Search results for: model predictive control (MPC)

Authors: Aline Valverde Arroteia, Tatiana Gondim do Amaral, Silvio Burrattino Melhado

Abstract:

During the last twenty years, the construction field in Brazil has evolved significantly in response to its market growing and competitiveness. However, this evolving path has faced many obstacles such as cultural barriers and the lack of efforts to achieve quality at the construction site. At the same time, the greatest amount of information generated on the designing or construction phases is lost due to the lack of an effective coordination of these activities. Face this problem, the aim of this research was to implement a French method named PEO which means preparation for building construction (in Portuguese) seeking to understand the design management process and its interface with the building construction phase. The research method applied was qualitative, and it was carried out through two case studies in the city of Goiania, in Goias, Brazil. The research was divided into two stages called pilot study at Company A and implementation of PEO at Company B. After the implementation; the results demonstrated the PEO method's effectiveness and feasibility while a booster on the quality improvement of design management. The analysis showed that the method has a purpose to improve the design and allow the reduction of failures, errors and rework commonly found in the production of buildings. Therefore, it can be concluded that the PEO is feasible to be applied to real estate and building companies. But, companies need to believe in the contribution they can make to the discovery of design failures in conjunction with other stakeholders forming a construction team. The result of PEO can be maximized when adopting the principles of simultaneous engineering and insertion of new computer technologies, which use a three-dimensional model of the building with BIM process.

Keywords: communication, design and construction interface management, preparation for building construction (PEO), proactive coordination (CPA)

Procedia PDF Downloads 149

Authors: Cameron Jones

Abstract:

Emissions, produced by landfill waste from demolished obsolete buildings, have a damaging effect on both the Earth’s climate and human health. The philosophical theory of material vitalism - the potential for materials to react and emit harmful pollutants - therefore defines this construction and demolition waste (CDW) as having vitality. The European Union’s ‘Circular Economic Action Plan’ (CEAP) aims to mitigate the effects of CDW by prioritising the circularity of building materials. This dissertation examines how the philosophical theory of material vitalism can make an environmentally responsible contribution to CDW policy. The CEAP and Silvertown Quays development are used as case studies for the application of vitalism to policy revision. The study concludes that vitalism has a positive role to play in informing CDW policy, although its contribution is stronger in some areas. This is established by first appraising the aspects that relate to the obsolescence of buildings outlined in the EU’s existing CDW policies. Next, these policy directives are compared with the CE principles employed in the Silvertown Quays development. Subsequently, a keyword analysis model is used to categorise the language used in the CEAP, demonstrating how socio-political approaches to the CE and strategies to address resource scarcity could be strengthened to represent the EU’s policy aspirations more effectively. Recommendations are then made on how material vitalism could be utilised to strengthen legislation, arguing that a notable contribution can be made in most policy areas. Finally, theoretical testing of the impact of these revisions to policy on the case study development identified some practicalities for consideration in improving waste management outcomes.

Keywords: vitalism, construction waste, obsolescence, political ecology, exceptionalism

Procedia PDF Downloads 36

Authors: Tanit Daniel Jodar Vecina, Adriane Prisco Petry

Abstract:

The shape of the wind velocity profile changes according to local features of terrain shape and roughness, which are parameters responsible for defining the Atmospheric Boundary Layer (ABL) profile. Air flow characteristics over and around landforms, such as hills, are of considerable importance for applications related to Wind Farm and Turbine Engineering. The air flow is accelerated on top of hills, which can represent a decisive factor for Wind Turbine placement choices. The present work focuses on the study of ABL behavior as a function of slope and surface roughness of hill-shaped landforms, using the Computational Fluid Dynamics (CFD) to build wind velocity and turbulent intensity profiles. Reynolds-Averaged Navier-Stokes (RANS) equations are closed using the SST k-ω turbulence model; numerical results are compared to experimental data measured in wind tunnel over scale models of the hills under consideration. Eight hill models with slopes varying from 25° to 68° were tested for two types of terrain categories in 2D and 3D, and two analytical codes are used to represent the inlet velocity profiles. Numerical results for the velocity profiles show differences under 4% when compared to their respective experimental data. Turbulent intensity profiles show maximum differences around 7% when compared to experimental data; this can be explained by not being possible to insert inlet turbulent intensity profiles in the simulations. Alternatively, constant values based on the averages of the turbulent intensity at the wind tunnel inlet were used.

Keywords: Atmospheric Boundary Layer, Computational Fluid Dynamic (CFD), Numerical Modeling, Wind Tunnel

Procedia PDF Downloads 369

Authors: Shu-Jen Chen, Yi-Chien Wan, Ruey-Chi Wang

Abstract:

Hydroxyapatite (Ca10(PO4)6(OH)2, HAp) can be applied to the fabrication of bone replacement materials, the composite of dental filling, and the adsorption of biomolecules and dyes. The integration of HAp and magnetic materials would offer several advantages for bio-separation process because the magnetic adsorbents is capable of recovered by applied magnetic field. C-phycocyanin (C-PC) and Allophycocyanin (APC), isolated from Spirulina platensis, can be used in fluorescent labeling probes, health care foods and clinical diagnostic reagents. Although the purification of C-PC and APC are reported by HAp adsorption, the adsorption of C-PC and APC by magnetic HAp composites was not reported yet. Therefore, the fabrication of HAp with magnetic silica nanoparticles for proteins adsorption was investigated in this work. First, the magnetic silica particles were prepared by covering silica layer on Fe3O4 nanoparticles with a reverse micelle method. Then, the Fe3O4@SiO2 nanoparticles were mixed with calcium carbonate to obtain magnetic silica/calcium carbonate composites (Fe3O4@SiO2/CaCO3). The Fe3O4@SiO2/CaCO3 was further reacted with K2HPO4 for preparing the magnetic silica/hydroxyapatite composites (Fe3O4@SiO2/HAp). The adsorption experiments indicated that the adsorption capacity of Fe3O4@SiO2/HAp toward C-PC and APC were highest at pH 6. The adsorption of C-PC and APC by Fe3O4@SiO2/HAp could be correlated by the pseudo-second-order model, indicating chemical adsorption dominating the adsorption process. Furthermore, the adsorption data showed that the adsorption of Fe3O4@SiO2/HAp toward C-PC and APC followed the Langmuir isotherm. The isoelectric points of C-PC and APC were around 5.0. Additionally, the zeta potential data showed the Fe3O4@SiO2/HAp composite was negative charged at pH 6. Accordingly, the adsorption mechanism of Fe3O4@SiO2/HAp toward C-PC and APC should be governed by hydrogen bonding rather than electrostatic interaction. On the other hand, as compared to C-PC, the Fe3O4@SiO2/HAp shows higher adsorption affinity toward APC. Although the Fe3O4@SiO2/HAp cannot recover C-PC and APC from Spirulina platensis homogenate, the Fe3O4@SiO2/HAp can be applied to separate C-PC and APC.

