production using weather data. The predictions of the GFS model and those of the ECMWF model are used as explanatory variables. The variable to be predicted is the production of a wind farm. We do two approaches: a direct approach that predicts wind generation directly from weather data, and an integrated approach that estimâtes wind from weather data and converts it into wind power by power curves. We used machine learning techniques to predict this production. The models tested are random forests, CART + Bagging, CART + Boosting, SVM (Support Vector Machine). The application is made on a wind farm of 22MW (11 wind turbines) of the Compagnie du Vent (that became Engie Green France). Our results are very conclusive compared to the literature.

Keywords: forecast aggregation, machine learning, spatio-temporal dynamics modeling, wind power forcast

Procedia PDF Downloads 217

Authors: Md. Najiur Rahman

Abstract:

This hypothesis reveals a profound and symmetrical connection that goes beyond the boundaries of quantum physics and cosmology, revolutionizing our understanding of the fundamental building blocks of the cosmos, given its name ‘The Theory of the Mystery’. This theory has an elegantly simple equation, “R = ∆r / √∆m” which establishes a beautiful and well-crafted relationship between the radius (R) of an elementary particle or galaxy, the relative change in radius (∆r), and the mass difference (∆m) between related entities. It is fascinating to note that this formula presents a super synchronization, one which involves the convergence of every basic particle and any single celestial entity into perfect alignment with its respective mass and radius. In addition, we have a Supporting equation that defines the mass-radius connection of an entity by the equation: R=√m/N, where N is an empirically established constant, determined to be approximately 42.86 kg/m, representing the proportionality between mass and radius. It provides precise predictions, collects empirical evidence, and explores the far-reaching consequences of theories such as General Relativity. This elegant symmetry reveals a fundamental principle that underpins the cosmos: each component, whether small or large, follows a precise mass-radius relationship to exert gravity by a universal law. This hypothesis represents a transformative process towards a unified theory of physics, and the pursuit of experimental verification will show that each particle and galaxy is bound by gravity and plays a unique but harmonious role in shaping the universe. It promises to reveal the great symphony of the mighty cosmos. The predictive power of our hypothesis invites the exploration of entities at the farthest reaches of the cosmos, providing a bridge between the known and the unknown.

Keywords: unified theory, quantum gravity, mass-radius relationship, dark matter, uniform gravity

Procedia PDF Downloads 105

Authors: Jinny Hong, Jeanne C. Watson

Abstract:

Three types of autobiographical memory recall -specific, episodic, and generic- were examined in relation to the quality of descriptions and in-session levels of emotional arousal. Correlational analyses and general estimating equation were conducted to test the relationships between 1) quality of descriptions and type of memory, 2) type of memory and emotional arousal, and 3) quality of descriptions and emotional arousal. The data was transcripts drawn from an archival randomized-control study comparing cognitive-behavioral therapy and emotion-focused therapy in a 16-week treatment for depression. Autobiographical memory recall segments were identified and sorted into three categories: specific, episodic, and generic. Quality of descriptions of these segments was then operationalized and measured using the Referential Activity Scale, and each memory segment was rated on four dimensions: concreteness, specificity, clarity, and overall imagery. Clients’ level of emotional arousal for each recall was measured using the Client’s Expression Emotion Scale. Contrary to the predictions, generic memories are associated with higher emotional arousal ratings and descriptive language ratings compared to specific memories. However, a positive relationship emerged between the quality of descriptions and expressed emotional arousal, indicating that the quality of descriptions in which memories are described in sessions is more important than the type of memory recalled in predicting clients’ level of emotional arousal. The results from this study provide a clearer understanding of the role of memory recall types and use of language in activating emotional arousal in psychotherapy sessions in a depressed sample.

Keywords: autobiographical memory recall, emotional arousal, psychotherapy for depression, quality of descriptions, referential activity

Procedia PDF Downloads 162

Authors: Yue Zhang, Bo Yang, Gang Xiong, Mohamed Elchalakanic, Shidong Nie

Abstract:

This study aims to investigate the lateral torsional buckling of I-shaped cross-section beams fabricated from Q460GJ structural steel plates. Both experimental and numerical simulation results are presented in this paper. A total of eight specimens were tested under a three-point bending, and the corresponding numerical models were established to conduct parametric studies. The effects of some key parameters such as the non-dimensional member slenderness and the height-to-width ratio, were investigated based on the verified numerical models. Also, the results obtained from the parametric studies were compared with the predictions calculated by different design codes including the Chinese design code (GB50017-2003, 2003), the new draft version of Chinese design code (GB50017-201X, 2012), Eurocode 3 (EC3, 2005) and the North America design code (ANSI/AISC360-10, 2010). These comparisons indicated that the sectional height-to-width ratio does not play an important role to influence the overall stability load-carrying capacity of Q460GJ structural steel beams with welded I-shaped cross-sections. It was also found that the design methods in GB50017-2003 and ANSI/AISC360-10 overestimate the overall stability and load-carrying capacity of Q460GJ welded I-shaped cross-section beams.