Keywords: hydroxyapatite, magnetic, C-phycocyanin, allophycocyanin

Procedia PDF Downloads 140

Authors: Angela Maria Fenu

Abstract:

The aim of this study was to better characterize the nature of word association responses in people with aphasia. The participants selected for the experimental group were 4 individuals with mild Broca’s aphasia. The control group consisted of 51 cognitively intact age- and gender-matched individuals. The participants were asked to perform a word association task in which they had to say the first word they thought of when hearing each cue. The cue words (n= 16) were the translation in Italian of the set of English cue words of a published study. The participants from the experimental group were administered the word association test every two weeks for a period of two months when they received speech-language therapy A combination of analytical approaches to measure the data was used. To analyse different patterns of word association responses in both groups, the nature of the relationship between the cue and the response was examined: responses were divided into five categories of association. To investigate the similarity between aphasic and non-aphasic subjects, the stereotypy of responses was examined.While certain stimulus words (nouns, adjectives) elicited responses from Broca’s aphasics that tended to resemble those made by non-aphasic subjects; others (adverbs, verbs) showed the tendency to elicit responses different from the ones given by normal subjects. This suggests that some mechanisms underlying certain types of associations are degraded in aphasics individuals, while others display little evidence of disruption. The high number of paradigmatic associations given in response to a noun or an adjective might imply that the mechanisms, largely semantic, underlying paradigmatic associations are relatively preserved in Broca’s aphasia, but it might also mean that some words are more easily processed depending on their grammatical class (nouns, adjectives). The most significant variation was noticed when the grammatical class of the cue word was an adverb. Unlike the normal individuals, the experimental subjects gave the most idiosyncratic associations, which are often produced when the attempt to give a paradigmatic response fails. In turn, the failure to retrieve paradigmatic responses when the cue is an adverb might suggest that Broca’s aphasics are more sensitive to this grammatical class.The findings from this study suggest that, from research on word associations in people with aphasia, important data can arise concerning the specific lexical retrieval impairments that characterize the different types of aphasia and the various treatments that might positively influence the kinds of word association responses affected by language disruption.

Keywords: aphasia therapy, clinical linguistics, word-association behaviour, mental lexicon

Procedia PDF Downloads 78

Authors: S. Jamshidi, E. Feizi Ashtiani, M. Ardestani, A. Feizi Ashtiani

Abstract:

Waste load allocation (WLA) strategies usually intend to find economical policies for water resource management. Water quality trading (WQT) is an approach that uses discharge permit market to reduce total environmental protection costs. This primarily requires assigning discharge limits known as total maximum daily loads (TMDLs). These are determined by monitoring organizations with respect to the receiving water quality and remediation capabilities. The purpose of this study is to compare two approaches of TMDL assignment for WQT policy in small catchment area of Haraz River, in north of Iran. At first, TMDLs are assigned uniformly for the whole point sources to keep the concentrations of BOD and dissolved oxygen (DO) at the standard level at checkpoint (terminus point). This was simply simulated and controlled by Qual2kw software. In the second scenario, TMDLs are assigned using multi objective particle swarm optimization (MOPSO) method in which the environmental violation at river basin and total treatment costs are minimized simultaneously. In both scenarios, the equity index and the WLA based on trading discharge permits (TDP) are calculated. The comparative results showed that using economically optimized TMDLs (2nd scenario) has slightly more cost savings rather than uniform TMDL approach (1st scenario). The former annually costs about 1 M$ while the latter is 1.15 M$. WQT can decrease these annual costs to 0.9 and 1.1 M$, respectively. In other word, these approaches may save 35 and 45% economically in comparison with command and control policy. It means that using multi objective decision support systems (DSS) may find more economical WLA, however its outcome is not necessarily significant in comparison with uniform TMDLs. This may be due to the similar impact factors of dischargers in small catchments. Conversely, using uniform TMDLs for WQT brings more equity that makes stakeholders not feel that much envious of difference between TMDL and WQT allocation. In addition, for this case, determination of TMDLs uniformly would be much easier for monitoring. Consequently, uniform TMDL for TDP market is recommended as a sustainable approach. However, economical TMDLs can be used for larger watersheds.

Keywords: waste load allocation (WLA), water quality trading (WQT), total maximum daily loads (TMDLs), Haraz River, multi objective particle swarm optimization (MOPSO), equity

Procedia PDF Downloads 385

Authors: Zainab Elazab, Azhar Aziz

Abstract:

Background: Spontaneous Splenic artery pseudoaneurysm rupture is a rare condition which is potentially life threatening, if not detected and managed early. We report a case of abdominal pain with intraperitoneal free fluid, which turned out to be spontaneous rupture of a splenic artery pseudoaneurysm, and was treated with arterial embolization. Case presentation: A 28-year old, previously healthy male presented to the ED with a history of sudden onset upper abdominal pain and fainting attack. The patient denied any history of trauma or prior similar attacks. On examination, the patient had tachycardia and a low-normal BP (HR 110, BP 106/66) but his other vital signs were normal (Temp. 37.2, RR 18 and SpO2 100%). His abdomen was initially soft with mild tenderness in the upper region. Blood tests showed leukocytosis of 12.3 X109/L, Hb of 12.6 g/dl and lactic acid of 5.9 mmol/L. Ultrasound showed trace of free fluid in the perihepatic and perisplenic areas, and a splenic hypoechoic lesion. The patient remained stable; however, his abdomen became increasingly tender with guarding. We made a provisional diagnosis of a perforated viscus and the patient was started on IV fluids and IV antibiotics. An erect abdominal x-ray did not show any free air under the diaphragm so a CT abdomen was requested. Meanwhile, bedside ultrasound was repeated which showed increased amount of free fluid, suggesting intra-abdominal bleeding as the most probable etiology for the condition. His CT abdomen revealed a splenic injury with multiple lacerations, a focal intrasplenic enhancing area on venous phase scan (suggesting a pseudoaneurysm with associated splenic intraparenchymal, sub capsular and perisplenic hematomas). Free fluid in the subhepatic and intraperitoneal regions along the small bowel was also detected. Angiogram was done which confirmed a diagnosis of pseudoaneurysm of intrasplenic arterial branch, and angio-embolization was done to control the bleeding. The patient was later discharged in good condition with a surgery follow-up. Conclusion: Splenic artery pseudoaneurysm rupture is a rare cause of abdominal pain which should be considered in any case of abdominal pain with intraperitoneal bleeding. Early management is crucial as it carries a high mortality. Bedside ultrasound is a useful tool to help for early diagnosis of such cases.

Keywords: abdominal pain, pseudo aneurysm, rupture, splenic artery

Procedia PDF Downloads 303

Authors: Nitin Pipralia, Amit Kmar Sinha, Gudrun de Boeck

Abstract:

Atmospheric carbon dioxide (CO2) concentrations have been increasing since the beginning of the industrial revolution due to combustion of fossils fuel and many anthropogenic means. As the number of scenarios assembled by the International Panel on Climate Change (IPCC) predict a rise of pCO2 from today’s 380 μatm to approximately 900 μatm until the year 2100 and a further rise of up to 1900 μatm by the year 2300. A rise in pCO2 results in more dissolution in ocean surface water which lead to cange in water pH, This phenomena of decrease in ocean pH due to increase on pCO2 is ocean acidification is considered a potential threat to the marine ecosystems and expected to affect fish as well as calcerious organisms. The situation may get worste when the stress of salinity adds on, due to migratory movement of fishes, where fish moves to different salinity region for various specific activities likes spawning and other. Therefore, to understand the interactive impact of these whole range of two important environmental abiotic stresses (viz. pCO2 ranging from 380 μatm, 900 μatm and 1900 μatm, along with salinity gradients of 32ppt, 10 ppt and 2.5ppt) on the ecophysiologal performance of fish, we investigated various biological adaptive response in European sea bass (Dicentrarchus labrax), a model estuarine teleost. Overall, we hypothesize that effect of ocean acidification would be exacerbate with shift in ambient salinity. Oxygen consumption, ammonia metabolism, iono-osmoregulation, energy budget, ion-regulatory enzymes, hormones and pH amendments in plasma were assayed as the potential indices of compensatory responses.

Keywords: ocean acidification, sea bass, pH climate change, salinity

Procedia PDF Downloads 218

Authors: Hager Elsheikh, Matthias Sendler, Juliana Glaubnitz

Abstract:

In pancreatitis, an inflammatory reaction occurs in the pancreatic secretory cells due to premature activation of proteases, leading to pancreatic self-digestion and necrotic cell death of acinar cells. Acute pancreatitis in patients is characterized by a severe immune reaction that could lead to serious complications, such as organ failure or septic shock, if left untreated. Chronic pancreatitis is a recurrence of episodes of acute pancreatitis resulting in a fibro-inflammatory immune response, in which the type 2 immune response is primarily driven by AAMs in the pancreas. One of the most important signaling pathways for M2 macrophage activation is the IL-4/STAT6 pathway. Pancreatic fibrosis is induced by the hyperactivation of pancreatic stellate cells by dysregulation in the inflammatory response, leading to further damage, autodigestion and possibly necrosis of pancreatic acinar cells. The aim of this research is to investigate the effect of STAT6 knockout in disease severity and development of fibrosis wound healing in the presence of different macrophage populations, regulated by the type 2 immune response, after inducing chronic and/or acute pancreatitis in mice models via cerulean injection. We further investigate the influence of the JAK/STAT6 signaling pathway on the balance of fibrosis and regeneration in STAT6 deficient and wild-type mice. The characterization of resident and recruited macrophages will provide insight into the influence of the JAK/STAT6 signaling pathway on infiltrating cells and, ultimately, tissue fibrosis and disease severity.

Keywords: acute and chronic pancreatitis, tissue regeneration, macrophage polarization, Gastroenterology

Procedia PDF Downloads 55

Authors: Tomoya Oshiro, Hiroko Ono

Abstract:

Japan's aging population is increasing due to the decrease in birthrate. It causes various problems like the decrease in the gross domestic product of the country. The reason is why the local government of Japan has been on the way to a sustainable city recently. Then it is essential to get control of an urban structure to make the compact city successful. There are many kinds of paper about the compact city; however, the paper about a compact city of the island-type city is less. The purpose of this study is to clarify difference of urban structure between an island-type and a general city type. The method which has conducted in this research has two steps. First of all, by using evaluation indexes in the handbook, we evaluated the urban structures among each same -population-class cities from 50,000 to 100,000 people. Next, to clear the difference about the urban structure and feature between island-type and general-type cities compare the radar chart which is composed with each evaluation indexes of urban structure. Moreover, in order to clarify the relationship between evaluation indexes and the place of residence by using GIS software to show up population density on the map. As a result of this research, the management of local government and the local economy in evaluation indexes are indicated to be negative point in comparison of island-type cities with general cities. However, evaluation indexes of safety/security and low-carbon/energy are proved to be positive point. The research to find the difference features of the island-type of urban structure proves that the management of local government or the local economy is negative point in these island-type cities. In addition, the public transportation coverage in Miyako Island, Sado Island, and Amakusa Island show low value compare with other islands and average value. Relationship between evaluation indexes of an urban structure and the place of residence prove that the place of residence is related to public transportation coverage. If the place of residence is spread out, the public transportation coverage will be decreased. The results of this research reveal that the finances in island-type cities are negative point compare to general cities. This problem is caused by declining population. In addition, the place of residence is related to the public transportation coverage. Even though, it needs a much money to increase the public transportation coverage. It is possibly to cause other problems furthermore the aspect of finance is influenced by that as well. The conclusion in this research suggests that it is important for creating the compact city in island-type cities that we first need to address solving the problems about the management of local government and the local economy.