Keywords: experimental study, finite element analysis, global stability, lateral torsional buckling, Q460GJ structural steel

Procedia PDF Downloads 327

Authors: Sudhir Kumar Singh, Debashish Chakravarty

Abstract:

Slope stability analysis is an important aspect in the field of geotechnical engineering. It is also important from safety, and economic point of view as any slope failure leads to loss of valuable lives and damage to property worth millions. This paper aims at mitigating the risk of slope failure by studying the effect of different joint sets on the stability of mine pit slopes under the influence of various external factors, namely degree of saturation, rainfall intensity, and seismic coefficients. Supervised machine learning approach has been utilized for making accurate and reliable predictions regarding the stability of slopes based on the value of Factor of Safety. Numerous cases have been studied for analyzing the stability of slopes using the popular Finite Element Method, and the data thus obtained has been used as training data for the supervised machine learning models. The input data has been trained on different supervised machine learning models, namely Random Forest, Decision Tree, Support vector Machine, and XGBoost. Distinct test data that is not present in training data has been used for measuring the performance and accuracy of different models. Although all models have performed well on the test dataset but Random Forest stands out from others due to its high accuracy of greater than 95%, thus helping us by providing a valuable tool at our disposition which is neither computationally expensive nor time consuming and in good accordance with the numerical analysis result.

Keywords: finite element method, geotechnical engineering, machine learning, slope stability

Procedia PDF Downloads 101

Authors: Alexandros Pournaras, Anastasia Papadopoulou, Serafim Kontos, Anastasios Karakostas

Abstract:

The air quality of modern cities is an important concern, as poor air quality contributes to human health and environmental issues. Reliable air quality forecasting has, thus, gained scientific and governmental attention as an essential tool that enables authorities to take proactive measures for public safety. In this study, the potential of Machine Learning (ML) models to forecast PM2.5 at local scale is investigated in the city of Thessaloniki, the second largest city in Greece, which has been struggling with the persistent issue of air pollution. ML models, with proven ability to address timeseries forecasting, are employed to predict the PM2.5 concentrations and the respective Air Quality Index 5-days ahead by learning from daily historical air quality and meteorological data from 2014 to 2016 and gathered from two stations with different land use characteristics in the urban fabric of Thessaloniki. The performance of the ML models on PM2.5 concentrations is evaluated with common statistical methods, such as R squared (r²) and Root Mean Squared Error (RMSE), utilizing a portion of the stations’ measurements as test set. A multi-categorical evaluation is utilized for the assessment of their performance on respective AQIs. Several conclusions were made from the experiments conducted. Experimenting on MLs’ configuration revealed a moderate effect of various parameters and training schemas on the model’s predictions. Their performance of all these models were found to produce satisfactory results on PM2.5 concentrations. In addition, their application on untrained stations showed that these models can perform well, indicating a generalized behavior. Moreover, their performance on AQI was even better, showing that the MLs can be used as predictors for AQI, which is the direct information provided to the general public.

Keywords: Air Quality, AQ Forecasting, AQI, Machine Learning, PM2.5

Procedia PDF Downloads 77

Authors: Muhammet Baldan, Emel Timuçin

Abstract:

Molecular solubility prediction plays a crucial role in various fields, such as drug discovery, environmental science, and material science. In this study, we compare the performance of five machine learning algorithms—linear regression, support vector machines (SVM), random forests, gradient boosting machines (GBM), and neural networks—for predicting molecular solubility using the AqSolDB dataset. The dataset consists of 9981 data points with their corresponding solubility values. MACCS keys (166 bits), RDKit properties (20 properties), and structural properties(3) features are extracted for every smile representation in the dataset. A total of 189 features were used for training and testing for every molecule. Each algorithm is trained on a subset of the dataset and evaluated using metrics accuracy scores. Additionally, computational time for training and testing is recorded to assess the efficiency of each algorithm. Our results demonstrate that random forest model outperformed other algorithms in terms of predictive accuracy, achieving an 0.93 accuracy score. Gradient boosting machines and neural networks also exhibit strong performance, closely followed by support vector machines. Linear regression, while simpler in nature, demonstrates competitive performance but with slightly higher errors compared to ensemble methods. Overall, this study provides valuable insights into the performance of machine learning algorithms for molecular solubility prediction, highlighting the importance of algorithm selection in achieving accurate and efficient predictions in practical applications.