Keywords: sustainable city, comparative analysis, geographic information system, urban structure

Procedia PDF Downloads 140

Authors: Masoud Sheidai

Abstract:

Biologists with a special field of population genetics and phylogeny have different research tasks such as populations’ genetic variability and divergence, species relatedness, the evolution of genetic and morphological characters, and identification of DNA SNPs with adaptive potential. To tackle these problems and reach a concise conclusion, they must use the proper and efficient statistical and bioinformatic methods as well as suitable genetic and morphological characteristics. In recent years application of different bioinformatic and statistical methods, which are based on various well-documented assumptions, are the proper analytical tools in the hands of researchers. The species delineation is usually carried out with the use of different clustering methods like K-means clustering based on proper distance measures according to the studied features of organisms. A well-defined species are assumed to be separated from the other taxa by molecular barcodes. The species relationships are studied by using molecular markers, which are analyzed by different analytical methods like multidimensional scaling (MDS) and principal coordinate analysis (PCoA). The species population structuring and genetic divergence are usually investigated by PCoA and PCA methods and a network diagram. These are based on bootstrapping of data. The Association of different genes and DNA sequences to ecological and geographical variables is determined by LFMM (Latent factor mixed model) and redundancy analysis (RDA), which are based on Bayesian and distance methods. Molecular and morphological differentiating characters in the studied species may be identified by linear discriminant analysis (DA) and discriminant analysis of principal components (DAPC). We shall illustrate these methods and related conclusions by giving examples from different edible and medicinal plant species.

Keywords: GWAS analysis, K-Means clustering, LFMM, multidimensional scaling, redundancy analysis

Procedia PDF Downloads 111

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 65

Authors: Yoshifumi Hino

Abstract:

An infinitely repeated prisoner’s dilemma is a typical model that represents teamwork situation. If both players choose costly actions and contribute to the team, then both players are better off. However, each player has an incentive to choose a selfish action. We analyze the game under costly observation. Each player can observe the action of the opponent only when he pays an observation cost in that period. In reality, teamwork situations are often costly observation. Members of some teams sometimes work in distinct rooms, areas, or countries. In those cases, they have to spend their time and money to see other team members if they want to observe it. The costly observation assumption makes the cooperation difficult substantially because the equilibrium must satisfy the incentives not only on the action but also on the observational decision. Especially, it is the most difficult to cooperate each other when the stage-game is prisoner's dilemma because players have to communicate through only two actions. We examine whether or not players can cooperate each other in prisoner’s dilemma under costly observation. Specifically, we check whether symmetric Pareto efficient payoff vectors in repeated prisoner’s dilemma can be approximated by sequential equilibria or not (efficiency result). We show the efficiency result without any randomization device under certain circumstances. It means that players can cooperate with each other without any randomization device even if the observation is costly. Next, we assume that public randomization device is available, and then we show that any feasible and individual rational payoffs in prisoner’s dilemma can be approximated by sequential equilibria under a specific situation (folk theorem). It implies that players can achieve asymmetric teamwork like leadership situation when public randomization device is available.

Keywords: cost observation, efficiency, folk theorem, prisoner's dilemma, private monitoring, repeated games.

Procedia PDF Downloads 228

Authors: Jiří F. Urbánek, David Král

Abstract:

Small and Middle Enterprises (SME) have a specific mission, characteristics, and behavior in global business competitive environments. They must respect policy, rules, requirements and standards in all their inherent and outer processes of supply - customer chains and networks. Paper aims and purposes are to introduce computational assistance, which enables us the using of prevailing operation system MS Office (SmartArt...) for mathematical models, using DYVELOP (Dynamic Vector Logistics of Processes) method. It is providing for SMS´s global environment the capability and profit to achieve its commitment regarding the effectiveness of the quality management system in customer requirements meeting and also the continual improvement of the organization’s and SME´s processes overall performance and efficiency, as well as its societal security via continual planning improvement. DYVELOP model´s maps - the Blazons are able mathematically - graphically express the relationships among entities, actors, and processes, including the discovering and modeling of the cycling cases and their phases. The blazons need live PowerPoint presentation for better comprehension of this paper mission – added value analysis. The crisis management of SMEs is obliged to use the cycles for successful coping of crisis situations.  Several times cycling of these cases is a necessary condition for the encompassment of the both the emergency event and the mitigation of organization´s damages. Uninterrupted and continuous cycling process is a good indicator and controlling actor of SME continuity and its sustainable development advanced possibilities.

Keywords: blazons, computational assistance, DYVELOP method, small and middle enterprises

Procedia PDF Downloads 330

Authors: Wenbo Wang, Yi-Fang Brook Wu

Abstract:

The spread of misinformation and disinformation has become a major concern, particularly with the rise of social media as a primary source of information for many people. As a means to address this phenomenon, automated fact-checking has emerged as a safeguard against the spread of misinformation and disinformation. Existing fact-checking approaches aim to determine whether a news claim is true or false, and they have achieved decent veracity prediction accuracy. However, the state-of-the-art methods rely on manually verified external information to assist the checking model in making judgments, which requires significant human resources. This study introduces a framework, SAC, which focuses on 1) augmenting the representation of a claim by incorporating additional context using general-purpose, comprehensive, and authoritative data; 2) developing a search function to automatically select relevant, new, and credible references; 3) focusing on the important parts of the representations of a claim and its reference that are most relevant to the fact-checking task. The experimental results demonstrate that 1) Augmenting the representations of claims and references through the use of a knowledge base, combined with the multi-head attention technique, contributes to improved performance of fact-checking. 2) SAC with auto-selected references outperforms existing fact-checking approaches with manual selected references. Future directions of this study include I) exploring knowledge graphs in Wikidata to dynamically augment the representations of claims and references without introducing too much noise, II) exploring semantic relations in claims and references to further enhance fact-checking.