Keywords: random forest, machine learning, comparison, feature extraction

Procedia PDF Downloads 40

Authors: Ali Nour El Hajj

Abstract:

Background: The perennial deficiencies of the failure models in the materials field have profoundly and significantly impacted all associated technical fields that depend on accurate failure predictions. Many preeminent and well-known scientists from an earlier era of groundbreaking discoveries attempted to solve the issue of material failure. However, a thorough understanding of material failure has been frustratingly elusive. Objective: The heart of this study is the presentation of a methodology that identifies a newly derived one-parameter criterion as the only general failure theory for noncompressible, homogeneous, and isotropic materials subjected to multiaxial states of stress and various boundary conditions, providing the solution to this longstanding problem. This theory is the counterpart and companion piece to the theory of elasticity and is in a formalism that is suitable for broad application. Methods: Utilizing advanced finite-element analysis, the maximum internal breaking stress corresponding to the maximum applied external force is identified as a unified and universal material failure criterion for determining the structural capacity of any system, regardless of its geometry or architecture. Results: A comparison between the proposed criterion and methodology against design codes reveals that current provisions may underestimate the structural capacity by 2.17 times or overestimate the capacity by 2.096 times. It also shows that existing standards may underestimate the structural capacity by 1.4 times or overestimate the capacity by 2.49 times. Conclusion: The proposed failure criterion and methodology will pave the way for a new era in designing unconventional structural systems composed of unconventional materials.

Keywords: failure criteria, strength theory, failure mechanics, materials mechanics, rock mechanics, concrete strength, finite-element analysis, mechanical engineering, aeronautical engineering, civil engineering

Procedia PDF Downloads 78

Authors: D. Hilton

Abstract:

An analysis of the Australian Diabetes Screening Study estimated undiagnosed diabetes mellitus [DM] prevalence in a high risk general practice based cohort. DM prevalence varied from 9.4% to 18.1% depending upon the diagnostic criteria utilised with age being a highly significant risk factor. Utilising the gold standard oral glucose tolerance test, the prevalence of DM was 22-23% in those aged >= 70 years and <15% in those aged 40-59 years. Opportunistic screening in Australian general practice potentially can identify many persons with undiagnosed type 2 DM. An Australian Bureau of Statistics document published three years ago, reported the highest rate of DM in men aged 65-74 years [19%] whereas the rate for women was highest in those over 75 years [13%]. If you consider that the Australian Bureau of Statistics report in 2007 found that 13% of the population was over 65 years of age and that this will increase to 23-25% by 2056 with a further projected increase to 25-28% by 2101, obviously this information has to be factored into the equation when age related diabetes prevalence predictions are calculated. This 10-15% proportional increase of elderly persons within the population demographics has dramatic implications for the estimated number of elderly persons with DM in these age groupings. Computational methodology showing the age related demographic changes reported in these official statistical documents will be done showing estimates for 2056 and 2101 for different age groups. This has relevance for future diabetes prevalence rates and shows that along with many countries worldwide Australia is facing an increasing pandemic. In contrast Japan is expected to have a decrease in the next twenty years in the number of persons with diabetes.

Keywords: epidemiological methods, aging, prevalence, diabetes mellitus

Procedia PDF Downloads 374

Authors: Hojjat Mohammadi, Randall Divito, Gary J. E. Kramer

Abstract:

Tunnelling and pipe jacking in very soft soils (fat clays), even with an Earth Pressure Balance tunnel boring machine (EPBM), can cause large ground displacements. In this study, the short-term and long-term ground and tunnel response is predicted for twin, pipe-jacked EPBM 3 meter diameter tunnels with a narrow pillar width. Initial modelling indicated complete closure of the annulus gap at the tail shield onto the centrifugally cast, glass-fiber-reinforced, polymer mortar jacking pipe (FRP). Numerical modelling was employed to simulate the excavation and support installation sequence, examine the ground response during excavation, confirm the adequacy of the pillar width and check the structural adequacy of the installed pipe. In the numerical models, Mohr-Coulomb constitutive model with the effect of unloading was adopted for the fat clays, while for the bedrock layer, the generalized Hoek-Brown was employed. The numerical models considered explicit excavation sequences and different levels of ground convergence prior to support installation. The well-studied excavation sequences made the analysis possible for this study on a very soft clay, otherwise, obtaining the convergency in the numerical analysis would be impossible. The predicted results indicate that the ground displacements around the tunnel and its effect on the pipe would be acceptable despite predictions of large zones of plastic behaviour around the tunnels and within the entire pillar between them due to excavation-induced ground movements.

Keywords: finite element modeling (FEM), pipe-jacked tunneling, very soft clay, EPBM

Procedia PDF Downloads 82

Authors: Niloofar Bahramian, Mohammad Atai, Mohammad Reza Naimi-Jamal

Abstract:

Rule of mixtures is the simple analytical model is used to predict various properties of composites before design. The aim of this study was to demonstrate the benefits and limitations of the Rule-of-Mixtures (ROM) for predicting bending modulus of a continuous and unidirectional fiber reinforced composites using in dental applications. The Composites were fabricated from light curing resin (with and without silica nanoparticles) and modified and non-modified fibers. Composite samples were divided into eight groups with ten specimens for each group. The bending modulus (flexural modulus) of samples was determined from the slope of the initial linear region of stress-strain curve on 2mm×2mm×25mm specimens with different designs: fibers corona treatment time (0s, 5s, 7s), fibers silane treatment (0%wt, 2%wt), fibers volume fraction (41%, 33%, 25%) and nanoparticles incorporation in resin (0%wt, 10%wt, 15%wt). To study the fiber and matrix interface after fracture, single edge notch beam (SENB) method and scanning electron microscope (SEM) were used. SEM also was used to show the nanoparticles dispersion in resin. Experimental results of bending modulus for composites made of both physical (corona) and chemical (silane) treated fibers were in reasonable agreement with linear ROM estimates, but untreated fibers or non-optimized treated fibers and poor nanoparticles dispersion did not correlate as well with ROM results. This study shows that the ROM is useful to predict the mechanical behavior of unidirectional dental composites but fiber-resin interface and quality of nanoparticles dispersion play important role in ROM accurate predictions.