Keywords: fact checking, claim verification, deep learning, natural language processing

Procedia PDF Downloads 51

Authors: O.O. Ehinmowo, A.I. Fatuase, D.F. Oke

Abstract:

Nigeria is endowed with resources that could boost the economy as well as generate income and provide jobs to the teaming populace. One of the keys of attaining this is by making the environment conducive for the entrepreneurs to excel in their respective enterprises so that more income could be accrued to the entrepreneurs. This study therefore examines income inequality among selected entrepreneurs in Ondo State, Nigeria using primary data. A multistage sampling technique was used to select 200 respondents for the study with the aid of structured questionnaire and personal interview. The data collected were subjected to descriptive statistics, Lorenz curve, Gini coefficient and Double - Log regression model. Results revealed that majority of the entrepreneurs (63%) were males and 90% were married with an average age of 44 years. About 40% of the respondents spent at most 12 years in school with 81% of the respondents had 4-6 members per household, while hair dressing (43.5%) and fashion designing (31.5%) were the most common enterprises among the sampled respondents. The findings also showed that majority of the entrepreneurs in hairdressing, fashion designing and laundry service earned below N200,000 per annum while the majority of those in restaurant and food vending earned between N400,000 – N600,000 followed by the entrepreneurs in pure water enterprise where majority earned N800,000 and above per annum. The result of the Gini coefficient (0.58) indicated that there was presence of inequality among the entrepreneurs which was also affirmed by the Lorenz curve. The Regression results showed that gender, household size and number of employees significantly affected the income of the entrepreneurs in the study area. Therefore, more female households should be encouraged into entrepreneurial businesses and government should give incentive cum conductive environment that could bridge the disparity in the income of the entrepreneurs in their various enterprises.

Keywords: entrepreneurs, Gini coefficient, income inequality, Lorenz curve

Procedia PDF Downloads 336

Authors: Namwinwelbere Dabire, Eugene C. Ezin, Adandedji M. Firmin

Abstract:

The prediction of hydrological flows (rainfall-depth or rainfall-discharge) is becoming increasingly important in the management of hydrological risks such as floods. In this study, the Long Short-Term Memory (LSTM) network, a state-of-the-art algorithm dedicated to time series, is applied to predict the daily water level of Nokoue Lake in Benin. This paper aims to provide an effective and reliable method enable of reproducing the future daily water level of Nokoue Lake, which is influenced by a combination of two phenomena: rainfall and river flow (runoff from the Ouémé River, the Sô River, the Porto-Novo lagoon, and the Atlantic Ocean). Performance analysis based on the forecasting horizon indicates that LSTM can predict the water level of Nokoué Lake up to a forecast horizon of t+10 days. Performance metrics such as Root Mean Square Error (RMSE), coefficient of correlation (R²), Nash-Sutcliffe Efficiency (NSE), and Mean Absolute Error (MAE) agree on a forecast horizon of up to t+3 days. The values of these metrics remain stable for forecast horizons of t+1 days, t+2 days, and t+3 days. The values of R² and NSE are greater than 0.97 during the training and testing phases in the Nokoué Lake basin. Based on the evaluation indices used to assess the model's performance for the appropriate forecast horizon of water level in the Nokoué Lake basin, the forecast horizon of t+3 days is chosen for predicting future daily water levels.

Keywords: forecasting, long short-term memory cell, recurrent artificial neural network, Nokoué lake

Procedia PDF Downloads 51

Authors: Mustafa Salman, Nurcan Cetinkaya, Zehra Selcuk, Bugra Genc

Abstract:

The objectives of the present study were to estimate the microbial-N flow to the small intestine and to predict the digestible organic matter intake (DOMI) in grazing Karayaka sheep based on urinary excretion of purine derivatives (xanthine, hypoxanthine, uric acid, and allantoin) by the use of spot urine sampling under field conditions. In the trial, 10 Karayaka sheep from 2 to 3 years of age were used. The animals were grazed in a pasture for ten months and fed with concentrate and vetch plus oat hay for the other two months (January and February) indoors. Highly significant linear and cubic relationships (P<0.001) were found among months for purine derivatives index, purine derivatives excretion, purine derivatives absorption, microbial-N and DOMI. Through urine sampling and the determination of levels of excreted urinary PD and Purine Derivatives / Creatinine ratio (PDC index), microbial-N values were estimated and they indicated that the protein nutrition of the sheep was insufficient. In conclusion, the prediction of protein nutrition of sheep under the field conditions may be possible with the use of spot urine sampling, urinary excreted PD and PDC index. The mean purine derivative levels in spot urine samples from sheep were highest in June, July and October. Protein nutrition of pastured sheep may be affected by weather changes, including rainfall. Spot urine sampling may useful in modeling the feed consumption of pasturing sheep. However, further studies are required under different field conditions with different breeds of sheep to develop spot urine sampling as a model.

Keywords: Karayaka sheep, spot sampling, urinary purine derivatives, PDC index, microbial-N, feed intake

Procedia PDF Downloads 520

Authors: Diobein C. Flores

Abstract:

The populace in Municipality of Talaingod is composed of Ata-Manobo. The said lumads enrich their culture, orientation and self because the place is a hive of their tribe. In lieu, the study would analyze the participation of the Ata-Manobo in the making of school improvement plan (SIP). Thus, it recommends alternative policy options that would help strengthen their involvement. The school stakeholders-Ata Manobo representatives from students, parent-teacher association, alumni, basic sector, municipal/barangay government unit, civic/social organizations and other government various agencies are the key participants in this study. The research used descriptive design. The responses of the representatives were analyzed through the criteria involved in employing Rational Model. The technical dimension, administrative, political acceptability and economic are the criteria in revealing decision. The policy alternative option 3- recommends to formulate policy for the purpose of capacitating stakeholders or governing council members in the making of SIP was pointed out as the most preferred option. This could strengthen the participation among Ata-Manobo as stakeholders in planning. Hence, the formulation alternative policy- capacitating stakeholders in the crafting of school improvement plan is recommended. The suggested initiative would assist the Department of Education in forging consensus across neighborhoods during the making of SIP. The appropriation of the definite budget to be used during the conduct of capability building activities is also suggested. Training-workshops are identified as possible intervention to ensure that the stakeholders are equipped with necessary knowledge and skills needed in the making of SIP. Indeed, the equal opportunities for all stakeholders regardless of their life circumstances must be noted. With the belief, people must be empowered to take advantage and spearhead progress in the making of SIP.