Keywords: bending modulus, fiber reinforced composite, fiber treatment, rule-of-mixtures

Procedia PDF Downloads 274

Authors: Tai Yuan Yu, Pei-Jen Wang

Abstract:

Oil-free turbomachinery is considered one of the critical technologies for future green power generation systems as rotor machinery systems. Oil-free technology allows clean, compact, and maintenance-free working, and gas foil bearings, abbreviated as GFBs, are important for the technology. Since the first applications in the auxiliary power units and air cycle machines in the 1970s, obvious improvement has been created to the computational models for dynamic rotor behavior. However, many technical issues are still poorly understood or remain unsolved, and some of those are thermal management and the pattern of how pressure will be distributed in bearing clearance. This paper presents a three-dimensional, abbreviated as 3D, fluid-structure interaction model of single pad foil bearings and three pad foil bearings to predict bearing working behavior that researchers could compare characteristics of those. The coupling analysis model involves dynamic working characteristics applied to all the gas film and mechanical structures. Therefore, the elastic deformation of foil structure and the hydrodynamic pressure of gas film can both be calculated by a finite element method program. As a result, the temperature distribution pattern could also be iteratively solved by coupling analysis. In conclusion, the working fluid state in a gas film of various pad forms of bearings working characteristic at constant rotational speed for both can be solved for comparisons with the experimental results.

Keywords: fluid-structure interaction, multi-physics simulations, gas foil bearing, oil-free, transient thermo-hydrodynamic

Procedia PDF Downloads 163

Authors: Amritanshu Sandilya, M. V. Shah

Abstract:

Collapsible soils such as loess are a common geotechnical challenge due to their potential to undergo sudden and severe settlement under certain loading conditions. The need for filling engineering to increase developing land has grown significantly in recent years, which has created several difficulties in managing soil strength and stability during compaction. Numerous engineering problems, such as roadbed subsidence and pavement cracking, have been brought about by insufficient fill strength. Therefore, strict control of compaction parameters is essential to reduce these distresses. Accurately measuring the degree of compaction, which is often represented by compactness is an important component of compaction control. For credible predictions of how collapsible soils will behave under complicated loading situations, the accuracy of laboratory studies is essential. Therefore, this study aims to investigate the energy transfer in collapsible soils during laboratory Proctor compaction tests to provide insights into how energy transfer can be optimized to achieve more accurate and reliable results in compaction testing. The compaction characteristics in terms of energy of loess soil have been studied at moisture content corresponding to dry of optimum, at the optimum and wet side of optimum and at different compaction energy levels. The hammer impact force (E0) and soil bottom force (E) were measured using an impact load cell mounted at the bottom of the compaction mould. The variation in energy consumption ratio (E/ E0) was observed and compared with the compaction curve of the soil. The results indicate that the plot of energy consumption ratio versus moisture content can serve as a reliable indicator of the compaction characteristics of the soil in terms of energy.

Keywords: soil compaction, proctor compaction test, collapsible soil, energy transfer

Procedia PDF Downloads 92

Authors: Lavanya Annadi, Fahimeh Jafari

Abstract:

Transportation brings immense benefits to society, but it also has its costs. Costs include such as the cost of infrastructure, personnel and equipment, but also the loss of life and property in traffic accidents on the road, delays in travel due to traffic congestion and various indirect costs in terms of air transport. More research has been done to identify the various factors that affect road accidents, such as road infrastructure, traffic, sociodemographic characteristics, land use, and the environment. The aim of this research is to predict the probabilistic crash prediction of vehicles using machine learning due to natural and structural reasons by excluding spontaneous reasons like overspeeding etc., in the United States. These factors range from weather factors, like weather conditions, precipitation, visibility, wind speed, wind direction, temperature, pressure, and humidity to human made structures like road structure factors like bump, roundabout, no exit, turning loop, give away, etc. Probabilities are dissected into ten different classes. All the predictions are based on multiclass classification techniques, which are supervised learning. This study considers all crashes that happened in all states collected by the US government. To calculate the probability, multinomial expected value was used and assigned a classification label as the crash probability. We applied three different classification models, including multiclass Logistic Regression, Random Forest and XGBoost. The numerical results show that XGBoost achieved a 75.2% accuracy rate which indicates the part that is being played by natural and structural reasons for the crash. The paper has provided in-deep insights through exploratory data analysis.

Keywords: road safety, crash prediction, exploratory analysis, machine learning

Procedia PDF Downloads 111

Authors: Hamdi Beji, Toufik Kanit, Tanguy Messager

Abstract:

This study aims to construct a predictive model proficient in foreseeing the linear elastic and thermal characteristics of composite materials, drawing on a multitude of influencing parameters. These parameters encompass the shape of inclusions (circular, elliptical, square, triangle), their spatial coordinates within the matrix, orientation, volume fraction (ranging from 0.05 to 0.4), and variations in contrast (spanning from 10 to 200). A variety of machine learning techniques are deployed, including decision trees, random forests, support vector machines, k-nearest neighbors, and an artificial neural network (ANN), to facilitate this predictive model. Moreover, this research goes beyond the predictive aspect by delving into an inverse analysis using genetic algorithms. The intent is to unveil the intrinsic characteristics of composite materials by evaluating their thermomechanical responses. The foundation of this research lies in the establishment of a comprehensive database that accounts for the array of input parameters mentioned earlier. This database, enriched with this diversity of input variables, serves as a bedrock for the creation of machine learning and genetic algorithm-based models. These models are meticulously trained to not only predict but also elucidate the mechanical and thermal conduct of composite materials. Remarkably, the coupling of machine learning and genetic algorithms has proven highly effective, yielding predictions with remarkable accuracy, boasting scores ranging between 0.97 and 0.99. This achievement marks a significant breakthrough, demonstrating the potential of this innovative approach in the field of materials engineering.

Keywords: machine learning, composite materials, genetic algorithms, mechanical and thermal proprieties

Procedia PDF Downloads 54

Authors: Juan Huang, Hugo Ninanya

Abstract:

Oil has been used as a source of energy and supply to make materials, such as asphalt or rubber for many years. This is the reason why new technologies have been implemented through time. However, research still needs to continue increasing due to new challenges engineers face every day, just like unconventional reservoirs. Various numerical methodologies have been applied in petroleum engineering as tools in order to optimize the production of reservoirs before drilling a wellbore, although not all of these have the same efficiency when talking about studying fracture propagation. Analytical methods like those based on linear elastic fractures mechanics fail to give a reasonable prediction when simulating fracture propagation in ductile materials whereas numerical methods based on the cohesive zone method (CZM) allow to represent the elastoplastic behavior in a reservoir based on a constitutive model; therefore, predictions in terms of displacements and pressure will be more reliable. In this work, a hydro-geomechanical coupled model of horizontal wells in fractured rock was developed using ABAQUS; both extended element method and cohesive elements were used to represent predefined fractures in a model (2-D). A power law for representing the rheological behavior of fluid (shear-thinning, power index <1) through fractures and leak-off rate permeating to the matrix was considered. Results have been showed in terms of aperture and length of the fracture, pressure within fracture and fluid loss. It was showed a high infiltration rate to the matrix as power index decreases. A sensitivity analysis is conclusively performed to identify the most influential factor of fluid loss.

Keywords: fracture, hydro-geomechanical model, non-Newtonian fluid, numerical analysis, sensitivity analysis

Procedia PDF Downloads 206

Authors: Stefano M. Spagocci

Abstract:

The efficiency of photovoltaic panels can be calculated with such software packages as RETScreen that allow design engineers to take financial as well as technical considerations into account. RETScreen is interfaced with meteorological databases, so that efficiency calculations can be realistically carried out. The author has recently contributed to the development of solar modules with accumulation capability and an embedded water purifier, aimed at off-grid users such as users in developing countries. The software packages examined do not allow to take ancillary equipment into account, hence the decision to implement a technical and financial model of the system. The author realized that, rather than re-implementing the quite sophisticated model of RETScreen - a mathematical description of which is anyway not publicly available - it was possible to drastically simplify it, including the meteorological factors which, in RETScreen, are presented in a numerical form. The day-by-day efficiency of a photovoltaic solar panel was parametrized by the product of factors expressing, respectively, daytime duration, solar right ascension motion, solar declination motion, cloudiness, temperature. For the sun-motion-dependent factors, positional astronomy formulae, simplified by the author, were employed. Meteorology-dependent factors were fitted by simple trigonometric functions, employing numerical data supplied by RETScreen. The accuracy of our model was tested by comparing it to the predictions of RETScreen; the accuracy obtained was 11%. In conclusion, our study resulted in a model that can be easily implemented in a spreadsheet - thus being easily manageable by non-specialist personnel - or in more sophisticated software packages. The model was used in a number of design exercises, concerning photovoltaic solar panels and ancillary equipment like the above-mentioned water purifier.