Keywords: Ata-Manobo Tribe, stakeholders, school improvement plan, Municipality of Talaingod, Philippines

Procedia PDF Downloads 313

Authors: Mark A. S. Laidlaw, Howard W. Mielke

Abstract:

In California between the late 1920’s and 1986 the lead concentrations in urban soils and dust climbed rapidly following the deposition of greater than 387,000 tonnes of lead emitted from gasoline. Previous research indicates that when children are lead exposed around 90% of the lead is retained in their bones and teeth due to the substitution of lead for calcium. Lead in children’s bones has been shown to accumulate over time and is highest in inner-city urban areas, lower in suburban areas and lowest in rural areas. It is also known that women’s bones demineralize during pregnancy due to the foetus's high demand for calcium. Lead accumulates in women’s bones during childhood and the accumulated lead is subsequently released during pregnancy – a lagged response. This results in calcium plus lead to enter the blood stream and cross the placenta to expose the foetus with lead. In 1970 in the United States, the average age of a first‐time mother was about 21. In 2008, the average age was 25.1. In this study, it is demonstrated that in California there is a forward lagged relationship between the accumulated emissions of lead from vehicle fuel additives and later autism prevalence trends between the 1990’s and current time period. Regression analysis between a 24 year forward lag of accumulated lead emissions and autism prevalence trends in California are associated strongly (R2=0.95, p=0.00000000127). It is hypothesized that autism in genetically susceptible children may stem from vehicle fuel lead emission exposures of their mothers during childhood and that the release of stored lead during subsequent pregnancy resulted in lead exposure of foetuses during a critical developmental period. It is furthermore hypothesized that the 24 years forward lag between lead exposures has occurred because that is time period is the average length for women to enter childbearing age. To test the hypothesis that lead in mothers bones is associated with autism, it is hypothesized that retrospective case-control studies would show an association between the lead in mother’s bones and autism. Furthermore, it is hypothesized that the forward lagged relationship between accumulated historical vehicle fuel lead emissions (or air lead concentrations) and autism prevalence trends will be similar in cities at the national and international scale. If further epidemiological studies indicate a strong relationship between accumulated vehicle fuel lead emissions (or accumulated air lead concentrations) and lead in mother’s bones and autism rates, then urban areas may require extensive soil intervention to prevent the development of autism in children.

Keywords: autism, bones, lead, gasoline, petrol, prevalence

Procedia PDF Downloads 289

Authors: Mandlenkosi George Robert Mahlobo, Tumelo Seadira, Major Melusi Mabuza, Peter Apata Olubambi

Abstract:

Cathodic protection (CP) has been widely considered a suitable technique for mitigating corrosion of buried metal structures. Plenty of efforts have been made in developing techniques, in particular non-destructive techniques, for monitoring and quantifying the effectiveness of CP to ensure the sustainability and performance of buried steel structures. The aim of this study was to investigate the evolution of the electrochemical processes at the steel/soil interface during the application of CP on steel in simulated soil. Carbon steel was subjected to electrochemical tests with NS4 solution used as simulated soil conditions for 4 days before applying CP for a further 11 days. A previously modified non-destructive voltammetry technique was applied before and after the application of CP to measure the corrosion rate. Electrochemical impedance spectroscopy (EIS), in combination with mathematical modeling through equivalent electric circuits, was applied to determine the electrochemical behavior at the steel/soil interface. The measured corrosion rate was found to have decreased from 410 µm/yr to 8 µm/yr between days 5 and 14 because of the applied CP. Equivalent electrical circuits were successfully constructed and used to adequately model the EIS results. The modeling of the obtained EIS results revealed the formation of corrosion products via a mixed activation-diffusion mechanism during the first 4 days, while the activation mechanism prevailed in the presence of CP, resulting in a protective film. The x-ray diffraction analysis confirmed the presence of corrosion products and the predominant protective film corresponding to the calcareous deposit.

Keywords: carbon steel, cathodic protection, NS4 solution, voltammetry, EIS

Procedia PDF Downloads 51

Authors: Alexander Street, Nina Wollersberger, Paul Fernie, Leonardo Muller, Ming Hung HSU, Helen Odell-Miller, Jorg Fachner, Patrizia Di Campli San Vito, Stephen Brewster, Hari Shaji, Satvik Venkatesh, Paolo Itaborai, Nicolas Farina, Alexis Kirke, Sube Banerjee, Eduardo Reck Miranda

Abstract:

Escalating neuropsychiatric symptoms (NPS) in people with dementia may lead to earlier care home admission. Music listening has been reported to stimulate cognitive function, potentially reducing agitation in this population. We present a scoping review, reporting on current developments and discussing the potential for music listening with related technology in managing agitation in dementia care. Of two searches for music listening studies, one focused on older people or people living with dementia where music listening interventions, including technology, were delivered in participants’ homes or in institutions to address neuropsychiatric symptoms, quality of life and independence. The second included any population focusing on the use of music technology for health and wellbeing. In search one 70/251 full texts were included. The majority reported either statistical significance (6, 8.5%), significance (17, 24.2%) or improvements (26, 37.1%). Agitation was specifically reported in 36 (51.4%). The second search included 51/99 full texts, reporting improvement (28, 54.9%), significance (11, 21.5%), statistical significance (1, 1.9%) and no difference compared to the control (6, 11.7%). The majority in the first focused on mood and agitation, and the second on mood and psychophysiological responses. Five studies used AI or machine learning systems to select music, all involving healthy controls and reporting benefits. Most studies in both reviews were not conducted in a home environment (review 1 = 12; 17.1%; review 2 = 11; 21.5%). Preferred music listening may help manage NPS in the care home settings. Based on these and other data extracted in the review, a reasonable progression would be to co-design and test music listening systems and protocols for NPS in all settings, including people’s homes. Machine learning and automated technology for music selection and arousal adjustment, driven by live biodata, have not been explored in dementia care. Such approaches may help deliver the right music at the appropriate time in the required dosage, reducing the use of medication and improving quality of life.