Keywords: clean energy, energy engineering, mathematical modelling, photovoltaic panels, solar energy

Procedia PDF Downloads 68

Authors: L. Freeborn

Abstract:

This paper discusses the application of complex dynamic system theory (DST) to the study of individual differences in second language development. This transdisciplinary framework allows researchers to view the trajectory of language development as a dynamic, non-linear process. A DST approach views language as multi-componential, consisting of multiple complex systems and nested layers. These multiple components and systems continuously interact and influence each other at both the macro- and micro-level. Dynamic systems theory aims to explain and describe the development of the language system, rather than make predictions about its trajectory. Such a holistic and ecological approach to second language development allows researchers to include various research methods from neurological, cognitive, and social perspectives. A DST perspective would involve in-depth analyses as well as mixed methods research. To illustrate, a neurobiological approach to second language development could include non-invasive neuroimaging techniques such as electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) to investigate areas of brain activation during language-related tasks. A cognitive framework would further include behavioural research methods to assess the influence of intelligence and personality traits, as well as individual differences in foreign language aptitude, such as phonetic coding ability and working memory capacity. Exploring second language development from a DST approach would also benefit from including perspectives from the field of applied linguistics, regarding the teaching context, second language input, and the role of affective factors such as motivation. In this way, applying mixed research methods from neurobiological, cognitive, and social approaches would enable researchers to have a more holistic view of the dynamic and complex processes of second language development.

Keywords: dynamic systems theory, mixed methods, research design, second language development

Procedia PDF Downloads 135

Authors: Erifyli Tsagkari, Stephanie Connelly, Zhaowei Liu, Andrew McBride, William Sloan

Abstract:

Biofilms play an essential role in treating water in biofiltration systems. The biofilm morphology and function are inextricably linked to the hydrodynamics of flow through a filter, and yet engineers rarely explicitly engineer this interaction. We develop a system that links computer simulation and 3-D printing to optimize and rapidly prototype filter media to optimize biofilm function with the hypothesis that biofilm function is intimately linked to the flow passing through the filter. A computational model that numerically solves the incompressible time-dependent Navier Stokes equations coupled to a model for biofilm growth and function is developed. The model is imbedded in an optimization algorithm that allows the model domain to adapt until criteria on biofilm functioning are met. This is applied to optimize the shape of filter media in a simple flow channel to promote biofilm formation. The computer code links directly to a 3-D printer, and this allows us to prototype the design rapidly. Its validity is tested in flow visualization experiments and by microscopy. As proof of concept, the code was constrained to explore a small range of potential filter media, where the medium acts as an obstacle in the flow that sheds a von Karman vortex street that was found to enhance the deposition of bacteria on surfaces downstream. The flow visualization and microscopy in the 3-D printed realization of the flow channel validated the predictions of the model and hence its potential as a design tool. Overall, it is shown that the combination of our computational model and the 3-D printing can be effectively used as a design tool to prototype filter media to optimize biofilm formation.

Keywords: biofilm, biofilter, computational model, von karman vortices, 3-D printing.

Procedia PDF Downloads 142

Authors: Raghavi C. Janaswamy

Abstract:

In the healthcare sector, heterogenous data elements such as patients, diagnosis, symptoms, conditions, observation text from physician notes, and prescriptions form the essentials of the Electronic Health Record (EHR). The data in the form of clear text and images are stored or processed in a relational format in most systems. However, the intrinsic structure restrictions and complex joins of relational databases limit the widespread utility. In this regard, the design and development of realistic mapping and deep connections as real-time objects offer unparallel advantages. Herein, a graph neural network-based classification of EHR data has been developed. The patient conditions have been predicted as a node classification task using a graph-based open source EHR data, Synthea Database, stored in Tigergraph. The Synthea DB dataset is leveraged due to its closer representation of the real-time data and being voluminous. The graph model is built from the EHR heterogeneous data using python modules, namely, pyTigerGraph to get nodes and edges from the Tigergraph database, PyTorch to tensorize the nodes and edges, PyTorch-Geometric (PyG) to train the Graph Neural Network (GNN) and adopt the self-supervised learning techniques with the AutoEncoders to generate the node embeddings and eventually perform the node classifications using the node embeddings. The model predicts patient conditions ranging from common to rare situations. The outcome is deemed to open up opportunities for data querying toward better predictions and accuracy.

Keywords: electronic health record, graph neural network, heterogeneous data, prediction

Procedia PDF Downloads 86

Authors: Lucile Soudani, Hervé Illy, Rémi Bouchié

Abstract:

Mould growth in living environments has been widely reported for decades all throughout the world. A higher level of moisture in housings can lead to building degradation, chemical component emissions from construction materials as well as enhancing mould growth within the envelope elements or on the internal surfaces. Moreover, a significant number of studies have highlighted the link between mould presence and the prevalence of respiratory diseases. In recent years, the proportion of biobased materials used in construction has been increasing, as seen as an effective lever to reduce the environmental impact of the building sector. Besides, bio-based materials are also hygroscopic materials: when in contact with the wet air of a surrounding environment, their porous structures enable a better capture of water molecules, thus providing a more suitable background for mould growth. Many studies have been conducted to develop reliable models to be able to predict mould appearance, growth, and decay over many building materials and external exposures. Some of them require information about temperature and/or relative humidity, exposure times, material sensitivities, etc. Nevertheless, several studies have highlighted a large disparity between predictions and actual mould growth in experimental settings as well as in occupied buildings. The difficulty of considering the influence of all parameters appears to be the most challenging issue. As many complex phenomena take place simultaneously, a preliminary study has been carried out to evaluate the feasibility to sadopt a reliability approach rather than a deterministic approach. Both epistemic and random uncertainties were identified specifically for the prediction of mould appearance and growth. Several studies published in the literature were selected and analysed, from the agri-food or automotive sectors, as the deployed methodology appeared promising.

Keywords: bio-based materials, mould growth, numerical prediction, reliability approach

Procedia PDF Downloads 46

Authors: Kodo Sektani, Apostolos Tsouvalas, Andrei Metrikine

Abstract:

The reassessment of existing movable bridges in The Netherlands has created the need for acceptance/rejection criteria to assess whether the machineries are meet certain design demands. However, the existing design code defines a different limit state design, meant for new machineries which is based on a simple linear spring-mass model. Observations show that existing bridges do not confirm the model predictions. In fact, movable bridges are nonlinear systems consisting of mechanical components, such as, gears, electric motors and brakes. Next to that, each movable bridge is characterized by a unique set of parameters. However, in the existing code various variables that describe the physical characteristics of the bridge are neglected or replaced by partial factors. For instance, the damping ratio ζ, which is different for drawbridges compared to bascule bridges, is taken as a constant for all bridge types. In this paper, a model is developed that overcomes some of the limitations of existing modelling approaches to capture the dynamics of the powertrain of a class of bridge machineries First, a semidefinite dynamic model is proposed, which accounts for stiffness, damping, and some additional variables of the physical system, which are neglected by the code, such as nonlinear braking torques. The model gives an upper bound of the peak forces/torques occurring in the powertrain during emergency braking. Second, a discrete nonlinear dynamic model is discussed, with realistic motor torque characteristics during normal operation. This model succeeds to accurately predict the full time history of the occurred stress state of the opening and closing cycle for fatigue purposes.

Keywords: Dynamics of movable bridges, Bridge machinery, Powertrains, Torque measurements

Procedia PDF Downloads 156

Authors: Tom Ryan

Abstract:

This paper investigates the rural mobility and accessibility challenges of a specific target group - Seniors. The target group is those over 66 years of age who are entitled to use the Public Transport (PT) Free Travel Scheme in rural Ireland. The paper explores at a high level some of the projected rural PT challenges and requirements over the next 10-15 years, noting that statistical predictions show that there will be a significant population demographic shift within the Senior's age profile. Using the PESTEL framework, the literature review explored existing research concerning mobility, accessibility challenges, and the opportunities Seniors face. Twenty-seven qualitative in-depth interviews with stakeholders within the ecosystem were undertaken. The stakeholders included: rural PT customers, Local-Link managers, NTA senior management, a Minister of State, and a European parliament policymaker. Tier 1 interviewee feedback spotlights that the PT network system does not exist for rural patients to access hospital facilities. There was no evidence from the Tier 2 research findings to show that health policymakers and transport planners are working to deliver a national solution to support patients getting access to hospital appointments. Several research interviewees discussed the theme of isolation and the perceived stigma of senior males utilising PT. The findings indicated that MaaS is potentially revolutionary in the PT arena. Finally, this paper suggests several short-, medium- and long-term recommendations based on the research findings. These recommendations are a potential springboard to ensure that rural PT is suitable for future Irish generations.

Keywords: accessibility, active ageing, car dependence, isolation, seniors health issues, behavioural changes, environmental challenges, internet of things, demand responsive, mobility as a service

Procedia PDF Downloads 109

Authors: Livia Herle

Abstract:

A large part of the Principality of Liechtenstein is covered by forest. Three-quarters of this forest is defined as protective due to the alpine landscape of the country, which is deteriorating the quality of the wood. Nevertheless, the forest is one of the most important sources of raw material. However, out of the wood harvested annually in Liechtenstein, about two-thirds are used directly as an energy source, drastically shortening up the carbon storage cycle of wood. Furthermore, due to climate change, forest structures are changing. Predictions for the forest in Liechtenstein have stated that the spruce will mostly vanish in low altitudes, only being able to survive in the higher regions. In contrast, hardwood species will experience a rise, resulting in a more mixed forest. Thus, the main research focus will be put upon the potential of hardwood as well as prolonging the lifespan of a timber log before ending up as an energy source. An analysis of the local occurrence of hardwood species and their quality will serve as a tool to implement this knowledge upon constructional solutions. As a system that works with short spam timber and thus qualifies for the regional conditions of hardwood, reciprocal frame systems will be further investigated. These can be defined as load-bearing structures with only two beams connecting at a time, avoiding complex joining situations. Furthermore, every beam is mutually supporting. This allows the usage of short pieces of preferably massive wood. As a result, the system permits for an easy assembly but also disassembly. To promote a more circular application of wood, possible cascading scenarios of the structural solutions will be added. In a workshop at the School of Architecture of the University of Liechtenstein in the Sommer Semester 2024, prototypes in 1:1 of reciprocal frame systems using only local hardwood will help as a tool to further test the theoretical analyses.