Keywords: music listening, dementia, agitation, scoping review, technology

Procedia PDF Downloads 98

Authors: Hossein Jafari, Xiangfang Li, Lijun Qian, Alexander Aved, Timothy Kroecker

Abstract:

Traditionally in sensor networks and recently in the Internet of Things, numerous heterogeneous sensors are deployed in distributed manner to monitor a phenomenon that often can be model by an underlying stochastic process. The big time-series data collected by the sensors must be analyzed to detect change in the stochastic process as quickly as possible with tolerable false alarm rate. However, sensors may have different accuracy and sensitivity range, and they decay along time. As a result, the big time-series data collected by the sensors will contain uncertainties and sometimes they are conflicting. In this study, we present a framework to take advantage of Evidence Theory (a.k.a. Dempster-Shafer and Dezert-Smarandache Theories) capabilities of representing and managing uncertainty and conflict to fast change detection and effectively deal with complementary hypotheses. Specifically, Kullback-Leibler divergence is used as the similarity metric to calculate the distances between the estimated current distribution with the pre- and post-change distributions. Then mass functions are calculated and related combination rules are applied to combine the mass values among all sensors. Furthermore, we applied the method to estimate the minimum number of sensors needed to combine, so computational efficiency could be improved. Cumulative sum test is then applied on the ratio of pignistic probability to detect and declare the change for decision making purpose. Simulation results using both synthetic data and real data from experimental setup demonstrate the effectiveness of the presented schemes.

Keywords: CUSUM, evidence theory, kl divergence, quickest change detection, time series data

Procedia PDF Downloads 320

Authors: Rohit Kumar Shrivastava, Amalia Thomas, Nathalie Vriend, Stefan Luding

Abstract:

A mechanical wave or vibration propagating through granular media exhibits a specific signature in time. A coherent pulse or wavefront arrives first with multiply scattered waves (coda) arriving later. The coherent pulse is micro-structure independent i.e. it depends only on the bulk properties of the disordered granular sample, the sound wave velocity of the granular sample and hence bulk and shear moduli. The coherent wavefront attenuates (decreases in amplitude) and broadens with distance from its source. The pulse attenuation and broadening effects are affected by disorder (polydispersity; contrast in size of the granules) and have often been attributed to dispersion and scattering. To study the effect of disorder and initial amplitude (non-linearity) of the pulse imparted to the system on the coherent wavefront, numerical simulations have been carried out on one-dimensional sets of particles (granular chains). The interaction force between the particles is given by a Hertzian contact model. The sizes of particles have been selected randomly from a Gaussian distribution, where the standard deviation of this distribution is the relevant parameter that quantifies the effect of disorder on the coherent wavefront. Since, the coherent wavefront is system configuration independent, ensemble averaging has been used for improving the signal quality of the coherent pulse and removing the multiply scattered waves. The results concerning the width of the coherent wavefront have been formulated in terms of scaling laws. An experimental set-up of photoelastic particles constituting a granular chain is proposed to validate the numerical results.

Keywords: discrete elements, Hertzian contact, polydispersity, weakly nonlinear, wave propagation

Procedia PDF Downloads 190

Authors: Sudhir Kumar, V. R. Sinha

Abstract:

Water in oil topical microemulsions of 5-FU were developed and optimized using face centered central composite design. Topical w/o microemulsion of 5-FU were prepared using sorbitan monooleate (Span 80), polysorbate 80 (Tween 80), with different oils such as oleic acid (OA), triacetin (TA), and isopropyl myristate (IPM). The ternary phase diagrams designated the microemulsion region and face centered central composite design helped in determining the effects of selected variables viz. type of oil, smix ratio and water concentration on responses like drug content, globule size and viscosity of microemulsions. The CCD design exhibited that the factors have statistically significant effects (p<0.01) on the selected responses. The actual responses showed excellent agreement with the predicted values as suggested by the CCD with lower residual standard error. Similarly, the optimized values were found within the range as predicted by the model. Furthermore, other characteristics of microemulsions like pH, conductivity were investigated. For the optimized microemulsion batch, ex-vivo skin flux, skin irritation and retention studies were performed and compared with marketed 5-FU formulation. In ex vivo skin permeation studies, higher skin retention of drug and minimal flux was achieved for optimized microemulsion batch then the marketed cream. Results confirmed the actual responses to be in agreement with predicted ones with least residual standard errors. Controlled release of drug was achieved for the optimized batch with higher skin retention of 5-FU, which can further be utilized for the treatment of many dermatological disorders.

Keywords: 5-FU, central composite design, microemulsion, ternanry phase diagram

Procedia PDF Downloads 470

Authors: Adam Y. Sulaiman, Gerard I.Obasi, Roma Chang, Hussein Sayed Moghaieb, Ming J. Huang, Neil J. Hewitt

Abstract:

Residential air-conditioning units are essential for quality indoor comfort in hot climate countries. Nevertheless, because of their non-renewable energy sources and the contribution of ecologically unfriendly working fluids, these units are a major source of CO2 emissions in these countries. The utilisation of sustainable technologies nowadays is essential to reduce the adverse effects of CO2 emissions by replacing conventional technologies. This paper investigates the feasibility of running an off-grid solar-powered air-conditioning bed unit using three low GWP refrigerants (R32, R290, and R600a) to supersede conventional refrigerants.A prototype air conditioning unit was built to supply cold air to a canopy that was connected to it. The assembled unit was designed to distribute cold air to a canopy connected to it. This system is powered by two 400 W photovoltaic panels, with battery storage supplying power to the unit at night-time. Engineering Equation Solver (EES) software is used to mathematically model the vapor compression cycle (VCC) and predict the unit's energetic and exergetic performance. The TRNSYS software was used to simulate the electricity storage performance of the batteries, whereas the IES-VE was used to determine the amount of solar energy required to power the unit. The article provides an analytical design guideline, as well as a comprehensible process system. Combining a renewable energy source to power an AC based-VCC provides an excellent solution to the real problems of high-energy consumption in warm-climate countries.

Keywords: air-conditioning, refrigerants, PV panel, energy storages, VCC, exergy

Procedia PDF Downloads 166

Authors: Nishi Bhuvandas, P. V. Timbadiya, P. L. Patel, P. D. Porey

Abstract:

Recent perceived climate variability raises concerns with unprecedented hydrological phenomena and extremes. Distribution and circulation of the waters of the Earth become increasingly difficult to determine because of additional uncertainty related to anthropogenic emissions. According to the sixth Intergovernmental Panel on Climate Change (IPCC) Technical Paper on Climate Change and water, changes in the large-scale hydrological cycle have been related to an increase in the observed temperature over several decades. Although many previous research carried on effect of change in climate on hydrology provides a general picture of possible hydrological global change, new tools and frameworks for modelling hydrological series with nonstationary characteristics at finer scales, are required for assessing climate change impacts. Of the downscaling techniques, dynamic downscaling is usually based on the use of Regional Climate Models (RCMs), which generate finer resolution output based on atmospheric physics over a region using General Circulation Model (GCM) fields as boundary conditions. However, RCMs are not expected to capture the observed spatial precipitation extremes at a fine cell scale or at a basin scale. Statistical downscaling derives a statistical or empirical relationship between the variables simulated by the GCMs, called predictors, and station-scale hydrologic variables, called predictands. The main focus of the paper is on the need for using statistical downscaling techniques for projection of local hydrometeorological variables under climate change scenarios. The projections can be then served as a means of input source to various hydrologic models to obtain streamflow, evapotranspiration, soil moisture and other hydrological variables of interest.