Keywords: hardwood, cascading wood, reciprocal frames, crooked wood, forest structures, climate change

Procedia PDF Downloads 74

Authors: Nir Schreiber, Reuven Cohen, Simi Haber

Abstract:

The Potts model has been widely explored in the literature for the last few decades. While many analytical and numerical results concern with the traditional two site interaction model in various geometries and dimensions, little is yet known about models where more than two spins simultaneously interact. We consider a ferromagnetic four site interaction Potts model on the square lattice (FFPS), where the four spins reside in the corners of an elementary square. Each spin can take an integer value 1,2,...,q. We write the partition function as a sum over clusters consisting of monochromatic faces. When the number of faces becomes large, tracing out spin configurations is equivalent to enumerating large lattice animals. It is known that the asymptotic number of animals with k faces is governed by λᵏ, with λ ≈ 4.0626. Based on this observation, systems with q < 4 and q > 4 exhibit a second and first order phase transitions, respectively. The transition nature of the q = 4 case is borderline. For any q, a critical giant component (GC) is formed. In the finite order case, GC is simple, while it is fractal when the transition is continuous. Using simple equilibrium arguments, we obtain a (zero order) bound on the transition point. It is claimed that this bound should apply for other lattices as well. Next, taking into account higher order sites contributions, the critical bound becomes tighter. Moreover, for q > 4, if corrections due to contributions from small clusters are negligible in the thermodynamic limit, the improved bound should be exact. The improved bound is used to relate the critical point to the finite correlation length. Our analytical predictions are confirmed by an extensive numerical study of FFPS, using the Wang-Landau method. In particular, the q=4 marginal case is supported by a very ambiguous pseudo-critical finite size behavior.

Keywords: entropic sampling, lattice animals, phase transitions, Potts model

Procedia PDF Downloads 160

Authors: Maryam Zarabian, Hector Guzman, Pedro Pereira-Almao, Abraham Fapojuwo

Abstract:

Dry reforming of methane (DRM) has sparked significant industrial and scientific interest not only as a viable alternative for addressing the environmental concerns of two main contributors of the greenhouse effect, i.e., carbon dioxide (CO₂) and methane (CH₄), but also produces syngas, i.e., a mixture of hydrogen (H₂) and carbon monoxide (CO) utilized by a wide range of downstream processes as a feedstock for other chemical productions. In this study, we develop an AI-enable syngas production model to tackle the problem of achieving an equivalent H₂/CO ratio [1:1] with respect to the most efficient conversion. Firstly, the unsupervised density-based spatial clustering of applications with noise (DBSAN) algorithm removes outlier data points from the original experimental dataset. Then, random forest (RF) and deep neural network (DNN) models employ the error-free dataset to predict the DRM results. DNN models inherently would not be able to obtain accurate predictions without a huge dataset. To cope with this limitation, we employ reusing pre-trained layers’ approaches such as transfer learning and greedy layer-wise pretraining. Compared to the other deep models (i.e., pure deep model and transferred deep model), the greedy layer-wise pre-trained deep model provides the most accurate prediction as well as similar accuracy to the RF model with R² values 1.00, 0.999, 0.999, 0.999, 0.999, and 0.999 for the total outlet flow, H₂/CO ratio, H₂ yield, CO yield, CH₄ conversion, and CO₂ conversion outputs, respectively.

Keywords: artificial intelligence, dry reforming of methane, artificial neural network, deep learning, machine learning, transfer learning, greedy layer-wise pretraining

Procedia PDF Downloads 86

Authors: D. S. Gomes, A. T. Silva

Abstract:

Analysis of the uncertainty quantification related to nuclear safety margins applied to the nuclear reactor is an important concept to prevent future radioactive accidents. The nuclear fuel performance code may involve the tolerance level determined by traditional deterministic models producing acceptable results at burn cycles under 62 GWd/MTU. The behavior of nuclear fuel can simulate applying a series of material properties under irradiation and physics models to calculate the safety limits. In this study, theoretical predictions of nuclear fuel failure under transient conditions investigate extended radiation cycles at 75 GWd/MTU, considering the behavior of fuel rods in light-water reactors under reactivity accident conditions. The fuel pellet can melt due to the quick increase of reactivity during a transient. Large power excursions in the reactor are the subject of interest bringing to a treatment that is known as the Fuchs-Hansen model. The point kinetic neutron equations show similar characteristics of non-linear differential equations. In this investigation, the multivariate logistic regression is employed to a probabilistic forecast of fuel failure. A comparison of computational simulation and experimental results was acceptable. The experiments carried out use the pre-irradiated fuels rods subjected to a rapid energy pulse which exhibits the same behavior during a nuclear accident. The propagation of uncertainty utilizes the Wilk's formulation. The variables chosen as essential to failure prediction were the fuel burnup, the applied peak power, the pulse width, the oxidation layer thickness, and the cladding type.

Keywords: logistic regression, reactivity-initiated accident, safety margins, uncertainty propagation

Procedia PDF Downloads 292