Keywords: climate change, downscaling, GCM, RCM

Procedia PDF Downloads 394

Authors: Mona Hejazi, Ali Motie Nasrabadi

Abstract:

Epilepsy is a persistent neurological disorder that affects more than 50 million people worldwide. Hence, there is a necessity to introduce an efficient prediction model for making a correct diagnosis of the epileptic seizure and accurate prediction of its type. In this study we consider how the Effective Connectivity (EC) patterns obtained from intracranial Electroencephalographic (EEG) recordings reveal information about the dynamics of the epileptic brain and can be used to predict imminent seizures, as this will enable the patients (and caregivers) to take appropriate precautions. We use this definition because we believe that effective connectivity near seizures begin to change, so we can predict seizures according to this feature. Results are reported on the standard Freiburg EEG dataset which contains data from 21 patients suffering from medically intractable focal epilepsy. Six channels of EEG from each patients are considered and effective connectivity using Directed Transfer Function (DTF) and Granger Causality (GC) methods is estimated. We concentrate on effective connectivity standard deviation over time and feature changes in five brain frequency sub-bands (Alpha, Beta, Theta, Delta, and Gamma) are compared. The performance obtained for the proposed scheme in predicting seizures is: average prediction time is 50 minutes before seizure onset, the maximum sensitivity is approximate ~80% and the false positive rate is 0.33 FP/h. DTF method is more acceptable to predict epileptic seizures and generally we can observe that the greater results are in gamma and beta sub-bands. The research of this paper is significantly helpful for clinical applications, especially for the exploitation of online portable devices.

Keywords: effective connectivity, Granger causality, directed transfer function, epilepsy seizure prediction, EEG

Procedia PDF Downloads 450

Authors: Peter C. St. John, Michael F. Crowley, Yannick J. Bomble

Abstract:

Production of chemicals from engineered organisms in a batch culture typically involves a trade-off between productivity, yield, and titer. However, strategies for strain design typically involve designing mutations to achieve the highest yield possible while maintaining growth viability. Such approaches tend to follow the principle of designing static networks with minimum metabolic functionality to achieve desired yields. While these methods are computationally tractable, optimum productivity is likely achieved by a dynamic strategy, in which intracellular fluxes change their distribution over time. One can use multi-stage fermentations to increase either productivity or yield. Such strategies would range from simple manipulations (aerobic growth phase, anaerobic production phase), to more complex genetic toggle switches. Additionally, some computational methods can also be developed to aid in optimizing two-stage fermentation systems. One can assume an initial control strategy (i.e., a single reaction target) in maximizing productivity - but it is unclear how close this productivity would come to a global optimum. The calculation of maximum theoretical yield in metabolic engineering can help guide strain and pathway selection for static strain design efforts. Here, we present a method for the calculation of a maximum theoretical productivity of a batch culture system. This method follows the traditional assumptions of dynamic flux balance analysis: that internal metabolite fluxes are governed by a pseudo-steady state and external metabolite fluxes are represented by dynamic system including Michealis-Menten or hill-type regulation. The productivity optimization is achieved via dynamic programming, and accounts explicitly for an arbitrary number of fermentation stages and flux variable changes. We have applied our method to succinate production in two common microbial hosts: E. coli and A. succinogenes. The method can be further extended to calculate the complete productivity versus yield Pareto surface. Our results demonstrate that nearly optimal yields and productivities can indeed be achieved with only two discrete flux stages.

Keywords: A. succinogenes, E. coli, metabolic engineering, metabolite fluxes, multi-stage fermentations, succinate

Procedia PDF Downloads 201

Authors: Housein Deli, Loui Al-Shrouf, Hammoud Al Joumaa, Mohieddine Jelali

Abstract:

When forming metallic materials, fluctuations in material properties, process conditions, and wear lead to deviations in the component geometry. Several hundred features sometimes need to be measured, especially in the case of functional and safety-relevant components. These can only be measured offline due to the large number of features and the accuracy requirements. The risk of producing components outside the tolerances is minimized but not eliminated by the statistical evaluation of process capability and control measurements. The inspection intervals are based on the acceptable risk and are at the expense of productivity but remain reactive and, in some cases, considerably delayed. Due to the considerable progress made in the field of condition monitoring and measurement technology, permanently installed sensor systems in combination with machine learning and artificial intelligence, in particular, offer the potential to independently derive forecasts for component geometry and thus eliminate the risk of defective products - actively and preventively. The reliability of forecasts depends on the quality, completeness, and timeliness of the data. Measuring all geometric characteristics is neither sensible nor technically possible. This paper, therefore, uses the example of car seat rail production to discuss the necessary first step of feature selection and reduction by correlation analysis, as otherwise, it would not be possible to forecast components in real-time and inline. Four different car seat rails with an average of 130 features were selected and measured using a coordinate measuring machine (CMM). The run of such measuring programs alone takes up to 20 minutes. In practice, this results in the risk of faulty production of at least 2000 components that have to be sorted or scrapped if the measurement results are negative. Over a period of 2 months, all measurement data (> 200 measurements/ variant) was collected and evaluated using correlation analysis. As part of this study, the number of characteristics to be measured for all 6 car seat rail variants was reduced by over 80%. Specifically, direct correlations for almost 100 characteristics were proven for an average of 125 characteristics for 4 different products. A further 10 features correlate via indirect relationships so that the number of features required for a prediction could be reduced to less than 20. A correlation factor >0.8 was assumed for all correlations.

Keywords: long-term SHM, condition monitoring, machine learning, correlation analysis, component prediction, wear prediction, regressions analysis

Procedia PDF Downloads 24